{"meta":{"query_hash":"432751205d30","filters":{"venue":"BMC Bioinformatics"},"cohort_total":647,"direct_labels_cover":1,"predictions_cover":647,"exported":647,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/432751205d30","api":"https://metacan.xera.ac/api/v1/cohort?venue=BMC+Bioinformatics"},"results":[{"id":"W1480287196","doi":"10.1186/1471-2105-7-356","title":"New directions in biomedical text annotation: definitions, guidelines and corpus construction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Task (project management); Information retrieval; Natural language processing; Categorization; Set (abstract data type); Biomedical text mining; Executable; Focus (optics); Artificial intelligence; Unified Medical Language System; Text corpus; Text mining","score_opus":0.03638827609910656,"score_gpt":0.27885588333730144,"score_spread":0.24246760723819488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480287196","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24291223,0.0075209034,0.7344451,0.0026944303,0.0013325323,0.00048046862,0.00013866289,0.00021659283,0.010259081],"genre_scores_gemma":[0.018872196,0.00097537,0.9784367,0.00028713857,0.0004337459,0.000016005519,0.00045333468,0.000011754517,0.00051372475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918246,0.000018219558,0.0004092055,0.00011960765,0.00011318457,0.00015729418],"domain_scores_gemma":[0.99962556,0.000029507211,0.0000881013,0.00012736199,0.000059328046,0.000070162096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001253207,0.00010488813,0.000112646325,0.00010044076,0.000072735646,0.000030599294,0.00006404593,0.00018701852,0.000013336594],"category_scores_gemma":[0.00023739415,0.00009265472,0.000033059983,0.00018510762,0.00019945565,0.0000071732607,0.000044098073,0.00007030617,0.000012273065],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098505625,0.00015286807,0.054694705,0.00020008937,0.000040637893,0.000004897346,0.00023229142,0.00012416311,0.0039865314,0.0067400043,0.152099,0.7816263],"study_design_scores_gemma":[0.0036252146,0.0005532669,0.06640336,0.0001755859,0.00005594333,0.0006293616,0.0021485884,0.019685913,0.003054662,0.006025677,0.8968548,0.0007876422],"about_ca_topic_score_codex":0.00011801694,"about_ca_topic_score_gemma":0.00026392099,"teacher_disagreement_score":0.78083867,"about_ca_system_score_codex":0.000010479729,"about_ca_system_score_gemma":0.00012478685,"threshold_uncertainty_score":0.377835},"labels":[],"label_agreement":null},{"id":"W1491709863","doi":"10.1186/1471-2105-6-64","title":"MBEToolbox: a Matlab toolbox for sequence data analysis in molecular biology and evolution","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Directorate for Biological Sciences; Texas Tech University","keywords":"Computer science; Visualization; Toolbox; Graphical user interface; Graphics; Interface (matter); MATLAB; Software; Python (programming language); Computer graphics; Theoretical computer science; Data mining; Computational science; Data visualization; Programming language; Computer graphics (images)","score_opus":0.031234246627478465,"score_gpt":0.30439328537247495,"score_spread":0.2731590387449965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1491709863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42939153,0.0018773959,0.5674963,0.00012353381,0.000045802513,0.00032850762,0.00041575244,0.0000050662898,0.00031614903],"genre_scores_gemma":[0.6415563,0.0002048449,0.3573084,0.00020080576,0.000067319335,0.000025695717,0.0005843232,0.000009110364,0.00004320766],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991062,0.000020823118,0.00033154112,0.00024919907,0.000052523475,0.00023967921],"domain_scores_gemma":[0.99922186,0.000023791934,0.00010122508,0.00055389997,0.000052491177,0.00004674977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028341127,0.00013926056,0.00019826338,0.000111952715,0.00005242146,0.000026223295,0.00026992545,0.00012571889,0.0000019973531],"category_scores_gemma":[0.00011259986,0.00013097661,0.000058254816,0.00018207611,0.000078552264,0.000004742479,0.00024099942,0.00004177941,0.0000022956988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033881047,0.00025400345,0.4766958,0.0005723205,0.0020329647,0.0000017276213,0.0010494025,0.024157759,0.44000518,0.015730778,0.0022078706,0.036953364],"study_design_scores_gemma":[0.0022091917,0.00042015058,0.04628673,0.000019017834,0.0005730985,0.000020092379,0.00061166193,0.8938601,0.008612737,0.001323834,0.04519402,0.00086935057],"about_ca_topic_score_codex":0.000025738787,"about_ca_topic_score_gemma":0.00037132477,"teacher_disagreement_score":0.86970234,"about_ca_system_score_codex":0.000020258973,"about_ca_system_score_gemma":0.00006500604,"threshold_uncertainty_score":0.5341071},"labels":[],"label_agreement":null},{"id":"W1494019191","doi":"10.1186/1471-2105-8-33","title":"Considerations in the identification of functional RNA structural elements in genomic alignments","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Pairwise comparison; Nucleic acid secondary structure; Shuffling; Computational biology; Biology; Computer science; Identification (biology); Genome; Genetics; Data mining; RNA; Artificial intelligence; Gene","score_opus":0.022282450520768902,"score_gpt":0.2611371528625071,"score_spread":0.2388547023417382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494019191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95875007,0.000059947597,0.040199675,0.000026033073,0.0001002659,0.00029153816,0.000015047633,0.0000019946688,0.0005554399],"genre_scores_gemma":[0.9887624,0.00000943825,0.010952829,0.00012713733,0.000028952485,0.000011298804,0.00007062637,0.0000037397115,0.000033624623],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990733,0.000033254197,0.0005710949,0.000067446555,0.00013451927,0.00012034714],"domain_scores_gemma":[0.9995733,0.000029510415,0.00017778124,0.0001779428,0.000026913764,0.000014558756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007978183,0.00006603667,0.00006481511,0.00006366446,0.00003800221,0.000016163835,0.000093074465,0.00006351906,0.000019406472],"category_scores_gemma":[0.000084531646,0.000052260464,0.00002994681,0.00006541687,0.000026749674,0.000008515236,0.000025315594,0.000036168563,0.00000650008],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005119566,0.000044428278,0.021674821,0.000049456943,0.000017268603,6.922162e-7,0.00072180235,0.0009808721,0.97123665,0.002711934,0.00020068347,0.002310172],"study_design_scores_gemma":[0.0011847103,0.00011158969,0.2850813,0.000022252545,0.000014846677,0.000021340797,0.0024180673,0.007090346,0.699482,0.0038681538,0.0004762376,0.0002291689],"about_ca_topic_score_codex":0.0000073400506,"about_ca_topic_score_gemma":0.00013040668,"teacher_disagreement_score":0.27175468,"about_ca_system_score_codex":0.0000154481,"about_ca_system_score_gemma":0.000041931155,"threshold_uncertainty_score":0.21311198},"labels":[],"label_agreement":null},{"id":"W1496257230","doi":"10.1186/s12859-015-0586-0","title":"ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidad de San Buenaventura","keywords":"Computer science; Data mining; Sequence (biology); Java; Feature (linguistics); Sequence alignment; Software; Key (lock); Protein function prediction; Artificial intelligence; Theoretical computer science; Machine learning; Programming language; Protein function; Peptide sequence","score_opus":0.03172182749760137,"score_gpt":0.30741463866839125,"score_spread":0.27569281117078986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496257230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16943671,0.00014304365,0.8243211,0.00016135996,0.00024132933,0.0046158824,0.00008232175,0.00009896783,0.00089930603],"genre_scores_gemma":[0.029417202,0.000006242099,0.96957284,0.00028541902,0.0001232041,0.00027265956,0.00014005922,0.000024063926,0.00015829729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986406,0.000035761477,0.00058851414,0.0001657095,0.00024877168,0.0003206695],"domain_scores_gemma":[0.9988888,0.00001777544,0.00027359414,0.00032562722,0.00023965599,0.0002545796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034499087,0.0002323421,0.00027706687,0.00008531394,0.00006992371,0.00007063879,0.0002792291,0.00017393404,0.0000018387392],"category_scores_gemma":[0.0004456703,0.00018763689,0.000077046614,0.00015252456,0.0001370003,0.00001889954,0.00021756036,0.000099530895,0.0000037774548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036085253,0.0013335656,0.088494256,0.0152456025,0.0010037799,0.0000049832165,0.022546798,0.08221702,0.03315035,0.014833658,0.092747405,0.6448141],"study_design_scores_gemma":[0.0020043382,0.00556362,0.0013504815,0.00008645164,0.000063714375,0.00009327011,0.000580967,0.77491564,0.021971466,0.0004769226,0.19212452,0.0007686365],"about_ca_topic_score_codex":0.00001940417,"about_ca_topic_score_gemma":0.000009259032,"teacher_disagreement_score":0.6926986,"about_ca_system_score_codex":0.000018885694,"about_ca_system_score_gemma":0.00020629642,"threshold_uncertainty_score":0.76516104},"labels":[],"label_agreement":null},{"id":"W1497984091","doi":"10.1186/1471-2105-7-441","title":"Exhaustive assignment of compositional bias reveals universally prevalent biased regions: analysis of functional associations in human and Drosophila","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Biology; Drosophila melanogaster; Melanogaster; Genetics; Proteome; Transcription factor; Computational biology; Gene; Evolutionary biology; Homeobox","score_opus":0.02236267727418445,"score_gpt":0.23964584734983221,"score_spread":0.21728317007564776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1497984091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97974306,0.000058257545,0.01877024,0.00003628467,0.000017189035,0.00015967127,0.00039881482,0.0000030994527,0.0008133738],"genre_scores_gemma":[0.9899034,0.000027532687,0.008045799,0.000019327283,0.000016522737,0.000004859026,0.0018386592,0.0000045436022,0.0001393545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991105,0.000027967892,0.0005032914,0.000098071614,0.00016099798,0.00009917155],"domain_scores_gemma":[0.9992479,0.000034915964,0.00041016104,0.00015380877,0.0001269,0.000026312478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019954369,0.00009414823,0.00020631713,0.0001947361,0.000046797162,0.000009008124,0.00007119403,0.00009632771,0.000007802842],"category_scores_gemma":[0.000022799739,0.00009780477,0.00010463729,0.00023262082,0.00008098805,0.0000065479917,0.00005541331,0.0000403414,2.9435367e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078930265,0.00061828224,0.5594698,0.00027724702,0.0008990604,7.6539374e-7,0.0003205428,0.26162493,0.15479766,0.020654,0.0012165908,0.000042139494],"study_design_scores_gemma":[0.00082504464,0.000146812,0.909802,0.000033783934,0.00031085545,0.0000015704738,0.00024837055,0.08523158,0.0023972348,0.0008036424,0.00005052506,0.00014853168],"about_ca_topic_score_codex":0.000032768407,"about_ca_topic_score_gemma":0.00020689964,"teacher_disagreement_score":0.3503322,"about_ca_system_score_codex":0.00004846049,"about_ca_system_score_gemma":0.000065352564,"threshold_uncertainty_score":0.39883628},"labels":[],"label_agreement":null},{"id":"W1504124766","doi":"10.1186/1471-2105-14-s3-s14","title":"Protein Function Prediction using Text-based Features extracted from the Biomedical Literature: The CAFA Challenge","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Protein function prediction; Classifier (UML); Function (biology); DNA microarray; Gene ontology; Artificial intelligence; Data mining; Precision and recall; Protein function; Computational biology; Machine learning; Gene; Biology; Genetics","score_opus":0.019870383805722213,"score_gpt":0.2384098960389598,"score_spread":0.2185395122332376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504124766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5477993,0.007791749,0.4311469,0.0070429067,0.0017028481,0.0026593814,0.0005878464,0.00030494013,0.00096414215],"genre_scores_gemma":[0.9173678,0.00009643867,0.074776135,0.0023386665,0.0018724988,0.00025345222,0.0028072204,0.000046213387,0.00044155403],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988092,0.00010265313,0.000338648,0.00017874461,0.00029781248,0.00027290048],"domain_scores_gemma":[0.9990737,0.000087550296,0.00016388117,0.00048502762,0.00010359494,0.000086275206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026206972,0.00019633176,0.00012757163,0.000033898934,0.00027256864,0.00015675419,0.00032214395,0.0004345992,0.000041922078],"category_scores_gemma":[0.00032120274,0.00009860393,0.00010299799,0.00018816268,0.0003270823,0.00001560257,0.00009007405,0.00030801396,0.000030578874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000966542,0.001019542,0.0046588085,0.0007233479,0.00081654073,0.0000070470173,0.005171504,0.0005581264,0.207401,0.0006563857,0.23321378,0.5448074],"study_design_scores_gemma":[0.004057933,0.0021989222,0.09821472,0.0007712691,0.00030744605,0.00007709605,0.005371997,0.3885515,0.012089104,0.0015079994,0.48565066,0.0012013579],"about_ca_topic_score_codex":0.000083221086,"about_ca_topic_score_gemma":0.00003978244,"teacher_disagreement_score":0.543606,"about_ca_system_score_codex":0.00001740643,"about_ca_system_score_gemma":0.00012133194,"threshold_uncertainty_score":0.40209514},"labels":[],"label_agreement":null},{"id":"W1505843021","doi":"10.1186/1471-2105-16-s5-s7","title":"Isomorphism and similarity for 2-generation pedigrees","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Pedigree chart; Isomorphism (crystallography); Combinatorics; Partition (number theory); Integer (computer science); Mathematics; Computer science; Property (philosophy); Time complexity; Theoretical computer science; Biology; Genetics","score_opus":0.09091666958478403,"score_gpt":0.2843398320754851,"score_spread":0.19342316249070104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505843021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023488414,0.00005926719,0.9953997,0.00049641007,0.00030479056,0.00012925625,0.000004813697,0.0001007253,0.0011561743],"genre_scores_gemma":[0.012164706,0.0000052393552,0.9869196,0.00036071148,0.00019352906,0.000009225887,0.000016558068,0.000003881217,0.0003265387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994648,0.000015100881,0.00016707665,0.00008482678,0.00013909483,0.0001290837],"domain_scores_gemma":[0.9995103,0.000047343103,0.00007249122,0.00019100071,0.000079689606,0.00009918355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000374809,0.00007558315,0.0000852356,0.00004127451,0.00009372519,0.00017472547,0.00018871739,0.000043854234,0.000001033642],"category_scores_gemma":[0.00015151933,0.00006311868,0.000022609545,0.000068763606,0.000021233162,0.00034229388,0.000092570524,0.000060789404,0.000011733316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002955267,0.0001984715,0.013679039,0.0007112063,0.00004924883,0.0000033374633,0.024762327,0.014443309,0.000063788524,0.21746515,0.23220193,0.49639264],"study_design_scores_gemma":[0.00035450165,0.00008695609,0.00023708043,0.0000038008468,0.0000032181445,0.000010752303,0.00007011275,0.98462445,0.000043751126,0.0012192804,0.013253642,0.00009247247],"about_ca_topic_score_codex":0.000009467873,"about_ca_topic_score_gemma":0.000010728616,"teacher_disagreement_score":0.9701811,"about_ca_system_score_codex":0.000011257085,"about_ca_system_score_gemma":0.000062378625,"threshold_uncertainty_score":0.2573905},"labels":[],"label_agreement":null},{"id":"W1510029899","doi":"10.1186/1471-2105-5-45","title":"A hybrid clustering approach to recognition of protein families in 114 microbial genomes","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Medical Research Council; University of Queensland","keywords":"Cluster analysis; Markov chain; Data mining; Single-linkage clustering; Complete-linkage clustering; Computer science; Hierarchical clustering; Computational biology; Correlation clustering; Biology; Artificial intelligence; CURE data clustering algorithm; Machine learning","score_opus":0.015093997896921526,"score_gpt":0.21160764773952587,"score_spread":0.19651364984260433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510029899","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.554139,0.00016951514,0.4385563,0.000019930152,0.000088147885,0.0008505792,0.00007603203,0.000014539467,0.0060859304],"genre_scores_gemma":[0.48500478,0.00008517683,0.51408565,0.00024249476,0.00009993375,0.00005397992,0.0003319745,0.000020000645,0.000076004406],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892277,0.00001339836,0.00054038136,0.00013277115,0.00010744242,0.00028324267],"domain_scores_gemma":[0.9994174,0.00000428775,0.00016647569,0.00027823797,0.000058225287,0.00007531964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023959795,0.00017318655,0.00020615457,0.00013807234,0.000038998714,0.000027529462,0.00020599333,0.00012163708,0.00000191745],"category_scores_gemma":[0.000029320201,0.00016856722,0.000081490405,0.00013208097,0.00005360599,0.000014146909,0.00017399629,0.000095368174,0.000019471303],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016776958,0.0014362665,0.0011496182,0.0071107834,0.00032559477,0.000005280182,0.015181986,0.27633724,0.30920336,0.0009039193,0.0028786864,0.3837896],"study_design_scores_gemma":[0.017686566,0.0031857474,0.0018922733,0.0019821478,0.00013047762,0.00039701347,0.009710403,0.30010596,0.6234621,0.003764511,0.033315428,0.004367412],"about_ca_topic_score_codex":0.000028057442,"about_ca_topic_score_gemma":0.00009702732,"teacher_disagreement_score":0.37942216,"about_ca_system_score_codex":0.000036908914,"about_ca_system_score_gemma":0.00011378852,"threshold_uncertainty_score":0.6873971},"labels":[],"label_agreement":null},{"id":"W1515882292","doi":"10.1186/1471-2105-7-343","title":"Multivariate curve resolution of time course microarray data","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":119,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Principal component analysis; Multivariate statistics; Linear model; Data mining; Computer science; Least-squares function approximation; Gene chip analysis; DNA microarray; Missing data; Algorithm; Biological data; Statistics; Mathematics; Bioinformatics; Biology; Gene expression; Gene; Genetics","score_opus":0.025184432124388444,"score_gpt":0.27798983067147187,"score_spread":0.25280539854708345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515882292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13012396,0.0017718654,0.8360692,0.00027518097,0.0006055709,0.00086523726,0.0009729769,0.000082183906,0.02923379],"genre_scores_gemma":[0.6742257,0.0001959029,0.30748186,0.00023487711,0.00058439485,0.000023070119,0.010269859,0.000049282957,0.0069350624],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992507,0.000029187137,0.00032769036,0.0001406676,0.00012079385,0.00013095002],"domain_scores_gemma":[0.9989008,0.000007334683,0.00022196535,0.0007577042,0.00008013598,0.00003210739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021018296,0.000093578376,0.00009547453,0.000032732274,0.00004208707,0.000014445464,0.00030629354,0.000112290145,0.000021801716],"category_scores_gemma":[0.00003986144,0.00008389703,0.00003685884,0.00008289232,0.000058947968,0.000011582823,0.00014307971,0.00003997304,0.0000453953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000871743,0.00014699361,0.0025577412,0.00009653482,0.000022875438,1.1609492e-7,0.000050338425,0.0011584891,0.86301094,0.00019128057,0.13073526,0.0019422441],"study_design_scores_gemma":[0.0022187768,0.00020168744,0.030581914,0.00008579388,0.00008500993,0.000014211976,0.0002448806,0.37337765,0.3600087,0.00016786721,0.23244317,0.0005703453],"about_ca_topic_score_codex":0.000030332387,"about_ca_topic_score_gemma":0.000021092932,"teacher_disagreement_score":0.5441017,"about_ca_system_score_codex":0.000007848267,"about_ca_system_score_gemma":0.00010990841,"threshold_uncertainty_score":0.34212214},"labels":[],"label_agreement":null},{"id":"W1518614040","doi":"10.1186/1471-2105-7-338","title":"Cluster analysis of protein array results via similarity of Gene Ontology annotation","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Annotation; Gene ontology; Computational biology; Set (abstract data type); Ontology; Gene Annotation; Computer science; Protein microarray; Similarity (geometry); DNA microarray; Proteomics; Graph; Protein function prediction; Biology; Genome; Information retrieval; Data mining; Gene; Bioinformatics; Genetics; Image (mathematics); Theoretical computer science; Protein function; Artificial intelligence; Gene expression","score_opus":0.008225236861544173,"score_gpt":0.24896429969994288,"score_spread":0.24073906283839872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518614040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28979105,0.00007568848,0.7058279,0.00002693192,0.000007693329,0.00026317727,0.00006201937,0.000015384809,0.003930161],"genre_scores_gemma":[0.7333644,0.000011399716,0.2649595,0.00006324366,0.000028212411,0.000011674535,0.0013463994,0.000008058829,0.00020711723],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986476,0.000053198768,0.0008420247,0.00014533031,0.00016486239,0.00014701916],"domain_scores_gemma":[0.9985509,0.000018881368,0.00059583515,0.00053704367,0.00027135538,0.000026005144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035829254,0.00012743015,0.00032465588,0.0002523109,0.000024498624,0.000008538417,0.00017369763,0.00018302645,0.000006703858],"category_scores_gemma":[0.00011793753,0.00011892328,0.00023943526,0.00045562992,0.00010771032,0.000010669655,0.000045174325,0.000052402025,0.0000015606364],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002398159,0.00019277657,0.0063525094,0.00016383611,0.0005309988,3.8032414e-7,0.00015229185,0.0040810914,0.98539406,0.000039913746,0.0016753435,0.0011769582],"study_design_scores_gemma":[0.00040965775,0.00014588557,0.006169809,0.0000072128773,0.00046030965,0.0000015375327,0.000042309715,0.05099949,0.94065917,0.00007358418,0.0008897756,0.0001412635],"about_ca_topic_score_codex":0.00019255184,"about_ca_topic_score_gemma":0.0009556953,"teacher_disagreement_score":0.44357336,"about_ca_system_score_codex":0.000012398809,"about_ca_system_score_gemma":0.000044577828,"threshold_uncertainty_score":0.48495504},"labels":[],"label_agreement":null},{"id":"W1525672751","doi":"10.1186/1471-2105-6-75","title":"Ranking the whole MEDLINE database according to a large training set using text indexing","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics","funders":"U.S. National Library of Medicine; Universität Stuttgart; Ontario Genomics Institute; Stem Cell Network; Ontario Genomics; Ontario Innovation Trust","keywords":"MEDLINE; Computer science; Information retrieval; Relevance (law); Ranking (information retrieval); Set (abstract data type); Controlled vocabulary; Vocabulary; Subject (documents); National library; Natural language processing; Artificial intelligence; World Wide Web; Library science; Linguistics","score_opus":0.07540264134123546,"score_gpt":0.33009792757829903,"score_spread":0.25469528623706356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525672751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39582357,0.00040279687,0.60168076,0.00059642154,0.00022515554,0.00027787662,0.00011887818,0.0000659462,0.0008085968],"genre_scores_gemma":[0.6413625,0.000020777328,0.35488138,0.0026847143,0.0006727587,0.000013828737,0.00019973313,0.000025901352,0.00013844883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986007,0.00004427507,0.00042789173,0.00019059025,0.00023741012,0.0004991293],"domain_scores_gemma":[0.99916756,0.00006796503,0.00014140112,0.00044421465,0.000049647086,0.00012918162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008698193,0.00019637225,0.0001949099,0.00007809043,0.0003090305,0.000087054745,0.00040418172,0.0001649112,0.000012705913],"category_scores_gemma":[0.0005625029,0.00013991998,0.00008788806,0.00022441214,0.00008543025,0.000015036745,0.0003886552,0.0001899667,0.00003877805],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004260755,0.00020823324,0.015164627,0.00062563585,0.00038957052,0.000012873078,0.03127192,0.017542208,0.13564555,0.0007485806,0.022074195,0.7758905],"study_design_scores_gemma":[0.0016914103,0.00018102732,0.00047269536,0.0002686554,0.00007153354,0.000116622454,0.03167439,0.5340252,0.008998353,0.000028250939,0.42177525,0.0006966008],"about_ca_topic_score_codex":0.000007061779,"about_ca_topic_score_gemma":0.000081016056,"teacher_disagreement_score":0.7751939,"about_ca_system_score_codex":0.000028701681,"about_ca_system_score_gemma":0.00013275153,"threshold_uncertainty_score":0.57057714},"labels":[],"label_agreement":null},{"id":"W1531430623","doi":"10.1186/1471-2105-3-1","title":"Identification and characterization of subfamily-specific signatures in a large protein superfamily by a hidden Markov model approach","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Canadian Institutes of Health Research; Howard Hughes Medical Institute","keywords":"Hidden Markov model; Subfamily; Biology; Structural Classification of Proteins database; Computational biology; Threading (protein sequence); Sequence alignment; Sequence motif; GenBank; Multiple sequence alignment; Sequence database; Protein family; Structural motif; Genetics; Protein structure; Artificial intelligence; Computer science; Peptide sequence; Gene","score_opus":0.008643251258559427,"score_gpt":0.19888992884917417,"score_spread":0.19024667759061475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1531430623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74609053,0.00057256344,0.252047,0.000014668492,0.000019290286,0.0005327687,0.0001812028,0.000009999515,0.00053199346],"genre_scores_gemma":[0.9564377,0.00035615888,0.041934885,0.00008099013,0.000024316229,0.000050197836,0.0006424452,0.00001635885,0.00045694175],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909586,0.0000260357,0.00039821636,0.00016258637,0.0001382323,0.00017906105],"domain_scores_gemma":[0.99946856,0.0000034933805,0.00016099085,0.00026491183,0.000052623487,0.00004943848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015967723,0.00014062223,0.00014777311,0.000074622,0.000038486138,0.00003122758,0.00013784609,0.00021568092,0.0000041742046],"category_scores_gemma":[0.00002916203,0.00013316247,0.000035657245,0.000121380916,0.000052008843,0.000024611996,0.00006760472,0.000090129855,0.0000013572073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046443118,0.00009445987,0.000798903,0.00026673736,0.000010639101,1.3515057e-7,0.0004494953,0.00010773264,0.9936398,0.00035621473,0.0005770813,0.0036523447],"study_design_scores_gemma":[0.00077298377,0.000063562824,0.0023596901,0.000024462965,0.000007723436,0.0000030645053,0.0001594439,0.95737314,0.03850805,0.00011389519,0.0003766785,0.00023729402],"about_ca_topic_score_codex":0.0000015953792,"about_ca_topic_score_gemma":0.0000034064108,"teacher_disagreement_score":0.95726544,"about_ca_system_score_codex":0.000011379531,"about_ca_system_score_gemma":0.000021054582,"threshold_uncertainty_score":0.5430207},"labels":[],"label_agreement":null},{"id":"W1533736623","doi":"10.1186/1471-2105-3-39","title":"Species-specific protein sequence and fold optimizations","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Toronto; St. Michael's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"ORFS; Genome; Biology; Archaea; Amino acid; Eukaryote; Computational biology; Genetics; Homology (biology); Open reading frame; Bacteria; Peptide sequence; Gene","score_opus":0.04602734988357537,"score_gpt":0.22612767535671227,"score_spread":0.1801003254731369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1533736623","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076729566,0.0023560196,0.87016433,0.0003596807,0.00022346989,0.0013917725,0.000100941266,0.00009537013,0.048578847],"genre_scores_gemma":[0.17228621,0.0016497435,0.8118972,0.00036820304,0.00026040772,0.00010964347,0.00009570242,0.000043165728,0.013289679],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930394,0.000022747336,0.00023189194,0.00013510897,0.0001162674,0.00019003716],"domain_scores_gemma":[0.999471,0.000008975145,0.00008499369,0.00031386028,0.00004183035,0.000079339334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000109263405,0.0001317948,0.00010185013,0.00003817038,0.00011837909,0.00006592212,0.00014429905,0.00011719614,0.00017574901],"category_scores_gemma":[0.00005372618,0.000119352284,0.000044835004,0.00008186742,0.000069584305,0.000012318607,0.000074171505,0.00004746837,0.000074883836],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060194405,0.00016561031,0.0006711788,0.00035967925,0.00008009,0.000005260615,0.00094263005,0.0010672017,0.9227468,0.018250369,0.019315574,0.036335453],"study_design_scores_gemma":[0.0011734568,0.00054276426,0.0002612644,0.0001138903,0.00002829607,0.00011338507,0.0006398118,0.09015407,0.503951,0.0006238158,0.40137208,0.0010261594],"about_ca_topic_score_codex":0.0000010468142,"about_ca_topic_score_gemma":0.0000027213944,"teacher_disagreement_score":0.41879576,"about_ca_system_score_codex":0.000007922531,"about_ca_system_score_gemma":0.000014243271,"threshold_uncertainty_score":0.4867045},"labels":[],"label_agreement":null},{"id":"W1541953909","doi":"10.1186/1471-2105-7-521","title":"Dynamic variable selection in SNP genotype autocalling from APEX microarray data","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; British Columbia Lung Association; National Sanitarium Association","keywords":"Single-nucleotide polymorphism; SNP genotyping; DNA microarray; Genotyping; Genotype; SNP array; Genetics; SNP; Biology; Tag SNP; Molecular Inversion Probe; Sanger sequencing; Computational biology; DNA sequencing; Algorithm; Computer science; DNA; Gene","score_opus":0.021810520933346858,"score_gpt":0.26371961140742356,"score_spread":0.24190909047407672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541953909","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08084309,0.0005033017,0.9138052,0.00004771762,0.00023224308,0.00026523118,0.000102629994,0.000039775347,0.004160799],"genre_scores_gemma":[0.35183272,0.000107309985,0.6408911,0.00026756324,0.00022586853,0.000026280417,0.0054221153,0.0000310489,0.0011960234],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991123,0.000025613055,0.0003464641,0.00022150902,0.000109481065,0.00018463586],"domain_scores_gemma":[0.99934596,0.00000937559,0.00013042963,0.00044004552,0.00004066294,0.00003355679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016318493,0.0001176804,0.000100031866,0.00006093616,0.000057925175,0.00004733699,0.00029890085,0.00016708573,0.000026728278],"category_scores_gemma":[0.000032889195,0.00011481175,0.000023024384,0.00017704073,0.00002214967,0.000017423243,0.00011531884,0.000086308486,0.000031839354],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008147661,0.00009847596,0.0064632166,0.000068912006,0.000018141738,2.491739e-7,0.00006666747,0.009775528,0.97042716,0.0003614907,0.009062463,0.0035762414],"study_design_scores_gemma":[0.00083380216,0.000050491155,0.014921235,0.00003924267,0.000020603859,0.000004904818,0.0001406621,0.861129,0.029261976,0.0005611454,0.09271427,0.00032268895],"about_ca_topic_score_codex":0.00017085188,"about_ca_topic_score_gemma":0.00053075736,"teacher_disagreement_score":0.94116515,"about_ca_system_score_codex":0.000036489146,"about_ca_system_score_gemma":0.00015404099,"threshold_uncertainty_score":0.46818873},"labels":[],"label_agreement":null},{"id":"W1542595575","doi":"10.1186/1471-2105-7-270","title":"Improving the specificity of high-throughput ortholog prediction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia","funders":"Genome Prairie; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Throughput; Computational biology; DNA microarray; Computer science; Biology; Bioinformatics; Genetics; Gene; Gene expression","score_opus":0.010276379109183264,"score_gpt":0.20080798536633135,"score_spread":0.19053160625714807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1542595575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.935775,0.00041607508,0.06078007,0.000030979536,0.00024463763,0.000192164,0.000096594704,0.0000056389345,0.0024588504],"genre_scores_gemma":[0.9686918,0.000086788255,0.0306612,0.00004996683,0.00024964107,0.000007922584,0.00006107789,0.000008402769,0.00018316058],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993171,0.000016056181,0.0003279321,0.000096958596,0.00009546565,0.00014649381],"domain_scores_gemma":[0.999414,0.000015107723,0.00017510144,0.00030865852,0.00007153108,0.000015594527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016397593,0.00010182079,0.000107548025,0.00001831692,0.00009576852,0.000013891785,0.00014230516,0.00008078865,0.0000035180994],"category_scores_gemma":[0.000030482293,0.00007114401,0.00006736544,0.000058578466,0.000118310876,0.0000013078546,0.00012232231,0.000045954122,0.0000047957456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028822874,0.0003936,0.23523507,0.00071377,0.0003017836,0.0000014125633,0.0009765964,0.028643884,0.6705646,0.013177498,0.026964944,0.022738615],"study_design_scores_gemma":[0.0020085813,0.000921745,0.5911167,0.000028924713,0.00016465427,0.00005567779,0.0016013129,0.031861022,0.32491466,0.0020439683,0.044585366,0.0006973607],"about_ca_topic_score_codex":0.00010332747,"about_ca_topic_score_gemma":0.0000881713,"teacher_disagreement_score":0.35588166,"about_ca_system_score_codex":0.0000067928427,"about_ca_system_score_gemma":0.000038522412,"threshold_uncertainty_score":0.29011685},"labels":[],"label_agreement":null},{"id":"W1553029142","doi":"10.1186/1471-2105-8-54","title":"BIRCH: A user-oriented, locally-customizable, bioinformatics system","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Genome Prairie; Genome Canada","keywords":"Computer science; Installation; Graphical user interface; Documentation; Software; User interface; Betula pendula; Set (abstract data type); Hierarchy; World Wide Web; Software engineering; Data science; Operating system","score_opus":0.018125852863450337,"score_gpt":0.26769001621134875,"score_spread":0.2495641633478984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553029142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024134178,0.00028640789,0.9311288,0.00007500235,0.0010835319,0.0011291631,0.0001456674,0.00021292082,0.041804302],"genre_scores_gemma":[0.13553338,0.0008653983,0.852545,0.0018538057,0.0015318757,0.000075331875,0.0015820478,0.0001864019,0.005826708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99488056,0.000055929577,0.0019730234,0.00033908917,0.0012353839,0.0015160213],"domain_scores_gemma":[0.9967152,0.00011367582,0.00053182297,0.0012179068,0.0005590803,0.00086235517],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024504391,0.00057043164,0.00051623955,0.00046678586,0.00034702502,0.00018328939,0.0009402371,0.0007135095,0.000038543367],"category_scores_gemma":[0.0006516426,0.00048431507,0.00032466138,0.00069085654,0.0005139253,0.000056467023,0.0006598319,0.000423026,0.00085425196],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070595876,0.0032204306,0.05047425,0.037501715,0.002948053,0.00020161291,0.012705805,0.0061783823,0.026615717,0.02857517,0.3972745,0.42724478],"study_design_scores_gemma":[0.0060911775,0.0018420294,0.0021680936,0.0004380997,0.00014735041,0.000442786,0.018735139,0.30769974,0.028975936,0.000039882627,0.63131374,0.002106049],"about_ca_topic_score_codex":0.0000273621,"about_ca_topic_score_gemma":0.00011612879,"teacher_disagreement_score":0.42513874,"about_ca_system_score_codex":0.0001580893,"about_ca_system_score_gemma":0.00053599087,"threshold_uncertainty_score":0.9999237},"labels":[],"label_agreement":null},{"id":"W1554361839","doi":"10.1186/1471-2105-3-32","title":"SeqHound: biological sequence and structure database as a platform for bioinformatics research","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Annotation; Perl; Biological database; GenBank; XML; Application programming interface; Information retrieval; World Wide Web; Database; UniProt; User interface; Web server; Bioinformatics; Biology; The Internet; Programming language","score_opus":0.15206778089041978,"score_gpt":0.3391928206073035,"score_spread":0.1871250397168837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554361839","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825374,0.0018804544,0.01011618,0.00013035792,0.00020940794,0.0011056252,0.0010931562,0.000018737,0.0029086946],"genre_scores_gemma":[0.6704631,0.003075019,0.32439512,0.0006823158,0.0003213348,0.00008294348,0.00049511966,0.00003621514,0.00044883922],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985849,0.000023569599,0.00043832476,0.00022741899,0.00021265009,0.0005130871],"domain_scores_gemma":[0.99895555,0.000110911475,0.00012280048,0.00046382574,0.00019384475,0.00015309015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004131279,0.000233587,0.00021598123,0.000093879484,0.00035676284,0.00010060425,0.00029921933,0.00023974727,0.0000250987],"category_scores_gemma":[0.0003958896,0.0001846342,0.00007248881,0.00013964323,0.0003324794,0.000009117174,0.00038293345,0.00016259486,0.000027886688],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001644225,0.0008260913,0.034456734,0.0066426136,0.0015451728,0.00001954074,0.024569489,0.001366018,0.5752589,0.03469366,0.11961383,0.19936372],"study_design_scores_gemma":[0.00586967,0.0052413396,0.0022398229,0.00015756534,0.00012081073,0.00068427983,0.010003321,0.42157036,0.04299107,0.007893734,0.5008302,0.002397851],"about_ca_topic_score_codex":0.000009578618,"about_ca_topic_score_gemma":0.00003454665,"teacher_disagreement_score":0.53226787,"about_ca_system_score_codex":0.000020932199,"about_ca_system_score_gemma":0.000055780638,"threshold_uncertainty_score":0.7529164},"labels":[],"label_agreement":null},{"id":"W1554825545","doi":"10.1186/1471-2105-7-216","title":"A factor analysis model for functional genomics","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto; Toronto Public Health","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Functional genomics; Computer science; Genomics; Factor (programming language); Gene ontology; Expression (computer science); DNA microarray; Computational biology; Structural genomics; Data mining; Biological data; Computation; Genome; Artificial intelligence; Machine learning; Bioinformatics; Gene; Biology; Algorithm; Genetics; Gene expression","score_opus":0.01901459151223892,"score_gpt":0.22530185389627383,"score_spread":0.20628726238403491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554825545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030432338,0.00012880244,0.9666911,0.000022507096,0.00011219969,0.00029975903,0.00033111632,0.000021859243,0.001960331],"genre_scores_gemma":[0.40691137,0.00004909853,0.5829618,0.00069284294,0.00069267576,0.00008904129,0.0041613122,0.000046018817,0.004395836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988694,0.000006306884,0.0005230814,0.00015104425,0.00012844703,0.00032167495],"domain_scores_gemma":[0.9992242,0.00001832318,0.00020522345,0.00036570607,0.000112471076,0.00007410888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001449786,0.00019640989,0.00020787674,0.000112459595,0.00013429386,0.000069349204,0.0001756053,0.00020957814,0.000011558081],"category_scores_gemma":[0.000016366008,0.0001822268,0.00034178508,0.00016707419,0.000049899252,0.000011209881,0.000077851364,0.00006342703,0.000016697515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015872665,0.00008324286,0.0035580671,0.00012408821,0.00041451547,9.395951e-8,0.00015866557,0.9632287,0.0021046316,0.0039045156,0.02275454,0.0035102249],"study_design_scores_gemma":[0.000542763,0.00004934893,0.0012415538,0.0000019410215,0.0001528474,0.0000027451122,0.00004682407,0.9824375,0.00047602574,0.0007073432,0.014085311,0.00025580416],"about_ca_topic_score_codex":0.0000046255504,"about_ca_topic_score_gemma":0.00011630281,"teacher_disagreement_score":0.38372928,"about_ca_system_score_codex":0.000031244446,"about_ca_system_score_gemma":0.00014680895,"threshold_uncertainty_score":0.74309933},"labels":[],"label_agreement":null},{"id":"W1563388055","doi":"10.1186/1471-2105-5-103","title":"Improving the scaling normalization for high-density oligonucleotide GeneChip expression microarrays","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"DNA microarray; Normalization (sociology); Computational biology; Gene chip analysis; Microarray; Oligonucleotide; Biology; Gene expression profiling; Computer science; Bioinformatics; Gene expression; Genetics; Gene","score_opus":0.013614672881765124,"score_gpt":0.2318689874051802,"score_spread":0.21825431452341507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563388055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27936882,0.00008246041,0.7197162,0.000083458996,0.0002313834,0.00035545457,0.000012710754,0.000025532361,0.00012398939],"genre_scores_gemma":[0.8344772,0.000052465755,0.16421765,0.0005508296,0.00027248033,0.000057882353,0.0002571962,0.000022726685,0.00009158563],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913484,0.000021539345,0.00032286884,0.00017072179,0.00013542206,0.00021463764],"domain_scores_gemma":[0.9991599,0.000011943143,0.00022637034,0.00042189637,0.00011912179,0.0000608228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024085908,0.00014293213,0.000096968506,0.000041183903,0.00031409145,0.000069567875,0.00023121934,0.00013901456,0.0000035587425],"category_scores_gemma":[0.00010692201,0.000104211824,0.00008185575,0.00009274114,0.00005134175,0.00001660059,0.00009602951,0.000062766194,0.000009947555],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007534536,0.000028211873,0.00020587233,0.00011299358,0.000008673967,5.7848716e-8,0.00036640617,0.005835886,0.987167,0.0006906913,0.0012382397,0.0042706355],"study_design_scores_gemma":[0.0009084336,0.000066674605,0.0010483536,0.000035381036,0.00001919994,0.0000061831815,0.0005637799,0.008373929,0.98601633,0.00031551937,0.0024556594,0.00019057539],"about_ca_topic_score_codex":0.000022030938,"about_ca_topic_score_gemma":0.000032642052,"teacher_disagreement_score":0.55549854,"about_ca_system_score_codex":0.00003457461,"about_ca_system_score_gemma":0.00013826492,"threshold_uncertainty_score":0.4249635},"labels":[],"label_agreement":null},{"id":"W1563772569","doi":"10.1186/1471-2105-7-185","title":"Ebbie: automated analysis and storage of small RNA cloning data using a dynamic web server","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Simon Fraser University; Michael Smith Health Research BC","keywords":"Cloning (programming); Substring; Insert (composites); Computer science; Computational biology; Sequence analysis; DNA sequencing; Biology; Database; Sequence database; Genetics; Data mining; DNA; Gene; Data structure; Programming language","score_opus":0.03417064336361586,"score_gpt":0.24395543796955318,"score_spread":0.20978479460593732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563772569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972241,0.00007298194,0.0019673326,0.000030861233,0.00002702464,0.0000913475,0.00033383226,0.000073593445,0.00017892355],"genre_scores_gemma":[0.94752294,0.000008806214,0.05175979,0.000018554798,0.000021356214,8.366943e-7,0.0006249912,6.1188786e-7,0.000042110525],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924815,0.00002241164,0.00034330896,0.00011478754,0.00012434543,0.0001470115],"domain_scores_gemma":[0.9995087,0.000091375085,0.00018766924,0.0001267285,0.00004557363,0.0000399649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016039942,0.00009539263,0.00017508006,0.000032175358,0.00011925895,0.000056684104,0.00021895749,0.00006609517,0.000060316954],"category_scores_gemma":[0.000026895783,0.000041227104,0.000053222444,0.00068728736,0.000039160608,0.00014793582,0.00018972714,0.00004214791,0.000003614465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008402776,0.0008598332,0.3445826,0.00089021673,0.0012879054,0.000010621112,0.0015975254,0.09619734,0.5251744,0.0025271873,0.0007376281,0.026050765],"study_design_scores_gemma":[0.00009377935,0.000021221042,0.15166722,0.000011574881,0.00015731854,0.0000036190538,0.000108313645,0.84760916,0.00008792076,0.000095725605,0.000053115447,0.00009101369],"about_ca_topic_score_codex":0.0006564052,"about_ca_topic_score_gemma":0.009736328,"teacher_disagreement_score":0.75141186,"about_ca_system_score_codex":0.000013549846,"about_ca_system_score_gemma":0.000018515922,"threshold_uncertainty_score":0.54331},"labels":[],"label_agreement":null},{"id":"W1564554862","doi":"10.1186/1471-2105-13-s17-s1","title":"InCoB2012 Conference: from biological data to knowledge to technological breakthroughs","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Genetic Engineering and Biotechnology; Hospital for Sick Children; Macquarie University; National Science and Technology Development Agency; King Mongkut's University of Technology Thonburi; Danmarks Tekniske Universitet; Chinese Academy of Sciences; Thailand Science Park; National University of Singapore","keywords":"Asia pacific; Dissemination; Theme (computing); China; Library science; Data science; Political science; Bioinformatics; Biology; World Wide Web; Computer science; History","score_opus":0.13239455089816796,"score_gpt":0.35720306245475947,"score_spread":0.2248085115565915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564554862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.444812,0.0011096502,0.52775884,0.0014426993,0.0012959986,0.0020519332,0.0020504904,0.00024721588,0.019231193],"genre_scores_gemma":[0.6541848,0.00030004434,0.3396984,0.0018073965,0.0009176597,0.000062151,0.00245757,0.000030366078,0.00054159353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972997,0.00007960625,0.0007579232,0.0003780032,0.00044366647,0.0010411257],"domain_scores_gemma":[0.99700046,0.00009592893,0.00011546114,0.0016195414,0.00020024338,0.00096839055],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010789249,0.00035373055,0.00036466087,0.00015745453,0.00014872164,0.00010876107,0.001869259,0.00064601086,0.00016808265],"category_scores_gemma":[0.0017943943,0.0002610627,0.000090796464,0.0003795433,0.0003632042,0.000039164566,0.0035568953,0.00027857936,0.0026722122],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077085337,0.002164202,0.051249072,0.0004847251,0.000396455,0.0000038716057,0.0049150805,0.000043598295,0.08461265,0.002517939,0.39829764,0.45454392],"study_design_scores_gemma":[0.00092114706,0.0009977546,0.01836983,0.000072583265,0.000036161997,0.00002514554,0.0027399908,0.0072352877,0.018591663,0.00016583975,0.94983476,0.0010098369],"about_ca_topic_score_codex":0.000024373876,"about_ca_topic_score_gemma":0.000088277964,"teacher_disagreement_score":0.5515371,"about_ca_system_score_codex":0.000041065054,"about_ca_system_score_gemma":0.00021457346,"threshold_uncertainty_score":0.99998415},"labels":[],"label_agreement":null},{"id":"W1574079093","doi":"10.1186/1471-2105-4-18","title":"Genome wide identification of regulatory motifs in Bacillus subtilis","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Materials Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Regulon; Operon; Biology; Genetics; Genome; Gene; Computational biology; DNA binding site; Transcription factor; Promoter; Gene expression","score_opus":0.009240679745021633,"score_gpt":0.2097476990422918,"score_spread":0.20050701929727016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574079093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99067163,0.0002506679,0.007739494,0.000017419365,0.0001492346,0.00018819828,0.000023752422,0.0000092185555,0.0009503848],"genre_scores_gemma":[0.98829824,0.0001583285,0.011178896,0.00004061645,0.000020431567,0.000007351932,0.000075094234,0.000011429085,0.00020964276],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99898094,0.00003237404,0.0005594419,0.00013803986,0.00009750482,0.00019170226],"domain_scores_gemma":[0.99921525,0.000007874582,0.00020980115,0.00046136917,0.00006724626,0.00003848188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031987717,0.000118012504,0.0001487646,0.00010003552,0.000024074883,0.000013190468,0.0001823385,0.00027451076,0.00001423991],"category_scores_gemma":[0.00016971008,0.00011573579,0.00005934468,0.00015519258,0.000109351015,0.0000055243718,0.00005855383,0.000064680564,0.000014212668],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028680068,0.000065735156,0.00942741,0.00012377824,0.000017396193,3.5046745e-7,0.00011070525,0.00041185258,0.98816425,0.00057865283,0.000073163894,0.0009980202],"study_design_scores_gemma":[0.00070960226,0.00017074768,0.08762012,0.000012555436,0.0000133886915,0.000013149442,0.00027368183,0.0015858974,0.8915279,0.0002465343,0.017566027,0.00026040382],"about_ca_topic_score_codex":0.0000034942245,"about_ca_topic_score_gemma":0.000030254381,"teacher_disagreement_score":0.09663636,"about_ca_system_score_codex":0.000016210884,"about_ca_system_score_gemma":0.000089416615,"threshold_uncertainty_score":0.47195688},"labels":[],"label_agreement":null},{"id":"W1575415973","doi":"10.1186/1471-2105-7-502","title":"A correlated motif approach for finding short linear motifs from protein interaction networks","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National University of Singapore; Agency for Science, Technology and Research","keywords":"Motif (music); Sequence motif; Computational biology; Network motif; Structural motif; Protein–protein interaction; Computer science; Biology; DNA microarray; Binding site; Genetics; Biological network; Gene; Physics; Biochemistry","score_opus":0.016896112930759988,"score_gpt":0.23701226446665197,"score_spread":0.22011615153589198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1575415973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0545512,0.00015771252,0.94074214,0.00001044662,0.00030394088,0.0009996886,0.0000922502,0.00004830001,0.003094328],"genre_scores_gemma":[0.54113984,0.000019802808,0.45017096,0.00014227227,0.0010096029,0.00014084757,0.006538271,0.00005275685,0.0007856576],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842006,0.000021809325,0.0007523173,0.00022964481,0.00014378258,0.00043236918],"domain_scores_gemma":[0.99909544,0.000028916804,0.00025504612,0.00042722595,0.00010375879,0.00008960124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027029167,0.00029100745,0.00025258685,0.00006771149,0.0001748824,0.00010107903,0.00026028007,0.0004461068,0.000009790184],"category_scores_gemma":[0.000036996073,0.0002716009,0.00019368604,0.00012647874,0.000059474933,0.000026972048,0.00012739073,0.000219652,0.000013413699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006551506,0.00037590662,0.0037928056,0.00044165793,0.0003130873,0.000001004497,0.00037084773,0.9412079,0.0072782077,0.0009520113,0.024567513,0.020043924],"study_design_scores_gemma":[0.0006628609,0.00013624776,0.00026588244,0.0000380455,0.00004244643,0.000008509994,0.00022757289,0.9899227,0.0017111406,0.00012479941,0.006516522,0.0003432418],"about_ca_topic_score_codex":0.000040458974,"about_ca_topic_score_gemma":0.00003297114,"teacher_disagreement_score":0.49057117,"about_ca_system_score_codex":0.00004077399,"about_ca_system_score_gemma":0.00006142787,"threshold_uncertainty_score":0.9999736},"labels":[],"label_agreement":null},{"id":"W1579098064","doi":"10.1186/1471-2105-7-150","title":"Development of an unbiased statistical method for the analysis of unigenic evolution","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computational biology; Mutagenesis; Protein function; Identification (biology); Biology; Genetics; Function (biology); Selection (genetic algorithm); Mutation; Algorithm; Computer science; Statistics; Mathematics; Gene; Artificial intelligence","score_opus":0.01333470820897769,"score_gpt":0.2973163542991686,"score_spread":0.2839816460901909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579098064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07149845,0.000060339495,0.9279547,0.0000051164684,0.000027334974,0.00016648538,0.0001606343,0.0000039503598,0.00012299688],"genre_scores_gemma":[0.16677941,0.000003719189,0.83216655,0.000018053934,0.000015675525,0.0000101224705,0.0009275803,0.0000051205257,0.000073732765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999148,0.000030193478,0.00048731457,0.00008156859,0.00013094327,0.00012194508],"domain_scores_gemma":[0.99929845,0.000060666713,0.00020135852,0.0002653107,0.00014502612,0.000029160536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004122695,0.0000814375,0.0001516163,0.000079874895,0.000059828988,0.00000593091,0.0001406021,0.000080549784,0.00000715413],"category_scores_gemma":[0.00006403932,0.000061550745,0.00009691835,0.00022786667,0.000065351065,0.0000029952598,0.000033321474,0.00002383847,6.4470186e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063711504,0.00080223574,0.009689596,0.0007639488,0.0027730744,1.4789246e-7,0.0012646962,0.7460462,0.13820882,0.04510628,0.0018826212,0.05282525],"study_design_scores_gemma":[0.00032271113,0.000071147755,0.039972436,0.000002432541,0.00034089928,6.3768755e-7,0.00038820432,0.9486657,0.008420983,0.00013330439,0.0015919823,0.000089605484],"about_ca_topic_score_codex":0.000027819015,"about_ca_topic_score_gemma":0.0010455142,"teacher_disagreement_score":0.20261945,"about_ca_system_score_codex":0.000016658129,"about_ca_system_score_gemma":0.00018858547,"threshold_uncertainty_score":0.25099665},"labels":[],"label_agreement":null},{"id":"W1582408600","doi":"10.1186/1471-2105-16-s4-s3","title":"The relative vertex clustering value - a new criterion for the fast discovery of functional modules in protein interaction networks","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute for Health and Care Research; Menzies Centre for Australian Studies, King's College London, University of London; Maudsley Charity","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Data mining; Node (physics); Vertex (graph theory); Modular design; Similarity (geometry); Gene ontology; False positive paradox; Theoretical computer science; Computational biology; Artificial intelligence; Biology; Gene; Graph; Engineering","score_opus":0.027339656887565112,"score_gpt":0.2520429527433197,"score_spread":0.2247032958557546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582408600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009824746,0.0005000723,0.9878741,0.00015365615,0.00052062055,0.00066010846,0.000013111393,0.0000055177243,0.00044810103],"genre_scores_gemma":[0.9407325,0.00023148616,0.05567426,0.00031210136,0.0006787904,0.00016934707,0.00028104798,0.000038591388,0.0018818735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903613,0.000029097977,0.00050300616,0.000089904905,0.00012870769,0.00021314419],"domain_scores_gemma":[0.9992163,0.00010325127,0.00026306484,0.0002864952,0.0000810852,0.000049797698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000511518,0.00013823085,0.00012504462,0.000030076628,0.0001204317,0.00009371386,0.00019814409,0.00013083185,7.929406e-7],"category_scores_gemma":[0.00013826221,0.000084709114,0.000101313584,0.000086707725,0.0000828835,0.000055219352,0.00015138276,0.00013786685,0.00000202725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025465034,0.00008630357,0.00046021666,0.00024771356,0.00024584206,2.2810288e-7,0.00275165,0.8788599,0.0014933051,0.012140784,0.01883654,0.08233106],"study_design_scores_gemma":[0.0008052864,0.00019006961,0.00044494492,0.00006866837,0.000016616807,0.0000068815993,0.0014535337,0.9885152,0.00031117274,0.001140545,0.0069252574,0.000121851874],"about_ca_topic_score_codex":0.00003070107,"about_ca_topic_score_gemma":0.00027151007,"teacher_disagreement_score":0.93219984,"about_ca_system_score_codex":0.00003911661,"about_ca_system_score_gemma":0.00013802649,"threshold_uncertainty_score":0.34543374},"labels":[],"label_agreement":null},{"id":"W1583563537","doi":"10.1186/1471-2105-8-21","title":"GraphDNA: a Java program for graphical display of DNA composition analyses","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service","keywords":"GenBank; Genome; DNA sequencing; DNA; Biology; Computational biology; Java; Computer science; Genetics; Programming language; Gene","score_opus":0.024989114800006554,"score_gpt":0.3339482154069852,"score_spread":0.3089591006069787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583563537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6893567,0.0001542803,0.30924356,0.000024089291,0.000049107522,0.0003530469,0.000048003203,0.000020858814,0.00075039646],"genre_scores_gemma":[0.886339,0.000044226443,0.11274514,0.00010032154,0.00006384778,0.000021844533,0.0006452983,0.0000084746935,0.000031858817],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907047,0.000010100935,0.0004391241,0.0001139219,0.00014456396,0.00022179467],"domain_scores_gemma":[0.99934006,0.000029222989,0.00018957812,0.00022823372,0.00013502178,0.00007789553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024564366,0.00012514311,0.00018051761,0.00012016975,0.000064371234,0.000018018498,0.00013678185,0.0001402289,0.0000034640564],"category_scores_gemma":[0.000046198147,0.000100024656,0.0002883268,0.0002621031,0.00013747907,0.000011269487,0.00003681601,0.00004401214,0.0000026342077],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009493408,0.0010374789,0.025044391,0.0010460626,0.00069774245,0.0000025505076,0.00030227483,0.0006122135,0.92383385,0.0028481397,0.0020775946,0.041548364],"study_design_scores_gemma":[0.0019063824,0.0023413354,0.019099109,0.000083339524,0.00053363206,0.000032463948,0.0010083779,0.06360994,0.9002122,0.00079317857,0.0096441265,0.00073587993],"about_ca_topic_score_codex":0.000012370606,"about_ca_topic_score_gemma":0.00006647818,"teacher_disagreement_score":0.19698232,"about_ca_system_score_codex":0.0000057751136,"about_ca_system_score_gemma":0.00003119518,"threshold_uncertainty_score":0.4078887},"labels":[],"label_agreement":null},{"id":"W1585902742","doi":"10.1186/1471-2105-7-193","title":"An interactive tool for visualization of relationships between gene expression profiles","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; Occupational Cancer Research Centre","funders":"Michael Smith Health Research BC; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; BC Cancer Foundation; Genome Canada","keywords":"DNA microarray; Visualization; Computational biology; Gene expression; Expression (computer science); Gene expression profiling; Biology; Gene; Computer science; Data science; Genetics; Data mining; Programming language","score_opus":0.030013852555015635,"score_gpt":0.3056036402523903,"score_spread":0.27558978769737463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1585902742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27678794,0.00003201294,0.7222938,0.000008130221,0.00005578768,0.00033595017,0.0000631591,0.000015017082,0.00040821012],"genre_scores_gemma":[0.8877861,0.0000076673205,0.10966191,0.00001320719,0.00018067946,0.00006493335,0.0021258425,0.000012800469,0.00014684636],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925333,0.00004764099,0.0003736477,0.00011830963,0.000106997315,0.00010009582],"domain_scores_gemma":[0.99924517,0.000025281468,0.00028161416,0.00025750673,0.00016051291,0.000029900119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018586338,0.00009223222,0.000096568205,0.00006584849,0.00008499208,0.000020136758,0.00011077135,0.00013724748,0.0000048648517],"category_scores_gemma":[0.00008177749,0.00008251452,0.000052360927,0.00008073387,0.00002894846,0.000024948227,0.000024714978,0.00003680028,0.000002369769],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012125128,0.0000900017,0.050377607,0.00014584935,0.000010852106,1.3505414e-8,0.00023650208,0.0014152656,0.94139236,0.0008508315,0.0039207777,0.0014386689],"study_design_scores_gemma":[0.00048642824,0.00016056233,0.02805963,0.000030410058,0.00001721017,6.533464e-7,0.00028792134,0.012730608,0.9545882,0.00031117958,0.0031885023,0.0001387077],"about_ca_topic_score_codex":0.0000020962327,"about_ca_topic_score_gemma":0.0000030250706,"teacher_disagreement_score":0.6126319,"about_ca_system_score_codex":0.00001244932,"about_ca_system_score_gemma":0.000062611805,"threshold_uncertainty_score":0.33648443},"labels":[],"label_agreement":null},{"id":"W1593404939","doi":"10.1186/1471-2105-5-37","title":"Structural characterization of genomes by large scale sequence-structure threading","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Genome Prairie; Genome British Columbia; Michael Smith Health Research BC","keywords":"Threading (protein sequence); Proteome; Computational biology; Biology; Sequence motif; Genome; DNA microarray; Gene; Genetics; Protein structure; Gene expression; Biochemistry","score_opus":0.009893237619123097,"score_gpt":0.2328918501546392,"score_spread":0.22299861253551612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593404939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9794753,0.00012295635,0.019610845,0.000028305758,0.000059537782,0.000094071554,0.0004028137,0.000011213286,0.00019496774],"genre_scores_gemma":[0.9853848,0.00010796852,0.011872567,0.00017617576,0.00006316976,0.0000023836003,0.0022683698,0.000010228057,0.00011431828],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992332,0.00000859813,0.00030577523,0.000115944174,0.00013720496,0.00019931262],"domain_scores_gemma":[0.9994511,0.000002434136,0.00019590041,0.00022467162,0.000069722286,0.000056169632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000535595,0.00013364246,0.00015362426,0.000043827513,0.00007480068,0.000024652083,0.00015970372,0.00013354323,0.0000299166],"category_scores_gemma":[0.000016587743,0.00011067218,0.00008529358,0.00013614741,0.000069513706,0.00002801795,0.000057645335,0.000056129666,0.0000069740518],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020550206,0.000011835373,0.006280123,0.00009039308,0.000030291994,2.3361122e-7,0.00036433525,0.00044804852,0.99164546,0.00010065855,0.000031089134,0.0009770019],"study_design_scores_gemma":[0.0008882826,0.00021403462,0.003537681,0.000042684173,0.00006096101,0.000026306647,0.0006220985,0.014164828,0.97745484,0.0005343748,0.0020356334,0.00041826448],"about_ca_topic_score_codex":0.0000107422675,"about_ca_topic_score_gemma":0.00003725553,"teacher_disagreement_score":0.014190588,"about_ca_system_score_codex":0.000019713223,"about_ca_system_score_gemma":0.00006703947,"threshold_uncertainty_score":0.45130807},"labels":[],"label_agreement":null},{"id":"W1595684610","doi":"10.1186/1471-2105-5-61","title":"An approach to large scale identification of non-obvious structural similarities between proteins","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"Genome Prairie; Genome British Columbia; Michael Smith Health Research BC","keywords":"Threading (protein sequence); Computational biology; Biology; Genome; Sequence alignment; Genetics; Structural similarity; Peptide sequence; Protein structure; Sequence (biology); Protein sequencing; Gene; DNA microarray; Virulence; Gene expression","score_opus":0.009320389599279316,"score_gpt":0.26985422941676046,"score_spread":0.2605338398174811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595684610","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49086368,0.000009833522,0.5072505,0.000013455954,0.000051511113,0.000480317,0.00014183194,0.000026321351,0.001162592],"genre_scores_gemma":[0.6823338,0.0000029283376,0.31660748,0.00010270633,0.00010678237,0.000023708026,0.0007451851,0.000019465579,0.000057941714],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834615,0.000028029835,0.0008024014,0.00017379357,0.00031013033,0.00033952217],"domain_scores_gemma":[0.99861807,0.0000074791033,0.00035373867,0.00071056234,0.00015807511,0.00015208739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041647948,0.00022257035,0.00024577716,0.00012248885,0.00014325752,0.00007563033,0.00048595158,0.00021900871,0.000003470753],"category_scores_gemma":[0.000107986045,0.00020722314,0.00009369758,0.00019173876,0.00008659189,0.000041396917,0.00015614196,0.00015055496,0.0000214816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051971176,0.0013633531,0.367834,0.009591426,0.0005337357,0.0000012119306,0.060659654,0.35909823,0.18061416,0.0047745164,0.0019026969,0.013107305],"study_design_scores_gemma":[0.0043757963,0.0019113693,0.28015056,0.00015346752,0.00016367053,0.000050308605,0.0093738055,0.39115056,0.30807555,0.0006319966,0.0021846404,0.0017782485],"about_ca_topic_score_codex":0.000019332234,"about_ca_topic_score_gemma":0.000021660073,"teacher_disagreement_score":0.19147013,"about_ca_system_score_codex":0.0000306086,"about_ca_system_score_gemma":0.00012884293,"threshold_uncertainty_score":0.84503144},"labels":[],"label_agreement":null},{"id":"W1597403892","doi":"10.1186/1471-2105-7-497","title":"cPath: open source software for collecting, storing, and querying biological pathways","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Oregon Health and Science University; GlaxoSmithKline","keywords":"Computer science; SBML; Identifier; Software; Data exchange; World Wide Web; Visualization; Web service; Application programming interface; Database; XML; Data mining; Markup language","score_opus":0.03728236492655906,"score_gpt":0.25595017992542096,"score_spread":0.2186678149988619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597403892","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1249002,0.00068668794,0.8691036,0.000028111674,0.00027499642,0.0011890513,0.000117216725,0.00006742343,0.0036326938],"genre_scores_gemma":[0.15604755,0.00018057543,0.83816046,0.00079269405,0.00085177907,0.00020958051,0.0009752717,0.000073768824,0.0027083212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987405,0.000020293839,0.00052572426,0.00021043122,0.00009424561,0.00040879636],"domain_scores_gemma":[0.9991516,0.00006314601,0.00026544655,0.00031584827,0.00010623821,0.00009775597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046393022,0.00023593777,0.00025742664,0.00004662694,0.0003505893,0.00023398135,0.00037278185,0.00028545872,0.000006150962],"category_scores_gemma":[0.00016183015,0.00020298254,0.00008613557,0.00010572098,0.000090338115,0.000020253303,0.0005120924,0.00010448382,0.0000065417216],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022277483,0.0010775826,0.15090398,0.0038912967,0.000716692,0.0000068557683,0.0063161985,0.021424225,0.025674477,0.02501527,0.42773458,0.3350111],"study_design_scores_gemma":[0.0062133847,0.001828941,0.003833162,0.00017652904,0.00009561994,0.00016328203,0.0024117173,0.20543215,0.0072800736,0.004642249,0.76585925,0.0020636728],"about_ca_topic_score_codex":0.000035910412,"about_ca_topic_score_gemma":0.00007888518,"teacher_disagreement_score":0.33812463,"about_ca_system_score_codex":0.000024668627,"about_ca_system_score_gemma":0.0001243964,"threshold_uncertainty_score":0.82773876},"labels":[],"label_agreement":null},{"id":"W1600834905","doi":"10.1186/1471-2105-6-78","title":"CGMIM: Automated text-mining of Online Mendelian Inheritance in Man (OMIM) to identify genetically-associated cancers and candidate genes","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Michael Smith Health Research BC","keywords":"OMIM : Online Mendelian Inheritance in Man; CDKN2A; Cancer; Gene; Mendelian inheritance; Biology; Genetics; Candidate gene; Computational biology; Bioinformatics; Phenotype","score_opus":0.020657280603231,"score_gpt":0.3130826807367318,"score_spread":0.29242540013350077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600834905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965353,0.00092606683,0.0016085857,0.00027188257,0.00007389203,0.00017774799,0.00010958343,0.0000593758,0.00023756151],"genre_scores_gemma":[0.82407624,0.000495686,0.17451984,0.0005496414,0.000060445334,0.000015009609,0.00013948324,0.000019039666,0.00012464225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868083,0.0000367475,0.00057616923,0.00019495682,0.00016975352,0.00034152227],"domain_scores_gemma":[0.9993648,0.000027129603,0.00016516034,0.00023362189,0.00006934927,0.00013996306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002478296,0.00018019605,0.00027661995,0.00010907227,0.000045323945,0.000024600158,0.00021062265,0.00023606644,0.000008195344],"category_scores_gemma":[0.00023835587,0.00016543256,0.000041271476,0.0002184072,0.00014763967,0.000008422213,0.00015863587,0.000082730185,0.000005170898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005905119,0.00059676287,0.15327033,0.000976795,0.0004348031,0.000014450246,0.0062720496,0.00933054,0.22756383,0.00007351611,0.01923945,0.58163697],"study_design_scores_gemma":[0.005748695,0.0015632355,0.40084827,0.00073386537,0.00011734604,0.000048849783,0.006376931,0.49016017,0.054145336,0.000050097824,0.038583856,0.0016233644],"about_ca_topic_score_codex":0.00009152959,"about_ca_topic_score_gemma":0.0033173528,"teacher_disagreement_score":0.5800136,"about_ca_system_score_codex":0.000057022688,"about_ca_system_score_gemma":0.00016846869,"threshold_uncertainty_score":0.6746144},"labels":[],"label_agreement":null},{"id":"W1602695191","doi":"10.1186/s12859-015-0633-x","title":"PredSTP: a highly accurate SVM based model to predict sequential cystine stabilized peptides","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Baylor University","keywords":"Computational biology; Peptide; Leverage (statistics); Support vector machine; Computer science; Combinatorial chemistry; Biological system; Chemistry; Bioinformatics; Biology; Biochemistry; Artificial intelligence","score_opus":0.05321804551242116,"score_gpt":0.26556696284134373,"score_spread":0.21234891732892258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602695191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4077111,0.0001928477,0.5786356,0.00047278008,0.0012600996,0.0014913782,0.0010449912,0.0006843867,0.008506834],"genre_scores_gemma":[0.86837167,0.000008591755,0.12438234,0.0009666206,0.000080381375,0.00005459617,0.00046281883,0.00004379147,0.005629183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984256,0.00007783778,0.00063701504,0.00021052055,0.00009461011,0.0005544033],"domain_scores_gemma":[0.9989223,0.0001038282,0.00022895237,0.0004287841,0.00019793616,0.000118215416],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038472514,0.00031404506,0.00041718525,0.00016607803,0.00016509311,0.0000851201,0.0003487584,0.0002501733,0.000100318415],"category_scores_gemma":[0.00023065046,0.00026292907,0.00014475164,0.00018261278,0.00020229431,0.00046424693,0.00020409508,0.0002372105,0.0008671727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005861263,0.00095932215,0.0032672482,0.0012307278,0.000548171,0.000011184261,0.01138231,0.42624575,0.15456852,0.003320521,0.38904327,0.003561711],"study_design_scores_gemma":[0.0092235,0.0011705016,0.00023865947,0.00029477858,0.00022640088,0.00009041757,0.0031741734,0.8597448,0.083944336,0.00037548988,0.040200297,0.0013166803],"about_ca_topic_score_codex":0.000081554615,"about_ca_topic_score_gemma":0.00010635077,"teacher_disagreement_score":0.46066058,"about_ca_system_score_codex":0.000080962476,"about_ca_system_score_gemma":0.00051631354,"threshold_uncertainty_score":0.9999823},"labels":[],"label_agreement":null},{"id":"W1605701032","doi":"10.1186/1471-2105-6-274","title":"A stepwise framework for the normalization of array CGH data","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; University of British Columbia","funders":"National Institute of Dental and Craniofacial Research; Genome British Columbia; Genome Canada","keywords":"Normalization (sociology); DNA microarray; Comparative genomic hybridization; Biology; Copy-number variation; Computational biology; Microarray; Genetics; Computer science; Pattern recognition (psychology); Chromosome; Gene; Artificial intelligence; Gene expression; Genome","score_opus":0.03866257181589215,"score_gpt":0.2817151930408506,"score_spread":0.2430526212249584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605701032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009334175,0.0003336578,0.98876643,0.00016836054,0.00011437145,0.0002937859,0.0003263631,0.000008058353,0.00065480307],"genre_scores_gemma":[0.39338773,0.00017802902,0.6043894,0.00033362393,0.00042543127,0.00002989101,0.00088392885,0.000014354165,0.0003575816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993459,0.0000113619335,0.0003257892,0.00008852452,0.00008992305,0.00013851526],"domain_scores_gemma":[0.9989559,0.00005607122,0.00017524349,0.00069866085,0.00008729567,0.000026804542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002266429,0.00008942389,0.000087722896,0.000019661715,0.000100329395,0.000027231992,0.00042500166,0.00009567824,0.000020596082],"category_scores_gemma":[0.00015527065,0.000064226675,0.00005136427,0.00005938157,0.000050002538,0.000017592502,0.00012255835,0.00003828374,0.000008101227],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019109409,0.0017460553,0.058272768,0.005864872,0.0024346185,4.971429e-7,0.026045226,0.17575909,0.04293939,0.38419977,0.13012579,0.17070098],"study_design_scores_gemma":[0.0015892996,0.00040215914,0.0027891996,0.00007893683,0.00023445791,0.000026952486,0.0050616306,0.32283422,0.06901006,0.0013516509,0.5960175,0.0006039477],"about_ca_topic_score_codex":0.0000050928315,"about_ca_topic_score_gemma":0.000041087762,"teacher_disagreement_score":0.4658917,"about_ca_system_score_codex":0.000006517719,"about_ca_system_score_gemma":0.00008888431,"threshold_uncertainty_score":0.2619088},"labels":[],"label_agreement":null},{"id":"W1606410455","doi":"10.1186/1471-2105-7-301","title":"Improving the accuracy of protein secondary structure prediction using structural alignment","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":148,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Prairie; Genome Canada","keywords":"Sequence (biology); Protein secondary structure; Computer science; Structural genomics; Protein structure database; Set (abstract data type); Alignment-free sequence analysis; Structural alignment; Sequence alignment; Protein structure prediction; Multiple sequence alignment; Data mining; Protein structure; Test set; Computational biology; Artificial intelligence; Sequence database; Peptide sequence; Biology; Genetics","score_opus":0.006201983545477943,"score_gpt":0.21759728903657752,"score_spread":0.21139530549109958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606410455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90889263,0.00026836572,0.08954392,0.000010412662,0.0001926239,0.0005492051,0.0002675861,0.000015093956,0.00026015696],"genre_scores_gemma":[0.90801483,0.0000029741864,0.09133133,0.000048017042,0.00025718776,0.0000072216462,0.0002809296,0.000014898696,0.00004262235],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99894625,0.000027764323,0.00048919115,0.00012840667,0.00019681048,0.00021159915],"domain_scores_gemma":[0.9990741,0.000013568917,0.0004051676,0.00039806272,0.000078335856,0.000030780957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011259245,0.0001727472,0.00013168233,0.000034256114,0.00013689205,0.000038937847,0.00022529351,0.00016747181,0.0000127538815],"category_scores_gemma":[0.000078788755,0.00011767089,0.00008401018,0.00008514545,0.00010506017,0.000020679056,0.0001396975,0.00012430122,5.2414987e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094659095,0.000012217331,0.0033897816,0.00046459676,0.000054416523,4.7905274e-7,0.00015952866,0.011486124,0.97312963,0.0010523786,0.00020804352,0.009948151],"study_design_scores_gemma":[0.0011683991,0.0002500464,0.0074918903,0.000052233987,0.00007674077,0.000106605345,0.0004332929,0.41481927,0.5713325,0.0020024427,0.0018422289,0.00042434392],"about_ca_topic_score_codex":0.0000859532,"about_ca_topic_score_gemma":0.000058259044,"teacher_disagreement_score":0.40333316,"about_ca_system_score_codex":0.000025571457,"about_ca_system_score_gemma":0.00016499504,"threshold_uncertainty_score":0.47984797},"labels":[],"label_agreement":null},{"id":"W1608637158","doi":"10.1186/s12859-015-0584-2","title":"Probing long-range interactions by extracting free energies from genome-wide chromosome conformation capture data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Chromosome conformation capture; Chromatin; Pairwise comparison; Normalization (sociology); Genome; Biological system; Principal component analysis; Computational biology; Distance matrix; Biology; DNA; Physics; Computer science; Genetics; Algorithm; Artificial intelligence; Transcription factor; Gene","score_opus":0.028626476542384725,"score_gpt":0.24887909791723126,"score_spread":0.22025262137484652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1608637158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81008804,0.0013353634,0.18131542,0.00014757075,0.00060757675,0.00044797923,0.0019492944,0.000078999605,0.004029727],"genre_scores_gemma":[0.7852498,0.0003434721,0.17136395,0.00083099474,0.0005959309,0.000046858266,0.04027961,0.0000915156,0.001197831],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864733,0.000027207323,0.0005779509,0.00023163694,0.00021829031,0.00029756347],"domain_scores_gemma":[0.9980645,0.000033212604,0.00039665258,0.0012342872,0.00013628518,0.00013504826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026232525,0.00024395568,0.00019769967,0.000053547054,0.00013202954,0.0001449715,0.0008367266,0.00018722551,0.000020395066],"category_scores_gemma":[0.00029153316,0.00023725636,0.000060086048,0.0000853346,0.000056402325,0.00011126385,0.00069744233,0.00017870027,0.000050527047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006944962,0.0012139806,0.08438522,0.0022237266,0.0019131928,0.000024579731,0.041320372,0.078827575,0.16054626,0.00035121525,0.61159843,0.016900986],"study_design_scores_gemma":[0.0030269574,0.00020715682,0.0025482706,0.000119395256,0.00017277467,0.00010045766,0.012936049,0.8006974,0.0061274446,0.00020850929,0.17249209,0.001363516],"about_ca_topic_score_codex":0.0001054931,"about_ca_topic_score_gemma":0.00044379817,"teacher_disagreement_score":0.7218698,"about_ca_system_score_codex":0.000081272534,"about_ca_system_score_gemma":0.0002321979,"threshold_uncertainty_score":0.96750337},"labels":[],"label_agreement":null},{"id":"W1615242748","doi":"10.1186/1471-2105-6-236","title":"SIMPROT: Using an empirically determined indel distribution in simulations of protein evolution","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Indel; Alignment-free sequence analysis; Multiple sequence alignment; Sequence (biology); Phylogenetic tree; INDEL Mutation; Sequence alignment; Sequence analysis; Computational biology; Biology; Genetics; Molecular evolution; Protein family; Computer science; Algorithm; Peptide sequence; Gene","score_opus":0.02861468696996599,"score_gpt":0.28027649220881806,"score_spread":0.25166180523885207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1615242748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8906315,0.00008032551,0.108790636,0.000011026901,0.000017616443,0.00031161006,0.000103370054,0.0000024202795,0.000051512223],"genre_scores_gemma":[0.94323236,0.0000044101057,0.056504335,0.00001958291,0.00005849821,0.000008551495,0.00015349597,0.0000065545246,0.0000122153615],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925596,0.000023306331,0.00038419568,0.00009711643,0.0000863775,0.0001530704],"domain_scores_gemma":[0.999516,0.0000068189156,0.00014230405,0.00020579684,0.00009037532,0.000038694074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001218231,0.00009985407,0.000112913796,0.00004211715,0.000049772883,0.000010068514,0.000094398965,0.00010812455,0.0000023788255],"category_scores_gemma":[0.0000748822,0.00009737675,0.000040107778,0.00010224585,0.00004677289,0.000005273271,0.000064095126,0.000041805342,0.0000012133831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014056012,0.0003900378,0.052341428,0.00017132043,0.0000365768,2.0658966e-7,0.0006164506,0.30500907,0.6328023,0.00028025024,0.000031091386,0.008180704],"study_design_scores_gemma":[0.00072000636,0.00023308433,0.026110997,0.000020232366,0.00001407425,0.0000029518371,0.00016271858,0.9420767,0.029374938,0.00014169971,0.0009482864,0.00019433236],"about_ca_topic_score_codex":0.000021354586,"about_ca_topic_score_gemma":0.0002938146,"teacher_disagreement_score":0.6370676,"about_ca_system_score_codex":0.000040325132,"about_ca_system_score_gemma":0.00010509036,"threshold_uncertainty_score":0.39709088},"labels":[],"label_agreement":null},{"id":"W1619065037","doi":"10.1186/1471-2105-16-s14-s4","title":"Reconstructing a SuperGeneTree minimizing reconciliation","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Supertree; Phylogenetic tree; Tree (set theory); Tree rearrangement; Set (abstract data type); Heuristic; Computer science; Computational phylogenetics; Algorithm; Theoretical computer science; Mathematics; Phylogenetic network; Combinatorics; Biology; Artificial intelligence; Gene; Genetics","score_opus":0.051889195989607555,"score_gpt":0.24952029348179056,"score_spread":0.197631097492183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1619065037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9765615,0.00070893153,0.010412151,0.000042345346,0.00054607796,0.00015680258,0.000018417457,0.000010050806,0.011543708],"genre_scores_gemma":[0.5666794,0.00017227049,0.4319019,0.000261999,0.00042837948,0.000018915043,0.00007569905,0.000024392442,0.00043700583],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992383,0.000019968818,0.00031381124,0.00012579632,0.00010314122,0.00019897896],"domain_scores_gemma":[0.9994097,0.0000124213675,0.0001108079,0.00024171083,0.0001256568,0.000099743724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026296507,0.00012397155,0.000116825955,0.000037724785,0.00006962383,0.00002923551,0.0001243874,0.00009324329,0.0000043229434],"category_scores_gemma":[0.00022985775,0.00011904551,0.000060046845,0.00007051546,0.000041145682,0.000002245704,0.00010690623,0.000042735886,0.000030423464],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027609972,0.000108266635,0.8037101,0.00030844667,0.0003708145,0.0000020265832,0.0060116695,0.0072725434,0.064785175,0.0009128963,0.029759461,0.08648249],"study_design_scores_gemma":[0.009633231,0.0023590054,0.028198263,0.00014428895,0.00024657373,0.00046051777,0.042165954,0.33170557,0.16262747,0.0029162911,0.4159081,0.0036347378],"about_ca_topic_score_codex":0.000010046331,"about_ca_topic_score_gemma":0.00007038793,"teacher_disagreement_score":0.77551186,"about_ca_system_score_codex":0.00001919287,"about_ca_system_score_gemma":0.00015415852,"threshold_uncertainty_score":0.4854535},"labels":[],"label_agreement":null},{"id":"W1640378004","doi":"10.1186/1471-2105-6-30","title":"An ant colony optimisation algorithm for the 2D and 3D hydrophobic polar protein folding problem","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":261,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein folding; Polar; Protein structure prediction; Computer science; Folding (DSP implementation); Ant colony optimization algorithms; Ant colony; Computational biology; DNA microarray; Algorithm; Chemistry; Artificial intelligence; Protein structure; Biology; Engineering; Biochemistry; Physics; Gene","score_opus":0.007372782569299728,"score_gpt":0.23658003288229887,"score_spread":0.22920725031299913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1640378004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09500834,0.0005614203,0.9025057,0.0001059318,0.00005150385,0.0014687136,0.00007537123,0.00002609004,0.00019693948],"genre_scores_gemma":[0.08826487,0.00007821541,0.9106774,0.00026374913,0.0002678452,0.00012502218,0.00017956083,0.000019219953,0.00012413917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925464,0.000017696455,0.00026119713,0.00013909771,0.00010425565,0.00022312568],"domain_scores_gemma":[0.99943596,0.000015573303,0.00013449085,0.00028873215,0.000060030627,0.00006521893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025076533,0.00014888914,0.0001072135,0.000028954586,0.00020804068,0.00007922498,0.00016822047,0.00015290751,0.0000026269256],"category_scores_gemma":[0.000022929475,0.00010717522,0.000046952053,0.000049143495,0.00006665617,0.000025085914,0.00006061864,0.000071248265,0.0000020675902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021535615,0.00013666849,0.00047372677,0.0005155514,0.00016917469,7.340424e-7,0.0014867667,0.016756276,0.19560106,0.001400112,0.00095324166,0.78229135],"study_design_scores_gemma":[0.0006051107,0.00040861234,0.00008669282,0.000014997131,0.000030217916,0.00002380365,0.00016553319,0.9609353,0.02053837,0.00017507345,0.01681608,0.0002001945],"about_ca_topic_score_codex":0.000011062299,"about_ca_topic_score_gemma":0.000044076904,"teacher_disagreement_score":0.94417906,"about_ca_system_score_codex":0.000019275898,"about_ca_system_score_gemma":0.00007488898,"threshold_uncertainty_score":0.43704787},"labels":[],"label_agreement":null},{"id":"W1649804825","doi":"10.1186/1471-2105-7-523","title":"BioMoby extensions to the Taverna workflow management and enactment software","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Genome Alberta; Genome Canada","keywords":"Workflow; Computer science; Interoperability; Web service; World Wide Web; Workflow management system; Software; Software engineering; Plug-in; Service (business); Data science; Database; Programming language","score_opus":0.06956754340785506,"score_gpt":0.3193051713387781,"score_spread":0.24973762793092305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1649804825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010326661,0.00011442749,0.975248,0.0014738948,0.0012130032,0.0007201025,0.00005800199,0.00012600912,0.010719927],"genre_scores_gemma":[0.04098781,0.000019946574,0.93324137,0.002165328,0.00017602275,0.000036342404,0.00004434809,0.000014759812,0.023314096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972655,0.00004795306,0.00069998985,0.00034479654,0.001306144,0.00033561746],"domain_scores_gemma":[0.9977165,0.00044680998,0.00018029497,0.0014278927,0.00010680281,0.00012169806],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026375293,0.00015535206,0.00015794956,0.00028890886,0.00048518632,0.0010065986,0.0009560574,0.00003065992,0.000081483595],"category_scores_gemma":[0.0004332575,0.00008723408,0.00006967947,0.0010280842,0.000078703066,0.0002437577,0.0012423127,0.00006368082,0.0016745622],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008562486,0.000050684343,0.0025542136,0.000018888562,0.000012273772,0.000004216831,0.00042652022,0.0063966084,7.6160165e-7,0.0042953687,0.68743324,0.29879868],"study_design_scores_gemma":[0.00030364416,0.00003443682,0.04810964,0.000042122378,0.0000264662,0.000009560406,0.0020715892,0.16243346,0.000010745772,0.0063918433,0.78035,0.00021646408],"about_ca_topic_score_codex":0.000039423277,"about_ca_topic_score_gemma":0.000119105775,"teacher_disagreement_score":0.2985822,"about_ca_system_score_codex":0.00003817213,"about_ca_system_score_gemma":0.000018041805,"threshold_uncertainty_score":0.9991028},"labels":[],"label_agreement":null},{"id":"W1659685982","doi":"10.1186/1471-2105-16-s11-s1","title":"Highlights from the 5th Symposium on Biological Data Visualization: Part 1","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Visualization; Data science; Computer science; Data visualization; Process (computing); Creative visualization; Soundness; Data mining","score_opus":0.10683240757574981,"score_gpt":0.2995042047459029,"score_spread":0.1926717971701531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1659685982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90685725,0.0052164146,0.044123683,0.00370999,0.0039508375,0.001458351,0.0026000293,0.000073603704,0.032009833],"genre_scores_gemma":[0.9296856,0.0052132374,0.04277594,0.008041933,0.0043266853,0.00006299311,0.00892845,0.00006880393,0.0008963346],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916357,0.0000475047,0.00026698966,0.00020062193,0.0001436721,0.0001776234],"domain_scores_gemma":[0.9987942,0.000046636243,0.000104929044,0.00090070785,0.000071273265,0.000082250124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023953179,0.00014972057,0.00012261044,0.000011311567,0.0001114401,0.000049288286,0.00057567353,0.00011441609,0.000007350187],"category_scores_gemma":[0.00012981404,0.000088362925,0.000037694466,0.000059538866,0.00009153933,0.0000021280043,0.00049599365,0.00004664766,0.00008221466],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005639457,0.00044104288,0.049951892,0.00004973422,0.0006162948,0.0000034591844,0.0028532536,0.0026944554,0.013933074,0.013848577,0.91171575,0.0033285473],"study_design_scores_gemma":[0.00060419337,0.00035965838,0.0025924183,0.000012279195,0.00002344148,0.000004232395,0.0005608098,0.009358655,0.003951431,0.00022846226,0.98205084,0.00025355374],"about_ca_topic_score_codex":0.000011005189,"about_ca_topic_score_gemma":0.000034148045,"teacher_disagreement_score":0.07033514,"about_ca_system_score_codex":0.000008195994,"about_ca_system_score_gemma":0.0000827334,"threshold_uncertainty_score":0.36033356},"labels":[],"label_agreement":null},{"id":"W1689468366","doi":"10.1186/1471-2105-6-6","title":"Cyclic nucleotide binding proteins in the Arabidopsis thaliana and Oryza sativa genomes","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Kinase Regulation and GTPase Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation pour la Recherche Médicale","keywords":"Oryza sativa; Nucleotide; Biology; Arabidopsis thaliana; Arabidopsis; Cyclic nucleotide; Effector; Protein kinase A; Genome; Second messenger system; Cyclic nucleotide-binding domain; Oryza; Genetics; Biochemistry; Cell biology; Kinase; Signal transduction; Gene; Mutant","score_opus":0.017012467508508936,"score_gpt":0.24554592737879735,"score_spread":0.22853345987028842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1689468366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98534703,0.0008661906,0.008482856,0.0005276024,0.00002992878,0.00069681084,0.000017582648,0.000020768583,0.0040112096],"genre_scores_gemma":[0.94898796,0.0001453021,0.04975433,0.00059727044,0.00015840572,0.000040562714,0.000058894333,0.000014502745,0.00024277483],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918765,0.000049374292,0.00029194323,0.00012087691,0.0001401289,0.0002100153],"domain_scores_gemma":[0.9995505,0.00001710382,0.00010803291,0.00025435843,0.000020856553,0.000049150203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035848527,0.00013359907,0.00010858117,0.000075546115,0.00010558293,0.00006429763,0.0001548017,0.00009323445,0.000013871919],"category_scores_gemma":[0.00006782724,0.00009735516,0.000049234364,0.00013160662,0.00006653896,0.000016972648,0.00006461684,0.00008753267,0.000021299777],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047043996,0.0007642352,0.1203478,0.0019764772,0.00031659447,0.000025217356,0.017737895,0.009972154,0.46614403,0.017381746,0.008292052,0.35657135],"study_design_scores_gemma":[0.0057291333,0.0006490242,0.05244862,0.0004077245,0.00011118786,0.00029165612,0.010212769,0.13307215,0.30710533,0.00048825206,0.48730287,0.0021812858],"about_ca_topic_score_codex":0.0000064081714,"about_ca_topic_score_gemma":0.000054536005,"teacher_disagreement_score":0.47901082,"about_ca_system_score_codex":0.000015909602,"about_ca_system_score_gemma":0.000044263048,"threshold_uncertainty_score":0.39700282},"labels":[],"label_agreement":null},{"id":"W1691146018","doi":"10.1186/1471-2105-7-305","title":"Taking U out, with two nucleases?","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA regulation and disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases; National Institute on Aging; National Institutes of Health; U.S. Department of Energy","keywords":"Trypanosoma brucei; Biology; Computational biology; Subfamily; RNA editing; RNA; Function (biology); Genetics; Protein domain; Gene","score_opus":0.011830757204466818,"score_gpt":0.2450078684551008,"score_spread":0.23317711125063398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1691146018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66267866,0.00019779787,0.2246154,0.00007406013,0.00013902356,0.00030856024,0.00003881677,0.00008188647,0.11186582],"genre_scores_gemma":[0.94174963,0.0000038443304,0.055747654,0.00040454973,0.00019960458,0.0000066458956,0.00022613889,0.000016788861,0.0016451238],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994474,0.000009254043,0.00018105743,0.00008719595,0.00012097251,0.00015410724],"domain_scores_gemma":[0.99950886,0.0000041458366,0.00013155775,0.00023987252,0.000048807804,0.00006676784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000459675,0.000104053324,0.00007009873,0.00002957765,0.00006388602,0.000048085527,0.00009117744,0.000046860594,0.000051839303],"category_scores_gemma":[0.000020247562,0.00008291369,0.00004911012,0.000051390707,0.000049491377,0.000008224601,0.000035030993,0.000027034106,0.00007152522],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018814001,0.0011454036,0.66948944,0.0010744168,0.0002681335,0.000031589145,0.00071626913,0.07756126,0.046034284,0.028330555,0.13278249,0.040684734],"study_design_scores_gemma":[0.013453298,0.00094643707,0.3223384,0.00015647875,0.00023518084,0.00016562191,0.0013827503,0.29619533,0.04026769,0.00077145617,0.32158753,0.00249983],"about_ca_topic_score_codex":0.000013069516,"about_ca_topic_score_gemma":0.00009302918,"teacher_disagreement_score":0.34715107,"about_ca_system_score_codex":0.0000074875015,"about_ca_system_score_gemma":0.00006501797,"threshold_uncertainty_score":0.3381122},"labels":[],"label_agreement":null},{"id":"W1755797074","doi":"10.1186/s12859-015-0581-5","title":"GENLIB: an R package for the analysis of genealogical data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Université du Québec à Chicoutimi; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Canadian Institutes of Health Research","keywords":"Pedigree chart; Kinship; Population; Inbreeding; Genealogy; Sample (material); R package; Software; Computer science; Flexibility (engineering); Genetic genealogy; Selection (genetic algorithm); Data science; Biology; Genetics; Demography; Artificial intelligence; Statistics; Mathematics","score_opus":0.15548907319973773,"score_gpt":0.3560723914392484,"score_spread":0.20058331823951067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1755797074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16946824,0.0003814416,0.82863194,0.00012138423,0.0001096228,0.0002558677,0.00066499383,0.000008715096,0.00035781533],"genre_scores_gemma":[0.60703,0.00015626916,0.38552874,0.0006215085,0.00021348041,0.000028948662,0.006228541,0.00001433446,0.00017820418],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918526,0.000052526815,0.0003675145,0.00013179299,0.00009453428,0.00016836927],"domain_scores_gemma":[0.9984971,0.00008970877,0.00020413418,0.0009932517,0.00013753431,0.00007821955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009894278,0.0000854974,0.0001970739,0.00004184986,0.000057513364,0.000012710952,0.0005406078,0.0001308368,0.0000052945993],"category_scores_gemma":[0.0007027887,0.000055065626,0.00009806968,0.0001713943,0.00007275082,0.000006124905,0.00021221626,0.000033471268,0.000003527905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005218325,0.0007306902,0.6250725,0.00022221757,0.00803149,6.044364e-7,0.0029214432,0.0912556,0.0051481295,0.0032089404,0.20556311,0.05732344],"study_design_scores_gemma":[0.00046073017,0.00026801217,0.06840006,0.0000010783895,0.0007717344,0.000002029697,0.0012994485,0.90172327,0.00027173903,0.00015983373,0.026494654,0.00014737982],"about_ca_topic_score_codex":0.000017914317,"about_ca_topic_score_gemma":0.0001755412,"teacher_disagreement_score":0.8104677,"about_ca_system_score_codex":0.0000065783306,"about_ca_system_score_gemma":0.00010574035,"threshold_uncertainty_score":0.22455111},"labels":[],"label_agreement":null},{"id":"W1756130223","doi":"10.1186/1471-2105-4-63","title":"AnaBench: a Web/CORBA-based workbench for biomolecular sequence analysis","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Canadian Institutes of Health Research","keywords":"Workbench; Computer science; Java; Common Object Request Broker Architecture; Software engineering; Software; Middleware (distributed applications); Data management; World Wide Web; Identification (biology); Flexibility (engineering); Protocol (science); Database; Data science; Operating system; Data mining; Visualization","score_opus":0.028738048256720827,"score_gpt":0.26600156579285333,"score_spread":0.2372635175361325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1756130223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24992557,0.0012777369,0.74424106,0.000046928017,0.00021412189,0.00065512536,0.00023607144,0.000014887852,0.0033884973],"genre_scores_gemma":[0.74647963,0.0000805754,0.25252518,0.0004435808,0.000043983855,0.00007047075,0.00018333855,0.000018685558,0.00015457053],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988497,0.00003422099,0.0003815786,0.00023896396,0.00013496827,0.00036056634],"domain_scores_gemma":[0.99904704,0.000032789103,0.0001563253,0.0005129733,0.00014957793,0.00010129849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028536355,0.00022006301,0.00024486054,0.00013670382,0.00014466142,0.000047371705,0.00021277461,0.00014239665,0.00001366136],"category_scores_gemma":[0.000168177,0.00020427028,0.0003185164,0.000441038,0.00008961045,0.0000016315041,0.00004473663,0.00004500969,0.0000088459055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037160146,0.0006174025,0.17673907,0.0011561012,0.0054455744,0.000007440782,0.0008310592,0.08700036,0.699617,0.0090525085,0.011379766,0.007782078],"study_design_scores_gemma":[0.0044149663,0.001352688,0.005746792,0.00004236487,0.0019566007,0.000019934054,0.0010452959,0.52448255,0.16838813,0.00096285675,0.28942236,0.0021654754],"about_ca_topic_score_codex":0.000004586038,"about_ca_topic_score_gemma":0.000060914343,"teacher_disagreement_score":0.5312289,"about_ca_system_score_codex":0.000017430748,"about_ca_system_score_gemma":0.00023420152,"threshold_uncertainty_score":0.83299005},"labels":[],"label_agreement":null},{"id":"W1758070551","doi":"10.1186/1471-2105-7-152","title":"Domain-based small molecule binding site annotation","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Carleton University","funders":"Genome Canada","keywords":"Computational biology; Annotation; DNA microarray; Domain (mathematical analysis); Computer science; Biology; Genetics; Gene; Mathematics; Gene expression","score_opus":0.02041210304383086,"score_gpt":0.253512328128054,"score_spread":0.23310022508422315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758070551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0955196,0.000018522524,0.89922386,0.00013122897,0.00018563967,0.00016526897,0.000013114221,0.00018004823,0.0045627267],"genre_scores_gemma":[0.012952416,3.9084716e-7,0.98651356,0.00030059653,0.000049275928,0.000010247275,0.000091465896,0.000008879608,0.00007320048],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872875,0.0000764803,0.00042988616,0.00015850898,0.0003437915,0.0002626057],"domain_scores_gemma":[0.9989573,0.00031440027,0.00020439441,0.00036628247,0.000099650744,0.000057986166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046249,0.00014936653,0.00012939275,0.00023398493,0.0001328299,0.000292359,0.00044409823,0.000055562803,0.00000511916],"category_scores_gemma":[0.00003729297,0.00014664215,0.00008538665,0.0006031709,0.000033827593,0.0005624999,0.000120742196,0.00008780651,0.00027932323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012798597,0.000113602735,0.0023689854,0.00019697663,0.000009680759,0.000007468297,0.0007698742,0.85734034,0.00060439185,0.12825297,0.0017811429,0.008541786],"study_design_scores_gemma":[0.00038855296,0.000027764414,0.0034614478,0.000020770922,0.0000038199782,0.0000063746384,0.00002412066,0.98867816,0.0013370882,0.0040713893,0.001784171,0.00019634802],"about_ca_topic_score_codex":0.000020214653,"about_ca_topic_score_gemma":0.00002234282,"teacher_disagreement_score":0.13133784,"about_ca_system_score_codex":0.00008127927,"about_ca_system_score_gemma":0.00019555505,"threshold_uncertainty_score":0.5979893},"labels":[],"label_agreement":null},{"id":"W1759632117","doi":"10.1186/1471-2105-5-24","title":"Biochemical Network Stochastic Simulator (BioNetS): software for stochastic modeling of biochemical networks","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Defense Advanced Research Projects Agency; Alfred P. Sloan Foundation","keywords":"Computer science; Software; Stochastic modelling; Simulation; Programming language; Mathematics; Statistics","score_opus":0.014494119066310335,"score_gpt":0.2385294678884628,"score_spread":0.22403534882215245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1759632117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10592682,0.0015310858,0.8916488,0.000018412395,0.00019507595,0.0005731362,0.000047149755,0.000048194823,0.0000113004735],"genre_scores_gemma":[0.8171256,0.000018880588,0.18129806,0.000112954614,0.0006530909,0.000048745507,0.0006631977,0.00006098139,0.000018455876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749905,0.000024361894,0.0010071751,0.00041245163,0.0003131906,0.00074374746],"domain_scores_gemma":[0.9981485,0.00007822763,0.0003675139,0.0007660353,0.00037588287,0.0002638216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034099154,0.00043074266,0.0005423443,0.00009629676,0.00015534475,0.00003463341,0.00045642658,0.0005407029,0.0000065065838],"category_scores_gemma":[0.00037540917,0.0004249114,0.00043528716,0.00043139458,0.00018554073,0.000013573529,0.0002542519,0.00017282882,0.0000071971363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018226035,0.00007103666,0.000053125794,0.00012963286,0.00015837372,1.5414409e-7,0.000036160513,0.99629843,0.0016683625,0.00010536245,0.001102866,0.00019423691],"study_design_scores_gemma":[0.001534383,0.00021645366,0.000014030765,0.00011582637,0.00022583155,0.000013850993,0.00007293726,0.994579,0.0022143826,0.00045697132,0.0000722149,0.00048412778],"about_ca_topic_score_codex":0.0000053231324,"about_ca_topic_score_gemma":0.000007634624,"teacher_disagreement_score":0.7111988,"about_ca_system_score_codex":0.00006437252,"about_ca_system_score_gemma":0.00029420038,"threshold_uncertainty_score":0.9998203},"labels":[],"label_agreement":null},{"id":"W1775447850","doi":"10.1186/1471-2105-7-471","title":"The accuracy of several multiple sequence alignment programs for proteins","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Multiple sequence alignment; Alignment-free sequence analysis; Indel; Sequence alignment; Computer science; Benchmark (surveying); Inference; Software; Data mining; Range (aeronautics); Sequence (biology); Machine learning; Artificial intelligence; Biology; Genetics; Gene; Peptide sequence","score_opus":0.015664792955574713,"score_gpt":0.2533747827090948,"score_spread":0.2377099897535201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1775447850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12229423,0.00031710256,0.87306,0.00009175151,0.00017592563,0.0028111604,0.000146564,0.000029192524,0.0010740524],"genre_scores_gemma":[0.64779097,0.000033053413,0.35082018,0.00007534141,0.00015648334,0.000254624,0.0004446645,0.000016219608,0.0004084327],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991924,0.000012142525,0.00034331038,0.00009330923,0.00013018129,0.00022866232],"domain_scores_gemma":[0.9992871,0.000037697795,0.00022100445,0.0003270459,0.00009743705,0.000029666426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015782013,0.00011991557,0.00009818331,0.000012250965,0.00012255133,0.00003597446,0.00022946318,0.000099276906,5.3081385e-7],"category_scores_gemma":[0.00013837211,0.000080278645,0.00009723424,0.0000505674,0.000107058826,0.00000783855,0.0000766162,0.00003920227,0.0000014225441],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002896383,0.0010144775,0.045943025,0.004784451,0.0006386853,0.000002971696,0.0013782952,0.03383153,0.50325763,0.04532466,0.023424653,0.33750322],"study_design_scores_gemma":[0.0032907494,0.0012130748,0.0023750425,0.000086093634,0.00006483909,0.000042266125,0.0005305374,0.48025808,0.30094832,0.006004185,0.20438023,0.0008065756],"about_ca_topic_score_codex":0.000029703488,"about_ca_topic_score_gemma":0.00015957456,"teacher_disagreement_score":0.5254968,"about_ca_system_score_codex":0.000013309505,"about_ca_system_score_gemma":0.00010166567,"threshold_uncertainty_score":0.32736683},"labels":[],"label_agreement":null},{"id":"W1781293113","doi":"10.1186/1471-2105-7-159","title":"Amplification of the Gene Ontology annotation of Affymetrix probe sets","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics","funders":"Stem Cell Network; Ontario Genomics; Genome Canada","keywords":"Annotation; Computer science; DNA microarray; Gene ontology; Gene nomenclature; Microarray; Scripting language; Microarray databases; Computational biology; Correctness; Microarray analysis techniques; Gene; Biology; Genetics; Artificial intelligence; Gene expression; Programming language","score_opus":0.010993362669437,"score_gpt":0.2287200413035721,"score_spread":0.21772667863413508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1781293113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43654242,0.00048482008,0.55636126,0.000087874534,0.0003173435,0.0006820717,0.0001211334,0.000012864046,0.0053902073],"genre_scores_gemma":[0.8774724,0.000031421554,0.12187529,0.00007635312,0.00006626209,0.000010309149,0.000274857,0.000010042334,0.00018303585],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989679,0.000024602716,0.0006361105,0.00007794198,0.00013965582,0.0001538254],"domain_scores_gemma":[0.9988238,0.000016927297,0.0005668699,0.00042294004,0.00014709204,0.000022364453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022188475,0.00011031247,0.00015083342,0.000051619718,0.00004824818,0.0000092896635,0.00023852006,0.00016522927,0.000004311975],"category_scores_gemma":[0.000042147745,0.00008204278,0.00010254086,0.00017991789,0.00012345679,0.000008243373,0.00008515105,0.000057413778,0.0000039882293],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005883186,0.0009985074,0.10710134,0.0033129503,0.00039182263,4.2223778e-7,0.0025871356,0.0507966,0.6919289,0.052465998,0.034338463,0.05548954],"study_design_scores_gemma":[0.0027615712,0.00064400025,0.139386,0.000111995665,0.00016078539,0.000063294116,0.00076706236,0.2004034,0.6336694,0.0060925973,0.015167923,0.00077201],"about_ca_topic_score_codex":0.000026972677,"about_ca_topic_score_gemma":0.0000776002,"teacher_disagreement_score":0.44093,"about_ca_system_score_codex":0.000010605484,"about_ca_system_score_gemma":0.000095937874,"threshold_uncertainty_score":0.33456075},"labels":[],"label_agreement":null},{"id":"W1793987388","doi":"10.1186/s12859-015-0663-4","title":"Sealer: a scalable gap-closing application for finishing draft genomes","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Closing (real estate); Scalability; DNA microarray; Computer science; Genome; Computational biology; Biology; Genetics; Database; Business; Gene","score_opus":0.04185362854053402,"score_gpt":0.2695208117224522,"score_spread":0.22766718318191817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1793987388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3854345,0.0048399,0.5925799,0.0003195219,0.0005326503,0.001658834,0.000193288,0.000036448633,0.014404982],"genre_scores_gemma":[0.6085329,0.00027208467,0.3887979,0.000593766,0.0005399536,0.00019067716,0.00031986425,0.00004296276,0.0007098628],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992092,0.000010880449,0.00028110633,0.0001484834,0.00010204638,0.00024828513],"domain_scores_gemma":[0.99929374,0.000020558069,0.0001268403,0.00029115504,0.00016610915,0.000101610756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028207013,0.00013716065,0.0001384193,0.000030932275,0.00012064337,0.000053431657,0.00017088088,0.00010487376,0.0000010859368],"category_scores_gemma":[0.00009564907,0.00013038446,0.000075582895,0.00006256474,0.000045632554,0.0000031260176,0.00012222542,0.000037159567,0.000018637033],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001308668,0.00076497777,0.1771716,0.0032943357,0.0012069674,0.0000016409239,0.015187685,0.055247966,0.34069127,0.010634952,0.15234552,0.24214442],"study_design_scores_gemma":[0.002675287,0.00066793064,0.0019535872,0.000030243442,0.00010198128,0.00002364121,0.0027316567,0.20596069,0.031444687,0.0024448673,0.7511024,0.0008630237],"about_ca_topic_score_codex":0.000007860337,"about_ca_topic_score_gemma":0.000027781593,"teacher_disagreement_score":0.5987569,"about_ca_system_score_codex":0.00002072327,"about_ca_system_score_gemma":0.00014278627,"threshold_uncertainty_score":0.5316924},"labels":[],"label_agreement":null},{"id":"W1802390868","doi":"10.1186/1471-2105-3-20","title":"Kangaroo – A pattern-matching program for biological sequences","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Cancer Institute","keywords":"Matching (statistics); DNA microarray; Computational biology; Computer science; Biology; Genetics; Mathematics; Statistics; Gene","score_opus":0.03534831055626175,"score_gpt":0.2560530521769923,"score_spread":0.22070474162073056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1802390868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75813735,0.00047525953,0.23318553,0.00019624188,0.0003232558,0.0011513773,0.00021825028,0.00012267639,0.0061900313],"genre_scores_gemma":[0.85130286,0.00009251688,0.14704463,0.0003310813,0.00022901664,0.00018495461,0.00024742517,0.000012161191,0.00055534963],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925554,0.000016793576,0.00028339218,0.00012282976,0.00007112573,0.00025030403],"domain_scores_gemma":[0.99957746,0.000020173446,0.000101826496,0.00019286206,0.000051281004,0.00005639885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011501274,0.00013135067,0.00011528845,0.000026269097,0.00013239287,0.00006466855,0.00017366506,0.00012820405,0.00005606227],"category_scores_gemma":[0.00004264742,0.00010336688,0.0001067812,0.000045133642,0.00005514736,0.000009106134,0.000066164066,0.000045120625,0.00003720892],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002763209,0.002498071,0.113639496,0.0032099853,0.0009591787,0.000009574565,0.015661629,0.0061793025,0.031445667,0.012460135,0.06291928,0.75074136],"study_design_scores_gemma":[0.0053120633,0.006394804,0.009202184,0.00016526801,0.00016460284,0.00037898246,0.011855384,0.3294318,0.032267105,0.0036303576,0.59819204,0.0030054003],"about_ca_topic_score_codex":0.0000073160177,"about_ca_topic_score_gemma":0.000018517276,"teacher_disagreement_score":0.747736,"about_ca_system_score_codex":0.000010120828,"about_ca_system_score_gemma":0.000020746626,"threshold_uncertainty_score":0.4215179},"labels":[],"label_agreement":null},{"id":"W1804740371","doi":"10.1186/1471-2105-7-462","title":"Java GUI for InterProScan (JIPS): A tool to help process multiple InterProScans and perform ortholog analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; National Institutes of Health","keywords":"Java; Computer science; Biological database; Function (biology); Data mining; DNA microarray; Process (computing); Computational biology; Database; Bioinformatics; Biology; Gene; Genetics; Programming language","score_opus":0.005128141935829156,"score_gpt":0.244131908550931,"score_spread":0.23900376661510184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1804740371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60794073,0.00005215116,0.39067683,0.00003367389,0.00006325175,0.0005949093,0.00016841029,0.000021990058,0.0004480318],"genre_scores_gemma":[0.8672602,0.000007663811,0.13125467,0.00033136626,0.00011873539,0.00014623556,0.000495337,0.000019381196,0.0003664062],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998836,0.000009279859,0.00045255575,0.00025515025,0.00012039208,0.0003266651],"domain_scores_gemma":[0.9992524,0.000017107603,0.00014285007,0.00036764113,0.00013412868,0.00008586678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017014578,0.0002291934,0.0002624741,0.00015536476,0.000115355695,0.00008390803,0.00021970525,0.00018270247,0.0000054423394],"category_scores_gemma":[0.00014699699,0.00019625096,0.00015399932,0.0002627801,0.000070979244,0.000016660138,0.00015042111,0.00007169422,0.0000034165062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003242859,0.00042337543,0.8149125,0.0032268465,0.0015005947,0.0000058215514,0.0035304623,0.019132767,0.052013777,0.0016717956,0.0069882507,0.09335097],"study_design_scores_gemma":[0.0027861653,0.0017206079,0.03687688,0.00007957778,0.0006985241,0.000080005375,0.0015199054,0.88971364,0.04692478,0.00085756433,0.017194686,0.0015476875],"about_ca_topic_score_codex":0.000032862066,"about_ca_topic_score_gemma":0.0011023006,"teacher_disagreement_score":0.87058085,"about_ca_system_score_codex":0.00002181866,"about_ca_system_score_gemma":0.000078850644,"threshold_uncertainty_score":0.8002882},"labels":[],"label_agreement":null},{"id":"W1807494956","doi":"10.1186/1471-2105-6-138","title":"libcov: A C++ bioinformatic library to manipulate protein structures, sequence alignments and phylogeny","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic","keywords":"Phylogenetic tree; Phylogenetics; Mega-; Tree (set theory); Computational biology; Multiple sequence alignment; Selection (genetic algorithm); Biology; Computer science; Sequence (biology); Alignment-free sequence analysis; Computational phylogenetics; Sequence alignment; Bioinformatics; Phylogenetic network; Data mining; Machine learning; Genetics; Gene; Mathematics; Peptide sequence","score_opus":0.019746366193102268,"score_gpt":0.236738358717995,"score_spread":0.21699199252489274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1807494956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99096763,0.0006202915,0.004357968,0.0002008563,0.00008362154,0.0008201664,0.000112504014,0.000022085496,0.00281485],"genre_scores_gemma":[0.72258425,0.0001814017,0.27468145,0.0015369279,0.00018475503,0.000053355914,0.0000793492,0.00003184537,0.0006666692],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988146,0.000018670744,0.0004492584,0.0001980426,0.00015639313,0.00036306886],"domain_scores_gemma":[0.9992409,0.000007846319,0.00013406177,0.00039905272,0.000029114282,0.00018905726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098186254,0.00026137003,0.00019495875,0.00007774479,0.00013232902,0.000100121644,0.00026962554,0.00012855872,0.0000153033],"category_scores_gemma":[0.000031123418,0.00022917107,0.00006242802,0.00010724268,0.00007186195,0.0000128370575,0.00042582044,0.000069345355,0.000057609494],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005932775,0.00023739046,0.028882032,0.0020422873,0.0007410875,0.000008224592,0.0070056664,0.008820302,0.78791404,0.0067848545,0.018370995,0.13859986],"study_design_scores_gemma":[0.0039894492,0.0019812572,0.053670645,0.00024569346,0.00015130173,0.00028259814,0.001954555,0.06399196,0.37622285,0.0025468557,0.49177444,0.003188411],"about_ca_topic_score_codex":0.0000045352135,"about_ca_topic_score_gemma":0.000013150822,"teacher_disagreement_score":0.47340345,"about_ca_system_score_codex":0.000013232692,"about_ca_system_score_gemma":0.00007400541,"threshold_uncertainty_score":0.9345325},"labels":[],"label_agreement":null},{"id":"W1813034246","doi":"10.1186/1471-2105-6-23","title":"Recent Hits Acquired by BLAST (ReHAB): A tool to identify new hits in sequence similarity searches","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Computer science; Similarity (geometry); Sequence (biology); Alignment-free sequence analysis; Information retrieval; Table (database); Interface (matter); Graphics; Data mining; Genome; Sequence alignment; Sequence database; Software; Multiple sequence alignment; Database; Artificial intelligence; Biology; Genetics; Programming language; Computer graphics (images)","score_opus":0.03302620209898142,"score_gpt":0.3249614275038759,"score_spread":0.29193522540489447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1813034246","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8891033,0.0007666224,0.09644914,0.0032756906,0.00041482516,0.0019558426,0.0003186614,0.00019043489,0.0075255153],"genre_scores_gemma":[0.15388179,0.0014147212,0.82767403,0.008914566,0.0007414058,0.00010317493,0.0015867,0.00013256421,0.005551069],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975022,0.00007061706,0.0009541582,0.00028801567,0.0004884247,0.0006965856],"domain_scores_gemma":[0.9985104,0.000048168506,0.00024779292,0.0007273889,0.00013623972,0.00033001046],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006569004,0.00036658865,0.0003096301,0.00016753378,0.00010783132,0.00015543867,0.00067606266,0.0003367862,0.00011387005],"category_scores_gemma":[0.0009523128,0.00036375047,0.00010545111,0.00042324016,0.00008713239,0.00006431182,0.00049177924,0.00026591282,0.00039632173],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005890997,0.0004646507,0.020313494,0.00093641825,0.00013722712,0.000005585586,0.0066448166,0.025137728,0.073809706,0.00024266829,0.44502982,0.4266888],"study_design_scores_gemma":[0.0021474978,0.0004452093,0.009274026,0.00016421328,0.000027866145,0.000052731375,0.0004967448,0.15986526,0.034978516,0.00005526327,0.7913448,0.0011478651],"about_ca_topic_score_codex":0.000032823904,"about_ca_topic_score_gemma":0.00029990566,"teacher_disagreement_score":0.7352215,"about_ca_system_score_codex":0.0001423687,"about_ca_system_score_gemma":0.00040872247,"threshold_uncertainty_score":0.99988145},"labels":[],"label_agreement":null},{"id":"W1819319716","doi":"10.1186/1471-2105-6-36","title":"GANN: Genetic algorithm neural networks for the detection of conserved combinations of features in DNA","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Ottawa","funders":"","keywords":"DNA microarray; Sequence (biology); Computer science; Artificial intelligence; DNA sequencing; Computational biology; Feature (linguistics); Machine learning; Protein sequencing; Artificial neural network; Algorithm; Data mining; Sequence analysis; Biology; Genetics; Peptide sequence; DNA; Gene","score_opus":0.007048980703530255,"score_gpt":0.21883051175330298,"score_spread":0.21178153104977274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819319716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37595522,0.0008925489,0.6223868,0.00006587696,0.00012284686,0.0004457514,0.000054127333,0.000004589103,0.000072219475],"genre_scores_gemma":[0.9288274,0.00014824107,0.07077288,0.000067375775,0.000050463368,0.000022157416,0.00006174737,0.0000093499375,0.00004038588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993671,0.00001490901,0.00036478863,0.00006292782,0.00006363967,0.00012659513],"domain_scores_gemma":[0.99942684,0.000049131042,0.00019854805,0.00021577903,0.00008954611,0.000020178655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013117347,0.000086660286,0.00011341569,0.000036344958,0.000045077875,0.000010258665,0.00015653356,0.00010543488,0.0000010951785],"category_scores_gemma":[0.000040817835,0.000069712325,0.00008091959,0.000079034195,0.00007028404,0.000004076317,0.000047858066,0.00005212828,2.503024e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016989087,0.0005076406,0.0030857867,0.00047357703,0.0001748052,2.179943e-7,0.0009068659,0.6382648,0.03989425,0.0004900295,0.000716967,0.31531522],"study_design_scores_gemma":[0.0008259268,0.0001394357,0.009343802,0.0000072439534,0.000019489491,0.0000071259915,0.00021392954,0.9751484,0.013733902,0.000039799503,0.00044334488,0.0000776214],"about_ca_topic_score_codex":0.00001115374,"about_ca_topic_score_gemma":0.00028873337,"teacher_disagreement_score":0.5528722,"about_ca_system_score_codex":0.000010153423,"about_ca_system_score_gemma":0.000034842233,"threshold_uncertainty_score":0.28427863},"labels":[],"label_agreement":null},{"id":"W1819658147","doi":"10.1186/1471-2105-6-68","title":"Feature selection and nearest centroid classification for protein mass spectrometry","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Feature selection; Computer science; Dimensionality reduction; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Linear discriminant analysis; Data mining; k-nearest neighbors algorithm; Curse of dimensionality; Centroid; Machine learning; Classifier (UML); Boosting (machine learning); Support vector machine","score_opus":0.013658956795105424,"score_gpt":0.24366443813738542,"score_spread":0.23000548134228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819658147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35459086,0.0017267549,0.6369594,0.001959745,0.0001748881,0.0015756849,0.00010488679,0.00006168092,0.0028461518],"genre_scores_gemma":[0.23251855,0.00037657816,0.7641679,0.00017605988,0.0005523437,0.00008952177,0.0001904386,0.000022650343,0.0019059472],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99930084,0.0000131088145,0.00018289067,0.00016680358,0.00009607821,0.00024031001],"domain_scores_gemma":[0.9995511,0.0000086065165,0.00013146848,0.00016540737,0.000081295344,0.000062083855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016400062,0.00014580048,0.00013965987,0.00007830958,0.00014328439,0.00005785413,0.000085467844,0.00013681964,0.000005320635],"category_scores_gemma":[0.00011951589,0.00013049622,0.000061193445,0.00012664817,0.000035246972,0.000013162416,0.0000397501,0.00007779924,0.0000067541105],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017207846,0.000064684544,0.0034524207,0.0002565165,0.00010158251,6.201436e-8,0.00007543756,0.00008260139,0.9704976,0.0070349844,0.01122585,0.007036148],"study_design_scores_gemma":[0.002428524,0.0008555139,0.015831301,0.00002667948,0.00009409094,0.000030548657,0.00065109343,0.13492621,0.2685142,0.00042373495,0.57550573,0.0007123827],"about_ca_topic_score_codex":8.2991073e-7,"about_ca_topic_score_gemma":0.000033077064,"teacher_disagreement_score":0.70198345,"about_ca_system_score_codex":0.00002670808,"about_ca_system_score_gemma":0.000042499345,"threshold_uncertainty_score":0.5321482},"labels":[],"label_agreement":null},{"id":"W1820242896","doi":"10.1186/1471-2105-6-271","title":"The yeast kinome displays scale free topology with functional hub clusters","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Kinome; Interactome; Computational biology; In silico; Degree distribution; Biology; Systems biology; Biological network; Computer science; Network topology; Modularity (biology); Function (biology); Distributed computing; Kinase; Complex network; Genetics; Computer network","score_opus":0.007692424662991029,"score_gpt":0.20040175836108556,"score_spread":0.19270933369809454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1820242896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18015575,0.0013417209,0.7467447,0.0030521497,0.0013678217,0.0012241132,0.0002304778,0.00010406309,0.0657792],"genre_scores_gemma":[0.7689942,0.0005096384,0.20951498,0.005780149,0.0031025228,0.0001389887,0.00097003434,0.00010910923,0.010880359],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883914,0.000019221075,0.0004136007,0.00013512756,0.00018747695,0.00040541496],"domain_scores_gemma":[0.99893945,0.000026810972,0.00018208707,0.00066257775,0.00007258484,0.00011645757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024194339,0.00020321141,0.00014021242,0.00003343173,0.00032900582,0.00009195254,0.00041423377,0.00017902083,0.000029036804],"category_scores_gemma":[0.000022226452,0.00013064961,0.000090660425,0.000086868786,0.0002725989,0.000018723182,0.00024696818,0.00015414733,0.00009757866],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030688907,0.00048614154,0.020529032,0.00056229613,0.0010089708,0.000003910205,0.0032277596,0.07834592,0.0030486716,0.020399753,0.66448057,0.20483808],"study_design_scores_gemma":[0.003136405,0.0006290236,0.0048912647,0.00003490932,0.00007940153,0.00027460928,0.0017069734,0.2786813,0.0015309389,0.0005593935,0.70766246,0.00081334676],"about_ca_topic_score_codex":0.0000044396984,"about_ca_topic_score_gemma":0.00053564407,"teacher_disagreement_score":0.58883846,"about_ca_system_score_codex":0.000027295244,"about_ca_system_score_gemma":0.00012465364,"threshold_uncertainty_score":0.5327737},"labels":[],"label_agreement":null},{"id":"W1860906034","doi":"10.1186/1471-2105-8-34","title":"Computational RNA secondary structure design: empirical complexity and improved methods","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Mitacs; Consejo Nacional de Ciencia y Tecnología; Government of Canada","keywords":"Nucleic acid secondary structure; Computer science; Algorithm; Nucleic acid structure; RNA; Scaling; Sequence (biology); Basis (linear algebra); Protein secondary structure; Theoretical computer science; Mathematics","score_opus":0.052991430173054535,"score_gpt":0.3410353599498488,"score_spread":0.28804392977679427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1860906034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036229663,0.00020076436,0.96242386,0.000039074344,0.00010879972,0.00024758597,0.000035254197,0.000018070361,0.000696943],"genre_scores_gemma":[0.055439368,0.000008926211,0.9437025,0.0005867579,0.00009163215,0.000003091383,0.000096580814,0.00001290422,0.000058236314],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990805,0.000086012034,0.0003391833,0.00015085668,0.00011152867,0.0002319387],"domain_scores_gemma":[0.99938846,0.0000993684,0.00012701962,0.00019846317,0.00006655412,0.000120153025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007424038,0.00016075374,0.0001582181,0.00004542236,0.0001206315,0.000042650023,0.0001346784,0.00020604275,0.000046807072],"category_scores_gemma":[0.00011074079,0.00013855829,0.00005452198,0.00006351214,0.000116563395,0.000009624167,0.00010598148,0.0001046744,0.0000039752745],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061876484,0.000083797146,0.0010631506,0.0004282333,0.00018555512,0.0000030075998,0.00092699897,0.0010563245,0.64725214,0.001840135,0.0028667792,0.34367508],"study_design_scores_gemma":[0.0015733981,0.0006411289,0.007637743,0.000022243348,0.00004942959,0.00017182883,0.00055014517,0.18008874,0.7767902,0.017625723,0.014095869,0.00075352314],"about_ca_topic_score_codex":0.0000021628107,"about_ca_topic_score_gemma":0.0000086628015,"teacher_disagreement_score":0.34292156,"about_ca_system_score_codex":0.00001043081,"about_ca_system_score_gemma":0.00010350633,"threshold_uncertainty_score":0.5650243},"labels":[],"label_agreement":null},{"id":"W1863852050","doi":"10.1186/1471-2105-7-79","title":"Taxonomic colouring of phylogenetic trees of protein sequences","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ontario Genomics","funders":"Ontario Genomics","keywords":"Phylogenetic tree; GenBank; Tree (set theory); Biology; Phylogenetic network; Phylogenetics; Taxonomic rank; Identification (biology); Documentation; Identifier; Computer science; Taxon; Genetics; Ecology; Combinatorics; Mathematics; Gene; Programming language","score_opus":0.01295903067258679,"score_gpt":0.21109257663741315,"score_spread":0.19813354596482635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1863852050","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931022,0.0009239885,0.0026414904,0.0000073100973,0.00004368684,0.00026423167,0.00004885884,0.0000023344228,0.0029659318],"genre_scores_gemma":[0.9407767,0.00006138692,0.05891326,0.000008509961,0.000056603494,0.000017340386,0.000016243415,0.000008367119,0.00014156477],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917114,0.000015930296,0.000463874,0.00009925488,0.00008978341,0.00015999643],"domain_scores_gemma":[0.9993614,0.0000108835175,0.0002932795,0.00023760923,0.00007328878,0.000023551036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001135871,0.00012412503,0.000194991,0.000046226967,0.000034938214,0.0000066395496,0.00017649075,0.00008040475,0.0000040897135],"category_scores_gemma":[0.000022262539,0.00011182509,0.00008998894,0.00006330524,0.00015447727,0.0000010478605,0.00009518429,0.000027096208,0.000002337011],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040512405,0.000058118174,0.029636025,0.00024852785,0.00005183095,1.5037558e-7,0.000071171075,0.0067047975,0.96148425,0.0005449748,0.00015849418,0.0010011568],"study_design_scores_gemma":[0.00063389924,0.00046839545,0.042166326,0.000044168974,0.000034310873,0.0000056050917,0.00030513672,0.0031091413,0.94889975,0.0003801116,0.0036948198,0.00025832537],"about_ca_topic_score_codex":0.000053160664,"about_ca_topic_score_gemma":0.00012516101,"teacher_disagreement_score":0.05627177,"about_ca_system_score_codex":0.000006460205,"about_ca_system_score_gemma":0.00008203669,"threshold_uncertainty_score":0.45600948},"labels":[],"label_agreement":null},{"id":"W1869957243","doi":"10.1186/1471-2105-6-183","title":"Inconsistencies over time in 5% of NetAffx probe-to-gene annotations","year":2005,"lang":"en","type":"letter","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics","funders":"Ministry of Education, India","keywords":"DNA microarray; Microarray; Microarray databases; Annotation; Microarray analysis techniques; Computational biology; Biology; Gene; Gene Annotation; Genetics; Set (abstract data type); Genome; Bioinformatics; Computer science; Gene expression","score_opus":0.016330462683547417,"score_gpt":0.2503158012860126,"score_spread":0.23398533860246518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1869957243","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1209179,0.0073854565,0.2160022,0.5089434,0.004775948,0.016661376,0.005409401,0.00047041228,0.11943392],"genre_scores_gemma":[0.007700469,0.00051845616,0.3917356,0.5490356,0.0042584906,0.00055882777,0.011037383,0.0002105278,0.034944642],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986544,0.000040756055,0.0006244604,0.00020194222,0.00024107519,0.00023732208],"domain_scores_gemma":[0.998935,0.000016666796,0.00032592268,0.0005501203,0.0001227507,0.00004956808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012717767,0.00022174619,0.00025834359,0.00025122668,0.00003203635,0.000024973508,0.00029066944,0.00054965494,0.00005487992],"category_scores_gemma":[0.000077029166,0.00020892988,0.00011257162,0.0002347313,0.00006201875,0.0000082761135,0.00011421445,0.00024546066,0.00008019183],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021364693,0.00003303035,0.00034642898,0.00024859715,0.000023859877,7.492129e-7,0.00023983694,0.0005597924,0.029064685,0.0000071825307,0.9681728,0.0012817112],"study_design_scores_gemma":[0.00045133833,0.0001230134,0.002181064,0.00011284356,0.00002852399,0.0000073707756,0.000061702085,0.0033631243,0.01769202,0.000023757508,0.9755701,0.00038517851],"about_ca_topic_score_codex":0.000006144385,"about_ca_topic_score_gemma":0.000033937547,"teacher_disagreement_score":0.17573343,"about_ca_system_score_codex":0.000035949895,"about_ca_system_score_gemma":0.0003056964,"threshold_uncertainty_score":0.85199136},"labels":[],"label_agreement":null},{"id":"W1870437443","doi":"10.1186/s12859-015-0655-4","title":"An investigation into inter- and intragenomic variations of graphic genomic signatures","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; Western University","funders":"","keywords":"Biology; Genome; Genetics; Homo sapiens; genomic DNA; Chromosome; Genome evolution; Phylogenetic tree; Comparative genomics; DNA sequencing; Genomics; Evolutionary biology; Computational biology; Gene","score_opus":0.013938743161031018,"score_gpt":0.2398146198718001,"score_spread":0.22587587671076909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1870437443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95854336,0.00025735132,0.040867843,0.000033131357,0.00004106641,0.00007913518,0.000010650784,0.000008392806,0.00015906442],"genre_scores_gemma":[0.9517382,0.000051654355,0.04781706,0.000140236,0.000044157667,0.000004108555,0.00017834107,0.000006038609,0.000020209096],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946463,0.000027629681,0.000255085,0.000093389724,0.000071601484,0.00008763326],"domain_scores_gemma":[0.99945277,0.000008545148,0.00013303355,0.00021138047,0.000086020606,0.00010825521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018356247,0.00008774731,0.00010204042,0.000088841625,0.000035665147,0.000025398349,0.00012025601,0.0001027436,0.0000029788794],"category_scores_gemma":[0.00007386526,0.00007761414,0.000037024914,0.00010247207,0.00011354163,0.000024023131,0.0000514667,0.000048836515,0.0000042769548],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011043335,0.00009755398,0.04118876,0.00025540826,0.0001761119,6.939746e-7,0.007896029,0.0064121145,0.931529,0.0025743302,0.0010067676,0.008752823],"study_design_scores_gemma":[0.00215102,0.0026953493,0.04254151,0.00009839781,0.00040109712,0.000041662177,0.012318617,0.703231,0.21782833,0.015199807,0.002164585,0.0013286481],"about_ca_topic_score_codex":0.00008405267,"about_ca_topic_score_gemma":0.00016626455,"teacher_disagreement_score":0.71370065,"about_ca_system_score_codex":0.000010379619,"about_ca_system_score_gemma":0.000104107225,"threshold_uncertainty_score":0.3165013},"labels":[],"label_agreement":null},{"id":"W1870764676","doi":"10.1186/1471-2105-5-156","title":"Modeling of cell signaling pathways in macrophages by semantic networks","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Michael Smith Health Research BC; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC; Faculty of Medicine, University of British Columbia","keywords":"Context (archaeology); Biological pathway; Cell signaling; Systems biology; Computer science; Signal transduction; Computational biology; Biology; Biological network; Semantic network; Cell biology; Artificial intelligence; Gene; Genetics; Gene expression","score_opus":0.010357711615998142,"score_gpt":0.20501339145718342,"score_spread":0.1946556798411853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1870764676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3234535,0.00093285326,0.6742157,0.000007867474,0.00009642145,0.00020297072,0.000022958136,0.000011336128,0.0010564548],"genre_scores_gemma":[0.9377885,0.00029676466,0.06147519,0.00014677797,0.00006490918,0.000007371973,0.00016861338,0.000021614034,0.000030256064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855095,0.000015543792,0.00077178405,0.0001385123,0.00014649669,0.00037668683],"domain_scores_gemma":[0.99931824,0.000011321219,0.00019757739,0.00033376922,0.00005532816,0.00008374947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031012992,0.00021163159,0.00024681605,0.00007024948,0.00005444284,0.000031813797,0.00026433342,0.0002538169,0.000004913484],"category_scores_gemma":[0.000015929672,0.00020230592,0.000109658,0.00015153122,0.0000546541,0.000014684592,0.00013327776,0.00016213849,0.000008363829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030918476,0.00006396819,0.00019828815,0.00021817879,0.000013595393,7.29582e-7,0.0003478886,0.9822709,0.01597127,0.00012017037,0.00015682621,0.0006072508],"study_design_scores_gemma":[0.0011407015,0.0001318839,0.000013657413,0.00007871525,0.000013918992,0.000006708299,0.0005606897,0.973811,0.023588086,0.000302814,0.00008586651,0.00026599976],"about_ca_topic_score_codex":0.000027518723,"about_ca_topic_score_gemma":0.00003612925,"teacher_disagreement_score":0.614335,"about_ca_system_score_codex":0.000024806937,"about_ca_system_score_gemma":0.000103220365,"threshold_uncertainty_score":0.8249796},"labels":[],"label_agreement":null},{"id":"W1878664294","doi":"10.1186/s12859-015-0597-x","title":"ISOpureR: an R implementation of a computational purification algorithm of mixed tumour profiles","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Canada Research Chairs; University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Lung cancer; R package; Prostate cancer; Cancer; Fraction (chemistry); Tumour heterogeneity; Computer science; DNA microarray; Computational biology; Algorithm; Bioinformatics; Data mining; Biology; Oncology; Computational science; Medicine; Gene; Gene expression; Chemistry; Genetics","score_opus":0.023086360785979296,"score_gpt":0.2899811739000443,"score_spread":0.266894813114065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1878664294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66412026,0.00015177017,0.33457962,0.00002858743,0.00014009791,0.00032276887,0.0004301988,0.000007383148,0.00021929252],"genre_scores_gemma":[0.5850296,0.0000310772,0.4131754,0.000036446938,0.00007800104,0.000014467302,0.0016141715,0.000009840579,0.000010999704],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925303,0.000018467428,0.000403137,0.00007894475,0.00015464019,0.0000917988],"domain_scores_gemma":[0.9991684,0.000012537832,0.00029177163,0.00016657259,0.00029525207,0.0000654753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019020334,0.000078919744,0.000108576256,0.00004863072,0.00001839427,0.000011393365,0.000110260495,0.000058743066,0.00000494145],"category_scores_gemma":[0.000045033437,0.00007910724,0.000041062944,0.00006909679,0.00004689991,0.000011204189,0.00004167728,0.000023328379,0.000002950972],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071382994,0.0017939596,0.09031836,0.001904991,0.0005146297,0.0000015978521,0.011236142,0.14370976,0.13141936,0.017027173,0.04517557,0.55618465],"study_design_scores_gemma":[0.0047493316,0.0025998813,0.05468992,0.00004134028,0.000114686234,0.000026767597,0.012624137,0.35418987,0.5613211,0.0030570999,0.0059637395,0.0006221704],"about_ca_topic_score_codex":0.000042259137,"about_ca_topic_score_gemma":0.000047518635,"teacher_disagreement_score":0.55556244,"about_ca_system_score_codex":0.000014321395,"about_ca_system_score_gemma":0.00032071542,"threshold_uncertainty_score":0.32258996},"labels":[],"label_agreement":null},{"id":"W1879935290","doi":"10.1186/1471-2105-6-139","title":"PentaPlot: A software tool for the illustration of genome mosaicism","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Aeronautics and Space Administration; National Science Foundation","keywords":"Computational biology; DNA microarray; Software; Genome; Computer science; Biology; Genetics; Bioinformatics; Programming language; Gene; Gene expression","score_opus":0.019939113460943753,"score_gpt":0.2429802835424754,"score_spread":0.22304117008153163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1879935290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05948031,0.0005754248,0.93830705,0.00014716346,0.00010601243,0.00095172896,0.00012219287,0.000019306484,0.00029080603],"genre_scores_gemma":[0.17729406,0.00030969075,0.8184295,0.0004931279,0.0006472489,0.00016324845,0.00070100476,0.00004225766,0.0019198116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992899,0.000008350525,0.0003189042,0.0000840643,0.00012926321,0.00016952644],"domain_scores_gemma":[0.99939483,0.000026553056,0.00014649233,0.00031165354,0.000094117706,0.000026373627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020647896,0.000106281565,0.00009584231,0.000026552087,0.00007412861,0.000021470554,0.00020606395,0.0000836772,0.000019651023],"category_scores_gemma":[0.00007439833,0.0000784809,0.000100818615,0.000055425804,0.000050826948,0.00000981664,0.000062992614,0.000036409605,0.000018619632],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009940023,0.0010390116,0.011610475,0.0038624208,0.0015855709,8.1555703e-7,0.009041198,0.15622577,0.27563888,0.0035535793,0.03948302,0.49696526],"study_design_scores_gemma":[0.0043815863,0.0011677304,0.013010682,0.000040297873,0.00028032405,0.000036857524,0.0018882555,0.2956067,0.062008277,0.00020313646,0.6203979,0.0009782471],"about_ca_topic_score_codex":0.0000016419032,"about_ca_topic_score_gemma":0.000014823623,"teacher_disagreement_score":0.5809149,"about_ca_system_score_codex":0.000013623373,"about_ca_system_score_gemma":0.000060566537,"threshold_uncertainty_score":0.32003585},"labels":[],"label_agreement":null},{"id":"W1882963036","doi":"10.1186/1471-2105-3-13","title":"NBLAST: a cluster variant of BLAST for NxN comparisons","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sequence (biology); Sequence alignment; Multiple sequence alignment; Perl; Cluster (spacecraft); Set (abstract data type); Sequence database; Task (project management); Cluster analysis; Smith–Waterman algorithm; Sequence logo; Heuristic; Data mining; Biology; Artificial intelligence; Genetics; Peptide sequence; Programming language","score_opus":0.02975952710185699,"score_gpt":0.23632033118439383,"score_spread":0.20656080408253685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882963036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2979841,0.0018116476,0.68144286,0.0002573191,0.000613692,0.0013390445,0.0005361929,0.000014001478,0.01600119],"genre_scores_gemma":[0.75703865,0.0001998599,0.24145156,0.00029732758,0.00016742999,0.000043935528,0.0000481187,0.000021712509,0.00073140825],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992512,0.000010588297,0.000357023,0.00010414057,0.00007529437,0.0002017621],"domain_scores_gemma":[0.9994077,0.00003189788,0.00015110314,0.0002706935,0.00008861791,0.000049975013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010633946,0.0001279678,0.00018172305,0.000032781703,0.00006589459,0.0000134796555,0.0001537634,0.000090823094,0.000014288373],"category_scores_gemma":[0.000058094105,0.00011267958,0.00011897333,0.00004886127,0.00007474266,0.0000010548903,0.00010790558,0.000032644435,0.0000146943],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011507428,0.0019577139,0.03533072,0.004118141,0.0021680589,0.000002122368,0.00954917,0.028012758,0.18634011,0.007845712,0.69514024,0.028384496],"study_design_scores_gemma":[0.004384518,0.0015080022,0.0045392946,0.0000540955,0.00016968937,0.0000501127,0.0013395973,0.56770444,0.030318134,0.00018798972,0.38897675,0.0007673509],"about_ca_topic_score_codex":0.0000027554859,"about_ca_topic_score_gemma":0.000027980395,"teacher_disagreement_score":0.5396917,"about_ca_system_score_codex":0.0000049497753,"about_ca_system_score_gemma":0.00002045718,"threshold_uncertainty_score":0.459494},"labels":[],"label_agreement":null},{"id":"W1886580489","doi":"10.1186/1471-2105-6-145","title":"Satellog: A database for the identification and prioritization of satellite repeats in disease association studies","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Neurodegenerative Diseases","field":"Neuroscience","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Agency; Canadian Institutes of Health Research; Canada's Michael Smith Genome Sciences Centre","keywords":"Genetics; Biology; Tandem repeat; Microsatellite; UniGene; Trinucleotide repeat expansion; Human genome; Direct repeat; RefSeq; Genome; UniProt; dbSNP; Gene; Expressed sequence tag; Single-nucleotide polymorphism; Allele; Genotype","score_opus":0.07048138815232072,"score_gpt":0.3252781653655949,"score_spread":0.2547967772132742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1886580489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9692295,0.0027183825,0.024256576,0.0011711413,0.0002414677,0.001912024,0.0003668087,0.000044511802,0.000059580165],"genre_scores_gemma":[0.98551774,0.004243588,0.009352293,0.00046896542,0.00005345888,0.000100587466,0.000038256185,0.000011194522,0.0002139041],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989596,0.000071171846,0.0004832564,0.00013710206,0.00021945882,0.00012941391],"domain_scores_gemma":[0.99825823,0.0010296163,0.00032917917,0.00023357949,0.0001097539,0.000039641312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039211608,0.000087761895,0.00010705788,0.00007458928,0.00009585606,0.00004435105,0.0001053952,0.000021220452,0.0000012935052],"category_scores_gemma":[0.005705869,0.00006748165,0.000031090694,0.00018603506,0.00006819147,0.00031249895,0.000051600287,0.000036615405,0.00000494766],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095619925,0.0011757598,0.31301266,0.0065287002,0.00010714182,0.000002774289,0.03301096,0.03399392,0.39218175,0.01808611,0.0033182306,0.19762579],"study_design_scores_gemma":[0.001299668,0.00005661509,0.1622567,0.00010919233,0.000141741,0.0000014767173,0.0013442169,0.4409222,0.38949326,0.0007234551,0.0033741342,0.00027732697],"about_ca_topic_score_codex":0.0000010006112,"about_ca_topic_score_gemma":0.000031076146,"teacher_disagreement_score":0.4069283,"about_ca_system_score_codex":0.00005303507,"about_ca_system_score_gemma":0.000049779246,"threshold_uncertainty_score":0.683087},"labels":[],"label_agreement":null},{"id":"W1918663757","doi":"10.1186/1471-2105-13-s19-s4","title":"A flexible ancestral genome reconstruction method based on gapped adjacencies","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Synteny; Genome; Phylogenetic tree; Biology; Tree (set theory); Adjacency list; Extant taxon; Phylogenetics; Set (abstract data type); Phylogenetic network; Computational biology; Data mining; Evolutionary biology; Genetics; Computer science; Gene; Algorithm; Mathematics; Combinatorics","score_opus":0.031277767100683175,"score_gpt":0.28122426960227037,"score_spread":0.2499465025015872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1918663757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11281423,0.00043870602,0.864792,0.00006826858,0.0007717769,0.00061319314,0.000067307985,0.00009362641,0.020340929],"genre_scores_gemma":[0.08897645,0.000061762476,0.9091092,0.0003458018,0.0004594454,0.00003943766,0.0002356736,0.00002783133,0.00074443046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989549,0.00004575231,0.00028652424,0.0001279935,0.00018076088,0.00040410506],"domain_scores_gemma":[0.99930716,0.000016225562,0.00014041155,0.00035455122,0.000052466163,0.00012916885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041527557,0.00017860533,0.0001417485,0.00009139184,0.00008542031,0.000033475808,0.00015237121,0.00014040421,0.00006824919],"category_scores_gemma":[0.000053634623,0.00016244366,0.000099250734,0.00013303774,0.00005156755,0.000019758925,0.000046784047,0.000084733816,0.00012193038],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014128508,0.0017064712,0.13920495,0.0029727325,0.00070310273,0.0000031651805,0.0039037634,0.07645114,0.37089583,0.0017906708,0.010549589,0.39040574],"study_design_scores_gemma":[0.005283564,0.0020962493,0.05260368,0.00013734397,0.00021048835,0.0002293732,0.0035372588,0.47016934,0.24044885,0.00016932614,0.22269604,0.0024184918],"about_ca_topic_score_codex":0.0000027526082,"about_ca_topic_score_gemma":0.0000026720286,"teacher_disagreement_score":0.3937182,"about_ca_system_score_codex":0.0000322141,"about_ca_system_score_gemma":0.00008144281,"threshold_uncertainty_score":0.662426},"labels":[],"label_agreement":null},{"id":"W1926090033","doi":"10.1186/1471-2105-4-51","title":"A knowledge discovery object model API for Java","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"Genome Canada","keywords":"Computer science; Application programming interface; Java; Documentation; Ontology; Software engineering; Software; Software mining; Interface (matter); Database; Software development; Programming language; Software construction; Operating system","score_opus":0.03862548388309531,"score_gpt":0.2979191660009343,"score_spread":0.259293682117839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926090033","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018995805,0.0008589835,0.96666384,0.000027441632,0.00024208827,0.00027573694,0.00006229174,0.00003977254,0.01283404],"genre_scores_gemma":[0.1883465,0.00016354048,0.8015975,0.00049630646,0.0001815678,0.00011092762,0.00021185658,0.000037887,0.008853945],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916863,0.000020205423,0.00028171105,0.00014863988,0.00008441254,0.00029640237],"domain_scores_gemma":[0.9994375,0.000041842002,0.00008136677,0.00030411687,0.000056928722,0.000078250574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002547044,0.00015508608,0.00015730965,0.000039390805,0.000091255024,0.00004523141,0.0001728307,0.00021917607,0.0000033001356],"category_scores_gemma":[0.0005004525,0.0001241927,0.00013510777,0.000071866176,0.00011478506,0.0000080947,0.000058048114,0.00006312093,0.000021190592],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012804933,0.002122243,0.008507903,0.005879441,0.0009704514,0.000004001574,0.007761621,0.013269334,0.050551653,0.067675255,0.6032001,0.23877755],"study_design_scores_gemma":[0.0029888349,0.0008985754,0.00016797737,0.00007473122,0.00008419452,0.000043679578,0.001932033,0.48882192,0.04129078,0.0024712617,0.46028596,0.0009400702],"about_ca_topic_score_codex":8.29181e-7,"about_ca_topic_score_gemma":0.000015857555,"teacher_disagreement_score":0.4755526,"about_ca_system_score_codex":0.000012434594,"about_ca_system_score_gemma":0.00023925124,"threshold_uncertainty_score":0.50644314},"labels":[],"label_agreement":null},{"id":"W1950772819","doi":"10.1186/1471-2105-7-326","title":"A maximum likelihood framework for protein design","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal; Canadian Institutes of Health Research; Centre National de la Recherche Scientifique","keywords":"Pairwise comparison; Computer science; Inference; Markov chain; Markov chain Monte Carlo; Model selection; Mathematical optimization; Algorithm; Machine learning; Artificial intelligence; Mathematics","score_opus":0.010899072567568748,"score_gpt":0.23688803867762806,"score_spread":0.2259889661100593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1950772819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061099944,0.00019179263,0.9914765,0.000042583735,0.000098058445,0.0010284084,0.000046381832,0.000035224122,0.0009710981],"genre_scores_gemma":[0.02795574,0.0000063474126,0.97087437,0.00021951168,0.00033618716,0.00016638314,0.00019785362,0.000025641952,0.00021797777],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990641,0.000017436767,0.00031595744,0.00014885668,0.00011766643,0.00033599327],"domain_scores_gemma":[0.99933773,0.00001782596,0.00013882983,0.0003671267,0.00008018901,0.00005827349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017531088,0.00017871088,0.000137336,0.00003744695,0.00009698186,0.000052089767,0.00020784483,0.0002893503,0.0000055208984],"category_scores_gemma":[0.00012425963,0.00015801434,0.000111370944,0.00007998417,0.00004767245,0.0000073030214,0.00006611622,0.000081901344,0.000015957134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004262829,0.0011042642,0.0049898033,0.005367188,0.000631689,0.00001168988,0.0009026601,0.019691931,0.39887547,0.29546756,0.078631856,0.19006306],"study_design_scores_gemma":[0.0023859467,0.0013384159,0.0004966564,0.00013074742,0.00007793429,0.000048099326,0.00019163189,0.11659269,0.23627232,0.5826552,0.058555726,0.0012546272],"about_ca_topic_score_codex":0.0000055791224,"about_ca_topic_score_gemma":0.000014065856,"teacher_disagreement_score":0.28718767,"about_ca_system_score_codex":0.000013415766,"about_ca_system_score_gemma":0.00012382552,"threshold_uncertainty_score":0.6443638},"labels":[],"label_agreement":null},{"id":"W1951428955","doi":"10.1186/1471-2105-13-s19-s7","title":"Multiple genome comparison based on overlap regions of pairwise local alignments","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Deutscher Akademischer Austauschdienst","keywords":"Pairwise comparison; Genome; Computational biology; DNA microarray; Biology; Genetics; Computer science; Artificial intelligence; Gene; Gene expression","score_opus":0.026902683882040798,"score_gpt":0.2514885947358425,"score_spread":0.2245859108538017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951428955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75192434,0.00092383847,0.24126296,0.00003854919,0.00035316544,0.00046414754,0.00017936582,0.000010349292,0.004843279],"genre_scores_gemma":[0.97421485,0.000042221393,0.025265284,0.00022129429,0.00008319123,0.000012383802,0.0000975832,0.000013357411,0.00004985898],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909854,0.000024342313,0.00035620524,0.00009407685,0.00015198832,0.00027483725],"domain_scores_gemma":[0.9992747,0.00003333395,0.00017260536,0.00037059266,0.000046648267,0.0001021568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015444707,0.00015284187,0.00018550539,0.000042047264,0.00006603806,0.000007165029,0.0001466749,0.00010378181,0.000006087399],"category_scores_gemma":[0.00004706474,0.00013575282,0.00010680974,0.000056898196,0.00009795675,0.0000016980081,0.00009158662,0.0000476914,0.000022309829],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050337194,0.0014498284,0.84406126,0.0005618109,0.0003057698,4.215262e-7,0.0018525661,0.058795903,0.080209106,0.00082433264,0.007278979,0.0041566314],"study_design_scores_gemma":[0.0051477295,0.0020786766,0.3200915,0.00009119476,0.00018725928,0.000009535985,0.0043971753,0.391476,0.12670667,0.00006954508,0.14840275,0.0013419706],"about_ca_topic_score_codex":0.0000073358315,"about_ca_topic_score_gemma":0.000009792914,"teacher_disagreement_score":0.5239698,"about_ca_system_score_codex":0.000017322993,"about_ca_system_score_gemma":0.00004768679,"threshold_uncertainty_score":0.5535839},"labels":[],"label_agreement":null},{"id":"W1964430425","doi":"10.1186/1471-2105-11-563","title":"TESTLoc: protein subcellular localization prediction from EST data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Université de Montréal; Canadian Institute for Advanced Research","keywords":"Subcellular localization; Computational biology; Support vector machine; Sequence (biology); Function (biology); Protein sequencing; Protein function prediction; Computer science; Biology; DNA microarray; Data mining; Protein function; Artificial intelligence; Peptide sequence; Biochemistry; Genetics; Cytoplasm; Gene","score_opus":0.015299169738053143,"score_gpt":0.24581988314883316,"score_spread":0.23052071341078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964430425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23107268,0.000056241774,0.7623827,0.00005085274,0.0005357827,0.00063552125,0.0005649252,0.00013285827,0.0045684557],"genre_scores_gemma":[0.3231368,0.00003802394,0.64813054,0.0004360374,0.0010199542,0.000040398936,0.026452558,0.00007574418,0.000669933],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853456,0.00003300946,0.0006016603,0.0002448688,0.00030664634,0.00027928004],"domain_scores_gemma":[0.99779165,0.000022308495,0.00029039657,0.0016551176,0.000113358146,0.00012719638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041610084,0.0002350712,0.00015807596,0.00006518798,0.00015937493,0.00011910578,0.0007629734,0.00035095535,0.00008131517],"category_scores_gemma":[0.0007097251,0.00021887197,0.000050812265,0.00014593016,0.000109551016,0.00005300674,0.00049050705,0.00033351957,0.00018725435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048742295,0.0008652185,0.3742195,0.0020682127,0.0004741468,0.0000071700647,0.0028281482,0.025745831,0.46187118,0.0030447587,0.070809916,0.057578504],"study_design_scores_gemma":[0.0005223416,0.00011480308,0.0021901447,0.000026974387,0.00003052443,0.000013599447,0.00009682843,0.87417674,0.013020213,0.00006128592,0.10947182,0.000274714],"about_ca_topic_score_codex":0.00006228462,"about_ca_topic_score_gemma":0.0002500662,"teacher_disagreement_score":0.84843093,"about_ca_system_score_codex":0.000013059256,"about_ca_system_score_gemma":0.00015498207,"threshold_uncertainty_score":0.89253396},"labels":[],"label_agreement":null},{"id":"W1964514748","doi":"10.1186/1471-2105-11-226","title":"Partitioning of copy-number genotypes in pedigrees","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université de Montréal; Montreal Heart Institute; Institut national de psychiatrie légale Philippe-Pinel","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Pedigree chart; Copy-number variation; Genetics; Biology; Copy number analysis; Genotype; SNP array; Single-nucleotide polymorphism; Computational biology; Genome; Gene","score_opus":0.007366957130148598,"score_gpt":0.23088223053548929,"score_spread":0.2235152734053407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964514748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98836154,0.000022217419,0.0032892805,0.000013679955,0.00012873636,0.000071228555,0.00002371977,0.000005811142,0.008083761],"genre_scores_gemma":[0.95297,0.000019019393,0.0465637,0.00003775775,0.00007532711,0.0000072735447,0.00006986339,0.0000056889994,0.00025134522],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999465,0.000008568515,0.00027504234,0.00005965605,0.00006646151,0.00012527207],"domain_scores_gemma":[0.99964345,0.000009506731,0.000092476126,0.0001763216,0.00004974783,0.000028492483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011920381,0.00007071534,0.00008519119,0.000027109778,0.00003244785,0.000014025847,0.000099017416,0.00009206553,0.000106247666],"category_scores_gemma":[0.000047082394,0.00006628133,0.00003923729,0.000054790846,0.000051162595,0.000008040998,0.000051938812,0.00006633196,0.00003079072],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038665054,0.00009248103,0.95779115,0.00021221061,0.000025828629,5.2946604e-7,0.0012420382,0.0009382049,0.030416863,0.0073363595,0.00093694497,0.00096870266],"study_design_scores_gemma":[0.0032685169,0.00045835017,0.43409738,0.00010202665,0.00007499011,0.00016029015,0.005721204,0.021324797,0.4704964,0.0022580146,0.060769487,0.001268542],"about_ca_topic_score_codex":0.000031660118,"about_ca_topic_score_gemma":0.0005173983,"teacher_disagreement_score":0.5236938,"about_ca_system_score_codex":0.0000033112608,"about_ca_system_score_gemma":0.000072705625,"threshold_uncertainty_score":0.27028742},"labels":[],"label_agreement":null},{"id":"W1965560116","doi":"10.1186/1471-2105-9-515","title":"Improved machine learning method for analysis of gas phase chemistry of peptides","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Army Research Office; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Feature selection; Artificial intelligence; Normalization (sociology); Machine learning; Data mining; Mass spectrometry; Fragmentation (computing); Proteomics; Software; Database search engine; Mass spectrum; Chemistry; Search engine; Chromatography; Information retrieval","score_opus":0.02971369162966547,"score_gpt":0.3309501063571692,"score_spread":0.30123641472750373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965560116","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052117873,0.000052458057,0.94570446,0.0000069250505,0.0000022311683,0.00013704396,0.00029771536,0.0000610931,0.0016202019],"genre_scores_gemma":[0.044746242,0.000103945575,0.9542827,0.000007138895,0.000012658613,0.0000717814,0.0003872548,0.000012672122,0.0003755904],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990873,0.0000033797833,0.0005853987,0.00009305912,0.00009445353,0.00013645347],"domain_scores_gemma":[0.99876785,0.00015118805,0.0005837035,0.0003196795,0.00013225286,0.000045311903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014039488,0.00011843905,0.0003436794,0.0000629765,0.000076796954,0.000004049777,0.00017806223,0.00009596591,0.00007410443],"category_scores_gemma":[0.00013340727,0.00011239024,0.000245248,0.00029343864,0.00006611525,0.00006742264,0.000047905596,0.000114761606,3.5888473e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015382099,0.00030329044,0.0017939284,0.002303359,0.00056642876,1.8439327e-7,0.0009228061,0.0079318285,0.96884584,0.00041965002,0.00007140174,0.016687466],"study_design_scores_gemma":[0.0003285585,0.000016218191,0.0000019519011,0.000009073646,0.00016558387,0.0000015450768,0.000102578575,0.5331127,0.46528125,0.000089233996,0.0008230543,0.00006827038],"about_ca_topic_score_codex":0.000021785832,"about_ca_topic_score_gemma":0.0000026102614,"teacher_disagreement_score":0.5251809,"about_ca_system_score_codex":0.0000213035,"about_ca_system_score_gemma":0.00004005715,"threshold_uncertainty_score":0.45831412},"labels":[],"label_agreement":null},{"id":"W1965744864","doi":"10.1186/1471-2105-12-s9-s14","title":"Origin and evolution of gene families in Bacteria and Archaea","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University; McMaster University","funders":"","keywords":"Genome; Biology; Gene; Horizontal gene transfer; Archaea; Gene duplication; Genetics; Gene family; Genome evolution; Bacterial genome size; Gene cluster; Genome size; Evolutionary biology; Computational biology","score_opus":0.02074680044134661,"score_gpt":0.22023558622248285,"score_spread":0.19948878578113624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965744864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98728645,0.00040291334,0.0113905845,0.0000025136037,0.00003225085,0.00012120316,0.000013248013,0.0000034729333,0.00074734446],"genre_scores_gemma":[0.78915226,0.00045105655,0.21027979,0.000010442472,0.000018869856,0.0000060157863,0.000028074312,0.0000065356426,0.000046914294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99957657,0.000011251597,0.00018736886,0.000070300106,0.000048593443,0.00010590668],"domain_scores_gemma":[0.9997584,0.0000034727489,0.000060954106,0.00012320404,0.000022701213,0.000031223764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011478395,0.000072691444,0.00008898182,0.000065578366,0.00001289804,0.0000047156286,0.000051874285,0.0000627261,0.0000042029524],"category_scores_gemma":[0.000017087194,0.00006695974,0.000013885028,0.000047828165,0.00008206682,0.000006624122,0.00006529702,0.000025538955,0.0000018116762],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017388466,0.00012260098,0.6385551,0.00094348355,0.00007461275,0.0000013342947,0.008109519,0.000017230346,0.33601895,0.0009498163,0.000104593295,0.014928879],"study_design_scores_gemma":[0.0018756322,0.00057420763,0.876319,0.00004987634,0.00003095105,0.00003632328,0.003326879,0.012204147,0.10276695,0.0005328611,0.0018795398,0.00040366017],"about_ca_topic_score_codex":0.00004264062,"about_ca_topic_score_gemma":0.000065436194,"teacher_disagreement_score":0.23776387,"about_ca_system_score_codex":0.0000072896514,"about_ca_system_score_gemma":0.000027299991,"threshold_uncertainty_score":0.2730539},"labels":[],"label_agreement":null},{"id":"W1966813277","doi":"10.1186/1471-2105-15-205","title":"A model-based information sharing protocol for profile Hidden Markov Models used for HIV-1 recombination detection","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Deutsche Forschungsgemeinschaft","keywords":"Hidden Markov model; Subfamily; Inference; Biology; Computer science; Subtyping; Computational biology; Markov chain; Data mining; Artificial intelligence; Genetics; Machine learning; Gene","score_opus":0.04325172657652011,"score_gpt":0.2975769257119991,"score_spread":0.254325199135479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966813277","genre_codex":"methods","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007506953,0.0000012752369,0.9124237,0.00005967171,0.00007049647,0.08518823,0.00025676246,0.00011780398,0.0011314186],"genre_scores_gemma":[0.06651113,4.1363882e-7,0.34804058,0.00012120038,0.000030825093,0.58022666,0.003953439,0.00003123141,0.0010845568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988574,0.00003467765,0.00051731186,0.0001276433,0.000070606926,0.00039235412],"domain_scores_gemma":[0.9990029,0.00017773424,0.00025564074,0.00027245568,0.0002517719,0.000039501585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005591608,0.00017900059,0.0001992181,0.00021607657,0.00030592133,0.000078653575,0.0001807734,0.0002260994,0.000028964603],"category_scores_gemma":[0.00018828874,0.00015183982,0.00012329887,0.000095138355,0.000041159165,0.0009147479,0.0000398416,0.00010942009,0.00029077329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008012796,0.0012190136,0.0012406434,0.011326615,0.00045232137,1.2414051e-7,0.0055148317,0.044662792,0.004916634,0.009805508,0.027911082,0.88493764],"study_design_scores_gemma":[0.008694347,0.0005572453,0.000041818734,0.000049100006,0.000021560227,0.0000019574318,0.000086079745,0.96906686,0.01243058,0.0015917053,0.007285156,0.00017359076],"about_ca_topic_score_codex":0.0000058897217,"about_ca_topic_score_gemma":0.000022521608,"teacher_disagreement_score":0.9244041,"about_ca_system_score_codex":0.0001375354,"about_ca_system_score_gemma":0.00014355815,"threshold_uncertainty_score":0.6191848},"labels":[],"label_agreement":null},{"id":"W1967609592","doi":"10.1186/1471-2105-9-388","title":"Sequence based residue depth prediction using evolutionary information and predicted secondary structure","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Nankai University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computational biology; DNA microarray; Sequence (biology); Computer science; Bioinformatics; Biology; Artificial intelligence; Data mining; Genetics; Gene; Gene expression","score_opus":0.013576292047910131,"score_gpt":0.22304533816159058,"score_spread":0.20946904611368045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967609592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75256056,0.00022287827,0.24485998,0.000016144642,0.00017918403,0.00040252513,0.0009937779,0.000060282644,0.00070464815],"genre_scores_gemma":[0.7380805,0.00007616919,0.25872186,0.00039101075,0.00012837081,0.0000073512924,0.0025600833,0.000012702569,0.000021951291],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990887,0.000026341353,0.000377852,0.0001167785,0.0001929116,0.00019743416],"domain_scores_gemma":[0.9993242,0.000009373906,0.0001806127,0.00027037138,0.00012704183,0.000088393215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006278274,0.00016948965,0.000117772914,0.000092071044,0.00023081384,0.000027618222,0.00011382088,0.0002665836,0.000010058576],"category_scores_gemma":[0.00008603362,0.00015831964,0.000041047646,0.00012403865,0.00015240494,0.000086133514,0.0000787879,0.00014422284,0.0000016237108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021346437,0.00015218068,0.6173203,0.004280345,0.00046191926,0.000023516843,0.0036167894,0.17077708,0.1388659,0.0012618825,0.02198326,0.03912217],"study_design_scores_gemma":[0.0011432776,0.00021532507,0.08573843,0.000037451537,0.000030965286,0.0005165128,0.00012805568,0.90002614,0.007264032,0.0001914911,0.004398534,0.00030978397],"about_ca_topic_score_codex":0.00001768551,"about_ca_topic_score_gemma":0.000027890259,"teacher_disagreement_score":0.72924906,"about_ca_system_score_codex":0.000036603753,"about_ca_system_score_gemma":0.00047277415,"threshold_uncertainty_score":0.6456088},"labels":[],"label_agreement":null},{"id":"W1968385806","doi":"10.1186/1471-2105-12-s11-a1","title":"Highlights from the Student Council Symposium 2011 at the International Conference on Intelligent Systems for Molecular Biology and European Conference on Computational Biology","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Oxford; Iowa State University; European Bioinformatics Institute; Genome Canada","keywords":"Context (archaeology); Computational biology; Engineering ethics; Research council; Library science; Systems biology; Biology; Computer science; Engineering; Philosophy","score_opus":0.09850664232369968,"score_gpt":0.31348265163778444,"score_spread":0.21497600931408475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968385806","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2412217,0.002002258,0.63114727,0.008100371,0.004933928,0.004896895,0.003479555,0.000104570296,0.10411346],"genre_scores_gemma":[0.9777517,0.0033973646,0.011488288,0.0033630216,0.00050154433,0.0001373471,0.0021446615,0.00004345386,0.0011726255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998236,0.00014849196,0.00057348853,0.00027579654,0.0004261386,0.000340074],"domain_scores_gemma":[0.9984458,0.00017778078,0.00025068127,0.00046478046,0.0005246604,0.0001362998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088801084,0.00025496588,0.00019735804,0.000041020365,0.000221426,0.00010905631,0.00086505373,0.0001719911,0.0000663442],"category_scores_gemma":[0.00015470598,0.00014246223,0.000091694936,0.000035160825,0.00059013936,0.0000075909898,0.00049759913,0.0001548374,0.00016533234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040653655,0.0017254039,0.011154623,0.0007102237,0.0030002936,0.000013085288,0.02376109,0.0028511325,0.07523595,0.7201852,0.13414642,0.023151187],"study_design_scores_gemma":[0.0070759463,0.009054184,0.008114747,0.00037518636,0.0002648199,0.00007444224,0.010117733,0.46903327,0.038433477,0.014425082,0.4408446,0.0021865093],"about_ca_topic_score_codex":0.00006487883,"about_ca_topic_score_gemma":0.00007543226,"teacher_disagreement_score":0.73653,"about_ca_system_score_codex":0.000076289165,"about_ca_system_score_gemma":0.00024673005,"threshold_uncertainty_score":0.5809441},"labels":[],"label_agreement":null},{"id":"W1969973065","doi":"10.1186/1471-2105-15-11","title":"kruX: matrix-based non-parametric eQTL discovery","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Expression quantitative trait loci; Parametric statistics; Computer science; Test statistic; Statistical hypothesis testing; Robustness (evolution); Quantitative trait locus; Multiple comparisons problem; Outlier; Computational biology; Biology; Genetics; Mathematics; Statistics; Artificial intelligence; Genotype; Single-nucleotide polymorphism; Gene","score_opus":0.011050091680946818,"score_gpt":0.2604783079881021,"score_spread":0.2494282163071553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969973065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2587474,0.000067975816,0.73603743,0.00010444913,0.0002403264,0.00017872838,0.000026655955,0.000019863144,0.0045771627],"genre_scores_gemma":[0.8051271,0.000034839435,0.1922258,0.0008532437,0.00020658251,0.00002170376,0.00029293093,0.000018982328,0.001218807],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883205,0.00006561338,0.00044968157,0.00017228576,0.00013376566,0.00034660826],"domain_scores_gemma":[0.9990176,0.00009882303,0.00023436571,0.00048414464,0.00007335478,0.00009174185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053549965,0.0001749776,0.00022311466,0.00010508594,0.00010249724,0.0000493378,0.00024050381,0.00024261058,0.000013192963],"category_scores_gemma":[0.00069930987,0.0001532485,0.00014838569,0.00020256761,0.00006557535,0.000008715784,0.0000905393,0.00008995426,0.00014417262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025884403,0.00059375673,0.6792175,0.00093184237,0.0003273849,0.0000013798921,0.00025857077,0.14870931,0.00949869,0.0029233913,0.13314655,0.02413274],"study_design_scores_gemma":[0.0017551463,0.0006639454,0.11016493,0.000023403454,0.00006841445,0.000010777087,0.0001942928,0.816908,0.0037313958,0.00039785713,0.06541524,0.00066662085],"about_ca_topic_score_codex":0.000013353875,"about_ca_topic_score_gemma":0.000018270139,"teacher_disagreement_score":0.66819865,"about_ca_system_score_codex":0.000020760384,"about_ca_system_score_gemma":0.00012022738,"threshold_uncertainty_score":0.6249293},"labels":[],"label_agreement":null},{"id":"W1970025484","doi":"10.1186/1471-2105-11-s10-p1","title":"Human protein-protein interaction prediction","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Canadian Institutes of Health Research","keywords":"Computer science; UniProt; Interactome; RefSeq; Gene ontology; Data mining; Set (abstract data type); Feature (linguistics); Similarity (geometry); Domain (mathematical analysis); Bayesian probability; Information retrieval; Machine learning; Artificial intelligence; Biology; Gene; Mathematics; Genome","score_opus":0.010798290032959106,"score_gpt":0.24204393179336045,"score_spread":0.23124564176040135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970025484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8962552,0.000022880087,0.08122174,0.00005316614,0.00067431934,0.0008540462,0.000049622286,0.00007914228,0.020789921],"genre_scores_gemma":[0.9190194,0.0000036935544,0.07751475,0.00017564185,0.0007131784,0.00007995726,0.00042046513,0.000030003926,0.0020429199],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989017,0.000015046716,0.00050548645,0.00014301391,0.00015709079,0.00027765246],"domain_scores_gemma":[0.99906015,0.0000032391445,0.000235217,0.0005010232,0.00008714425,0.00011324834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002783879,0.00019244482,0.00012819462,0.00006645357,0.00018954194,0.000093250266,0.00023136978,0.0003025049,0.00006565079],"category_scores_gemma":[0.00004441059,0.00017747401,0.00010274794,0.00008277504,0.00007954573,0.000027260228,0.0001284896,0.00032661867,0.000105979016],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007411572,0.00012025192,0.00077712134,0.00028109286,0.00007113379,6.1730765e-7,0.00030003634,0.00042130201,0.96916837,0.005614185,0.009554315,0.013617444],"study_design_scores_gemma":[0.00397095,0.001720771,0.0042576464,0.00023032555,0.00009135002,0.00019467314,0.0015051715,0.2923204,0.330175,0.0035187365,0.3601378,0.001877185],"about_ca_topic_score_codex":0.000008068862,"about_ca_topic_score_gemma":0.00009927475,"teacher_disagreement_score":0.6389934,"about_ca_system_score_codex":0.000013353907,"about_ca_system_score_gemma":0.00006542687,"threshold_uncertainty_score":0.723718},"labels":[],"label_agreement":null},{"id":"W1970439912","doi":"10.1186/1471-2105-14-87","title":"Empirical Bayes estimation of posterior probabilities of enrichment: A comparative study of five estimators of the local false discovery rate","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"False discovery rate; Estimator; Bonferroni correction; Multiple comparisons problem; Statistics; Mathematics; Bayes' theorem; Histogram; Computer science; Bayesian probability; Biology; Artificial intelligence; Genetics","score_opus":0.017311316872554647,"score_gpt":0.2692022317274214,"score_spread":0.25189091485486675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970439912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96364874,0.000069581176,0.03496574,0.000012203,0.000067352456,0.00097240164,0.00007088924,0.0000029367054,0.00019018899],"genre_scores_gemma":[0.9878532,0.0000063596617,0.011992856,0.000022249626,0.000009121601,0.00002619479,0.000033088618,0.000006819336,0.000050093033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835795,0.0000743277,0.0011160519,0.00009418708,0.00020512441,0.00015233572],"domain_scores_gemma":[0.9982951,0.000079124984,0.0009081359,0.0004511641,0.00022913665,0.000037324324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002451016,0.00017114656,0.0004103034,0.00005216805,0.000035755264,0.000015050511,0.00028335652,0.00011067784,0.000006277045],"category_scores_gemma":[0.000068377725,0.000113433525,0.00013013861,0.0001472994,0.00038576397,0.000038628183,0.00025323505,0.00007162327,0.0000016368593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015614675,0.004776454,0.13356319,0.011071883,0.0017704113,3.3975144e-7,0.13534527,0.66604483,0.024249073,0.0015726574,0.004767524,0.0152769005],"study_design_scores_gemma":[0.002349044,0.0026988834,0.04798763,0.00029443516,0.00016994022,0.00000764021,0.044494826,0.82622725,0.07443393,0.0009223139,0.000034256016,0.00037982437],"about_ca_topic_score_codex":0.000064338856,"about_ca_topic_score_gemma":0.000040827872,"teacher_disagreement_score":0.16018245,"about_ca_system_score_codex":0.000012869679,"about_ca_system_score_gemma":0.0001384784,"threshold_uncertainty_score":0.4625685},"labels":[],"label_agreement":null},{"id":"W1970616250","doi":"10.1186/1471-2105-13-123","title":"Quartet decomposition server: a platform for analyzing phylogenetic trees","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; West Virginia University; National Science Foundation","keywords":"Phylogenetic tree; Phylogenetic network; Tree (set theory); Phylogenetics; Decomposition; Biology; Web server; Genomics; Identification (biology); Genome; Computer science; Evolutionary biology; Data mining; Gene; Computational biology; The Internet; Genetics; Ecology; Mathematics; Combinatorics; World Wide Web","score_opus":0.023527810550278343,"score_gpt":0.2710020579131435,"score_spread":0.2474742473628652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970616250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9326064,0.0019708353,0.06400016,0.000024301544,0.00027712167,0.00040114493,0.00007796705,0.000009425807,0.00063262624],"genre_scores_gemma":[0.9116823,0.00017654285,0.08729671,0.00014525447,0.00036797047,0.000056172685,0.00017779283,0.000020157377,0.00007708446],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990555,0.0000112092785,0.0003291793,0.00011876941,0.00008859441,0.00039675017],"domain_scores_gemma":[0.9993799,0.000029007237,0.00013364133,0.00028086716,0.000069366375,0.00010725235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021993567,0.0001816454,0.00016716405,0.000051687475,0.00015805897,0.00003220596,0.0001482957,0.000118089956,0.000005167024],"category_scores_gemma":[0.00003428706,0.00016669132,0.00014855522,0.00006716692,0.000041131563,0.000004655377,0.0000819641,0.00003766106,0.000016260445],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060025183,0.0006093815,0.4658633,0.0010971726,0.0010017635,3.820161e-7,0.004315078,0.0067058154,0.46753657,0.003138455,0.010993906,0.038137957],"study_design_scores_gemma":[0.008512946,0.0035938441,0.32630816,0.00013883843,0.0008215341,0.00015270858,0.004322712,0.08892516,0.34528252,0.0016430457,0.21665436,0.0036441414],"about_ca_topic_score_codex":0.0000040904606,"about_ca_topic_score_gemma":0.000055970715,"teacher_disagreement_score":0.20566046,"about_ca_system_score_codex":0.000016084989,"about_ca_system_score_gemma":0.000037169975,"threshold_uncertainty_score":0.67974746},"labels":[],"label_agreement":null},{"id":"W1971536409","doi":"10.1186/1471-2105-11-s4-o3","title":"Genomic analysis of a rare human tumor","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Degradation and Inhibitors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Provincial Health Services Authority; BC Cancer Agency","funders":"","keywords":"Art history; Classics; Philosophy; Art","score_opus":0.010321697484914799,"score_gpt":0.2472995598436294,"score_spread":0.2369778623587146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971536409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98942447,0.000025024445,0.0066789268,0.000009580272,0.000087519125,0.000114981645,0.000042951848,0.000010690317,0.0036058445],"genre_scores_gemma":[0.9667115,0.000004247985,0.032353226,0.00014358597,0.000071568444,0.00000732981,0.00036438648,0.000007995782,0.00033612148],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993981,0.000009521076,0.0003103289,0.000079908605,0.000092126225,0.000109982044],"domain_scores_gemma":[0.9993509,0.000004459626,0.000170383,0.0003590376,0.00006336441,0.000051825533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012475389,0.00008455316,0.00013653688,0.00013033816,0.0000472816,0.000015651214,0.0001677469,0.00007887294,0.00008978716],"category_scores_gemma":[0.00006249844,0.000075515745,0.00011909359,0.00020223239,0.00006330151,0.0000048879883,0.00006961589,0.000069048096,0.000013617787],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015860378,0.000046610956,0.02507844,0.000060818835,0.00023548123,2.3471567e-7,0.00011510404,0.0001314754,0.9706015,0.000908851,0.0020077098,0.0007978864],"study_design_scores_gemma":[0.0010587224,0.0003403038,0.082970515,0.000012931043,0.00053424516,0.000012116354,0.0004158063,0.0432502,0.81428105,0.00008100805,0.056478634,0.00056448055],"about_ca_topic_score_codex":0.000008387099,"about_ca_topic_score_gemma":0.00013504882,"teacher_disagreement_score":0.1563205,"about_ca_system_score_codex":0.0000035503592,"about_ca_system_score_gemma":0.00004991425,"threshold_uncertainty_score":0.30794427},"labels":[],"label_agreement":null},{"id":"W1972818612","doi":"10.1186/1471-2105-12-s1-s4","title":"On the PATHGROUPS approach to rapid small phylogeny","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal; Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristic; Simulated annealing; Computer science; Genome; Phylogenetics; Set (abstract data type); Computational biology; Sequence (biology); Greedy algorithm; DNA microarray; Data mining; Algorithm; Biology; Theoretical computer science; Artificial intelligence; Gene; Genetics","score_opus":0.05217310429469563,"score_gpt":0.20729530492198414,"score_spread":0.15512220062728851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972818612","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.356473,0.00021810438,0.3506904,0.000073346535,0.00036985657,0.0016918189,0.00005779436,0.00006603323,0.29035965],"genre_scores_gemma":[0.48125842,0.000082384875,0.51301354,0.003384949,0.00030695478,0.00021071047,0.00018327587,0.0000652971,0.001494436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991598,0.000032286345,0.00023561585,0.0001534595,0.0001386383,0.0002801794],"domain_scores_gemma":[0.9991581,0.000012688645,0.00007821574,0.0006068096,0.00004811975,0.00009605671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029313046,0.0001701867,0.000106154774,0.00004711814,0.00008580407,0.000026975236,0.00041197802,0.00010372552,0.000041725743],"category_scores_gemma":[0.000070836,0.00011382247,0.00009120659,0.00011392496,0.00004570342,0.0000027145245,0.00016148991,0.00008057275,0.00028645157],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002553421,0.0072820666,0.015049038,0.0028179388,0.002666941,0.000014922424,0.06945101,0.0040846635,0.21415333,0.13321376,0.25716215,0.29155076],"study_design_scores_gemma":[0.008661446,0.011478797,0.068876356,0.00020852749,0.00046572156,0.00020917685,0.022561776,0.124307066,0.36738062,0.0050823265,0.38373074,0.0070374706],"about_ca_topic_score_codex":0.0000038748717,"about_ca_topic_score_gemma":0.0000040175905,"teacher_disagreement_score":0.2888652,"about_ca_system_score_codex":0.000010536084,"about_ca_system_score_gemma":0.000033664888,"threshold_uncertainty_score":0.46415457},"labels":[],"label_agreement":null},{"id":"W1973231190","doi":"10.1186/1471-2105-15-82","title":"Transient protein-protein interface prediction: datasets, features, algorithms, and the RAD-T predictor","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Machine learning; Computer science; Artificial intelligence; Docking (animal); Protein–protein interaction; Set (abstract data type); Predictive modelling; Interface (matter); Data mining; Algorithm; Biology","score_opus":0.005182954369622684,"score_gpt":0.21526032901183562,"score_spread":0.21007737464221293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973231190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037985243,0.0019317305,0.9536704,0.0005069777,0.00030599313,0.0022928666,0.0013658585,0.00008304238,0.0018579322],"genre_scores_gemma":[0.72579604,0.00027107509,0.263971,0.001552176,0.001375942,0.0004734531,0.004357729,0.00009671329,0.0021058458],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884105,0.00008516417,0.00036933908,0.00021771537,0.00022423414,0.00026249894],"domain_scores_gemma":[0.9990575,0.000013858152,0.0001449693,0.0006278531,0.000049323717,0.00010651938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043217008,0.00023148736,0.00019437433,0.00003250283,0.000172372,0.000088798326,0.0003177285,0.00020617915,0.0000055521054],"category_scores_gemma":[0.00014024157,0.00015096032,0.0000758599,0.00007633782,0.00029425885,0.000018155233,0.00018314339,0.00019810814,0.0000048635866],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014115884,0.00087656185,0.00219862,0.009626485,0.0019198329,0.000014459071,0.010183412,0.009477018,0.19514753,0.09369072,0.25716466,0.4055848],"study_design_scores_gemma":[0.010796087,0.0011668436,0.0023283577,0.00020657192,0.0002028679,0.00028756083,0.0006898937,0.3151961,0.04038103,0.0020879246,0.6256281,0.0010286717],"about_ca_topic_score_codex":0.000013647879,"about_ca_topic_score_gemma":0.00003849032,"teacher_disagreement_score":0.68969935,"about_ca_system_score_codex":0.000011529558,"about_ca_system_score_gemma":0.000059116697,"threshold_uncertainty_score":0.61559826},"labels":[],"label_agreement":null},{"id":"W1974821006","doi":"10.1186/1471-2105-14-167","title":"Identifying cancer mutation targets across thousands of samples: MuteProc, a high throughput mutation analysis pipeline","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Mutation; Pipeline (software); DNA microarray; Throughput; Computational biology; Mutation testing; Genetics; Biology; Cancer; Mutation rate; Computer science; Gene; Gene expression; Programming language","score_opus":0.019643209953688755,"score_gpt":0.29781806443139286,"score_spread":0.2781748544777041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974821006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50684446,0.00059925194,0.4916766,0.0000326181,0.00016545136,0.00027530346,0.00028714314,0.000013655562,0.00010549307],"genre_scores_gemma":[0.91179335,0.00063327845,0.085669376,0.00022230983,0.00017125106,0.00008185314,0.0012852694,0.000020647109,0.00012263858],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868494,0.000018900095,0.00061947154,0.0001999637,0.000200148,0.000276583],"domain_scores_gemma":[0.9987425,0.000053927455,0.00042019508,0.00036391921,0.0003439244,0.00007553756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001851919,0.0001797511,0.00027100646,0.00009163184,0.00010182649,0.0000898418,0.00017861875,0.00014974864,0.00006554926],"category_scores_gemma":[0.000188486,0.0001703545,0.00017452525,0.00035757443,0.000076872486,0.00003121589,0.00011823264,0.00006377702,0.00001915581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056955137,0.00095931004,0.12506919,0.0040528737,0.0050720703,0.0000113175065,0.033791453,0.5012077,0.114075795,0.0015528173,0.027450074,0.18618782],"study_design_scores_gemma":[0.004428992,0.0005522867,0.09530209,0.00013712623,0.0015946573,0.00002789659,0.011037254,0.58629256,0.29185498,0.0016939145,0.0055385963,0.0015396576],"about_ca_topic_score_codex":0.0011190465,"about_ca_topic_score_gemma":0.0013939813,"teacher_disagreement_score":0.40600723,"about_ca_system_score_codex":0.00003793045,"about_ca_system_score_gemma":0.00012260785,"threshold_uncertainty_score":0.69468546},"labels":[],"label_agreement":null},{"id":"W1976093396","doi":"10.1186/1471-2105-13-151","title":"Towards a theoretical understanding of false positives in DNA motif finding","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Motif (music); False positive paradox; DNA microarray; Computational biology; Sequence motif; DNA; Computer science; True positive rate; DNA sequencing; Biology; Artificial intelligence; Genetics; Gene; Gene expression","score_opus":0.02154658368688884,"score_gpt":0.25463714486312017,"score_spread":0.23309056117623134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976093396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8698318,0.00012058253,0.12322583,0.000020171277,0.00010118338,0.00013148188,0.000027827,0.000005997357,0.0065351413],"genre_scores_gemma":[0.96452194,0.000047941092,0.035254285,0.00004403596,0.000045144236,0.000003447348,0.000053511143,0.000012281814,0.000017387938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915624,0.000025890919,0.0003475458,0.000075041484,0.00010929471,0.0002859863],"domain_scores_gemma":[0.99956816,0.00002130649,0.00011791118,0.0001974096,0.000021556769,0.0000736607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032199762,0.00012152441,0.00015004879,0.00007218234,0.000035594134,0.000017059165,0.00013986848,0.00013456584,0.000014520039],"category_scores_gemma":[0.00008406669,0.000111104804,0.00007283187,0.00009029291,0.00013497757,0.000010876049,0.00012655034,0.00006701236,0.00000514056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021551554,0.0005405865,0.13778915,0.001066727,0.00016526628,0.0000018118704,0.008834257,0.0017102873,0.09129922,0.7551141,0.0003132133,0.0029498767],"study_design_scores_gemma":[0.0065365215,0.0014500306,0.12398982,0.0006422298,0.00020759385,0.00021151883,0.045369625,0.52494156,0.26082224,0.032037497,0.0010871841,0.0027042003],"about_ca_topic_score_codex":0.0000026544853,"about_ca_topic_score_gemma":0.0000089554405,"teacher_disagreement_score":0.7230766,"about_ca_system_score_codex":0.000047035224,"about_ca_system_score_gemma":0.000059501435,"threshold_uncertainty_score":0.45307225},"labels":[],"label_agreement":null},{"id":"W1976192231","doi":"10.1186/1471-2105-11-546","title":"Optimizing transformations for automated, high throughput analysis of flow cytometry data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Terry Fox Research Institute; Montreal Clinical Research Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Bioconductor; Computer science; Outlier; Data transformation; Transformation (genetics); Preprocessor; Throughput; Normalization (sociology); Data mining; Context (archaeology); Data conversion; Data pre-processing; Artificial intelligence; Biology","score_opus":0.03282107336187351,"score_gpt":0.2891452926312239,"score_spread":0.2563242192693504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976192231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13232635,0.000056126297,0.8646617,0.00003058959,0.00032267958,0.00029178703,0.0018043404,0.00006554565,0.0004408976],"genre_scores_gemma":[0.35133427,0.00005757371,0.64283967,0.00009138178,0.00007759789,0.000011411654,0.005545582,0.000016372362,0.000026100632],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885833,0.0000116844885,0.00057175104,0.00017503205,0.0001512703,0.00023193125],"domain_scores_gemma":[0.99868655,0.000045643428,0.00017421103,0.0008827628,0.00013911692,0.000071722054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003046391,0.00016392561,0.00028891838,0.00020908973,0.00010772928,0.000044382403,0.00054711057,0.00022641233,0.000017208242],"category_scores_gemma":[0.00010913368,0.00015008009,0.00019520204,0.00046091707,0.00008259344,0.000036892474,0.0000786345,0.00010525077,0.0000032591374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007469921,0.0011742153,0.013695992,0.00275484,0.0071342695,0.000001010173,0.005049167,0.2093645,0.71391505,0.002007955,0.013557046,0.03059897],"study_design_scores_gemma":[0.0006789772,0.000089331974,0.0007638228,0.000007809138,0.0006057491,0.0000026687735,0.00014523882,0.9713858,0.02208828,0.000010820046,0.0040215193,0.00020002962],"about_ca_topic_score_codex":0.000026890837,"about_ca_topic_score_gemma":0.0003976389,"teacher_disagreement_score":0.76202124,"about_ca_system_score_codex":0.0000068136496,"about_ca_system_score_gemma":0.00010606211,"threshold_uncertainty_score":0.6120088},"labels":[],"label_agreement":null},{"id":"W1979217166","doi":"10.1186/1471-2105-13-54","title":"Mining biological information from 3D short time-series gene expression data: the OPTricluster algorithm","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Plant Biotechnology Institute; National Research Council Canada","funders":"National Research Council Canada","keywords":"Cluster analysis; Biological data; Data mining; Computer science; Arabidopsis thaliana; Data set; DNA microarray; Algorithm; Computational biology; Biology; Artificial intelligence; Pattern recognition (psychology); Bioinformatics; Gene; Gene expression; Genetics","score_opus":0.04298185814857665,"score_gpt":0.27080440351767165,"score_spread":0.22782254536909502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979217166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04246374,0.0009043514,0.95161676,0.00011902189,0.00072592776,0.00047531433,0.0003421097,0.00006223075,0.0032905205],"genre_scores_gemma":[0.047796465,0.0004968118,0.93800527,0.0011651545,0.0012439765,0.0000807043,0.010813107,0.000022926251,0.00037561142],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890345,0.000060519367,0.00042347252,0.00013448013,0.00020958742,0.0002685083],"domain_scores_gemma":[0.9987837,0.000026870019,0.00016617875,0.00085802446,0.00006527486,0.00009991566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003612104,0.00016835012,0.00012655978,0.000042143944,0.00017805707,0.000087664615,0.00050909247,0.00020893362,0.000056282348],"category_scores_gemma":[0.00010701113,0.00010519858,0.00004722079,0.00010732519,0.00007730268,0.00016028348,0.00052291644,0.00008817281,0.00012912032],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044281955,0.00023517916,0.01916215,0.00008815549,0.00015020072,3.7433773e-7,0.0035586914,0.00035268156,0.24049002,0.00004443402,0.25843903,0.47703624],"study_design_scores_gemma":[0.00074540713,0.00012851083,0.008085449,0.000035151206,0.00004748116,0.000025009365,0.00190755,0.08253219,0.18989669,0.0000177315,0.71604294,0.0005359029],"about_ca_topic_score_codex":0.0000027927792,"about_ca_topic_score_gemma":0.0000010591403,"teacher_disagreement_score":0.47650033,"about_ca_system_score_codex":0.000014774213,"about_ca_system_score_gemma":0.000055766268,"threshold_uncertainty_score":0.42898735},"labels":[],"label_agreement":null},{"id":"W1979486483","doi":"10.1186/1471-2105-9-293","title":"Indel PDB: A database of structural insertions and deletions derived from sequence alignments of closely related proteins","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Indel; Protein Data Bank (RCSB PDB); INDEL Mutation; Protein Data Bank; Biology; Sequence (biology); Sequence alignment; Computational biology; Multiple sequence alignment; Genetics; Protein structure; Protein secondary structure; Peptide sequence; Gene; Biochemistry","score_opus":0.020820656183266284,"score_gpt":0.24764042432717712,"score_spread":0.22681976814391083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979486483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.968647,0.00022171752,0.029921638,0.00001176415,0.00003405218,0.0003129397,0.00070382666,0.000009025001,0.00013801878],"genre_scores_gemma":[0.8509456,0.000137112,0.148088,0.000042042986,0.000011897757,0.000010367279,0.0007385809,0.000007872108,0.000018524388],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913454,0.00002462196,0.0004439624,0.00011999037,0.00014179916,0.00013510276],"domain_scores_gemma":[0.9992292,0.000011981967,0.0002596503,0.00034095222,0.00009493127,0.00006331562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005106207,0.00012908806,0.00016374116,0.000046794798,0.00008527119,0.00000521307,0.00014625446,0.0001481376,0.000006901791],"category_scores_gemma":[0.000088099645,0.00011538199,0.00005042448,0.000099917306,0.0002404768,0.000019956426,0.00013543399,0.00007875722,0.0000011794511],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012988092,0.000047900703,0.03366209,0.00025765054,0.00015028578,0.0000023696534,0.001191575,0.0005156497,0.9626921,0.00058978156,0.00008213223,0.0006785855],"study_design_scores_gemma":[0.0035232168,0.0006807614,0.111581035,0.00021276102,0.00015464367,0.00022484935,0.0007157102,0.104605235,0.77461153,0.0026016384,0.00031809154,0.0007705134],"about_ca_topic_score_codex":0.00010375884,"about_ca_topic_score_gemma":0.000049999446,"teacher_disagreement_score":0.18808056,"about_ca_system_score_codex":0.000009081834,"about_ca_system_score_gemma":0.00014504665,"threshold_uncertainty_score":0.4705141},"labels":[],"label_agreement":null},{"id":"W1979595209","doi":"10.1186/1471-2105-14-61","title":"ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; Alberta Innovates; University of Alberta","funders":"Alberta Innovates; University of Alberta; Alberta Cancer Foundation","keywords":"International HapMap Project; Population stratification; Ancestry-informative marker; Single-nucleotide polymorphism; Population; Biology; Allele frequency; Classifier (UML); Evolutionary biology; Artificial intelligence; Genetics; Computational biology; Computer science; Genotype; Demography; Gene","score_opus":0.027115380264424675,"score_gpt":0.30137540958180353,"score_spread":0.27426002931737886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979595209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55572796,0.0001030554,0.4434726,0.000092479095,0.00014147838,0.00039284676,0.000022547842,0.000013901923,0.000033155262],"genre_scores_gemma":[0.8694583,0.00010243182,0.12814009,0.00006457997,0.000076820026,0.00009904298,0.0017302216,0.000011609371,0.00031691638],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908996,0.000047939582,0.0004449163,0.0001900622,0.00006414869,0.00016296405],"domain_scores_gemma":[0.99925625,0.0000708551,0.00038316488,0.00012191871,0.0001139289,0.00005390016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043670443,0.00012982788,0.00014737551,0.000047639383,0.00018131197,0.00007920227,0.00005206304,0.00017883179,0.000003101474],"category_scores_gemma":[0.00038910122,0.00012574103,0.000039525934,0.000055933157,0.00003644977,0.000036167483,0.000039008086,0.000081703045,0.0000026605771],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010982246,0.00010592342,0.3883442,0.00023008844,0.00010072073,3.306977e-8,0.0005723407,0.003255555,0.51004344,0.00026768757,0.0020965724,0.09487361],"study_design_scores_gemma":[0.0004928825,0.00008688544,0.39484352,0.000007317975,0.000024190831,0.000015741229,0.00048363532,0.6009179,0.0026454043,0.000085828695,0.0002700312,0.00012670249],"about_ca_topic_score_codex":0.00022171064,"about_ca_topic_score_gemma":0.00020300258,"teacher_disagreement_score":0.59766227,"about_ca_system_score_codex":0.000014398216,"about_ca_system_score_gemma":0.000017842203,"threshold_uncertainty_score":0.512757},"labels":[],"label_agreement":null},{"id":"W1980415335","doi":"10.1186/1471-2105-8-282","title":"Statistical analysis and significance testing of serial analysis of gene expression data using a Poisson mixture model","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Occupational Cancer Research Centre","funders":"Michael Smith Health Research BC; Canadian Institutes of Health Research; Western Canada Research Grid","keywords":"Negative binomial distribution; Poisson distribution; Mixture model; Count data; Statistics; Binomial test; Expression (computer science); Variance (accounting); Binomial distribution; Goodness of fit; Statistical model; Poisson regression; Statistical hypothesis testing; Computer science; Quasi-likelihood; Mathematics","score_opus":0.06164966361484645,"score_gpt":0.3232141807709215,"score_spread":0.26156451715607504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980415335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33904654,0.00006776381,0.66043,0.0000017220292,0.000015288037,0.00006480232,0.00029551238,0.0000032368055,0.00007514511],"genre_scores_gemma":[0.522438,0.00001412352,0.47691894,0.000011827817,0.000019163183,8.853986e-7,0.0005829693,0.0000045002653,0.000009586745],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886423,0.00002645196,0.0005474919,0.00021037832,0.00020492182,0.00014649294],"domain_scores_gemma":[0.9986679,0.000045961035,0.00042488772,0.00063667353,0.00014816308,0.00007640522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044991806,0.00011312924,0.00027964573,0.000261428,0.000044119563,0.000013374365,0.00021939081,0.0001304781,0.0000055770392],"category_scores_gemma":[0.00021768067,0.00009940205,0.0000636201,0.0008536648,0.00007845549,0.000014113564,0.00014341451,0.000047829726,1.04126315e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011459856,0.00003633085,0.025113942,0.00008652363,0.00033371605,1.3165409e-7,0.00013137776,0.048493654,0.92429996,0.00002306473,0.00006780249,0.001298916],"study_design_scores_gemma":[0.00018236696,0.000030181774,0.011194564,0.000010914399,0.0010250987,6.2966063e-7,0.00016946088,0.73082757,0.25643605,0.000009295002,0.000021104235,0.00009276138],"about_ca_topic_score_codex":0.000026959164,"about_ca_topic_score_gemma":0.000052486474,"teacher_disagreement_score":0.68233395,"about_ca_system_score_codex":0.000009220678,"about_ca_system_score_gemma":0.000101600235,"threshold_uncertainty_score":0.4053498},"labels":[],"label_agreement":null},{"id":"W1981890639","doi":"10.1186/1471-2105-10-206","title":"Representative transcript sets for evaluating a translational initiation sites predictor","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Calgary Laboratory Services","keywords":"Benchmark (surveying); Set (abstract data type); Population; Computer science; Data mining; Data set; Expression (computer science); Sequence (biology); Test set; Computational biology; Algorithm; Biology; Machine learning; Artificial intelligence; Genetics","score_opus":0.04719615713034547,"score_gpt":0.35682675967505173,"score_spread":0.30963060254470626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981890639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16218878,0.00014142477,0.8303544,0.00033596225,0.00015199947,0.0011640817,0.00025188172,0.00008173009,0.0053297444],"genre_scores_gemma":[0.3300297,0.000023067343,0.66544116,0.0009961196,0.00020075699,0.000060086873,0.0029848595,0.000023124207,0.00024109543],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985537,0.000052451305,0.0006305254,0.0001657506,0.0003115002,0.00028607887],"domain_scores_gemma":[0.9990659,0.000083400366,0.00027011926,0.00028476602,0.00021020055,0.000085658365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051803206,0.00020815729,0.00017319927,0.00008321861,0.00016922786,0.00006736937,0.0001975981,0.00017560871,0.000027495758],"category_scores_gemma":[0.0005636493,0.0001984985,0.0001549994,0.0001196978,0.00004966557,0.000042290147,0.000018247672,0.000117875396,0.00001338999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067451517,0.0016419482,0.06665986,0.0055317744,0.0012304389,0.0000034572436,0.08106658,0.2104223,0.26436046,0.02363402,0.12931845,0.20938556],"study_design_scores_gemma":[0.0022893846,0.0011879742,0.0096813245,0.00003656966,0.00007765533,0.000018666131,0.0005656611,0.97079265,0.008292267,0.0013185353,0.0053497422,0.00038956746],"about_ca_topic_score_codex":9.3165227e-7,"about_ca_topic_score_gemma":0.000006813334,"teacher_disagreement_score":0.7603704,"about_ca_system_score_codex":0.000015483984,"about_ca_system_score_gemma":0.00014193566,"threshold_uncertainty_score":0.8094534},"labels":[],"label_agreement":null},{"id":"W1983546999","doi":"10.1186/1471-2105-9-s12-s7","title":"Extracting transcription factor binding sites from unaligned gene sequences with statistical models","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alpha Technologies (Canada)","funders":"National Science Council","keywords":"DNA binding site; Chromatin immunoprecipitation; Computational biology; DNA microarray; Transcription factor; Computer science; False positive paradox; Bayes' theorem; Genetics; Binding site; Biology; Statistical model; Gene; Data mining; Bayesian probability; Gene expression; Artificial intelligence; Promoter","score_opus":0.03288224196300695,"score_gpt":0.2342696851814729,"score_spread":0.20138744321846594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983546999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6369091,0.00006259094,0.36226463,0.000006485062,0.0000393224,0.000098601995,0.00031466037,0.000016268003,0.00028833453],"genre_scores_gemma":[0.69332206,0.000114560615,0.30542782,0.00004421083,0.000060491304,0.000005971331,0.000950901,0.000016492471,0.000057478333],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990041,0.00002183866,0.00035093696,0.00017921675,0.00019136151,0.00025252797],"domain_scores_gemma":[0.9994167,0.0000313406,0.00016066998,0.0002322595,0.0000621858,0.00009685655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006889226,0.00019012115,0.0001653371,0.00004043966,0.00017924208,0.000050407925,0.00015812217,0.00013830792,0.000023490164],"category_scores_gemma":[0.000022703814,0.00015932342,0.000053461983,0.00006569104,0.000095738826,0.000026410291,0.000033056684,0.000083932384,0.000014891876],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018857775,0.00011044703,0.013245662,0.00014758625,0.00017128757,0.000015401749,0.0024977294,0.021225885,0.96032274,0.00045253983,0.00026671521,0.001355433],"study_design_scores_gemma":[0.001393426,0.0005002453,0.004775171,0.000047259808,0.00007397382,0.00018742678,0.0015813564,0.87801534,0.11170478,0.00053794996,0.00036315998,0.0008199154],"about_ca_topic_score_codex":0.00003858629,"about_ca_topic_score_gemma":0.00009152442,"teacher_disagreement_score":0.85678947,"about_ca_system_score_codex":0.000025352892,"about_ca_system_score_gemma":0.00012865361,"threshold_uncertainty_score":0.6497021},"labels":[],"label_agreement":null},{"id":"W1984586858","doi":"10.1186/1471-2105-12-245","title":"In-silico prediction of disorder content using hybrid sequence representation","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Killam Trusts","keywords":"Computer science; Correlation; In silico; Proteome; Artificial intelligence; Pattern recognition (psychology); Computational biology; Mathematics; Biology; Bioinformatics; Genetics","score_opus":0.09182528233705196,"score_gpt":0.2713163947888129,"score_spread":0.17949111245176097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984586858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76442295,0.00013891236,0.23223016,0.000006587372,0.00025724137,0.00033552252,0.0000843775,0.000009634645,0.0025146059],"genre_scores_gemma":[0.92175573,0.00012586603,0.077643916,0.00012293115,0.0000642523,0.000010452139,0.00017118314,0.000013261901,0.00009240579],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989945,0.00001891045,0.0005907993,0.000101074125,0.000111692396,0.00018298946],"domain_scores_gemma":[0.9993025,0.0000070341607,0.00025736028,0.00030847464,0.00007829616,0.000046349513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019048803,0.00011761248,0.00014316141,0.0000696065,0.00003353539,0.0000100714615,0.00014196648,0.00009683072,0.00001713128],"category_scores_gemma":[0.00003645009,0.000110229776,0.00006812148,0.00010153452,0.00008444203,0.00002999593,0.00008561624,0.000069646565,0.000005658701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014958584,0.0012384842,0.6414717,0.002376425,0.00048422688,0.000011408718,0.016184503,0.025881335,0.2527759,0.006066367,0.0067971162,0.045216713],"study_design_scores_gemma":[0.0018776528,0.0004173327,0.018575553,0.00010018086,0.000048371534,0.000086127875,0.0025282982,0.9006354,0.072998755,0.0008136232,0.0015187919,0.00039987947],"about_ca_topic_score_codex":0.00009713548,"about_ca_topic_score_gemma":0.000041628333,"teacher_disagreement_score":0.8747541,"about_ca_system_score_codex":0.00001783925,"about_ca_system_score_gemma":0.000067226516,"threshold_uncertainty_score":0.449504},"labels":[],"label_agreement":null},{"id":"W1984599252","doi":"10.1186/1471-2105-12-299","title":"Ranking insertion, deletion and nonsense mutations based on their effect on genetic information","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Biology; Genetics; Nonsense mutation; Indel; INDEL Mutation; Coding region; Mutation; Context (archaeology); Computational biology; Single-nucleotide polymorphism; Gene; Missense mutation; Genotype","score_opus":0.010218176418838525,"score_gpt":0.20795641678705967,"score_spread":0.19773824036822116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984599252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.671654,0.000023517276,0.32332507,0.000028010827,0.00012657791,0.0003915075,0.00003286216,0.000038398248,0.0043801134],"genre_scores_gemma":[0.96257716,0.000026312098,0.035860527,0.0010361117,0.0000348668,0.000028707225,0.0003894222,0.000012817372,0.000034085468],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992,0.000061172366,0.00032063658,0.00010776163,0.00013829599,0.00017212355],"domain_scores_gemma":[0.9993786,0.000035330442,0.00013991147,0.0002866703,0.00008339184,0.00007609826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020580439,0.00017191998,0.00010489105,0.00013212807,0.00013965428,0.000035243724,0.00008525751,0.00014292733,0.000012127172],"category_scores_gemma":[0.0001308794,0.0001454167,0.000060825576,0.00010096699,0.000069335525,0.00001554876,0.000028290471,0.00007982685,0.00006165886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008904302,0.0015854099,0.16428687,0.003209355,0.00051528553,0.000008287649,0.01544978,0.34290922,0.032355685,0.005588006,0.009881934,0.41530588],"study_design_scores_gemma":[0.0019073432,0.001972793,0.107273795,0.000059068592,0.000034255343,0.00002253739,0.00023701349,0.87777597,0.008064025,0.00012872489,0.0021637192,0.00036073526],"about_ca_topic_score_codex":0.0000056725594,"about_ca_topic_score_gemma":0.000021780355,"teacher_disagreement_score":0.53486675,"about_ca_system_score_codex":0.000018317292,"about_ca_system_score_gemma":0.00005963776,"threshold_uncertainty_score":0.5929921},"labels":[],"label_agreement":null},{"id":"W1985380607","doi":"10.1186/1471-2105-14-s6-s10","title":"Analytical results on the Beauchemin model of lymphocyte migration","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Simple (philosophy); Computer science; Stochastic modelling; Displacement (psychology); Point (geometry); Lymphocyte; Applied mathematics; Biological system; Statistical physics; Mathematics; Immunology; Biology; Statistics; Physics; Geometry","score_opus":0.0844187858694037,"score_gpt":0.2880181692788446,"score_spread":0.2035993834094409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985380607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66068834,0.000014776399,0.16544992,0.003004703,0.00011515959,0.002163649,0.0001584693,0.0002636136,0.1681414],"genre_scores_gemma":[0.5420176,0.000015190747,0.45478353,0.0007385052,0.000052934083,0.000120155426,0.000040664818,0.000039541745,0.0021919012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980954,0.000046437483,0.0010573762,0.0001290918,0.000382103,0.00028960177],"domain_scores_gemma":[0.9966513,0.0019341634,0.00041780606,0.0007476459,0.00015730679,0.000091809845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007168865,0.00021294231,0.00034089547,0.00008418064,0.000073447656,0.000036239777,0.00038948638,0.00015956326,0.000104538994],"category_scores_gemma":[0.0030111687,0.00012112378,0.00014173175,0.00019696778,0.00021253765,0.00015164413,0.00009543283,0.0001641043,0.00041348083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010063719,0.00029819476,0.00014194047,0.00068634306,0.00006856645,3.40619e-7,0.0025018097,0.00044147333,0.00029955155,0.93209726,0.062547944,0.0008159428],"study_design_scores_gemma":[0.000404701,0.000069961265,0.000039836075,0.000066912486,0.000033240776,0.0000039625484,0.00036335905,0.86534965,0.004599618,0.12887989,0.000054923144,0.00013395849],"about_ca_topic_score_codex":0.000010225655,"about_ca_topic_score_gemma":0.000009366494,"teacher_disagreement_score":0.86490816,"about_ca_system_score_codex":0.00006160247,"about_ca_system_score_gemma":0.00008989625,"threshold_uncertainty_score":0.53145975},"labels":[],"label_agreement":null},{"id":"W1985592898","doi":"10.1186/1471-2105-12-s4-s6","title":"Deploying mutation impact text-mining software with the SADI Semantic Web Services framework","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation; Canarie","keywords":"Computer science; World Wide Web; Context (archaeology); SPARQL; Web service; Semantic Web; Data science; Ontology; Reuse; Information retrieval; RDF; Biology","score_opus":0.021306098551409337,"score_gpt":0.2603210407245414,"score_spread":0.23901494217313204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985592898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78522927,0.00043752338,0.21315245,0.000055796827,0.0001055451,0.00019235817,0.000015356089,0.000106318956,0.00070540106],"genre_scores_gemma":[0.71318465,0.000030690888,0.28619134,0.00037859986,0.00008567822,0.000014325301,0.000044553686,0.000019907331,0.00005024937],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990879,0.00003360626,0.00024482628,0.0001447478,0.00018143731,0.00030744117],"domain_scores_gemma":[0.99922043,0.00007602591,0.00018466376,0.00036926154,0.000065783126,0.00008380875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022152638,0.00019192445,0.00014915378,0.000043192602,0.00018324706,0.000057616646,0.0003160511,0.00022682572,0.000024033114],"category_scores_gemma":[0.00012364815,0.00010760849,0.00007918284,0.00015918115,0.00017075679,0.000012677112,0.00010444108,0.00014401735,0.000029037075],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001455437,0.0004481821,0.59272057,0.0031847423,0.0014779343,0.000056915043,0.06250125,0.0015317905,0.0044085127,0.0004073654,0.010575627,0.32123166],"study_design_scores_gemma":[0.008239232,0.011763132,0.43208596,0.0034291614,0.0013832975,0.0019406534,0.13750297,0.32027304,0.033167865,0.0021395488,0.04200261,0.006072532],"about_ca_topic_score_codex":0.000021196794,"about_ca_topic_score_gemma":0.000103868224,"teacher_disagreement_score":0.31874123,"about_ca_system_score_codex":0.000011160698,"about_ca_system_score_gemma":0.00011146673,"threshold_uncertainty_score":0.43881467},"labels":[],"label_agreement":null},{"id":"W1986157690","doi":"10.1186/1471-2105-15-318","title":"Metabolic network prediction through pairwise rational kernels","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Computer science; Kernel (algebra); Support vector machine; Similarity (geometry); Artificial intelligence; Sequence (biology); Machine learning; Data mining; Pattern recognition (psychology); Mathematics; Biology","score_opus":0.009871139652815736,"score_gpt":0.21106332019350568,"score_spread":0.20119218054068994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986157690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068724595,0.0006854338,0.9259167,0.00007481658,0.0013389583,0.0002444011,0.00003363271,0.00009574081,0.0028857458],"genre_scores_gemma":[0.49862012,0.00085519475,0.4865558,0.0010004498,0.009089888,0.000054568918,0.001344206,0.000060058075,0.0024197116],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991879,0.000032283588,0.00029753597,0.00014633934,0.00012125468,0.0002146941],"domain_scores_gemma":[0.9994859,0.000004548392,0.00009546383,0.00029660406,0.00006894225,0.00004852144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003077899,0.00014071372,0.00013028174,0.000022522314,0.00009248925,0.00003131478,0.000108196255,0.00013223263,0.000015630141],"category_scores_gemma":[0.00011941454,0.00012457375,0.00007823194,0.00011597215,0.000038128517,0.000015850726,0.000046564637,0.00007279786,0.00004897488],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026475478,0.00026851607,0.009829656,0.000593801,0.00037499634,3.3009866e-7,0.00085003633,0.33671632,0.38739386,0.028904384,0.19340006,0.041403286],"study_design_scores_gemma":[0.00063182454,0.00013884589,0.004730924,0.000021523228,0.00005125748,0.000032454358,0.000037911133,0.06819209,0.050314996,0.00029216128,0.8752537,0.00030234782],"about_ca_topic_score_codex":0.000003960334,"about_ca_topic_score_gemma":0.0000047618405,"teacher_disagreement_score":0.6818536,"about_ca_system_score_codex":0.0000056280223,"about_ca_system_score_gemma":0.00003587166,"threshold_uncertainty_score":0.50799704},"labels":[],"label_agreement":null},{"id":"W1987067655","doi":"10.1186/1471-2105-12-67","title":"MIR@NT@N: a framework integrating transcription factors, microRNAs and their targets to identify sub-network motifs in a meta-regulation network model","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Child and Family Research Institute; Institute for Research in Immunology and Cancer; University of British Columbia","funders":"Canadian Institutes of Health Research; National Institute of General Medical Sciences; Centre National de la Recherche Scientifique; Fonds National de la Recherche Luxembourg; Michael Smith Health Research BC; Université de Montréal; Child and Family Research Institute; Institute of Genetics; Institut National de la Santé et de la Recherche Médicale; Université du Luxembourg","keywords":"Computational biology; Gene regulatory network; microRNA; Biology; Computer science; Biological network; Systems biology; Transcription factor; Gene; Bioinformatics; Genetics; Gene expression","score_opus":0.039982651521636915,"score_gpt":0.25350007155950977,"score_spread":0.21351742003787286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987067655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4579108,0.0012355904,0.5402776,0.000013406568,0.000103158294,0.00032684166,0.000013967902,0.00002290532,0.000095725125],"genre_scores_gemma":[0.78188246,0.000074527125,0.21746424,0.00016492675,0.00015282347,0.000037071626,0.00015697833,0.000033422217,0.000033555323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980389,0.00011240147,0.00077210343,0.0003501704,0.00016996422,0.00055644405],"domain_scores_gemma":[0.99890035,0.000032798787,0.0002690117,0.00051695615,0.00010170799,0.00017919327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006461221,0.00041770705,0.0005135683,0.00012396455,0.00015359472,0.00007306666,0.00025998172,0.00039613017,0.000019030012],"category_scores_gemma":[0.00006871406,0.00033292538,0.0003087521,0.00044805545,0.000067370485,0.000035986446,0.00013232391,0.00020067612,0.0000069473167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031499052,0.0001751358,0.04640981,0.0003142503,0.0018029135,0.0000013907312,0.013810013,0.8436254,0.08571836,0.0012017402,0.003903727,0.002722229],"study_design_scores_gemma":[0.00056353345,0.00021775717,0.03786153,0.00016817439,0.0007111945,0.00001185161,0.0012029893,0.906251,0.04606702,0.005111002,0.00081640744,0.0010175064],"about_ca_topic_score_codex":0.000025261661,"about_ca_topic_score_gemma":0.00082226825,"teacher_disagreement_score":0.32397166,"about_ca_system_score_codex":0.000037776208,"about_ca_system_score_gemma":0.00006385877,"threshold_uncertainty_score":0.99991226},"labels":[],"label_agreement":null},{"id":"W1987588530","doi":"10.1186/1471-2105-15-329","title":"trieFinder: an efficient program for annotating Digital Gene Expression (DGE) tags","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"UniGene; Computer science; DNA microarray; Annotation; Computational biology; Bioconductor; Gene Annotation; Data mining; Biology; Information retrieval; Expressed sequence tag; Gene; Genome; Genetics; Gene expression; Artificial intelligence","score_opus":0.017640864083337947,"score_gpt":0.28031880291463246,"score_spread":0.26267793883129453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987588530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15097637,0.00006112587,0.8452581,0.000037632057,0.00019540085,0.00091662345,0.000041800937,0.0000771998,0.002435713],"genre_scores_gemma":[0.6724038,0.000010706602,0.32496768,0.00026069186,0.0003280248,0.00038685268,0.001152783,0.000034618657,0.0004548351],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990018,0.000022771825,0.000347971,0.00021385938,0.00016248995,0.0002511306],"domain_scores_gemma":[0.9991245,0.000017588753,0.0001981127,0.000417547,0.00011610012,0.00012609965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019893178,0.00015690888,0.00012110815,0.000048508973,0.000121230994,0.00013501302,0.00019551151,0.0001455035,0.0000033894203],"category_scores_gemma":[0.00014411808,0.00013242243,0.00008808843,0.000079218145,0.000043232965,0.000016452943,0.000066848486,0.00005110776,0.000009724347],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041660696,0.00072504213,0.0017792571,0.00043977477,0.0000309372,1.4062363e-7,0.00093009387,0.010827878,0.45208344,0.00053726736,0.014569585,0.51765996],"study_design_scores_gemma":[0.0018405655,0.00099581,0.0005343711,0.0000416118,0.000016410226,0.000007756931,0.0005995063,0.5073509,0.29729748,0.00008694101,0.19078612,0.00044249473],"about_ca_topic_score_codex":5.16651e-7,"about_ca_topic_score_gemma":0.0000010292706,"teacher_disagreement_score":0.52142745,"about_ca_system_score_codex":0.000011776765,"about_ca_system_score_gemma":0.00006882259,"threshold_uncertainty_score":0.540003},"labels":[],"label_agreement":null},{"id":"W1988766191","doi":"10.1186/1471-2105-10-244","title":"ETISEQ – an algorithm for automated elution time ion sequencing of concurrently fragmented peptides for mass spectrometry-based proteomics","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Sydney; Australian Government; Ontario Ministry of Natural Resources and Forestry","keywords":"Fragmentation (computing); Shotgun proteomics; Proteomics; Peptide; Mass spectrometry; Data acquisition; Computer science; Quantitative proteomics; Tandem mass spectrometry; Chemistry; Computational biology; Chromatography; Biology; Biochemistry","score_opus":0.02039169974329908,"score_gpt":0.2938443584831975,"score_spread":0.27345265873989844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988766191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010271397,0.000013026389,0.9863702,0.000032286323,0.000017833863,0.0015190097,0.00084133685,0.0006469207,0.00028800557],"genre_scores_gemma":[0.0072836624,0.0000071308864,0.99080694,0.00004995209,0.00006407891,0.00037285095,0.0013251894,0.000024890856,0.00006529381],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987025,0.0000062420604,0.00065204897,0.00017550959,0.0001587382,0.00030494205],"domain_scores_gemma":[0.9987035,0.0000744741,0.00054418563,0.00036269805,0.0002300401,0.0000851225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020196974,0.00021322242,0.00027665086,0.00010934031,0.00014126966,0.00004016476,0.00023148424,0.0001892419,0.000016657563],"category_scores_gemma":[0.000060816143,0.00021747661,0.00013645663,0.00018364894,0.00005245747,0.00025695987,0.000013833377,0.00011039871,0.0000037766688],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007134305,0.000121533354,0.000019303256,0.00058299367,0.000020824018,9.267708e-8,0.00010223785,0.002837344,0.9846603,0.0019009461,0.00024847646,0.009434606],"study_design_scores_gemma":[0.00060908246,0.00014773794,0.000004003332,0.00007255412,0.000026067972,0.0000014872826,0.00006442301,0.571064,0.42627946,0.0014456761,0.0001358807,0.00014966658],"about_ca_topic_score_codex":0.0000023663265,"about_ca_topic_score_gemma":5.4652935e-7,"teacher_disagreement_score":0.56822664,"about_ca_system_score_codex":0.00023842392,"about_ca_system_score_gemma":0.00016067325,"threshold_uncertainty_score":0.8868439},"labels":[],"label_agreement":null},{"id":"W1989871058","doi":"10.1186/s12859-014-0435-6","title":"Pollux: platform independent error correction of single and mixed genomes","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Error detection and correction; Ion semiconductor sequencing; Computer science; Software; Sequence assembly; k-mer; Word error rate; Data mining; Algorithm; Computational biology; DNA sequencing; Biology; Genetics; Artificial intelligence; Operating system; DNA; Gene","score_opus":0.03855053966665911,"score_gpt":0.24253673561506203,"score_spread":0.20398619594840292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989871058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991374,0.001299196,0.0028045056,0.000012419252,0.00047521893,0.00014099113,0.00002315184,0.0000038689964,0.0038666031],"genre_scores_gemma":[0.9860591,0.000119051685,0.013378247,0.00004594998,0.00006458369,0.000004596817,0.000026795939,0.000009000921,0.00029261934],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941283,0.000007987818,0.0002531272,0.0000880365,0.00010358976,0.00013440223],"domain_scores_gemma":[0.99953014,0.000009099859,0.00013193711,0.00016563968,0.00008665632,0.00007652052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014089521,0.00010595097,0.00013142197,0.000040062958,0.000037624377,0.000014476139,0.00007842728,0.00009206527,0.0000016304352],"category_scores_gemma":[0.00005476651,0.000093835784,0.000038918544,0.00004592905,0.000067919405,0.0000021611386,0.00013279142,0.00003259245,0.000003973295],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001156387,0.00072707253,0.20017287,0.00092590676,0.00087637716,0.0000026204168,0.014105587,0.009451772,0.5598312,0.000621886,0.025707964,0.1864204],"study_design_scores_gemma":[0.007054837,0.0049533686,0.08475856,0.00008386948,0.00023444188,0.00020546849,0.029023893,0.05673686,0.6846423,0.0008935771,0.12979598,0.0016168546],"about_ca_topic_score_codex":0.000013172801,"about_ca_topic_score_gemma":0.00008744293,"teacher_disagreement_score":0.18480353,"about_ca_system_score_codex":0.000012929884,"about_ca_system_score_gemma":0.00006741876,"threshold_uncertainty_score":0.38265124},"labels":[],"label_agreement":null},{"id":"W1990193053","doi":"10.1186/1471-2105-11-s1-s11","title":"Fast motif recognition via application of statistical thresholds","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"","keywords":"Pairwise comparison; Hamming distance; Computer science; String (physics); String metric; Bounded function; Motif (music); Bottleneck; Theoretical computer science; String searching algorithm; Algorithm; Mathematics; Artificial intelligence; Pattern matching; Physics","score_opus":0.006674848646587189,"score_gpt":0.22524083350032448,"score_spread":0.2185659848537373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990193053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38697916,0.0000059759727,0.61118996,0.000006660014,0.00008729819,0.00013082745,0.00011806896,0.000007576488,0.0014744877],"genre_scores_gemma":[0.6662581,0.000010011348,0.332555,0.000044194156,0.00007206654,0.000012814463,0.0010095469,0.000012176525,0.00002606975],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993245,0.000007712573,0.00032937294,0.000101176374,0.0001017482,0.00013547394],"domain_scores_gemma":[0.9993571,0.000012367103,0.0001618633,0.00031458712,0.0000956446,0.000058423502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013544697,0.00010124141,0.000103541606,0.00003113798,0.0000393123,0.000015261354,0.00014210065,0.0001593458,0.000021221838],"category_scores_gemma":[0.000044411936,0.000097729855,0.00004549554,0.00005092346,0.000081873695,0.0000051344327,0.00006481876,0.00009154152,0.000041720476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097885735,0.0003030867,0.017921282,0.0006163032,0.00007308678,4.1546332e-7,0.0003035741,0.0010029756,0.73224366,0.0041824672,0.0010769306,0.24217834],"study_design_scores_gemma":[0.0007117605,0.00025560227,0.009620008,0.000008720986,0.000040524883,0.00004737184,0.00019666686,0.9395318,0.043927558,0.002694493,0.002605005,0.00036049334],"about_ca_topic_score_codex":0.000008322966,"about_ca_topic_score_gemma":0.00009823092,"teacher_disagreement_score":0.93852884,"about_ca_system_score_codex":0.0000048367324,"about_ca_system_score_gemma":0.00004084141,"threshold_uncertainty_score":0.39853078},"labels":[],"label_agreement":null},{"id":"W1991529077","doi":"10.1186/1471-2105-11-127","title":"Effects of scanning sensitivity and multiple scan algorithms on microarray data quality","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"Health Canada","keywords":"Reproducibility; Scanner; Computer science; Signal-to-noise ratio (imaging); Noise (video); Sensitivity (control systems); SIGNAL (programming language); Pattern recognition (psychology); Dynamic range; Algorithm; Artificial intelligence; Data mining; Statistics; Mathematics; Computer vision","score_opus":0.028665305716843514,"score_gpt":0.3006832648283446,"score_spread":0.2720179591115011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991529077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9509008,0.00008240859,0.047824655,0.00004293193,0.00026931753,0.00023188909,0.00008459232,0.000013522875,0.0005499057],"genre_scores_gemma":[0.9488729,0.000036646812,0.05059286,0.00012381753,0.000086264066,0.0000032689256,0.000210628,0.00000866219,0.00006491339],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999302,0.000047193444,0.00022940863,0.00017288802,0.00011593852,0.0001325393],"domain_scores_gemma":[0.9990303,0.00006370104,0.00016801324,0.0006161608,0.000052894175,0.00006892753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043278275,0.00010282243,0.000118227115,0.00003588548,0.00006357657,0.000019543628,0.0001457882,0.00012080463,0.0000015782182],"category_scores_gemma":[0.00035848378,0.000089444395,0.000027097401,0.00005301317,0.000091212125,0.000009888294,0.0001847196,0.00009890299,0.000002845363],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003906737,0.000040011615,0.0047970046,0.0001892392,0.000010317216,1.2515429e-7,0.00008992303,0.000017911017,0.9799432,0.00003714804,0.0010551199,0.013780929],"study_design_scores_gemma":[0.0007552582,0.00007850587,0.05067993,0.000035147106,0.0000133439125,0.0000056344893,0.00015606073,0.03226479,0.9092095,0.0000077534505,0.0066219703,0.00017213247],"about_ca_topic_score_codex":0.000020459227,"about_ca_topic_score_gemma":0.000074956435,"teacher_disagreement_score":0.07073373,"about_ca_system_score_codex":0.000003738039,"about_ca_system_score_gemma":0.0000617854,"threshold_uncertainty_score":0.36474368},"labels":[],"label_agreement":null},{"id":"W1991732078","doi":"10.1186/1471-2105-12-168","title":"More accurate recombination prediction in HIV-1 using a robust decoding algorithm for HMMs","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Hidden Markov model; Decoding methods; Breakpoint; Algorithm; Viterbi algorithm; Computer science; Markov chain; Task (project management); Artificial intelligence; Genetics; Biology; Machine learning; Engineering; Gene","score_opus":0.09920860630598254,"score_gpt":0.29572549804740794,"score_spread":0.1965168917414254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991732078","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06541066,0.00020844236,0.93073183,0.000018892706,0.0004645489,0.0010516361,0.0004642341,0.000084859224,0.001564871],"genre_scores_gemma":[0.070471935,0.00007068181,0.92573386,0.000050979535,0.000034668366,0.0001974668,0.0021005878,0.000028181976,0.0013116341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991732,0.000035692978,0.0003430383,0.000099732664,0.000032802163,0.00031550325],"domain_scores_gemma":[0.9995936,0.00006665368,0.00011076436,0.00013658355,0.0000679496,0.000024462799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002518876,0.00011266966,0.00014316315,0.00019022483,0.0001298793,0.000016467635,0.00009872354,0.00015326908,0.000121346566],"category_scores_gemma":[0.000067961126,0.00009701398,0.000054040975,0.0001299502,0.000053374883,0.0003187077,0.00003835524,0.000117433825,0.00030051585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012431333,0.002706985,0.12868145,0.001242525,0.000987395,0.000022368778,0.04491088,0.0033587953,0.0035785595,0.0017404233,0.016302628,0.79522485],"study_design_scores_gemma":[0.005856911,0.00041686956,0.013479037,0.0001265046,0.0000559362,0.00007022304,0.0031917752,0.9694176,0.0054974384,0.00023916087,0.0013924608,0.0002560837],"about_ca_topic_score_codex":0.000042688385,"about_ca_topic_score_gemma":0.000030393981,"teacher_disagreement_score":0.9660588,"about_ca_system_score_codex":0.000120828685,"about_ca_system_score_gemma":0.000080804595,"threshold_uncertainty_score":0.39561152},"labels":[],"label_agreement":null},{"id":"W1991777830","doi":"10.1186/1471-2105-11-64","title":"ICC-CLASS: isotopically-coded cleavable crosslinking analysis software suite","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of Victoria","funders":"Genome British Columbia; Genome Canada","keywords":"Reagent; Software suite; Mass spectrometry; Software; Combinatorial chemistry; Chemistry; Isotopic labeling; Computer science; Peptide; Chromatography; Programming language; Organic chemistry; Biochemistry","score_opus":0.012206019377268406,"score_gpt":0.2581573950639124,"score_spread":0.245951375686644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991777830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08764666,0.0000288632,0.6255356,0.0002603821,0.000118808886,0.0003330305,0.00019449867,0.0017955392,0.28408659],"genre_scores_gemma":[0.25727654,0.000019814932,0.7385802,0.00024235954,0.0001608405,0.00008421421,0.00022540851,0.000029581082,0.0033810239],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984556,0.000004141845,0.00060155056,0.00019968026,0.0003270177,0.00041203128],"domain_scores_gemma":[0.99839145,0.00012342636,0.00026767515,0.00095198443,0.00011019295,0.00015526054],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019413076,0.00021201812,0.00030932872,0.00018477748,0.00024593333,0.00025562893,0.00057952036,0.00029067334,0.0055503123],"category_scores_gemma":[0.00016223965,0.00019554772,0.00027436562,0.00080876896,0.000093021976,0.00021027248,0.00023660608,0.00050751795,0.00013851082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008471309,0.0011879194,0.5450952,0.003689346,0.0017519029,0.0000102015,0.0020395673,0.0011833702,0.054282427,0.29575577,0.019402282,0.075517274],"study_design_scores_gemma":[0.0013386443,0.000058387865,0.006879937,0.0000728497,0.0010627141,0.00003542238,0.000522728,0.6275641,0.07907179,0.020537594,0.26117614,0.0016797554],"about_ca_topic_score_codex":0.000028844674,"about_ca_topic_score_gemma":0.00018675598,"teacher_disagreement_score":0.6263807,"about_ca_system_score_codex":0.000051079234,"about_ca_system_score_gemma":0.00006717807,"threshold_uncertainty_score":0.99535877},"labels":[],"label_agreement":null},{"id":"W1993373022","doi":"10.1186/1471-2105-11-550","title":"Localizing triplet periodicity in DNA and cDNA sequences","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; National Science Foundation","keywords":"Complementary DNA; DNA microarray; Computational biology; DNA; Genetics; Biology; DNA sequencing; Gene; Gene expression","score_opus":0.009263907348636287,"score_gpt":0.23615520734689918,"score_spread":0.2268912999982629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993373022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945074,0.00012216867,0.00295156,0.00007792103,0.00008019666,0.00008016584,0.000010028566,0.000009753005,0.0021608416],"genre_scores_gemma":[0.98476434,0.00010355812,0.014549132,0.00033733656,0.00007426155,0.000006414047,0.000053127776,0.000005768013,0.000106061285],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931747,0.000013521829,0.00025762874,0.00012604137,0.00009917947,0.00018618653],"domain_scores_gemma":[0.99960816,0.000011379636,0.0000759838,0.00020184033,0.00002986367,0.00007278145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020975956,0.00011257251,0.00013059516,0.00006360552,0.00006427342,0.00005333944,0.0001256733,0.00014113425,0.00002123527],"category_scores_gemma":[0.00012873956,0.00009335677,0.00004969069,0.00012111206,0.00016527328,0.000017425502,0.00007313048,0.000126747,0.000013638022],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010804212,0.00011295962,0.2511955,0.00033311566,0.000060876046,0.00001039535,0.0013958879,0.00032947923,0.7193524,0.0009199945,0.0010044059,0.02517693],"study_design_scores_gemma":[0.0041946596,0.0009907482,0.08970611,0.00015659555,0.00015568563,0.00034119253,0.008296411,0.35456288,0.43825057,0.0022843827,0.09854595,0.0025148357],"about_ca_topic_score_codex":0.000091591784,"about_ca_topic_score_gemma":0.0010913053,"teacher_disagreement_score":0.35423338,"about_ca_system_score_codex":0.0000053588797,"about_ca_system_score_gemma":0.00006919388,"threshold_uncertainty_score":0.38069785},"labels":[],"label_agreement":null},{"id":"W1995701890","doi":"10.1186/s12859-015-0515-2","title":"aTRAM - automated target restricted assembly method: a fast method for assembling loci across divergent taxa from next-generation sequencing data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of Illinois at Urbana-Champaign; Genome Canada; National Science Foundation","keywords":"Biology; Sequence assembly; Genome; Taxon; Computational biology; Gene; Evolutionary biology; Genetics; Ecology","score_opus":0.20391782201242342,"score_gpt":0.37389083172445037,"score_spread":0.16997300971202695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995701890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15573668,0.0007383145,0.84069186,0.00004724264,0.00041922796,0.0005472306,0.0016634094,0.00005273333,0.000103302846],"genre_scores_gemma":[0.045403063,0.00011001808,0.94706476,0.00023918347,0.00055898225,0.000050442766,0.006465323,0.00004020501,0.00006803665],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979181,0.00013662374,0.0007138107,0.00046182706,0.00026777422,0.0005018611],"domain_scores_gemma":[0.9979635,0.000100528385,0.00041411218,0.00095066446,0.00036708618,0.0002041168],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010916603,0.00032560588,0.00036043496,0.000053123396,0.00027464307,0.00021262164,0.00062859105,0.00029128385,0.0000026846255],"category_scores_gemma":[0.0007390196,0.000304482,0.000116053634,0.00018824737,0.000036648864,0.000020766562,0.0007394708,0.000107194086,0.000009999484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001966523,0.00009640464,0.0017368122,0.0001739405,0.0006538666,0.0000021836552,0.0037060503,0.084269844,0.85437936,0.000060143706,0.040579703,0.014145052],"study_design_scores_gemma":[0.0010029016,0.00018340968,0.00041832522,0.000011468793,0.00008858836,0.000007641303,0.0021598306,0.93263507,0.046099324,0.00007606995,0.016931506,0.0003858465],"about_ca_topic_score_codex":0.00034184684,"about_ca_topic_score_gemma":0.00032314513,"teacher_disagreement_score":0.84836525,"about_ca_system_score_codex":0.00008002653,"about_ca_system_score_gemma":0.00040772697,"threshold_uncertainty_score":0.99994075},"labels":[],"label_agreement":null},{"id":"W1995803230","doi":"10.1186/1471-2105-12-s11-a4","title":"Variant detection and the Autism sequencing project","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Autism Spectrum Disorder Research","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Autism; Computational biology; DNA microarray; DNA sequencing; Biology; Genetics; Computer science; Medicine; Gene; Gene expression","score_opus":0.09087766062733735,"score_gpt":0.2811225290659108,"score_spread":0.19024486843857344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995803230","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.184706,0.00015554122,0.5803201,0.0011742322,0.0006851454,0.004267464,0.000024430177,0.00072816404,0.2279389],"genre_scores_gemma":[0.98622334,0.00007305508,0.013193829,0.00023588829,0.000012181825,0.000043935906,3.1127928e-7,0.000012771341,0.00020470437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892443,0.00011513361,0.00025979523,0.00012872076,0.00027389757,0.00029801382],"domain_scores_gemma":[0.9993688,0.00018325163,0.00010681501,0.000292049,0.0000051279944,0.000043987126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004996235,0.0001091391,0.00011264464,0.00010780985,0.0003006488,0.00009314765,0.0002479316,0.000055770546,0.000031715237],"category_scores_gemma":[0.00037412197,0.00006770964,0.00003749633,0.00031834294,0.00033151917,0.00038148335,0.00016951405,0.00021584095,0.00010447749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039721956,0.00006484738,0.00031467457,0.00039260247,0.000016409815,0.000025740745,0.07898133,0.000024742412,0.0034720788,0.8941142,0.00008488618,0.022111261],"study_design_scores_gemma":[0.0018357597,0.00014769721,0.0022405512,0.000027042088,0.000020228345,0.00052827713,0.0011890527,0.9170623,0.02626686,0.049865287,0.000550362,0.0002666069],"about_ca_topic_score_codex":0.00023051577,"about_ca_topic_score_gemma":0.000082991,"teacher_disagreement_score":0.91703755,"about_ca_system_score_codex":0.00004783405,"about_ca_system_score_gemma":0.00012887424,"threshold_uncertainty_score":0.2761119},"labels":[],"label_agreement":null},{"id":"W1996392240","doi":"10.1186/1471-2105-12-s11-a13","title":"Spectral classification of short numerical exon and intron sequences","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Queen's University; University of Ottawa","funders":"","keywords":"Intron; Exon; Computational biology; Genome; Annotation; Representation (politics); Human genome; Genome project; Genetics; Computer science; Biology; Gene","score_opus":0.03505932177159128,"score_gpt":0.252325421605623,"score_spread":0.21726609983403172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996392240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430389,0.00014695522,0.049051225,0.000020453625,0.000039055136,0.000083781684,0.000008398107,0.000009328118,0.0076019266],"genre_scores_gemma":[0.95809644,0.000111186666,0.04161822,0.00003571268,0.00003663705,0.0000036108963,0.000046519952,0.0000038122073,0.00004783804],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99947274,0.000012472011,0.00023587834,0.000087020104,0.00008361653,0.00010828466],"domain_scores_gemma":[0.99967015,0.000005036624,0.00007878679,0.00016157843,0.000037848728,0.00004662759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009534378,0.00007808015,0.00010369416,0.000034485663,0.000026028552,0.000008413621,0.000091331065,0.0000772,0.000017927647],"category_scores_gemma":[0.000033602682,0.00006274654,0.000049186398,0.00007337572,0.000117691015,0.000012975914,0.000035715326,0.000037836795,0.00000645377],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034215584,0.00033005545,0.34018028,0.00050488714,0.0002647549,0.0000028000197,0.0026023712,0.00012179566,0.59387743,0.0070477524,0.0010262718,0.053699426],"study_design_scores_gemma":[0.00063211,0.0016700326,0.2705264,0.000053603708,0.00022531273,0.00007840391,0.0053315996,0.13435614,0.5816097,0.001443253,0.0032334893,0.00083989784],"about_ca_topic_score_codex":0.000028476867,"about_ca_topic_score_gemma":0.000018258846,"teacher_disagreement_score":0.13423435,"about_ca_system_score_codex":0.0000051056477,"about_ca_system_score_gemma":0.00003232066,"threshold_uncertainty_score":0.25587296},"labels":[],"label_agreement":null},{"id":"W1996644160","doi":"10.1186/1471-2105-12-s5-s5","title":"Unsupervised fuzzy pattern discovery in gene expression data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Gene; DNA microarray; Gene cluster; Gene expression; Cluster analysis; Computational biology; Set (abstract data type); Fuzzy logic; Biology; Class (philosophy); Expression (computer science); Discretization; Gene regulatory network; Data mining; Genetics; Computer science; Mathematics; Artificial intelligence","score_opus":0.07563724883632382,"score_gpt":0.27097313619929536,"score_spread":0.19533588736297153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996644160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5268331,0.00060168613,0.4553088,0.000052018793,0.0005680949,0.00055992295,0.00020850076,0.000047064947,0.01582079],"genre_scores_gemma":[0.9476696,0.0002835361,0.049870893,0.00035485814,0.000121662306,0.000028996981,0.00125511,0.000021517251,0.00039380224],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990799,0.00003398749,0.00033392737,0.0002258872,0.0001352013,0.0001910951],"domain_scores_gemma":[0.9987102,0.000004818229,0.000110372326,0.0010839846,0.000027208518,0.00006341659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016952994,0.00013146999,0.000104993895,0.00006734973,0.000038748913,0.000032110052,0.00053125,0.00013104144,0.000028153303],"category_scores_gemma":[0.000037644328,0.00011067627,0.000034829256,0.00009848906,0.000035178437,0.000041090803,0.0003720467,0.00007050939,0.000031630327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037347668,0.0005008305,0.13766561,0.00036365978,0.000036563826,0.0000040817686,0.002352464,0.00013587017,0.79479647,0.00011212252,0.02610532,0.037553553],"study_design_scores_gemma":[0.002485723,0.000206588,0.06372528,0.00014634964,0.000024006535,0.00001605086,0.0017815891,0.020041855,0.8936536,0.00019426929,0.016962402,0.0007623173],"about_ca_topic_score_codex":0.000016401465,"about_ca_topic_score_gemma":0.000040307776,"teacher_disagreement_score":0.4208365,"about_ca_system_score_codex":0.000010664088,"about_ca_system_score_gemma":0.00008522699,"threshold_uncertainty_score":0.45132473},"labels":[],"label_agreement":null},{"id":"W1996936565","doi":"10.1186/1471-2105-12-s5-s6","title":"A robust approach to optimizing multi-source information for enhancing genomics retrieval performance","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Context (archaeology); Learning to rank; Reciprocal; Data mining; Mean reciprocal rank; Rank (graph theory); Baseline (sea)","score_opus":0.1088627182265075,"score_gpt":0.24921181395124425,"score_spread":0.14034909572473675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996936565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008854307,0.0000057867937,0.98476815,0.000015846563,0.00029439357,0.0012754046,0.000017185972,0.00029316344,0.004475733],"genre_scores_gemma":[0.010621352,0.000009123302,0.9883834,0.00059899146,0.000040372608,0.00006401067,0.00004969028,0.00001398695,0.00021908681],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760383,0.000021585567,0.0010559084,0.00017541094,0.00048115116,0.00066209707],"domain_scores_gemma":[0.99820316,0.00006368445,0.0003613014,0.0006268515,0.00045181828,0.00029316204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011036289,0.0002761179,0.0002711746,0.00043996752,0.00042175362,0.00042519736,0.0011763078,0.00016157624,0.0000065681065],"category_scores_gemma":[0.0002011054,0.00025108445,0.00013652726,0.00073703344,0.000043508677,0.005504775,0.00041021325,0.00021903525,0.000300956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011922069,0.0009231634,0.0016081585,0.005665517,0.00014898852,0.0000010646363,0.42866588,0.29014075,0.00055563595,0.031102294,0.002907531,0.2370888],"study_design_scores_gemma":[0.0008113972,0.00020409231,0.0006652226,0.000032341806,0.0000114844015,0.000020929907,0.0015767552,0.98758596,0.004575132,0.000008517841,0.0041244053,0.00038374765],"about_ca_topic_score_codex":0.00000872919,"about_ca_topic_score_gemma":0.000002784652,"teacher_disagreement_score":0.6974452,"about_ca_system_score_codex":0.00018923823,"about_ca_system_score_gemma":0.00027003605,"threshold_uncertainty_score":0.99999416},"labels":[],"label_agreement":null},{"id":"W1997463836","doi":"10.1186/1471-2105-10-s8-i1","title":"Between proteins and phenotypes: annotation and interpretation of mutations","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Annotation; Phenotype; Computational biology; Population; Relevance (law); Biology; Mutation; Ontology; Genetics; Computer science; Bioinformatics; Gene; Medicine","score_opus":0.014369674518912403,"score_gpt":0.2682694366990187,"score_spread":0.2538997621801063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997463836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6719682,0.00027744749,0.3268765,0.00010885244,0.000018164475,0.00015066567,0.000018009301,0.00001369217,0.00056847563],"genre_scores_gemma":[0.8747398,0.000030380821,0.12504494,0.000058827118,0.000022543421,0.000002699737,0.00007575537,0.0000021221988,0.000022887618],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9996177,0.000012452269,0.00018370687,0.0000617224,0.000056637156,0.00006777687],"domain_scores_gemma":[0.99974936,0.000019398232,0.000085761385,0.00007537981,0.0000373095,0.000032768075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089763475,0.00005767217,0.00008225184,0.000034244502,0.000031881813,0.000012010196,0.000037044334,0.00008155017,7.959279e-7],"category_scores_gemma":[0.00015325782,0.000048944297,0.0000147804185,0.000045591813,0.000098614204,0.0000062496174,0.000018564451,0.000031209984,8.405775e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006546735,0.000036540936,0.013196579,0.00024162821,0.000035326324,1.5546283e-7,0.0030197476,0.000042855947,0.010590361,0.0004866163,0.00023083478,0.9720539],"study_design_scores_gemma":[0.003909391,0.005937173,0.6955078,0.00038406326,0.00024313475,0.00004335421,0.008070664,0.19351014,0.07628283,0.0085766865,0.006496288,0.0010384597],"about_ca_topic_score_codex":0.0000020540836,"about_ca_topic_score_gemma":0.0000039342704,"teacher_disagreement_score":0.97101545,"about_ca_system_score_codex":0.0000021660364,"about_ca_system_score_gemma":0.000022163345,"threshold_uncertainty_score":0.19958904},"labels":[],"label_agreement":null},{"id":"W1998271648","doi":"10.1186/1471-2105-15-s12-s2","title":"Discovering co-occurring patterns and their biological significance in protein families","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Amino acid; Biology; Conserved sequence; Computational biology; Peptide sequence; Phylogenetic tree; Sequence alignment; Closeness; Genetics; Protein sequencing; Multiple sequence alignment; Taxonomic rank; Evolutionary biology; Bioinformatics; Gene; Ecology","score_opus":0.01057686144615,"score_gpt":0.2285720905072953,"score_spread":0.2179952290611453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998271648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8535847,0.00005776775,0.14533706,0.000006903814,0.00002714531,0.0002350534,0.000034826393,0.000012732843,0.00070382596],"genre_scores_gemma":[0.9883334,0.00005219475,0.011305615,0.00013746727,0.000060385104,0.00002849027,0.00006014715,0.000008294263,0.000013995866],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993228,0.000029694447,0.0002370072,0.00014608762,0.000054260876,0.00021016029],"domain_scores_gemma":[0.99963385,0.000016086646,0.00007677756,0.0002122059,0.000013223035,0.000047850404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016324664,0.00015155296,0.00014467548,0.000038130103,0.000046202174,0.000036692414,0.00013430888,0.00012928242,0.0000018030399],"category_scores_gemma":[0.00008384514,0.00010981056,0.00003509457,0.00004403609,0.00007536766,0.000010488181,0.00011353068,0.00009099695,0.0000020132013],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022108563,0.00008586791,0.71575123,0.0011031269,0.000052156058,0.0000019745364,0.0019375652,0.0021486867,0.200688,0.0028700428,0.000060874056,0.07507941],"study_design_scores_gemma":[0.0039835167,0.001597929,0.22156513,0.00050819444,0.000016517823,0.00007308778,0.006426403,0.30121708,0.4327,0.002927822,0.026582966,0.0024013494],"about_ca_topic_score_codex":0.000022019829,"about_ca_topic_score_gemma":0.000116911506,"teacher_disagreement_score":0.49418607,"about_ca_system_score_codex":0.0000085422025,"about_ca_system_score_gemma":0.000022494673,"threshold_uncertainty_score":0.44779447},"labels":[],"label_agreement":null},{"id":"W1998617521","doi":"10.1186/1471-2105-13-204","title":"Enabling dynamic network analysis through visualization in TVNViewer","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Science Foundation; National Institutes of Health; Advanced Research Projects Agency; U.S. Public Health Service; Defense Advanced Research Projects Agency","keywords":"Visualization; Computer science; DNA microarray; Data science; Computational biology; Biology; Data mining; Genetics; Gene expression","score_opus":0.013569325778311854,"score_gpt":0.2731328761428668,"score_spread":0.2595635503645549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998617521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047789253,0.0023681668,0.9444036,0.000017457605,0.0004064356,0.00031712383,0.000014621676,0.000026250675,0.004657128],"genre_scores_gemma":[0.84996724,0.0009933164,0.14582367,0.0010449643,0.00050839613,0.000030325979,0.0012061053,0.000036768175,0.00038922956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842304,0.00004290539,0.0006672165,0.00012334254,0.00016042027,0.00058307726],"domain_scores_gemma":[0.9991739,0.000020224006,0.00024296969,0.00041345897,0.000052903535,0.00009654481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006365712,0.0002077984,0.00026379726,0.0001145606,0.00009144762,0.000050509156,0.00019530764,0.00024530286,0.000034690576],"category_scores_gemma":[0.000044056487,0.000192659,0.00017015566,0.00076791947,0.00004523501,0.000045208104,0.00014446671,0.000111908754,0.000050384606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028903448,0.00065809634,0.35906383,0.0010087478,0.0019745838,0.0000015861249,0.008973319,0.5589537,0.00086291484,0.016443014,0.018560661,0.033210542],"study_design_scores_gemma":[0.0008886389,0.000094825504,0.016861167,0.000047431153,0.00030779288,0.00001102222,0.0009752652,0.91675246,0.00027697938,0.00042642074,0.06263608,0.000721917],"about_ca_topic_score_codex":0.000009770913,"about_ca_topic_score_gemma":0.00015687269,"teacher_disagreement_score":0.80217797,"about_ca_system_score_codex":0.00003698067,"about_ca_system_score_gemma":0.000048001442,"threshold_uncertainty_score":0.78564066},"labels":[],"label_agreement":null},{"id":"W1999079801","doi":"10.1186/1471-2105-8-206","title":"Selecting dissimilar genes for multi-class classification, an application in cancer subtyping","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Subtyping; Classifier (UML); Support vector machine; DNA microarray; Gene expression profiling; Microarray analysis techniques; Microarray; Cluster analysis; Gene chip analysis; Computational biology; Computer science; Artificial intelligence; Pattern recognition (psychology); Gene; Data mining; Biology; Gene expression; Genetics","score_opus":0.0687708537069852,"score_gpt":0.35891243433735676,"score_spread":0.29014158063037154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999079801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123137824,0.00027786806,0.87546813,0.000071107876,0.00013515796,0.0005745559,0.000015982121,0.00002975545,0.00028958608],"genre_scores_gemma":[0.84454584,0.0002431669,0.1532892,0.00037084467,0.00032670208,0.00039170604,0.00053656235,0.000038055052,0.00025794],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890655,0.0000202678,0.00045570207,0.0002342668,0.000110387205,0.00027283392],"domain_scores_gemma":[0.999166,0.000016539694,0.00023438496,0.00033747038,0.0001557507,0.00008983694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005143935,0.00013847186,0.000109858134,0.00011124876,0.00012485524,0.00003395657,0.00019109283,0.00017974753,0.000002773839],"category_scores_gemma":[0.00006983096,0.00013594895,0.000049354036,0.00021997404,0.00003242011,0.00002168381,0.00002866757,0.00006824772,0.0000030672547],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023231773,0.00025322562,0.097045675,0.00031105615,0.00002205184,9.1082335e-8,0.00077195204,0.0027215765,0.7444617,0.0008896931,0.0010282828,0.15226234],"study_design_scores_gemma":[0.0012522009,0.00009571071,0.06619499,0.000034821358,0.000017028682,0.0000028180618,0.0018544582,0.72197616,0.15308954,0.000045179713,0.05505181,0.0003852921],"about_ca_topic_score_codex":0.000018034987,"about_ca_topic_score_gemma":0.000950713,"teacher_disagreement_score":0.72217894,"about_ca_system_score_codex":0.00006197827,"about_ca_system_score_gemma":0.00013444602,"threshold_uncertainty_score":0.55438375},"labels":[],"label_agreement":null},{"id":"W2000165838","doi":"10.1186/1471-2105-9-373","title":"Increasing the efficiency of bacterial transcription simulations: When to exclude the genome without loss of accuracy","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Family Physicians of Canada; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computational biology; DNA microarray; Genome; Computer science; Genetics; Biology; Bioinformatics; Gene; Gene expression","score_opus":0.022106200086113265,"score_gpt":0.24717745227963084,"score_spread":0.22507125219351756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000165838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979013,0.00010702896,0.020016205,0.0001464326,0.00013787864,0.0003965379,0.00007591425,0.000007511298,0.000099437355],"genre_scores_gemma":[0.9835827,0.000119602555,0.015969127,0.000106918866,0.00011292522,0.0000059963736,0.000073306284,0.000009605134,0.000019836696],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905384,0.000055245622,0.00048103757,0.00010135204,0.000138079,0.0001704415],"domain_scores_gemma":[0.9991042,0.000043039636,0.00023508754,0.00046408075,0.000120656005,0.000032928074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025414958,0.00012308524,0.00015807177,0.000046821802,0.00013009035,0.000013947789,0.00039362436,0.00015848975,0.00001731783],"category_scores_gemma":[0.00021507252,0.000074165364,0.000081194776,0.00013207865,0.00026745914,0.000007395857,0.00011788726,0.00006862255,0.000003646589],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001673767,0.00004006693,0.0010784435,0.00004049133,0.000022175129,8.177037e-8,0.0011693778,0.0007477316,0.9961539,0.000061281986,0.0000353842,0.0004837262],"study_design_scores_gemma":[0.0016481691,0.0011153336,0.026332468,0.00005568314,0.000104165396,0.00015145302,0.0008886049,0.010189128,0.92639,0.00016649027,0.032482464,0.00047602525],"about_ca_topic_score_codex":0.000025287301,"about_ca_topic_score_gemma":0.000035704856,"teacher_disagreement_score":0.06976385,"about_ca_system_score_codex":0.0000074381805,"about_ca_system_score_gemma":0.00010197542,"threshold_uncertainty_score":0.30243757},"labels":[],"label_agreement":null},{"id":"W2001869885","doi":"10.1186/1471-2105-13-3","title":"Self-organizing ontology of biochemically relevant small molecules","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; European Bioinformatics Institute","keywords":"Computer science; Ontology; Annotation; Class (philosophy); Automation; Data science; Information retrieval; Artificial intelligence","score_opus":0.028460466526800444,"score_gpt":0.2657235007835735,"score_spread":0.23726303425677303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001869885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026787492,0.00018911037,0.9693145,0.00010077621,0.00026982772,0.00011702923,0.0000030877288,0.0001312733,0.0030869122],"genre_scores_gemma":[0.037831314,0.000010120646,0.96191645,0.00017718947,0.00003983089,0.0000031007116,0.0000048049633,0.0000073592,0.000009860191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987828,0.00007230221,0.00049855694,0.00010198404,0.00023049062,0.00031383923],"domain_scores_gemma":[0.9987071,0.00040999803,0.00024470975,0.0004118579,0.000116295836,0.000110050176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053865556,0.00013094691,0.00019518768,0.00011833485,0.00004128847,0.0000380866,0.00065840344,0.00007960939,0.0000046433684],"category_scores_gemma":[0.00026764025,0.000118966345,0.00007245186,0.0003341418,0.0000440662,0.00051030633,0.00040564203,0.00009947316,0.000057894336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030407973,0.00081387063,0.012365846,0.0018910011,0.00018418409,0.0000033740232,0.024375327,0.01029899,0.004624684,0.8938638,0.0010892272,0.050459318],"study_design_scores_gemma":[0.00022934286,0.00004079319,0.002984069,0.000024863913,0.000013876326,0.00005263055,0.0001211346,0.9791026,0.013538203,0.0025044314,0.001186327,0.00020169449],"about_ca_topic_score_codex":0.000003876733,"about_ca_topic_score_gemma":0.0000019460954,"teacher_disagreement_score":0.96880364,"about_ca_system_score_codex":0.000046084184,"about_ca_system_score_gemma":0.00015617193,"threshold_uncertainty_score":0.4851307},"labels":[],"label_agreement":null},{"id":"W2002496559","doi":"10.1186/1471-2105-13-s3-s6","title":"Detection of gene expression changes at chromosomal rearrangement breakpoints in evolution","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breakpoint; Biology; Genetics; Gene; Genome; Gene duplication; Chromosomal rearrangement; Chromosome; Computational biology; Karyotype","score_opus":0.013626995074313983,"score_gpt":0.2269050628505561,"score_spread":0.21327806777624211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002496559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96531904,0.00075752696,0.032525614,0.000010571546,0.00023555214,0.0003494277,0.000020551499,0.000012932262,0.00076880783],"genre_scores_gemma":[0.97087044,0.00009771512,0.02850114,0.00001830845,0.00018152894,0.0000349119,0.00011493106,0.000015117854,0.00016593515],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908686,0.000034792592,0.00029163176,0.000103988976,0.00019331506,0.00028944042],"domain_scores_gemma":[0.9994275,0.0000057460484,0.00017303329,0.00027809574,0.000045821642,0.0000698014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002830833,0.00013083224,0.0001287952,0.00010621284,0.00004256485,0.0000058415953,0.000105324725,0.00014074496,0.000023535538],"category_scores_gemma":[0.000032320146,0.00012309103,0.00005024277,0.00011407925,0.00003686923,0.000015407628,0.00013028386,0.000046492594,0.000033558605],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005341738,0.00006832381,0.018894212,0.00012452478,0.000010666242,1.0063848e-7,0.00032443213,0.00006458963,0.9783319,0.0000031592851,0.00008526484,0.0020393801],"study_design_scores_gemma":[0.00073942763,0.00018039998,0.04704652,0.0000337554,0.000013350129,0.000014576566,0.00029239312,0.0021898218,0.9471815,0.0000046660834,0.002134573,0.00016897742],"about_ca_topic_score_codex":0.000013213428,"about_ca_topic_score_gemma":0.00012325497,"teacher_disagreement_score":0.031150391,"about_ca_system_score_codex":0.0000951315,"about_ca_system_score_gemma":0.00001970125,"threshold_uncertainty_score":0.5019506},"labels":[],"label_agreement":null},{"id":"W2003601914","doi":"10.1186/1471-2105-13-s11-s7","title":"Biological event composition","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Coreference; Biomedical text mining; Event (particle physics); Natural language processing; Task (project management); Artificial intelligence; Parsing; Information extraction; Resolution (logic); Information retrieval; Text mining","score_opus":0.037038019145623165,"score_gpt":0.29050173312038574,"score_spread":0.2534637139747626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003601914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6231728,0.0012106363,0.36966676,0.00011748182,0.00057763053,0.00018772444,0.00002389979,0.0000858409,0.004957186],"genre_scores_gemma":[0.86361146,0.00007549082,0.13518308,0.00046654965,0.00031997563,0.000011309065,0.00019775114,0.0000064695437,0.00012791502],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99933815,0.000028341301,0.00020597465,0.00006873654,0.00009250716,0.00026630043],"domain_scores_gemma":[0.99961185,0.000017064165,0.00006460755,0.000174841,0.000022066017,0.00010959187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002189455,0.00009805423,0.000093569215,0.000021416505,0.000060734084,0.000011655442,0.00011715083,0.00018455712,0.00002998812],"category_scores_gemma":[0.00007789492,0.00007156815,0.0000675462,0.0000445704,0.000105916086,0.0000041480353,0.000091575304,0.00006129049,0.00014410856],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005301455,0.0015668374,0.4601416,0.00051016005,0.00029244774,0.000002597449,0.0022313572,0.0002663135,0.07811535,0.0053051184,0.120984375,0.3300537],"study_design_scores_gemma":[0.0021256274,0.0014232773,0.16874267,0.0000737537,0.00005814025,0.00024333558,0.0019911884,0.013061865,0.04704756,0.00021175364,0.76380825,0.001212556],"about_ca_topic_score_codex":0.0000010621545,"about_ca_topic_score_gemma":6.015897e-7,"teacher_disagreement_score":0.6428239,"about_ca_system_score_codex":0.0000085685815,"about_ca_system_score_gemma":0.000020288806,"threshold_uncertainty_score":0.29184645},"labels":[],"label_agreement":null},{"id":"W2004206064","doi":"10.1186/1471-2105-10-s1-s17","title":"Short read DNA fragment anchoring algorithm","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Fragment (logic); DNA microarray; Computer science; Computational biology; Anchoring; DNA; Algorithm; Genetics; Biology; Gene; Engineering; Gene expression","score_opus":0.015695801694614292,"score_gpt":0.24388270002834928,"score_spread":0.22818689833373498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004206064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74540406,0.00258678,0.21722922,0.00018953945,0.0007730813,0.0006789211,0.00008670914,0.00003831178,0.033013362],"genre_scores_gemma":[0.60190344,0.0009663176,0.39464644,0.0008676791,0.0007493928,0.000018708306,0.00011479009,0.000022623806,0.0007106014],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991719,0.000009198423,0.0002861174,0.00014366195,0.0001233814,0.0002657282],"domain_scores_gemma":[0.9994758,0.0000056129747,0.00005492117,0.00033269683,0.000052649902,0.00007834256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012420611,0.00016197519,0.00013882748,0.000032402855,0.00009871719,0.000031466065,0.00016722566,0.00009918375,0.000005619327],"category_scores_gemma":[0.000019253008,0.00014755395,0.00008402226,0.000059596947,0.000032202577,0.0000015932354,0.000083370935,0.000055155033,0.000019855035],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052049218,0.00018258067,0.0060297763,0.00008594982,0.00016821668,0.0000033330257,0.00075078907,0.0010208971,0.0726883,0.00045363445,0.010559931,0.9080045],"study_design_scores_gemma":[0.0027090237,0.0029805272,0.18961579,0.000120717086,0.00020144314,0.00011951081,0.002443478,0.074224144,0.19808833,0.0016070665,0.5251028,0.0027871588],"about_ca_topic_score_codex":0.0000015676435,"about_ca_topic_score_gemma":0.00000380525,"teacher_disagreement_score":0.9052174,"about_ca_system_score_codex":0.000013780065,"about_ca_system_score_gemma":0.000034038578,"threshold_uncertainty_score":0.6017076},"labels":[],"label_agreement":null},{"id":"W2004594378","doi":"10.1186/1471-2105-15-s9-s14","title":"A better sequence-read simulator program for metagenomics","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"","keywords":"Metagenomics; Computer science; Shotgun sequencing; Data mining; Emulation; Sequence (biology); Flexibility (engineering); Data quality; DNA sequencing; Biology; Metric (unit); Statistics; Engineering","score_opus":0.028154508968319534,"score_gpt":0.2794824156312894,"score_spread":0.25132790666296984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004594378","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77935976,0.0003380257,0.2147044,0.00014249091,0.00042167635,0.0014970344,0.00016245805,0.000033158576,0.003340984],"genre_scores_gemma":[0.42034534,0.00006440035,0.57717806,0.0010963631,0.00047169486,0.00020262286,0.00018949232,0.000038857932,0.00041315577],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910176,0.000016087834,0.00032432744,0.00017035575,0.00008254059,0.00030494848],"domain_scores_gemma":[0.999289,0.000035254696,0.00012682975,0.00037214084,0.00009740077,0.00007937398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022404798,0.00018513105,0.00018821699,0.00003145707,0.00011411577,0.000048039106,0.00020850351,0.00012539481,0.0000042977013],"category_scores_gemma":[0.000108555716,0.00016094945,0.00015253629,0.000045845143,0.00007604757,0.0000016468318,0.00010800633,0.00004258619,0.000018628347],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005615307,0.0006440381,0.02269891,0.0019603092,0.0014125287,8.4502904e-7,0.0018658757,0.022170462,0.19910124,0.007907515,0.021276094,0.72040063],"study_design_scores_gemma":[0.0011656733,0.0008365558,0.0011898022,0.000009809076,0.000085192376,0.000007174312,0.00012960327,0.2442083,0.011036898,0.00062158727,0.740237,0.00047240776],"about_ca_topic_score_codex":0.0000024105234,"about_ca_topic_score_gemma":0.000015589352,"teacher_disagreement_score":0.71992826,"about_ca_system_score_codex":0.0000103796865,"about_ca_system_score_gemma":0.000053076645,"threshold_uncertainty_score":0.65633285},"labels":[],"label_agreement":null},{"id":"W2005255873","doi":"10.1186/1471-2105-13-249","title":"Quantitative biomedical annotation using medical subject heading over-representation profiles (MeSHOPs)","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Child and Family Research Institute; University of British Columbia","funders":"National Institute of General Medical Sciences; Michael Smith Health Research BC; Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Computer science; Controlled vocabulary; Annotation; Information retrieval; Vocabulary; Ontology; Representation (politics); Subject (documents); Set (abstract data type); Unified Medical Language System; Open Biomedical Ontologies; Visualization; Data science; Natural language processing; Data mining; Artificial intelligence; World Wide Web; Ontology alignment","score_opus":0.06687942214877576,"score_gpt":0.36950989404859996,"score_spread":0.30263047189982417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005255873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.612516,0.0006222161,0.38514498,0.000113767695,0.0007025759,0.00021068167,0.00002862448,0.000058644804,0.0006025617],"genre_scores_gemma":[0.6326135,0.00009054197,0.36558634,0.0003322502,0.0006669262,0.000024609239,0.0005253236,0.000028493792,0.00013203372],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982975,0.00010094353,0.00047629734,0.00015930814,0.00053096627,0.00043498966],"domain_scores_gemma":[0.99913144,0.00011873182,0.0001873402,0.00022286024,0.00007080484,0.0002688412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068830664,0.00017936854,0.00019820276,0.00011004771,0.00013455283,0.00003508464,0.00019165459,0.00037121554,0.00006111589],"category_scores_gemma":[0.0015093114,0.00014914709,0.00009341598,0.000249175,0.0003098016,0.00003063264,0.00013073046,0.00014829704,0.000034951263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016205249,0.0019892803,0.37804815,0.002121148,0.00091146585,0.000024711484,0.015395108,0.00055293017,0.18743137,0.008582179,0.056022137,0.347301],"study_design_scores_gemma":[0.005074875,0.0017667882,0.032109816,0.00042347627,0.00019161201,0.0005312342,0.015708594,0.83446765,0.049891997,0.0002616602,0.057886228,0.00168608],"about_ca_topic_score_codex":0.000024784653,"about_ca_topic_score_gemma":0.000010693963,"teacher_disagreement_score":0.8339147,"about_ca_system_score_codex":0.000031550207,"about_ca_system_score_gemma":0.00021140646,"threshold_uncertainty_score":0.6082042},"labels":[],"label_agreement":null},{"id":"W2005713653","doi":"10.1186/1471-2105-14-s15-s8","title":"Practical aliquoting of flowering plant genomes","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Polyploid; Gene; Computational biology; Genetics","score_opus":0.03713003583218182,"score_gpt":0.23705449844082743,"score_spread":0.1999244626086456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005713653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930955,0.000028824314,0.0011252034,0.0006349345,0.0001083897,0.0002437147,0.000048356807,0.000049516526,0.0046655685],"genre_scores_gemma":[0.862678,0.000024886525,0.1368451,0.00012986356,0.00013837969,0.000013784162,0.00006613768,6.5189073e-7,0.00010322391],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994035,0.000010826952,0.00026952065,0.000052488114,0.00012108416,0.0001426266],"domain_scores_gemma":[0.99958974,0.00016487595,0.00010499005,0.00003798963,0.000046066172,0.000056349876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000786724,0.000065037384,0.0000949017,0.0000066202438,0.000071811904,0.000037126567,0.00008769987,0.000045881472,0.0006248911],"category_scores_gemma":[0.000046016372,0.00002357304,0.000046578094,0.00011008828,0.000022715878,0.00015768033,0.000058817346,0.000044911594,0.0001491275],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006400027,0.0010707973,0.18987365,0.00081828044,0.00028561725,0.000005800383,0.007511315,0.0014187971,0.37743664,0.033101227,0.012258947,0.37615496],"study_design_scores_gemma":[0.0004529563,0.000546198,0.41638714,0.000107681575,0.000063548556,0.00010771946,0.005921247,0.5378278,0.013953303,0.0020916867,0.021855379,0.00068533793],"about_ca_topic_score_codex":0.000060119055,"about_ca_topic_score_gemma":0.00007836418,"teacher_disagreement_score":0.536409,"about_ca_system_score_codex":0.0000067339142,"about_ca_system_score_gemma":0.000010893409,"threshold_uncertainty_score":0.6842119},"labels":[],"label_agreement":null},{"id":"W2006899413","doi":"10.1186/1471-2105-8-185","title":"160-fold acceleration of the Smith-Waterman algorithm using a field programmable gate array (FPGA)","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Field-programmable gate array; Smith–Waterman algorithm; Computer science; Computation; Gate array; Algorithm; Hardware acceleration; Parallel computing; Speedup; Software; Computer hardware; Sequence alignment; Biology","score_opus":0.02210297259056926,"score_gpt":0.2562518568089582,"score_spread":0.23414888421838892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006899413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72699314,0.00033215326,0.26948306,0.00003430903,0.00032043218,0.00041288964,0.000018964283,0.0000056736576,0.0023993864],"genre_scores_gemma":[0.75365144,0.00009759241,0.2453038,0.00026681597,0.00021490002,0.000008290581,0.000019621171,0.000018688925,0.00041887496],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999174,0.000013346072,0.00035638377,0.00009840311,0.000120867895,0.00023700451],"domain_scores_gemma":[0.99935985,0.000013529518,0.00018787557,0.00030954977,0.000089542125,0.00003967931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002521058,0.00012647251,0.00012167276,0.000028065568,0.00012247897,0.000027191194,0.00018920086,0.0001088926,0.000004537074],"category_scores_gemma":[0.000029037703,0.00009091444,0.00009686761,0.00009010738,0.0000553795,0.0000027475685,0.000117553216,0.000059080587,0.0000032341143],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001626531,0.00021762883,0.03138375,0.00063349114,0.0003430642,0.0000013140417,0.0028188885,0.0049727918,0.854898,0.00013467936,0.0019261244,0.10250764],"study_design_scores_gemma":[0.0005309012,0.0002356571,0.006300244,0.000036761216,0.000049746264,0.000018681034,0.000467777,0.025163403,0.9500174,0.00008080036,0.016839793,0.0002588394],"about_ca_topic_score_codex":0.000017256372,"about_ca_topic_score_gemma":0.000034659595,"teacher_disagreement_score":0.10224881,"about_ca_system_score_codex":0.000010523841,"about_ca_system_score_gemma":0.000067821726,"threshold_uncertainty_score":0.37073833},"labels":[],"label_agreement":null},{"id":"W2007139266","doi":"10.1186/1471-2105-10-260","title":"MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Institute for Materials Science; Natural Sciences and Engineering Research Council of Canada; Korea Research Council of Fundamental Science and Technology","keywords":"Cluster analysis; Computer science; Data mining; Rand index; Pattern recognition (psychology); Single-linkage clustering; Microarray analysis techniques; Clustering high-dimensional data; DNA microarray; Artificial intelligence; Ensemble learning; Gene chip analysis; CURE data clustering algorithm; Correlation clustering; Biology; Gene; Genetics; Gene expression","score_opus":0.05225903524028005,"score_gpt":0.30353862350213234,"score_spread":0.2512795882618523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007139266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18106547,0.00015454875,0.81725174,0.000041614865,0.0001239625,0.0001705888,0.000009312028,0.000016506645,0.0011662542],"genre_scores_gemma":[0.77862996,0.00007216898,0.22081019,0.00012461167,0.000055809447,0.0000033562337,0.000073283954,0.000009020272,0.00022161056],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992028,0.00002452773,0.00037558223,0.00013335819,0.00010731442,0.0001564405],"domain_scores_gemma":[0.9992117,0.0000051189354,0.00027056853,0.00035383628,0.000105932835,0.000052815758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013489406,0.000118437194,0.0001156953,0.00006874565,0.000063559855,0.000024276635,0.00016202839,0.00012869887,0.00000592913],"category_scores_gemma":[0.00004424613,0.00010963773,0.000067406676,0.00012018887,0.000037579422,0.000014090025,0.000032047825,0.000050570594,0.0000075487605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003856268,0.00003942024,0.00062191027,0.00004804378,0.000006847564,4.554598e-8,0.00016291079,0.0023485336,0.9920816,0.000033362627,0.00035672684,0.0042620706],"study_design_scores_gemma":[0.00066638005,0.00011690678,0.015880212,0.000049657963,0.000020639798,0.000009444691,0.00060436595,0.5611185,0.41655022,0.000017672923,0.0047399006,0.00022611888],"about_ca_topic_score_codex":0.0000031533814,"about_ca_topic_score_gemma":0.000015734271,"teacher_disagreement_score":0.59756446,"about_ca_system_score_codex":0.000020505719,"about_ca_system_score_gemma":0.00010205818,"threshold_uncertainty_score":0.4470897},"labels":[],"label_agreement":null},{"id":"W2009153021","doi":"10.1186/1471-2105-10-243","title":"Core Hunter: an algorithm for sampling genetic resources based on multiple genetic measures","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; International Fund for Agricultural Development; European Commission","keywords":"Core (optical fiber); Genetic diversity; Representativeness heuristic; Computer science; Genetic algorithm; Sampling (signal processing); Preference; Data mining; Machine learning; Statistics; Mathematics; Population","score_opus":0.06288921997742554,"score_gpt":0.30332164333721656,"score_spread":0.24043242335979104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009153021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2568383,0.00016873123,0.7419695,0.00006497792,0.00012819472,0.000455319,0.00010487542,0.000031940323,0.00023812037],"genre_scores_gemma":[0.25828242,0.00003930442,0.7393518,0.0015769519,0.00029787433,0.000041113293,0.00031570438,0.000022576378,0.000072264775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984807,0.000060685623,0.0005540571,0.0002843609,0.00017525331,0.0004449359],"domain_scores_gemma":[0.99878454,0.00012933639,0.0002445582,0.00054121966,0.00014991006,0.00015042184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034734383,0.0002496156,0.00025979467,0.00009103748,0.00021369422,0.000046188263,0.00029858275,0.00028242634,0.0000062505055],"category_scores_gemma":[0.0005003212,0.00022950173,0.00016542735,0.00008522618,0.000055692755,0.000005550759,0.00003110056,0.00008862529,0.000010956972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030654753,0.00054572424,0.08256928,0.00012630124,0.000112545895,0.0000013703534,0.0006492482,0.21475558,0.0062980163,0.000040258175,0.005497106,0.689098],"study_design_scores_gemma":[0.00109489,0.0014477372,0.12142211,0.000017718452,0.000035690435,0.0000066873154,0.00020084842,0.86212164,0.00057094987,0.0001876891,0.01257191,0.00032210894],"about_ca_topic_score_codex":0.0000084691455,"about_ca_topic_score_gemma":0.000044024986,"teacher_disagreement_score":0.6887759,"about_ca_system_score_codex":0.000026658105,"about_ca_system_score_gemma":0.00009055092,"threshold_uncertainty_score":0.9358809},"labels":[],"label_agreement":null},{"id":"W2009474665","doi":"10.1186/1471-2105-10-145","title":"flowClust: a Bioconductor package for automated gating of flow cytometry data","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Cluster analysis; Data mining; Data transformation; Throughput; Outlier; Workflow; Artificial intelligence; Database; Data warehouse","score_opus":0.05296027501363074,"score_gpt":0.3019501064415164,"score_spread":0.24898983142788564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009474665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36169636,0.00029597938,0.6345071,0.0000614632,0.00040753192,0.0007929248,0.0013307501,0.00015920916,0.00074865867],"genre_scores_gemma":[0.43957275,0.000037304402,0.5573564,0.0003140894,0.0001953971,0.0000064063033,0.00242138,0.000023041537,0.00007322838],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882907,0.000018559213,0.0005326598,0.000200117,0.00014330384,0.0002762786],"domain_scores_gemma":[0.9987603,0.00003257717,0.00019581635,0.0008134816,0.000117124764,0.00008072074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029665692,0.00018443166,0.00023527749,0.00007852489,0.00007739493,0.00003588732,0.00052443106,0.00019612478,0.0000062737454],"category_scores_gemma":[0.00031396007,0.00016685454,0.00010322227,0.00016809745,0.00005562105,0.000021504678,0.00009685587,0.000067264016,0.0000054316383],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029403763,0.00031469457,0.0023185266,0.0009775921,0.00012943568,8.396637e-7,0.0004770163,0.00079328904,0.96179205,0.0001008254,0.013007127,0.019794552],"study_design_scores_gemma":[0.0013926018,0.00048869365,0.0010135238,0.00005601008,0.000049822254,0.0000105172485,0.0001694032,0.7973941,0.19593973,0.000027885128,0.0031476442,0.0003100607],"about_ca_topic_score_codex":0.000005379292,"about_ca_topic_score_gemma":0.000014336953,"teacher_disagreement_score":0.7966008,"about_ca_system_score_codex":0.0000117661675,"about_ca_system_score_gemma":0.00012037683,"threshold_uncertainty_score":0.68041307},"labels":[],"label_agreement":null},{"id":"W2010854125","doi":"10.1186/s12859-014-0383-1","title":"Efficient prediction of human protein-protein interactions at a global scale","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Toronto; Carleton University","funders":"National Institute on Minority Health and Health Disparities; National Institute on Alcohol Abuse and Alcoholism; National Energy Research Scientific Computing Center; Sahlgrenska Akademin; Natural Sciences and Engineering Research Council of Canada; Office of Science; Saskatchewan Health Research Foundation; Linköpings Universitet; National Science Foundation; Canadian Institutes of Health Research; U.S. Department of Energy; National Institutes of Health; Vetenskapsrådet","keywords":"Computer science; Computational biology; Precision and recall; DNA microarray; Scale (ratio); Protein Interaction Networks; Range (aeronautics); Protein–protein interaction; Recall; Systems biology; Data mining; Machine learning; Artificial intelligence; Bioinformatics; Biology; Genetics; Gene; Engineering","score_opus":0.00988622166715788,"score_gpt":0.23572342032781868,"score_spread":0.2258371986606608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010854125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78486663,0.00003266624,0.20054662,0.000020884478,0.00014971184,0.0005005382,0.00012479587,0.000025959276,0.013732171],"genre_scores_gemma":[0.9686768,0.0000017998583,0.030091785,0.00006262752,0.00015913173,0.000038038586,0.0002491142,0.000012405876,0.0007083153],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881464,0.00002917944,0.00060069753,0.00012935756,0.00017823205,0.0002478819],"domain_scores_gemma":[0.9990223,0.0000054313864,0.0003199059,0.00045404528,0.00009830834,0.00010002284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026224277,0.0001700965,0.00017457746,0.00003931606,0.0001576549,0.000025446856,0.00019739516,0.00015147483,0.000025458014],"category_scores_gemma":[0.00003474983,0.00015536475,0.00012896517,0.000109710454,0.000108117085,0.00000625766,0.00021981847,0.00008444679,0.000044224736],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007670199,0.0011338543,0.017158106,0.0031584573,0.00045017689,6.502393e-7,0.0020576655,0.048376083,0.8548159,0.016730767,0.018657288,0.036694016],"study_design_scores_gemma":[0.0024449225,0.001259709,0.0049113366,0.00029036583,0.00007590521,0.00005043914,0.00043424708,0.8750363,0.08871978,0.0010029498,0.025139416,0.0006346282],"about_ca_topic_score_codex":0.0000104399205,"about_ca_topic_score_gemma":0.0000758216,"teacher_disagreement_score":0.8266602,"about_ca_system_score_codex":0.00005447328,"about_ca_system_score_gemma":0.000045465105,"threshold_uncertainty_score":0.63355905},"labels":[],"label_agreement":null},{"id":"W2012121247","doi":"10.1186/1471-2105-9-430","title":"Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; BETA (programming language); Computational biology; Computer science; Bioinformatics; Biology; Genetics; Gene","score_opus":0.014985455898290522,"score_gpt":0.23092082131133007,"score_spread":0.21593536541303954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012121247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9883208,0.00009166251,0.009742514,0.0000033989415,0.00008132226,0.00028635078,0.0008703559,0.00001269008,0.0005908688],"genre_scores_gemma":[0.97649103,0.00006478369,0.022291904,0.00010494191,0.000043351272,0.0000040448263,0.00095955963,0.000012473895,0.000027924701],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908495,0.000028472585,0.0003941226,0.00013755175,0.00020773416,0.0001471446],"domain_scores_gemma":[0.9991704,0.000030388577,0.0002790058,0.00037424391,0.00006835672,0.00007755603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007144765,0.00015688596,0.00018646749,0.000060951792,0.000063075444,0.0000059150107,0.00011941461,0.00019926389,0.000015881502],"category_scores_gemma":[0.00008161578,0.00013320189,0.000062438914,0.000056769502,0.0001281671,0.000019565408,0.000082025304,0.00007121841,3.4509767e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025490837,0.000382616,0.44489065,0.0022697712,0.0003471073,0.000004556865,0.0025320956,0.017130082,0.5193713,0.00025760365,0.0032569477,0.0070082336],"study_design_scores_gemma":[0.0036037348,0.001502011,0.30102485,0.00004685434,0.000063807514,0.000046460274,0.00012900271,0.28620982,0.40538642,0.00015705057,0.001536334,0.00029364508],"about_ca_topic_score_codex":0.000011253553,"about_ca_topic_score_gemma":0.00002454693,"teacher_disagreement_score":0.26907974,"about_ca_system_score_codex":0.000013805103,"about_ca_system_score_gemma":0.00009260446,"threshold_uncertainty_score":0.54318154},"labels":[],"label_agreement":null},{"id":"W2013290977","doi":"10.1186/1471-2105-11-487","title":"Analysis of lifestyle and metabolic predictors of visceral obesity with Bayesian Networks","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Bayesian network; Robustness (evolution); Causal inference; Obesity; Inference; Bayesian probability; Statistical inference; Computer science; Visceral fat; Artificial intelligence; Machine learning; Computational biology; Bioinformatics; Biology; Mathematics; Econometrics; Statistics; Endocrinology; Gene; Genetics","score_opus":0.008201214320869888,"score_gpt":0.2172830842938133,"score_spread":0.2090818699729434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013290977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19989079,0.000033380402,0.7995667,0.000011985496,0.00006604749,0.00005948267,0.000005998125,0.000033917586,0.00033171845],"genre_scores_gemma":[0.7330748,0.000017543307,0.26684603,0.000027830947,0.000014823697,0.0000015765459,0.000003914001,0.0000029238706,0.000010566162],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905413,0.00002227267,0.0004032813,0.000118121716,0.00022703646,0.00017517657],"domain_scores_gemma":[0.9989371,0.00007315174,0.00026740297,0.0004864418,0.00012363911,0.00011227331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031711883,0.00012143892,0.0003426659,0.00021843435,0.00004751237,0.000051706127,0.00040303692,0.00009112413,0.0000049267464],"category_scores_gemma":[0.000026909662,0.000090597045,0.000071933064,0.00084341195,0.0001305341,0.00036591574,0.00012246866,0.00016403639,6.5511733e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002525006,0.00016858777,0.8659037,0.00020066963,0.00077462435,9.578783e-7,0.0039158934,0.05480884,0.000086396045,0.060967375,0.000076862765,0.013070854],"study_design_scores_gemma":[0.00013308562,0.000057439964,0.092644185,0.00001212733,0.00020555292,0.0000034337365,0.000031914617,0.9065366,0.00016635968,0.000091426926,0.000020608824,0.00009728617],"about_ca_topic_score_codex":0.000043932065,"about_ca_topic_score_gemma":0.00015700197,"teacher_disagreement_score":0.8517277,"about_ca_system_score_codex":0.0000025827437,"about_ca_system_score_gemma":0.000083739316,"threshold_uncertainty_score":0.36944404},"labels":[],"label_agreement":null},{"id":"W2013577952","doi":"10.1186/1471-2105-10-78","title":"Performance of random forest when SNPs are in linkage disequilibrium","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Linkage disequilibrium; Single-nucleotide polymorphism; Tag SNP; Haplotype; Genetics; SNP; Linkage (software); SNP genotyping; Genetic association; Biology; Tree (set theory); Computational biology; Mathematics; Allele; Genotype; Gene","score_opus":0.013178378750088178,"score_gpt":0.2384478062535839,"score_spread":0.2252694275034957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013577952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9913264,0.0001839962,0.005428226,0.00013302865,0.000071044706,0.00019155175,0.000017346609,0.000007998366,0.0026404378],"genre_scores_gemma":[0.97164,0.00018496955,0.027488071,0.00025774832,0.00006589471,0.000007104849,0.00010665766,0.000006589774,0.0002429891],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989832,0.000038776554,0.00053312775,0.00010876004,0.00008964292,0.00024647574],"domain_scores_gemma":[0.99929065,0.00002888405,0.00027677242,0.00029428178,0.000058880978,0.00005055469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034871697,0.00012359364,0.00024975033,0.000062395186,0.000030835377,0.00000754948,0.00018171128,0.00018011138,0.000007742067],"category_scores_gemma":[0.00022896033,0.00010901339,0.0000860954,0.0000834438,0.00004879076,0.000008512301,0.000053241827,0.00007524819,0.000010839319],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013914736,0.00007732015,0.98707294,0.00011615752,0.00001584361,3.4826408e-7,0.00023613476,0.006477553,0.0014003952,0.000049692724,0.002252408,0.0021620337],"study_design_scores_gemma":[0.001680423,0.00035876044,0.85878557,0.000045332214,0.00001398561,0.0000051003944,0.0001641953,0.13609436,0.00087489065,0.00020386087,0.0015829022,0.00019063188],"about_ca_topic_score_codex":0.0000055139676,"about_ca_topic_score_gemma":0.000062155195,"teacher_disagreement_score":0.12961681,"about_ca_system_score_codex":0.0000130263425,"about_ca_system_score_gemma":0.00006216447,"threshold_uncertainty_score":0.4445437},"labels":[],"label_agreement":null},{"id":"W2013823401","doi":"10.1186/1471-2105-10-162","title":"Hydra: software for tailored processing of H/D exchange data from MS or tandem MS analyses","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research; Fondation pour la Recherche Médicale","keywords":"Computer science; Workflow; Software; Graphical user interface; Tandem mass spectrometry; Interface (matter); Database; Hydrogen–deuterium exchange; Visualization; Data visualization; Mass spectrometry; Data mining; Chemistry; Operating system; Chromatography","score_opus":0.131345965573557,"score_gpt":0.36589770495487595,"score_spread":0.23455173938131896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013823401","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051075197,0.00044472958,0.97895634,0.00012568866,0.000018387087,0.00041259505,0.0017677043,0.00043552206,0.012731507],"genre_scores_gemma":[0.10860779,0.00008658193,0.88790905,0.000117176125,0.00016058901,0.00005181686,0.002592466,0.000020126554,0.00045441443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880487,0.0000032555158,0.0005642629,0.00018238678,0.00021306562,0.00023216663],"domain_scores_gemma":[0.9983646,0.00011854081,0.00041940724,0.0009123994,0.00011453947,0.00007050139],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000112362024,0.0001736248,0.00030018878,0.00007569713,0.00010886368,0.00006637471,0.0006940725,0.00014317255,0.0010630996],"category_scores_gemma":[0.00022102834,0.00013571321,0.00006873216,0.0003623444,0.000043312586,0.0003265929,0.0001249028,0.00009644369,0.000006002491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088994374,0.0027043608,0.014527116,0.016042527,0.0006809512,0.000006284261,0.0050083417,0.000351882,0.06124848,0.0036704398,0.21581666,0.679053],"study_design_scores_gemma":[0.0017827703,0.00022249193,0.0010813859,0.0005330617,0.00045679585,0.000010457854,0.0011675779,0.813315,0.1167555,0.009093848,0.054666765,0.0009143859],"about_ca_topic_score_codex":0.000028114782,"about_ca_topic_score_gemma":0.00004231044,"teacher_disagreement_score":0.81296307,"about_ca_system_score_codex":0.000037006932,"about_ca_system_score_gemma":0.00010739837,"threshold_uncertainty_score":0.99985003},"labels":[],"label_agreement":null},{"id":"W2014097763","doi":"10.1186/1471-2105-13-264","title":"Sifting through genomes with iterative-sequence clustering produces a large, phylogenetically diverse protein-family resource","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Joint Genome Institute; Gordon and Betty Moore Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Genome; Computational biology; Cluster analysis; Identification (biology); Protein family; Phylogenetic tree; Computer science; Biology; Genomics; Comparative genomics; Sequence alignment; Genetics; Gene; Machine learning; Peptide sequence","score_opus":0.034131985975596454,"score_gpt":0.25701719782298676,"score_spread":0.2228852118473903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014097763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9531172,0.0027656984,0.036940996,0.000043292974,0.000105281615,0.00073058496,0.00007206253,0.000018539384,0.0062063346],"genre_scores_gemma":[0.78731394,0.000116267,0.21145713,0.0003821834,0.00033213675,0.0000624208,0.000047689267,0.000030881765,0.0002573551],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985134,0.00004575152,0.00036436887,0.00024379027,0.00020822325,0.00062446576],"domain_scores_gemma":[0.99913055,0.00001933106,0.00019212061,0.0004308121,0.0001125162,0.00011464785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002838097,0.00028939234,0.00022229618,0.000034616536,0.00027750176,0.000066620436,0.0002573711,0.00011266002,0.000005585868],"category_scores_gemma":[0.000069850816,0.00022757189,0.00007310915,0.0001239335,0.00014895717,0.000010975709,0.00039080347,0.00010302471,0.000021257923],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006367836,0.00052074593,0.13246886,0.0012219686,0.00067635323,0.0000064178803,0.02138049,0.0037170209,0.8244696,0.0013549,0.0013490056,0.012197815],"study_design_scores_gemma":[0.006431536,0.0036627187,0.06410315,0.0005683496,0.00038638382,0.0002481015,0.030883828,0.021051075,0.25332367,0.00020857995,0.6146103,0.0045222584],"about_ca_topic_score_codex":0.0000052742507,"about_ca_topic_score_gemma":0.000026112975,"teacher_disagreement_score":0.61326134,"about_ca_system_score_codex":0.000019109037,"about_ca_system_score_gemma":0.00007914575,"threshold_uncertainty_score":0.9280112},"labels":[],"label_agreement":null},{"id":"W2014141753","doi":"10.1186/s12859-015-0508-1","title":"Classification of bioinformatics workflows using weighted versions of partitioning and hierarchical clustering algorithms","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Computer science; Cluster analysis; Hierarchical clustering; Data mining; Pairwise comparison; Software; Algorithm; Artificial intelligence; Database; Programming language","score_opus":0.2720426029070439,"score_gpt":0.38204230321551835,"score_spread":0.10999970030847445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014141753","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14940341,0.000025628022,0.84724927,0.000045784487,0.00043669116,0.00016347879,0.00003765388,0.000027531536,0.0026105207],"genre_scores_gemma":[0.24241707,0.0000047918106,0.7574302,0.000023280827,0.00002586054,0.0000013657876,0.00002796214,0.000004695869,0.00006477826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713045,0.00006949117,0.0013422306,0.00016175327,0.0010971556,0.00019894468],"domain_scores_gemma":[0.9975914,0.00050553336,0.00070321705,0.0006708378,0.0003661486,0.0001629034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035166296,0.000112837246,0.0002661416,0.00045502977,0.00013445929,0.00018310486,0.00045065075,0.00006483665,0.000016548913],"category_scores_gemma":[0.0013811118,0.00008793908,0.00006243162,0.00096699555,0.00022467805,0.00067438785,0.0005218106,0.00008911085,0.000026806994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030245032,0.00055763137,0.15716423,0.0011587609,0.0001730346,0.0000033654696,0.04538242,0.1382948,0.0003055875,0.020005612,0.025049102,0.611603],"study_design_scores_gemma":[0.00038841387,0.0000437148,0.004106388,0.00008686788,0.000019883075,0.000006026383,0.008872216,0.9841774,0.000044164324,0.0009801147,0.0011771857,0.000097628734],"about_ca_topic_score_codex":0.00001822126,"about_ca_topic_score_gemma":0.000009271645,"teacher_disagreement_score":0.8458826,"about_ca_system_score_codex":0.00002767457,"about_ca_system_score_gemma":0.00012623258,"threshold_uncertainty_score":0.35860515},"labels":[],"label_agreement":null},{"id":"W2014519657","doi":"10.1186/1471-2105-8-483","title":"PARPs database: A LIMS systems for protein-protein interaction data mining or laboratory information management system","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Caprion (Canada); Université Laval; Bausch Health (Canada)","funders":"Canadian Institutes of Health Research","keywords":"Proteomics; Proteome; Pipeline (software); Computer science; Database search engine; Annotation; Computational biology; Database; Data management; Tandem mass spectrometry; Bioinformatics; Data mining; Mass spectrometry; Information retrieval; Chemistry; Biology; Search engine","score_opus":0.04278753517543161,"score_gpt":0.3111294744298611,"score_spread":0.2683419392544295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014519657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043804627,0.00004458655,0.9865481,0.000014492037,0.00009241961,0.0024076202,0.0015169757,0.00050736655,0.0044879448],"genre_scores_gemma":[0.012587515,0.00002206243,0.9818869,0.000037091344,0.0001536209,0.0014759569,0.0032939268,0.000032300446,0.00051059073],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806947,0.000008248343,0.0010657307,0.00020016075,0.00028782905,0.00036859224],"domain_scores_gemma":[0.9975316,0.000070669215,0.0007480159,0.0013577213,0.00018280224,0.00010920591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008559871,0.00023977029,0.00022333648,0.00014303646,0.00024193771,0.00019808658,0.00064217095,0.00015374257,0.0000139401145],"category_scores_gemma":[0.000098054516,0.00021170304,0.000040764702,0.00026661524,0.000032295262,0.0019881686,0.00033624598,0.00017336536,0.000047972375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0062862895,0.0011418939,0.00037964876,0.31516892,0.0012241238,0.000055810746,0.0063224547,0.004609149,0.05137809,0.24623959,0.05454508,0.31264895],"study_design_scores_gemma":[0.0012026253,0.00006366413,0.0000026919697,0.0023844945,0.00008356102,0.000038430873,0.023280226,0.6403141,0.032811638,0.000044899603,0.29914975,0.00062390225],"about_ca_topic_score_codex":0.000013459989,"about_ca_topic_score_gemma":0.00001005197,"teacher_disagreement_score":0.635705,"about_ca_system_score_codex":0.00025891536,"about_ca_system_score_gemma":0.00007814133,"threshold_uncertainty_score":0.86329997},"labels":[],"label_agreement":null},{"id":"W2015341379","doi":"10.1186/1471-2105-8-141","title":"Relating destabilizing regions to known functional sites in proteins","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Computational biology; DNA microarray; Biology; Evolutionary biology; Genetics; Bioinformatics; Gene; Gene expression","score_opus":0.019282405537499377,"score_gpt":0.25215638115509176,"score_spread":0.23287397561759238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015341379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41299742,0.00008870168,0.57886404,0.00004926156,0.00008907742,0.0004393584,0.0000073350493,0.000024349602,0.007440437],"genre_scores_gemma":[0.61194956,0.000007671409,0.38696468,0.00039479506,0.00018261858,0.000023749704,0.00012939653,0.000018214418,0.000329348],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99906445,0.000012654084,0.00036626615,0.00013672248,0.00013085287,0.0002890414],"domain_scores_gemma":[0.9994726,0.000027177093,0.00008503384,0.00026102515,0.00005924378,0.00009490298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037343273,0.00012751855,0.00010086301,0.000105903695,0.000085152,0.000023860997,0.000113453934,0.00015647418,0.000006677585],"category_scores_gemma":[0.00032839837,0.000119505465,0.000053285476,0.00021855146,0.00003542114,0.000011397122,0.00011284729,0.00011950021,0.000020921192],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000939361,0.00029089022,0.29437518,0.00083616463,0.00010250631,0.000018043986,0.0046931226,0.029087959,0.5982182,0.024326544,0.005000799,0.04211123],"study_design_scores_gemma":[0.007395606,0.0028253137,0.3746912,0.00077436917,0.000110317276,0.00056207913,0.010935269,0.17187797,0.29856807,0.010372665,0.11712969,0.0047574644],"about_ca_topic_score_codex":0.000010405335,"about_ca_topic_score_gemma":0.0007931064,"teacher_disagreement_score":0.29965013,"about_ca_system_score_codex":0.00003537271,"about_ca_system_score_gemma":0.00008618502,"threshold_uncertainty_score":0.48732916},"labels":[],"label_agreement":null},{"id":"W2016231246","doi":"10.1186/1471-2105-10-s6-s14","title":"iBarcode.org: web-based molecular biodiversity analysis","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Barcode; DNA barcoding; USable; Suite; Computer science; World Wide Web; Data science; Identification (biology); Web application; Set (abstract data type); SPARK (programming language); Information retrieval; Biology; Ecology; Geography","score_opus":0.01350209054431941,"score_gpt":0.2078110036386016,"score_spread":0.1943089130942822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016231246","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9591928,0.000028530212,0.022587778,0.00040136225,0.00005776309,0.00027138548,0.000104750616,0.0001629762,0.01719265],"genre_scores_gemma":[0.7562338,0.000026513613,0.24056652,0.0028988284,0.0000072112266,0.000002266492,0.00008771514,0.000004174135,0.00017293895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986739,0.000028304898,0.0002513238,0.00020692286,0.00050477294,0.00033475738],"domain_scores_gemma":[0.99929297,0.000027799726,0.00013094107,0.00040492183,0.0000053901517,0.00013800056],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016569535,0.00020627743,0.00022782333,0.00012381095,0.00027466714,0.000032528285,0.00039489073,0.000089137975,0.0009464807],"category_scores_gemma":[0.000024384317,0.00019767538,0.00023627697,0.00072962884,0.00027084106,0.00027760369,0.00024343227,0.000110605295,0.0041476456],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011941849,0.00009220641,0.97854626,0.000008534023,0.000066242814,0.0000058174865,0.00017527357,0.015921626,0.00039761417,0.000009989885,0.0041765086,0.000587959],"study_design_scores_gemma":[0.00057987316,0.00010910652,0.91628075,0.0000036146969,0.0004041071,9.1272193e-7,0.00031959492,0.07656703,0.001751637,0.000025951105,0.0036032714,0.00035414542],"about_ca_topic_score_codex":0.00003951718,"about_ca_topic_score_gemma":0.000021646365,"teacher_disagreement_score":0.21797875,"about_ca_system_score_codex":0.00023742854,"about_ca_system_score_gemma":0.000005436637,"threshold_uncertainty_score":0.9999668},"labels":[],"label_agreement":null},{"id":"W2016984855","doi":"10.1186/1471-2105-15-157","title":"Multidimensional mutual information methods for the analysis of covariation in multiple sequence alignments","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; Wayne State University","keywords":"Mutual information; Computer science; Set (abstract data type); Sequence (biology); Multiple sequence alignment; Data mining; Entropy (arrow of time); Multivariate statistics; Computational biology; Biology; Sequence alignment; Statistics; Artificial intelligence; Mathematics; Genetics; Machine learning","score_opus":0.02160173717026669,"score_gpt":0.31280156449726515,"score_spread":0.29119982732699845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016984855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037075456,0.000021831433,0.96233606,0.000015635394,0.00007682109,0.0003282524,0.00006194351,0.0000042370825,0.000079756515],"genre_scores_gemma":[0.33212474,0.000013074693,0.66692364,0.00018985067,0.000018516983,0.00003291482,0.0006829649,0.0000034714608,0.000010836352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992333,0.000049781996,0.0004210434,0.000065888635,0.000107810396,0.00012219073],"domain_scores_gemma":[0.999182,0.00019073952,0.00024780084,0.00025121926,0.00010492547,0.00002330924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069300004,0.00009016162,0.00014508404,0.0001105292,0.000053418014,0.000012631484,0.00013239977,0.000108882996,0.0000023707764],"category_scores_gemma":[0.0006430991,0.00006537164,0.0000990971,0.00022920231,0.00004540564,0.000022432907,0.000058646347,0.00003895752,0.0000014818802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008433617,0.00011426409,0.044356845,0.00049669936,0.0014301114,5.28248e-8,0.003187585,0.5423537,0.089934394,0.014237564,0.00037996206,0.3026655],"study_design_scores_gemma":[0.0005589145,0.00005434513,0.010083553,0.000004429448,0.00011177632,5.879551e-7,0.00011644456,0.9766237,0.008522909,0.00012426576,0.0037151566,0.00008388819],"about_ca_topic_score_codex":0.000025985593,"about_ca_topic_score_gemma":0.00006945125,"teacher_disagreement_score":0.43427005,"about_ca_system_score_codex":0.000015404998,"about_ca_system_score_gemma":0.00004690066,"threshold_uncertainty_score":0.2665778},"labels":[],"label_agreement":null},{"id":"W2017149761","doi":"10.1186/1471-2105-9-121","title":"SciDBMaker: new software for computer-aided design of specialized biological databases","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Agriculture and Agri-Food Canada","funders":"","keywords":"Biological database; Database; Computer science; Software; Biological data; Protein structure database; Variety (cybernetics); Scope (computer science); Interface (matter); Data mining; Sequence database; Data science; Bioinformatics; Biology; Programming language","score_opus":0.06878778794084801,"score_gpt":0.2769601502345303,"score_spread":0.2081723622936823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017149761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014055345,0.00022733535,0.9847815,0.000008298727,0.00015420096,0.0005296065,0.00015840774,0.000026035625,0.000059284772],"genre_scores_gemma":[0.004520937,0.0001783588,0.9939207,0.00022293282,0.00034617467,0.0000124266335,0.0006800981,0.000012857254,0.00010550715],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990789,0.000025644116,0.0004057225,0.00015342556,0.00011255094,0.00022374926],"domain_scores_gemma":[0.9991689,0.000064108644,0.00019402726,0.00036507298,0.0001160763,0.00009182797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012612154,0.00016760084,0.00024196952,0.00004187723,0.00009027877,0.000009851661,0.00022948933,0.00014355614,0.000010309668],"category_scores_gemma":[0.00024453257,0.0001349383,0.00010756663,0.00009862764,0.00014113798,0.000009269348,0.00013408887,0.000047806432,0.000004963287],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011000071,0.0012318705,0.06153189,0.0036012516,0.0014230406,0.00003367266,0.0025179773,0.1040974,0.16088255,0.011838798,0.47330117,0.16854031],"study_design_scores_gemma":[0.017904107,0.006928736,0.010659451,0.00025394926,0.00022364964,0.00078777445,0.00028316388,0.53224957,0.20560747,0.0034578189,0.218557,0.003087291],"about_ca_topic_score_codex":0.00000738801,"about_ca_topic_score_gemma":0.000006420436,"teacher_disagreement_score":0.4281522,"about_ca_system_score_codex":0.000008033491,"about_ca_system_score_gemma":0.00029422998,"threshold_uncertainty_score":0.5502624},"labels":[],"label_agreement":null},{"id":"W2017229033","doi":"10.1186/1471-2105-9-226","title":"SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Structural alignment; Protein structure prediction; Computer science; Structural similarity; Similarity (geometry); Classifier (UML); Protein secondary structure; Structural Classification of Proteins database; Protein structure; Sequence alignment; Mathematics; Biology; Peptide sequence; Genetics","score_opus":0.019655015260110244,"score_gpt":0.243559004356052,"score_spread":0.22390398909594175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017229033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87858415,0.00017045155,0.11966524,0.00001481244,0.00006688958,0.00076241326,0.0004961073,0.000020809715,0.00021910034],"genre_scores_gemma":[0.8479446,0.000029573013,0.15160526,0.000019224024,0.00007432032,0.00003926175,0.00023221067,0.000011437947,0.000044072352],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99875766,0.000026651967,0.0005709574,0.0001688265,0.00024733838,0.0002285588],"domain_scores_gemma":[0.9988001,0.000022990547,0.00053453154,0.00030467118,0.00027831024,0.000059423764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017053685,0.00019115939,0.0002581816,0.000055738325,0.00012731689,0.000012778959,0.00024132406,0.0002023807,0.000002857422],"category_scores_gemma":[0.000105587256,0.0001422493,0.00009120075,0.000127771,0.00033972104,0.000042360996,0.00006843385,0.00009219444,2.2466834e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022224716,0.000112471425,0.13834338,0.0049809916,0.0004944292,0.000003970829,0.0027261293,0.029313229,0.8164943,0.0016772883,0.00031186565,0.0033195151],"study_design_scores_gemma":[0.0016239161,0.0020173553,0.0064733457,0.00018913482,0.00008179276,0.00013266699,0.0007686585,0.20018174,0.7872614,0.00048680097,0.00042791624,0.00035528032],"about_ca_topic_score_codex":0.000028290904,"about_ca_topic_score_gemma":0.00006229347,"teacher_disagreement_score":0.1708685,"about_ca_system_score_codex":0.000015457561,"about_ca_system_score_gemma":0.00030210856,"threshold_uncertainty_score":0.5800758},"labels":[],"label_agreement":null},{"id":"W2017880952","doi":"10.1186/1471-2105-11-s1-s28","title":"Decoding HMMs using the k best paths: algorithms and applications","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Algorithm; Computer science; Sequence (biology); Decoding methods; Path (computing); Hidden Markov model; Markov chain; Sequence labeling; Feature (linguistics); State (computer science); Artificial intelligence; Machine learning; Task (project management)","score_opus":0.048164553412059975,"score_gpt":0.28816161978516885,"score_spread":0.23999706637310889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017880952","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030849567,0.00005382014,0.99542487,0.00007009498,0.00015221589,0.00014417681,0.000002862458,0.00007194892,0.0009950812],"genre_scores_gemma":[0.044239435,0.000020779644,0.95537895,0.00021682042,0.00009002385,0.000016352262,0.0000013205696,0.000004624838,0.00003169812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993479,0.000009921403,0.00022351542,0.00010407907,0.00013643784,0.00017810751],"domain_scores_gemma":[0.99923265,0.00008362908,0.00009009879,0.00045605574,0.00006262095,0.000074951044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026675212,0.00009306386,0.00007731215,0.00004158796,0.00030313485,0.00033533858,0.00051152933,0.00006340896,0.0000019194006],"category_scores_gemma":[0.0000238134,0.00006431938,0.000025519783,0.0001893292,0.00007957629,0.0004218858,0.00019124894,0.00020494318,0.00003174863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013730303,0.00006693496,0.0020530073,0.00012788539,0.000016840313,8.502685e-7,0.003951744,0.001532332,0.000777286,0.25203544,0.00018209782,0.7392542],"study_design_scores_gemma":[0.000060733695,0.000009603857,0.00005894106,0.000010254318,0.000005918748,0.000042005602,0.00022825359,0.99482316,0.00011837679,0.0032779977,0.0012636144,0.00010116185],"about_ca_topic_score_codex":0.000013251469,"about_ca_topic_score_gemma":0.000013308405,"teacher_disagreement_score":0.9932908,"about_ca_system_score_codex":0.000007382597,"about_ca_system_score_gemma":0.000074522555,"threshold_uncertainty_score":0.32336777},"labels":[],"label_agreement":null},{"id":"W2019000099","doi":"10.1186/1471-2105-12-205","title":"A scan statistic to extract causal gene clusters from case-control genome-wide rare CNV data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; SickKids Foundation","funders":"","keywords":"Scan statistic; False positive paradox; Cluster analysis; Computational biology; Statistic; Statistical power; Statistical hypothesis testing; Computer science; Data mining; Test statistic; Gene; Genome; False discovery rate; Genetics; Biology; Statistics; Artificial intelligence; Mathematics","score_opus":0.03702735802862018,"score_gpt":0.23824663090773626,"score_spread":0.2012192728791161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019000099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42410102,0.0002244911,0.5650419,0.000034017874,0.00026528412,0.0005177736,0.008270309,0.000033713033,0.0015115164],"genre_scores_gemma":[0.748897,0.00002380288,0.24738589,0.000677536,0.00018512462,0.000025235997,0.002514134,0.000028031813,0.0002632364],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863034,0.000049119706,0.0005286755,0.00028290902,0.00014144578,0.00036753246],"domain_scores_gemma":[0.99837506,0.000046499095,0.00017504573,0.0011064078,0.000083574916,0.00021344097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020937633,0.0002377801,0.00021409876,0.00006424336,0.0001524837,0.00007377682,0.0005363876,0.00014041708,0.00022185467],"category_scores_gemma":[0.00013846454,0.00022532635,0.000058298363,0.0000774123,0.00005215745,0.000030730695,0.00036150106,0.00008728611,0.00013437353],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008487252,0.0037702369,0.45802936,0.0038909123,0.010866037,0.005280625,0.14073542,0.03489006,0.073225416,0.00252856,0.1630786,0.0952175],"study_design_scores_gemma":[0.020901125,0.0048488807,0.29289752,0.00027074697,0.002805567,0.008690302,0.05283296,0.41439107,0.03563909,0.0013014717,0.15605639,0.009364874],"about_ca_topic_score_codex":0.00052702625,"about_ca_topic_score_gemma":0.0011495302,"teacher_disagreement_score":0.37950101,"about_ca_system_score_codex":0.000033928813,"about_ca_system_score_gemma":0.00020383965,"threshold_uncertainty_score":0.9188542},"labels":[],"label_agreement":null},{"id":"W2019590688","doi":"10.1186/1471-2105-14-139","title":"Ensemble-based prediction of RNA secondary structures","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Pseudoknot; Computer science; Machine learning; Resampling; Set (abstract data type); Data mining; Protein secondary structure; Exploit; Artificial intelligence; Nucleic acid secondary structure; Function (biology); RNA","score_opus":0.012940037251274156,"score_gpt":0.21182215388137687,"score_spread":0.19888211663010272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019590688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61337614,0.0002388341,0.37462142,0.000042918047,0.0002934982,0.0006612341,0.00010222266,0.00003370824,0.010630011],"genre_scores_gemma":[0.8391323,0.000018489529,0.16013707,0.00021980211,0.00009289795,0.00003626998,0.00014441284,0.00001483023,0.00020389579],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993159,0.000024385015,0.00030361794,0.0000861779,0.0001267291,0.0001431548],"domain_scores_gemma":[0.99939716,0.0000139005815,0.00015299403,0.00029811772,0.0000831688,0.00005464361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010256065,0.000111901354,0.000114079776,0.000043798387,0.00004111524,0.000020772619,0.0001406942,0.00015206823,0.00016472243],"category_scores_gemma":[0.000052618114,0.00009381999,0.000077174234,0.000046385543,0.00004280767,0.000009864353,0.000036505353,0.00004747866,0.000029590215],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004001972,0.000026602549,0.00053501973,0.00024528848,0.00003320088,1.12652295e-7,0.00007493894,0.00033575043,0.95222753,0.00037277027,0.0041332836,0.04197545],"study_design_scores_gemma":[0.00039494332,0.00022319233,0.0021475384,0.00001620381,0.0000116342435,0.0000037617285,0.00011803864,0.00825107,0.98518264,0.0006020187,0.002937588,0.000111347515],"about_ca_topic_score_codex":0.000010004942,"about_ca_topic_score_gemma":0.000003213138,"teacher_disagreement_score":0.22575618,"about_ca_system_score_codex":0.0000051619386,"about_ca_system_score_gemma":0.000098059754,"threshold_uncertainty_score":0.3825868},"labels":[],"label_agreement":null},{"id":"W2021166311","doi":"10.1186/1471-2105-12-s11-a9","title":"Computational purification of tumor gene expression data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Gene expression profiling; Concordance; DNA microarray; Gene expression; Biology; Gene; Computational biology; Bioinformatics; Genetics","score_opus":0.06824587109555594,"score_gpt":0.2790169882799327,"score_spread":0.21077111718437677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021166311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079077326,0.00022456882,0.91314965,0.000017693594,0.0001953372,0.00026773463,0.0001353275,0.000023648128,0.0069086817],"genre_scores_gemma":[0.47962978,0.00003479176,0.518718,0.00009149138,0.000056807832,0.000012173018,0.0013345858,0.000010196565,0.000112183574],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992511,0.000023083887,0.00033093055,0.00014901733,0.0001508495,0.00009497127],"domain_scores_gemma":[0.9988921,0.000005734302,0.0002452241,0.0007065863,0.00010121159,0.00004908715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001589557,0.000083844294,0.00008033801,0.000049803242,0.00004158065,0.000008354831,0.00038156798,0.00006338726,0.000042451484],"category_scores_gemma":[0.000051729927,0.00007394733,0.000030137491,0.000080364036,0.000051672334,0.0000160553,0.00016042127,0.000034736368,0.000018286464],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032849444,0.0003986253,0.012214811,0.0003372419,0.00004764601,4.0421656e-7,0.0010861146,0.0016669373,0.9362167,0.0013363231,0.037036113,0.009330566],"study_design_scores_gemma":[0.00062668254,0.00011965591,0.014649066,0.000034026973,0.00001882548,0.000011868865,0.0003924315,0.06153558,0.91175723,0.00034314525,0.010290965,0.00022052044],"about_ca_topic_score_codex":0.000002478229,"about_ca_topic_score_gemma":0.0000013254737,"teacher_disagreement_score":0.40055245,"about_ca_system_score_codex":0.000005066252,"about_ca_system_score_gemma":0.00010581075,"threshold_uncertainty_score":0.30154848},"labels":[],"label_agreement":null},{"id":"W2022059553","doi":"10.1186/1471-2105-12-379","title":"GOmotif: A web server for investigating the biological role of protein sequence motifs","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Agency of Canada","funders":"","keywords":"Gene ontology; Sequence motif; Computer science; Biological database; Computational biology; Web server; Biological data; Ontology; Motif (music); Biological network; Gene; Data mining; Biology; Bioinformatics; Genetics; The Internet; World Wide Web; Gene expression","score_opus":0.05431194829961473,"score_gpt":0.24357366344891151,"score_spread":0.1892617151492968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022059553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.937345,0.00047597775,0.054222245,0.000052172803,0.00014510812,0.0017369132,0.00016683021,0.000037351077,0.0058183437],"genre_scores_gemma":[0.8131148,0.0000295873,0.18611456,0.00029386542,0.000106201594,0.00009372342,0.000111572626,0.000017162683,0.000118464704],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988362,0.000031398773,0.0005851976,0.00012726632,0.00011200796,0.0003079262],"domain_scores_gemma":[0.9989701,0.000026395357,0.0003547041,0.00045831516,0.00010867151,0.00008181788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005194645,0.00018419704,0.0001826849,0.000027980754,0.00011756681,0.000023804749,0.000443086,0.0002229285,0.000013860332],"category_scores_gemma":[0.00015388819,0.000120059274,0.0001455062,0.00010257672,0.00025693985,0.00001333378,0.00019718266,0.000110443696,0.000011589981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083153555,0.00069463986,0.037151817,0.0034622352,0.0008552298,0.0000013562611,0.02048953,0.0023578312,0.72797954,0.09010323,0.0063476227,0.10972542],"study_design_scores_gemma":[0.0024856597,0.0021267778,0.002938864,0.00027432907,0.00010302234,0.00006400939,0.006504157,0.62755895,0.30796102,0.020652954,0.02806319,0.0012670606],"about_ca_topic_score_codex":0.000011140754,"about_ca_topic_score_gemma":0.000028403512,"teacher_disagreement_score":0.62520117,"about_ca_system_score_codex":0.000009658729,"about_ca_system_score_gemma":0.00014756908,"threshold_uncertainty_score":0.48958752},"labels":[],"label_agreement":null},{"id":"W2024909802","doi":"10.1186/s12859-015-0551-y","title":"A network model for angiogenesis in ovarian cancer","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Heart, Lung, and Blood Institute","keywords":"Biology; Angiogenesis; DNA microarray; DNA methylation; Computational biology; Ovarian cancer; Gene regulatory network; Gene; Transcription factor; Regulation of gene expression; Gene expression profiling; Gene expression; Bioinformatics; Genetics; Cancer","score_opus":0.04038979658660576,"score_gpt":0.26778370292767345,"score_spread":0.22739390634106768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024909802","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008190463,0.0009901887,0.987445,0.00012359001,0.0003256645,0.0006146114,0.00009187738,0.00001671486,0.0022019192],"genre_scores_gemma":[0.17569448,0.00021634057,0.8175043,0.002854181,0.0010339723,0.00038495945,0.00054423953,0.00006925855,0.00169831],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988262,0.000012357239,0.00047575223,0.00013445795,0.00011613101,0.0004350855],"domain_scores_gemma":[0.99925786,0.000012771366,0.00014933788,0.00032605988,0.000100816505,0.00015317104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004615316,0.00018163695,0.00019398093,0.00005114571,0.000054138694,0.00004018791,0.00023393414,0.00022506023,0.0000028798331],"category_scores_gemma":[0.000042920616,0.00016952903,0.00010306734,0.0001420643,0.000037882073,0.00001268239,0.00011656701,0.00006199389,0.00000947866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027084773,0.00004442741,0.0045950967,0.00014346771,0.000048691618,2.8333633e-7,0.0008440012,0.9118007,0.00016658583,0.0014951677,0.07526312,0.005327621],"study_design_scores_gemma":[0.0012969106,0.00008195596,0.0001642197,0.000023102624,0.000019072571,0.0000039853476,0.00017529036,0.9861201,0.00013361538,0.0018717363,0.009851084,0.0002589184],"about_ca_topic_score_codex":0.000018580715,"about_ca_topic_score_gemma":0.0003904099,"teacher_disagreement_score":0.16994071,"about_ca_system_score_codex":0.00003948042,"about_ca_system_score_gemma":0.00034854587,"threshold_uncertainty_score":0.6913193},"labels":[],"label_agreement":null},{"id":"W2025117991","doi":"10.1186/1471-2105-8-420","title":"'Unite and conquer': enhanced prediction of protein subcellular localization by integrating multiple specialized tools","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Canadian Institute for Advanced Research","keywords":"Interconnectivity; Computer science; Subcellular localization; Proteome; Function (biology); Computational biology; Protein function prediction; Identification (biology); Protein subcellular localization prediction; Set (abstract data type); Machine learning; Artificial intelligence; Biology; Bioinformatics; Protein function; Genetics","score_opus":0.010598265984508089,"score_gpt":0.2339617152942268,"score_spread":0.22336344930971871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025117991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25073838,0.00009681594,0.74614555,0.0000047019894,0.00005846736,0.00045808428,0.00006985418,0.000027944012,0.002400221],"genre_scores_gemma":[0.82250315,0.00006979134,0.17517735,0.00011704526,0.00011416685,0.000015016232,0.001673372,0.000028173348,0.00030193088],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985755,0.00004326445,0.0007963973,0.00012412417,0.0002192363,0.00024148071],"domain_scores_gemma":[0.99897325,0.000051489413,0.00044825047,0.0002742526,0.0001672679,0.0000855025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007077097,0.00019043012,0.00020017636,0.00008468645,0.00009746431,0.00004996064,0.00013690878,0.00022735966,0.000012460066],"category_scores_gemma":[0.0008110809,0.00017576027,0.00005326265,0.00015144392,0.00013059599,0.000035022207,0.000095538926,0.0001359994,0.000005174098],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005065678,0.00014588401,0.023208939,0.001726293,0.00010716085,6.6996165e-7,0.0028365,0.0017194301,0.93629056,0.001027282,0.0019165901,0.030514136],"study_design_scores_gemma":[0.0017698007,0.0004500157,0.0008379163,0.00013508505,0.000026628626,0.000011953355,0.0013775975,0.35521477,0.6198743,0.000031276075,0.01996959,0.00030107048],"about_ca_topic_score_codex":0.00001598314,"about_ca_topic_score_gemma":0.000035016972,"teacher_disagreement_score":0.57176477,"about_ca_system_score_codex":0.000021299627,"about_ca_system_score_gemma":0.000050739633,"threshold_uncertainty_score":0.71672964},"labels":[],"label_agreement":null},{"id":"W2025846584","doi":"10.1186/1471-2105-13-320","title":"Multiple-platform data integration method with application to combined analysis of microarray and proteomic data","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; York University","funders":"","keywords":"Data mining; Computer science; Data integration; False discovery rate; Statistical hypothesis testing; Test statistic; Statistic; Selection (genetic algorithm); DNA microarray; Computational biology; Statistics; Biology; Mathematics; Machine learning; Gene","score_opus":0.04850726272005896,"score_gpt":0.3225575594628057,"score_spread":0.2740502967427467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025846584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09034802,0.000053690528,0.9087387,0.000038226353,0.000024784518,0.00042361923,0.00023168541,0.000007699151,0.00013360038],"genre_scores_gemma":[0.5468297,0.000023385206,0.44650885,0.00008164044,0.000028991995,0.000029977075,0.0064593144,0.0000071525556,0.000030997944],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992584,0.000021502376,0.00028680853,0.00019309044,0.000116450035,0.00012377021],"domain_scores_gemma":[0.99817497,0.000015842365,0.00021172181,0.0014423827,0.000070934286,0.000084134976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044686333,0.00010275708,0.00014892418,0.0001227031,0.000041147683,0.000020688829,0.00041952525,0.00007901716,0.0000031420466],"category_scores_gemma":[0.0000894949,0.00007778387,0.000017376198,0.0003245652,0.000029137002,0.000045887853,0.00030394737,0.000040476792,0.0000028685781],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039396057,0.00012857346,0.040590987,0.00013588063,0.0003389954,1.2168259e-8,0.000689302,0.0004933132,0.9060048,0.00017526314,0.0026321888,0.04841672],"study_design_scores_gemma":[0.0008565096,0.00017030859,0.057743706,0.000024664154,0.0005368971,0.0000036541621,0.0009180065,0.71321315,0.21441534,0.0000062557624,0.011825752,0.00028574033],"about_ca_topic_score_codex":0.00002002023,"about_ca_topic_score_gemma":0.0001131148,"teacher_disagreement_score":0.71271986,"about_ca_system_score_codex":0.000008821314,"about_ca_system_score_gemma":0.000047671132,"threshold_uncertainty_score":0.31719342},"labels":[],"label_agreement":null},{"id":"W2026012474","doi":"10.1186/1471-2105-8-431","title":"Comparative evaluation of gene-set analysis methods","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale","keywords":"Permutation (music); Statistical inference; Null distribution; Inference; Resampling; Statistical hypothesis testing; Statistics; Statistical power; Type I and type II errors; Sample size determination; Mathematics; Gene expression profiling; Analysis of covariance; Multiple comparisons problem; False discovery rate; Asymptotic distribution; Biology; Test statistic; Computer science; Genetics; Gene expression; Gene; Artificial intelligence","score_opus":0.12111852523511878,"score_gpt":0.4413828526334908,"score_spread":0.320264327398372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026012474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11249899,0.00027895434,0.87945616,0.0000053894773,0.000076552926,0.00016082676,0.000012201694,0.0000057000975,0.00750523],"genre_scores_gemma":[0.6343848,0.000019929577,0.36512938,0.00004911481,0.000039635113,0.000009674404,0.0002743112,0.000003977741,0.00008920216],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999035,0.00009737513,0.0003819181,0.000103285805,0.000267948,0.000114497416],"domain_scores_gemma":[0.99900794,0.000020702955,0.00025931047,0.00033288906,0.000328397,0.00005074361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018837246,0.00008442486,0.00015590723,0.00015493993,0.000035343353,0.000009157502,0.00012141129,0.000094376206,0.00003617825],"category_scores_gemma":[0.000079246136,0.000073669835,0.00011320336,0.00041176027,0.000043855845,0.000005202933,0.000028247898,0.000034396468,0.0000058099295],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022731208,0.00014288472,0.01325691,0.00010063749,0.00095192593,7.3154794e-8,0.0027486263,0.02615159,0.8990605,0.00039956576,0.005475452,0.051484544],"study_design_scores_gemma":[0.00045523458,0.00006420318,0.025703147,0.000004070278,0.000426135,0.0000011241226,0.0015229111,0.17787687,0.7890475,0.00004729885,0.0047194837,0.00013204837],"about_ca_topic_score_codex":0.000003152567,"about_ca_topic_score_gemma":0.000030144147,"teacher_disagreement_score":0.5218858,"about_ca_system_score_codex":0.000019148274,"about_ca_system_score_gemma":0.000106352265,"threshold_uncertainty_score":0.30041686},"labels":[],"label_agreement":null},{"id":"W2027878425","doi":"10.1186/1471-2105-12-400","title":"MetaboHunter: an automatic approach for identification of metabolites from 1H-NMR spectra of complex mixtures","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University; National Research Council Canada; Université de Moncton","funders":"Mount Allison University","keywords":"Identification (biology); Metabolite; Metabolomics; Computer science; NMR spectra database; Data mining; Spectral line; Task (project management); Biological system; Database; Chemistry; Biology; Physics; Chromatography","score_opus":0.0462357203708497,"score_gpt":0.2672659518200872,"score_spread":0.22103023144923753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027878425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44504938,0.0017132367,0.5501904,0.000004778993,0.000113686976,0.0005970442,0.0007112525,0.0000206557,0.0015996033],"genre_scores_gemma":[0.48297477,0.00017231698,0.51609933,0.000022934848,0.000053985634,0.000030062045,0.0005954516,0.000013623578,0.000037510377],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985936,0.00003903056,0.00083224254,0.00018417396,0.00015305816,0.00019786936],"domain_scores_gemma":[0.9985828,0.000026410387,0.000602493,0.0005523176,0.0001792734,0.000056707642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003463027,0.00018670806,0.00043417182,0.000113331684,0.000053099124,0.000015894593,0.00033758915,0.00010748208,0.000028901262],"category_scores_gemma":[0.00013915832,0.00015760526,0.00019207179,0.0001281958,0.0001317294,0.000019698336,0.000085472704,0.000041521787,0.0000014837976],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001347199,0.0004890718,0.003537767,0.00080371834,0.0006176189,4.7987715e-8,0.001717851,0.00006688047,0.9823672,0.007297891,0.00048894493,0.0024782973],"study_design_scores_gemma":[0.0008474441,0.00031275483,0.028865812,0.000009935871,0.00034606122,0.0000021160893,0.0015053075,0.07946852,0.8862791,0.0012772948,0.00079993403,0.000285693],"about_ca_topic_score_codex":0.000039778948,"about_ca_topic_score_gemma":0.000016570717,"teacher_disagreement_score":0.09608806,"about_ca_system_score_codex":0.0000046934724,"about_ca_system_score_gemma":0.000041819454,"threshold_uncertainty_score":0.6426956},"labels":[],"label_agreement":null},{"id":"W2028126042","doi":"10.1186/1471-2105-9-463","title":"Information-based methods for predicting gene function from systematic gene knock-downs","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Division of Biological Infrastructure; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Biology; Phenotype; Computational biology; Gene; RNA interference; Functional genomics; Genetics; Caenorhabditis elegans; Gene regulatory network; DNA microarray; Function (biology); Gene prediction; Genome; Gene knockout; Genomics; Gene expression; RNA","score_opus":0.021769513734404333,"score_gpt":0.2629218602858384,"score_spread":0.24115234655143408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028126042","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08627767,0.0003744472,0.911339,0.000021161,0.0005596973,0.0010042243,0.00016009432,0.000072649265,0.00019106579],"genre_scores_gemma":[0.13650212,0.0000783979,0.8599057,0.00087254687,0.00034064343,0.00017898166,0.0019515302,0.000038948176,0.00013110253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981496,0.00009650393,0.0009605609,0.00017585348,0.00024027142,0.00037724143],"domain_scores_gemma":[0.99824816,0.00013709567,0.0004948704,0.0006742964,0.00029850096,0.0001470501],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005700563,0.00030429557,0.00037379152,0.0001159236,0.0003432207,0.00007800559,0.00031527053,0.00029429793,0.000015421736],"category_scores_gemma":[0.0005196133,0.0002847138,0.00021925096,0.000120344856,0.00008299764,0.00004237812,0.00009080313,0.00010848833,0.000053097294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021439556,0.0013127249,0.05556505,0.07890835,0.0035743625,0.000004925908,0.04843254,0.27975005,0.48390806,0.0005415014,0.027352935,0.018505564],"study_design_scores_gemma":[0.0021728869,0.0005539274,0.0018811347,0.00021012478,0.0003389055,0.00005235814,0.0010215635,0.82986605,0.15960312,0.00014552783,0.0034445077,0.0007099044],"about_ca_topic_score_codex":0.000030183699,"about_ca_topic_score_gemma":0.000013821538,"teacher_disagreement_score":0.550116,"about_ca_system_score_codex":0.00004051306,"about_ca_system_score_gemma":0.0002631859,"threshold_uncertainty_score":0.9999605},"labels":[],"label_agreement":null},{"id":"W2028245735","doi":"10.1186/1471-2105-9-305","title":"MAID : An effect size based model for microarray data integration across laboratories and platforms","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; Toronto Western Hospital; Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Replicate; DNA microarray; Sample size determination; Data mining; Computational biology; Computer science; Statistical power; Gene expression profiling; Permutation (music); Gene chip analysis; Microarray; False discovery rate; Microarray analysis techniques; Gene expression; Biology; Gene; Statistics; Mathematics; Genetics","score_opus":0.05440643697646198,"score_gpt":0.3195363113182625,"score_spread":0.2651298743418005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028245735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3885248,0.00009335671,0.6104977,0.000024910902,0.000084570805,0.0003155088,0.0003752242,0.000020259122,0.0000636666],"genre_scores_gemma":[0.8279622,0.000087025765,0.16872206,0.0003542496,0.00009821588,0.00006695647,0.002432565,0.000019716166,0.00025701374],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993002,0.000010973189,0.00022898962,0.00019539753,0.000095722324,0.00016870716],"domain_scores_gemma":[0.99907696,0.0000263132,0.00011232795,0.0006091097,0.000097082884,0.000078178666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002494266,0.00013724335,0.00011421327,0.000018055376,0.00019433032,0.000047990125,0.00023040458,0.00014498782,0.0000018258576],"category_scores_gemma":[0.00019069362,0.000106316285,0.000026943919,0.00006788897,0.00008229496,0.00004544554,0.00007927888,0.000048428024,0.0000017152353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021123881,0.00024601465,0.013167711,0.0010396643,0.00007549374,6.10532e-7,0.0047981003,0.0058145416,0.9052954,0.0004368815,0.0379677,0.02904553],"study_design_scores_gemma":[0.0011374704,0.00026666353,0.0007949348,0.000014642034,0.000011702138,0.0000057248058,0.00035497596,0.8564888,0.13612339,0.0000424647,0.0045636827,0.00019549664],"about_ca_topic_score_codex":0.0000016932612,"about_ca_topic_score_gemma":0.000061391074,"teacher_disagreement_score":0.85067433,"about_ca_system_score_codex":0.0000098327955,"about_ca_system_score_gemma":0.00015456659,"threshold_uncertainty_score":0.43354523},"labels":[],"label_agreement":null},{"id":"W2029036185","doi":"10.1186/1471-2105-10-120","title":"Multichromosomal median and halving problems under different genomic distances","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Genome; Breakpoint; Context (archaeology); Generalization; Time complexity; Biology; Computer science; Computational biology; Genetics; Combinatorics; Mathematics; Chromosome; Gene","score_opus":0.012402740614968691,"score_gpt":0.22283285140290676,"score_spread":0.21043011078793808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029036185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9266176,0.001174671,0.0699575,0.00019652508,0.00013939182,0.00042184375,0.000021369404,0.000033323886,0.0014377697],"genre_scores_gemma":[0.9463533,0.00036353507,0.052539233,0.00021211858,0.00014463921,0.000010838192,0.00012449805,0.000014747789,0.00023704444],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99915963,0.000014999051,0.00027019068,0.00015345821,0.00013230371,0.00026940412],"domain_scores_gemma":[0.9995227,0.000009060999,0.00009679326,0.00023428796,0.000028568831,0.00010858645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008472934,0.00017508339,0.00014162794,0.000041200226,0.00008804608,0.000065408676,0.0001427667,0.00009714915,0.000010448813],"category_scores_gemma":[0.000018665196,0.00014469137,0.000049415194,0.0000430122,0.00006487191,0.000009828411,0.00007448885,0.00006269808,0.000013117527],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023187582,0.00088978,0.08284508,0.0019910722,0.00056789623,0.000009393403,0.00737513,0.0066668736,0.70878536,0.002413608,0.0028473213,0.18537663],"study_design_scores_gemma":[0.009566296,0.0029497205,0.49355105,0.0003183965,0.00028882234,0.00018795578,0.005454137,0.41122943,0.04315278,0.003806083,0.026140712,0.0033546418],"about_ca_topic_score_codex":0.0000021268452,"about_ca_topic_score_gemma":0.000050868228,"teacher_disagreement_score":0.66563255,"about_ca_system_score_codex":0.000019860629,"about_ca_system_score_gemma":0.000028252336,"threshold_uncertainty_score":0.59003425},"labels":[],"label_agreement":null},{"id":"W2030006812","doi":"10.1186/1471-2105-10-99","title":"Markov clustering versus affinity propagation for the partitioning of protein interaction graphs","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":234,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Cluster analysis; Computer science; Markov chain; Affinity propagation; Partition (number theory); Theoretical computer science; Data mining; Machine learning; Correlation clustering; Mathematics; Canopy clustering algorithm; Combinatorics","score_opus":0.02334492071945516,"score_gpt":0.26218292354744616,"score_spread":0.238838002827991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030006812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0643014,0.00014960134,0.93143594,0.00015024519,0.00040120233,0.0011470547,0.000025480338,0.000020338166,0.0023687414],"genre_scores_gemma":[0.9150108,0.00004500929,0.0843836,0.00012276287,0.0001344145,0.00005598535,0.00015662653,0.000008689552,0.000082098704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992546,0.000013388648,0.00039948986,0.00007287969,0.00009373127,0.00016589757],"domain_scores_gemma":[0.99931186,0.00003574069,0.0002817529,0.00024477058,0.000094132374,0.00003174463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002970696,0.00010925792,0.000099983255,0.00003289551,0.00013590798,0.000041802967,0.00014255344,0.00009867418,0.000004101121],"category_scores_gemma":[0.00008784361,0.00008238751,0.00009995814,0.00007584267,0.000042123105,0.000019939365,0.000041141633,0.000073088646,0.000002612615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009982671,0.00053737446,0.00080833904,0.0025410356,0.00066766643,4.6960014e-7,0.0039804913,0.11289204,0.06603691,0.018967578,0.014767943,0.7688175],"study_design_scores_gemma":[0.00203969,0.001181435,0.0010392724,0.00010434684,0.00006409891,0.0000060713437,0.0011339817,0.9601766,0.025250567,0.0007639849,0.007937772,0.00030222232],"about_ca_topic_score_codex":0.000002792059,"about_ca_topic_score_gemma":0.0000392967,"teacher_disagreement_score":0.85070944,"about_ca_system_score_codex":0.000012845824,"about_ca_system_score_gemma":0.00004431334,"threshold_uncertainty_score":0.33596653},"labels":[],"label_agreement":null},{"id":"W2030393641","doi":"10.1186/1471-2105-12-s1-s55","title":"Closest string with outliers","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"String (physics); Hamming distance; Outlier; Combinatorics; Integer (computer science); String metric; Edit distance; Bounded function; Hamming code; Set (abstract data type); Discrete mathematics; Algorithm; Mathematics; String searching algorithm; Computer science; Artificial intelligence; Pattern matching","score_opus":0.04317960402421332,"score_gpt":0.2097569128317822,"score_spread":0.16657730880756888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030393641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014028506,0.000014411388,0.9826008,0.000007768325,0.00013786378,0.00008706574,0.0000037859945,0.0001513379,0.015594087],"genre_scores_gemma":[0.016332727,0.000005286556,0.9834489,0.00010026369,0.000020555324,0.0000035555415,0.000004475998,0.000004762774,0.00007944498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992645,0.000007728101,0.00019064065,0.00009877607,0.00019884502,0.000239543],"domain_scores_gemma":[0.99920404,0.000019409195,0.00009827679,0.0005317047,0.000037824553,0.000108736036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012591963,0.00009964133,0.000090854664,0.0000612226,0.00009527632,0.00009665549,0.00063311704,0.000036352343,0.000014922137],"category_scores_gemma":[0.000011052288,0.00006775292,0.000022868733,0.00017506427,0.000031809563,0.0011446901,0.00025591053,0.000079939586,0.00012493155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009712604,0.00043556248,0.035725694,0.00050265045,0.00009824935,0.000054895685,0.03256641,0.00090257335,0.000020233825,0.3255682,0.010589418,0.593439],"study_design_scores_gemma":[0.000491448,0.00018167577,0.006977727,0.000060524915,0.0000072066464,0.00004015373,0.0004340518,0.98433703,0.00045158505,0.0007393149,0.0059930803,0.00028617927],"about_ca_topic_score_codex":0.000018815465,"about_ca_topic_score_gemma":0.000006784814,"teacher_disagreement_score":0.9834345,"about_ca_system_score_codex":0.000016278249,"about_ca_system_score_gemma":0.00007177823,"threshold_uncertainty_score":0.2762884},"labels":[],"label_agreement":null},{"id":"W2030496326","doi":"10.1186/1471-2105-12-113","title":"A fully automatic gridding method for cDNA microarray images","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Computer science; Computational biology; Microarray; Complementary DNA; Artificial intelligence; Pattern recognition (psychology); Data mining; Bioinformatics; Biology; Genetics; Gene; Gene expression","score_opus":0.037787144706220105,"score_gpt":0.2927419322280458,"score_spread":0.25495478752182565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030496326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005519537,0.00015062279,0.9874341,0.00004331922,0.0002332611,0.00037460585,0.000031640848,0.000042486645,0.0061704367],"genre_scores_gemma":[0.02282981,0.0000351987,0.9753343,0.0003538038,0.00012073977,0.00012306427,0.000114070186,0.000022520524,0.0010665084],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991656,0.000028778628,0.00033499705,0.00015937461,0.00009137513,0.00021988478],"domain_scores_gemma":[0.9992578,0.00001625679,0.00018481484,0.0003724108,0.00009086691,0.00007786528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028703402,0.00014305241,0.00012810862,0.00006591922,0.000094359704,0.000031823132,0.00021812055,0.00012725158,0.00004230789],"category_scores_gemma":[0.00010052362,0.00012326731,0.00011460584,0.00008261265,0.0000339104,0.00001082633,0.000059626866,0.000046363188,0.000025801299],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016517978,0.0001359091,0.0011479843,0.0007927957,0.00009673895,3.2534555e-7,0.0017536425,0.000053971697,0.8251399,0.0009257392,0.08045276,0.08933507],"study_design_scores_gemma":[0.0012170832,0.00029666358,0.0023689987,0.000055421253,0.000062040075,0.000025322568,0.0012446941,0.061427124,0.85931396,0.00045314478,0.07307291,0.0004626149],"about_ca_topic_score_codex":0.0000034058091,"about_ca_topic_score_gemma":0.000004175328,"teacher_disagreement_score":0.088872455,"about_ca_system_score_codex":0.000013248592,"about_ca_system_score_gemma":0.00009581311,"threshold_uncertainty_score":0.5026695},"labels":[],"label_agreement":null},{"id":"W2030528974","doi":"10.1186/1471-2105-12-25","title":"Systematic error detection in experimental high-throughput screening","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Context (archaeology); Error detection and correction; Data mining; Systematic error; Statistical power; Type I and type II errors; Process (computing); Statistics; Algorithm; Reliability engineering; Mathematics; Biology","score_opus":0.06811592733085549,"score_gpt":0.29838761659394086,"score_spread":0.2302716892630854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030528974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035145,0.00006378066,0.96256787,0.000007662056,0.00039532056,0.00039387826,0.0000010432495,0.00013882111,0.0012866502],"genre_scores_gemma":[0.38911772,5.610728e-7,0.61075455,0.000061225815,0.0000138991945,0.000031730375,0.0000014297431,0.0000059325275,0.000012936725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984047,0.00015119738,0.0006763097,0.00016938467,0.00034638474,0.00025207142],"domain_scores_gemma":[0.9990191,0.00019971076,0.00023769024,0.00043320132,0.000043812135,0.0000665185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006975323,0.00016099574,0.00024701265,0.0002407221,0.00007882244,0.00010863524,0.00057291257,0.000063355445,0.0000101655505],"category_scores_gemma":[0.00011237657,0.00014772256,0.00007185573,0.00048671826,0.00003316981,0.0015247719,0.00028428787,0.000114778704,0.0001006327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002860451,0.0020566003,0.0039067,0.03845157,0.0003591462,0.000097104225,0.21254694,0.23644908,0.0012347671,0.44321203,0.00028722762,0.061112795],"study_design_scores_gemma":[0.00035464825,0.00006749542,0.0030159561,0.00041487336,0.0000051548327,0.000030855634,0.0009883821,0.9868062,0.006730091,0.001393106,0.000003897173,0.00018934702],"about_ca_topic_score_codex":0.000072528084,"about_ca_topic_score_gemma":0.0000313151,"teacher_disagreement_score":0.75035715,"about_ca_system_score_codex":0.00010271097,"about_ca_system_score_gemma":0.00006013208,"threshold_uncertainty_score":0.6023951},"labels":[],"label_agreement":null},{"id":"W2032345031","doi":"10.1186/1471-2105-13-174","title":"A novel hierarchical clustering algorithm for gene sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Hierarchical clustering; DNA sequencing; Complete-linkage clustering; Single-linkage clustering; DNA microarray; Tuple; Similarity (geometry); Phylogenetic tree; Pattern recognition (psychology); Measure (data warehouse); Sequence (biology); Correlation clustering; Data mining; Computational biology; Computer science; Artificial intelligence; Biology; Gene; Mathematics; CURE data clustering algorithm; Genetics; Image (mathematics)","score_opus":0.02575875611595342,"score_gpt":0.2702451143211852,"score_spread":0.2444863582052318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032345031","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020558694,0.00025519347,0.97813565,0.000035685174,0.0001477677,0.00015639256,0.00007272096,0.00001608513,0.00062178797],"genre_scores_gemma":[0.050916903,0.00005790173,0.94727695,0.00046749524,0.00053639745,0.00004212959,0.00031995494,0.000014179863,0.00036806712],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991598,0.000007979218,0.00026581125,0.00010203659,0.000117595584,0.000346777],"domain_scores_gemma":[0.9994997,0.000018763923,0.00008971609,0.00020997557,0.000051901527,0.0001299882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021018222,0.00013143742,0.00013077837,0.00004404066,0.00009516269,0.000032757212,0.00016006935,0.0001234548,0.000008875407],"category_scores_gemma":[0.0000622595,0.00010841867,0.00013947427,0.00008369269,0.00007204024,0.000023131597,0.00009373828,0.00005380358,0.000021327156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016713153,0.0005503755,0.006991779,0.00057691225,0.0004887915,0.0000011246601,0.0014738588,0.002688182,0.61220014,0.0006246175,0.0031990886,0.371038],"study_design_scores_gemma":[0.0010246687,0.00033601263,0.0008309467,0.000023757502,0.000103878854,0.00012655827,0.00064290495,0.84791654,0.11078347,0.000108493514,0.03747248,0.0006302913],"about_ca_topic_score_codex":0.000013594878,"about_ca_topic_score_gemma":0.000014705019,"teacher_disagreement_score":0.8452284,"about_ca_system_score_codex":0.000012969326,"about_ca_system_score_gemma":0.000054032236,"threshold_uncertainty_score":0.44211853},"labels":[],"label_agreement":null},{"id":"W2033377371","doi":"10.1186/1471-2105-10-s14-s4","title":"Googling DNA sequences on the World Wide Web","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"DNA microarray; World Wide Web; Computational biology; Biology; The Internet; Computer science; Genetics; Bioinformatics; Data science; Gene; Gene expression","score_opus":0.020518604062589485,"score_gpt":0.24137362208411092,"score_spread":0.22085501802152144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033377371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.929848,0.0005770417,0.0012087141,0.0016018299,0.00025550622,0.00030794312,0.00002661528,0.000013457239,0.06616085],"genre_scores_gemma":[0.98371315,0.00019199942,0.011019161,0.0038246908,0.0001758818,0.000007861827,0.000014226242,0.000007964142,0.0010450381],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993259,0.000018125342,0.00022722308,0.00010696984,0.00011115378,0.00021068219],"domain_scores_gemma":[0.9994654,0.000049818245,0.00009189437,0.00031414593,0.000036718637,0.000042010008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001808433,0.00013817176,0.00010124416,0.000033473967,0.00015653808,0.000043709726,0.00023120629,0.00005218538,0.000010135219],"category_scores_gemma":[0.00008531663,0.00008961595,0.00007679192,0.00009325311,0.00006402196,0.0000010874945,0.000052933767,0.00006788422,0.000042302487],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005640091,0.000526807,0.040747114,0.00030268083,0.0006989752,0.000008831544,0.0035995997,0.017528923,0.5881468,0.056977145,0.23212098,0.058778126],"study_design_scores_gemma":[0.0015341162,0.001784835,0.03197989,0.00014337775,0.00010309204,0.000028829549,0.0024630413,0.037378628,0.23461147,0.0046612574,0.68381214,0.0014993293],"about_ca_topic_score_codex":0.0000012095887,"about_ca_topic_score_gemma":0.000053570784,"teacher_disagreement_score":0.45169115,"about_ca_system_score_codex":0.00000833474,"about_ca_system_score_gemma":0.000058711772,"threshold_uncertainty_score":0.36544323},"labels":[],"label_agreement":null},{"id":"W2034031757","doi":"10.1186/1471-2105-15-302","title":"SAGE: String-overlap Assembly of GEnomes","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"De Bruijn graph; Contig; String (physics); Sequence assembly; Computer science; Graph; Theoretical computer science; Genomics; Genome; Computation; Biology; Computational biology; Algorithm; Mathematics; Genetics; Gene","score_opus":0.01149497004112611,"score_gpt":0.2257135221193186,"score_spread":0.21421855207819251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034031757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9173377,0.0011994077,0.0705686,0.000022141414,0.0002136988,0.00018450187,0.0000429081,0.000006543439,0.010424486],"genre_scores_gemma":[0.95071363,0.00032899366,0.048379418,0.000118349664,0.00012198785,0.000005420422,0.00002484022,0.000012672728,0.0002946602],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992872,0.000017252414,0.00030726593,0.00010120969,0.00010579091,0.00018132113],"domain_scores_gemma":[0.99939007,0.000021379843,0.00015252277,0.00032476374,0.00006120304,0.000050086506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018006402,0.00012442513,0.0001622643,0.00003380399,0.000049368617,0.00001407858,0.00017949208,0.00008723494,0.0000048067936],"category_scores_gemma":[0.00006892153,0.0001115066,0.00008755972,0.000054630713,0.000058238154,0.0000011158194,0.00014063009,0.000037739086,0.000012937601],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021846913,0.00030421987,0.22490308,0.0014797354,0.0006504701,6.365767e-7,0.0016452204,0.0073733064,0.5714484,0.011578876,0.005613016,0.17478462],"study_design_scores_gemma":[0.003941354,0.0023296138,0.14413288,0.00009767818,0.00020181073,0.00003457096,0.0022356065,0.05266346,0.4123456,0.0010281618,0.37932837,0.0016608908],"about_ca_topic_score_codex":0.0000047860735,"about_ca_topic_score_gemma":0.000014292843,"teacher_disagreement_score":0.37371534,"about_ca_system_score_codex":0.0000051602483,"about_ca_system_score_gemma":0.000044803288,"threshold_uncertainty_score":0.45471072},"labels":[],"label_agreement":null},{"id":"W2035486209","doi":"10.1186/1471-2105-9-243","title":"MD-SeeGH: a platform for integrative analysis of multi-dimensional genomic data","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency; Canadian Centre for Applied Research in Cancer Control","funders":"National Institutes of Health; National Institute of Dental and Craniofacial Research; Canadian Breast Cancer Research Alliance; Genome Canada","keywords":"Computational biology; DNA microarray; Genomics; Computer science; DNA methylation; Copy-number variation; Biology; Software; Genome; Data mining; Bioinformatics; Genetics; Gene; Gene expression","score_opus":0.06515720872580286,"score_gpt":0.28112740047967566,"score_spread":0.2159701917538728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035486209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7414528,0.00036146722,0.2543064,0.000011796631,0.00011027716,0.00037792485,0.0028667054,0.00001312257,0.0004994788],"genre_scores_gemma":[0.5461699,0.0001640608,0.44412333,0.00014775759,0.000080532125,0.000028208966,0.008298653,0.000017674429,0.00096990535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908733,0.000010312274,0.00046438066,0.0001601678,0.000101980826,0.00017583795],"domain_scores_gemma":[0.9989417,0.00003702211,0.00022800748,0.0005921887,0.00014906816,0.0000520226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016072829,0.00014383977,0.00025138215,0.00012612078,0.00011771361,0.0000106629595,0.00035713703,0.000107838,0.000023944878],"category_scores_gemma":[0.00008734971,0.00011811204,0.00016366907,0.00017138108,0.000098181416,0.00001790559,0.0002580233,0.000043538435,0.0000065597974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041195154,0.004361844,0.26323587,0.0029055334,0.04072449,0.000012606892,0.044935703,0.26721233,0.21077956,0.021508496,0.1275658,0.012638252],"study_design_scores_gemma":[0.0018022535,0.00035645906,0.012079954,0.000016637721,0.0008274422,0.00003801972,0.0023034425,0.9530229,0.017439652,0.00005905031,0.011577043,0.00047712936],"about_ca_topic_score_codex":0.000024539864,"about_ca_topic_score_gemma":0.0001569163,"teacher_disagreement_score":0.68581057,"about_ca_system_score_codex":0.000016634423,"about_ca_system_score_gemma":0.00021207985,"threshold_uncertainty_score":0.4816469},"labels":[],"label_agreement":null},{"id":"W2036298771","doi":"10.1186/1471-2105-12-s5-s8","title":"Promoting ranking diversity for genomics search with relevance-novelty combined model","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Beihang University; National Natural Science Foundation of China; State Key Laboratory of Software Development Environment; National Science Foundation","keywords":"Relevance (law); Novelty; Computer science; Information retrieval; Ranking (information retrieval); Term (time); Data science","score_opus":0.09916546799670223,"score_gpt":0.2562741648534256,"score_spread":0.15710869685672335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036298771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08279913,0.0000024327994,0.9145128,0.00003262936,0.00006791356,0.00070825167,0.000017058635,0.00015165734,0.0017081333],"genre_scores_gemma":[0.15789509,0.0000048495285,0.8417446,0.00016306581,0.000012180633,0.000016505015,0.000013137088,0.000008305067,0.00014226582],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985481,0.000014802021,0.00039198162,0.0001397582,0.00045428873,0.00045106237],"domain_scores_gemma":[0.9988519,0.00007740463,0.00017386494,0.00041448371,0.00034799345,0.00013436633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006996924,0.0001584727,0.00017859726,0.00012889938,0.0006076716,0.00014855382,0.00090469234,0.00007616377,0.000004925387],"category_scores_gemma":[0.000050101007,0.00012582823,0.00007451956,0.00029995083,0.00007003678,0.0017340285,0.00072790246,0.00016760174,0.0000330233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00158077,0.0008144874,0.021624092,0.0034609959,0.00017637128,0.0000108890135,0.54161084,0.018824687,0.00022213264,0.22832757,0.0008741719,0.182473],"study_design_scores_gemma":[0.0011036854,0.00030211313,0.00081862294,0.000026876118,0.000010519255,0.00000750809,0.00033133128,0.99490273,0.0014270119,0.00080148806,0.000059225233,0.00020888088],"about_ca_topic_score_codex":0.000010777944,"about_ca_topic_score_gemma":0.0000075232547,"teacher_disagreement_score":0.97607803,"about_ca_system_score_codex":0.00009773716,"about_ca_system_score_gemma":0.0002640157,"threshold_uncertainty_score":0.5131126},"labels":[],"label_agreement":null},{"id":"W2037567612","doi":"10.1186/1471-2105-10-s1-s60","title":"GAIA: a gram-based interaction analysis tool – an approach for identifying interacting domains in yeast","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ontario Institute for Cancer Research","funders":"Michael Smith Health Research BC; Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Domain (mathematical analysis); Protein–protein interaction; Set (abstract data type); Computational biology; Computer science; Gram; Saccharomyces cerevisiae; Budding yeast; Identification (biology); Protein domain; Folding (DSP implementation); Data mining; Yeast; Biology; Genetics; Gene; Mathematics","score_opus":0.028505559512490307,"score_gpt":0.2980608545648929,"score_spread":0.2695552950524026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037567612","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07944575,0.00003218095,0.9188596,0.000022704178,0.00012241704,0.00041280646,0.000029760025,0.00002278067,0.001052002],"genre_scores_gemma":[0.67160654,0.0000069339285,0.32654986,0.00045203636,0.00012125326,0.00002947719,0.0011912575,0.000012055759,0.00003061797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985836,0.000036764886,0.0007015109,0.00020523099,0.00011808371,0.00035481155],"domain_scores_gemma":[0.99903935,0.000029040846,0.00032239137,0.00042695444,0.000078909725,0.000103339815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062428386,0.00021573827,0.0002665818,0.00027950798,0.00010797656,0.00017171091,0.00024474875,0.00020084085,0.000005472745],"category_scores_gemma":[0.00012658845,0.00020856969,0.00024602152,0.00036454032,0.000027627886,0.000058056707,0.00004445248,0.00016064532,0.000003978262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012236682,0.0009994258,0.0071345633,0.0007711819,0.0006522697,0.0000018003465,0.0030225986,0.8768819,0.008494137,0.0012750375,0.0020187264,0.09752469],"study_design_scores_gemma":[0.0008973777,0.00018950894,0.0011311761,0.00002461995,0.000115104056,0.000006581561,0.0013517292,0.9941403,0.0008280424,0.000093397,0.0009343412,0.00028779608],"about_ca_topic_score_codex":0.000009242814,"about_ca_topic_score_gemma":0.000092530645,"teacher_disagreement_score":0.5923098,"about_ca_system_score_codex":0.000050986113,"about_ca_system_score_gemma":0.00008481781,"threshold_uncertainty_score":0.8505225},"labels":[],"label_agreement":null},{"id":"W2039740528","doi":"10.1186/1471-2105-10-193","title":"Filtering Genes for Cluster and Network Analysis","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Ted Rogers Centre for Heart Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada; Canadian Institutes of Health Research; Mitacs; Ontario Genomics; Ontario Genomics Institute","keywords":"Interpretability; Computer science; Similarity (geometry); Network analysis; Data mining; Set (abstract data type); Gene regulatory network; Cluster analysis; Filter (signal processing); Modular design; Cluster (spacecraft); Computational biology; Gene; Artificial intelligence; Biology; Genetics; Gene expression","score_opus":0.010698307085337215,"score_gpt":0.2370848833538894,"score_spread":0.22638657626855216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039740528","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024186306,0.00081659824,0.9727824,0.000095250136,0.00011858695,0.0003480347,0.00002968255,0.000019999805,0.0016031874],"genre_scores_gemma":[0.17395975,0.00047542577,0.82033324,0.0030690618,0.00081243075,0.000029402292,0.0006059811,0.000022094775,0.0006926312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990878,0.0000096724525,0.00038319235,0.00012802675,0.0000734478,0.00031783938],"domain_scores_gemma":[0.99939895,0.000021056441,0.0001395676,0.00029851956,0.000049159826,0.00009277417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026917882,0.00016363108,0.00021230736,0.00005997082,0.00012967474,0.00008126643,0.00013853886,0.00015508913,0.000004817779],"category_scores_gemma":[0.000018567705,0.00014544022,0.00015370082,0.00015432498,0.00003554073,0.000010849774,0.00007691877,0.00004925388,0.000003699679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010346404,0.00018243249,0.020977857,0.000978602,0.002805203,9.1758983e-7,0.0017030163,0.37775636,0.004497326,0.007575715,0.10232477,0.48016316],"study_design_scores_gemma":[0.0008800208,0.00035857817,0.0035361173,0.000015042667,0.00030889577,0.000013298089,0.00013061166,0.9340289,0.0005152265,0.00092795363,0.058862757,0.00042258474],"about_ca_topic_score_codex":9.744564e-7,"about_ca_topic_score_gemma":0.00002279778,"teacher_disagreement_score":0.55627257,"about_ca_system_score_codex":0.000006527985,"about_ca_system_score_gemma":0.000025895011,"threshold_uncertainty_score":0.593088},"labels":[],"label_agreement":null},{"id":"W2041184037","doi":"10.1186/1471-2105-8-117","title":"Colony size measurement of the yeast gene deletion strains for functional genomics","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo; Carleton University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Functional genomics; Yeast; Saccharomyces cerevisiae; DNA microarray; Biology; Computational biology; Genomics; Model organism; Genetics; Gene; Plasmid; Comparative genomics; Genome; Gene expression","score_opus":0.037444805723937255,"score_gpt":0.2591775465108114,"score_spread":0.2217327407868741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041184037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6531399,0.00017221288,0.34427467,0.000060813196,0.00030702027,0.0006140291,0.00015926828,0.000006361022,0.0012657193],"genre_scores_gemma":[0.9560382,0.000034851364,0.04305204,0.00014621372,0.0002577045,0.000019331485,0.000075199016,0.000016212443,0.0003602434],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990224,0.000014143411,0.00030924508,0.000094955765,0.00033336141,0.00022588698],"domain_scores_gemma":[0.9992167,0.000017793278,0.00011772766,0.00024944334,0.00033736968,0.0000609717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066870113,0.00009608736,0.00008466936,0.000023962042,0.000092467184,0.000013071214,0.0001842117,0.00010968614,0.000008784526],"category_scores_gemma":[0.00021575698,0.00007224879,0.000119616925,0.00007875984,0.00008312377,0.00000286126,0.00009568152,0.0000577852,0.0000047459407],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019270566,0.00006442714,0.0017943927,0.00013347139,0.000047331607,5.6099577e-8,0.000070144946,0.0013707886,0.991516,0.0001307397,0.0019834328,0.0026965234],"study_design_scores_gemma":[0.0010563881,0.00032639888,0.038460948,0.00001534041,0.000027985057,0.000011577144,0.00023876857,0.008295489,0.92818224,0.00009507083,0.023110708,0.00017906836],"about_ca_topic_score_codex":0.0000028889751,"about_ca_topic_score_gemma":0.00009334481,"teacher_disagreement_score":0.3028983,"about_ca_system_score_codex":0.000042645348,"about_ca_system_score_gemma":0.00025917112,"threshold_uncertainty_score":0.29462203},"labels":[],"label_agreement":null},{"id":"W2041435062","doi":"10.1186/1471-2105-15-52","title":"Comparison of genotype clustering tools with rare variants","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"Institut de Cardiologie de Montréal; Fondation Institut de Cardiologie de Montréal; Université de Montréal","keywords":"Concordance; Genotyping; Genotype; Minor allele frequency; Biology; Cluster analysis; Genetics; Gold standard (test); Allele; Allele frequency; Population; Computational biology; Computer science; Statistics; Medicine; Mathematics; Artificial intelligence; Gene","score_opus":0.03260006616483543,"score_gpt":0.2889988527256054,"score_spread":0.25639878656077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041435062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2932333,0.000062109095,0.7004931,0.000036721864,0.00008064043,0.00012895327,0.0000158782,0.000009670773,0.00593961],"genre_scores_gemma":[0.7774753,0.000011538406,0.22207192,0.00014316945,0.00005737947,0.0000050459403,0.000104047314,0.000008690784,0.00012292489],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992425,0.000042952666,0.0003637802,0.00009150086,0.00008276188,0.00017649992],"domain_scores_gemma":[0.9993078,0.0000402717,0.00024464732,0.00027834822,0.000083356485,0.000045565608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024998566,0.00009970291,0.00021197404,0.000027284445,0.000051310082,0.000011580868,0.000137328,0.00012631933,0.0000109806515],"category_scores_gemma":[0.00022013302,0.00008001466,0.000041862735,0.000058596233,0.00004550232,0.00000463608,0.00007751566,0.000049208662,0.000014116445],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002938092,0.0002227108,0.84838015,0.00060540484,0.00026778426,2.9761384e-7,0.0014406842,0.075009815,0.013435023,0.0009988603,0.008520261,0.0508252],"study_design_scores_gemma":[0.0016925941,0.0015156714,0.33566496,0.00005835769,0.000078920166,0.00002080082,0.001129142,0.62761754,0.0063543967,0.000113229726,0.025238708,0.0005157121],"about_ca_topic_score_codex":0.000006161427,"about_ca_topic_score_gemma":0.000065602835,"teacher_disagreement_score":0.5526077,"about_ca_system_score_codex":0.0000067136516,"about_ca_system_score_gemma":0.000048628794,"threshold_uncertainty_score":0.3262903},"labels":[],"label_agreement":null},{"id":"W2042301222","doi":"10.1186/1471-2105-11-562","title":"An improved method for scoring protein-protein interactions using semantic similarity within the gene ontology","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Semantic similarity; Gene ontology; Computer science; Similarity (geometry); Graph; Protein function prediction; Cluster analysis; Ontology; Gene Annotation; Representation (politics); Computational biology; Data mining; Protein function; Information retrieval; Artificial intelligence; Gene; Theoretical computer science; Biology; Genetics; Genome; Gene expression","score_opus":0.024240405385633584,"score_gpt":0.3072557650958416,"score_spread":0.283015359710208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042301222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27106383,0.000022729006,0.72706074,0.00006688798,0.00044922813,0.001111182,0.000039976094,0.000024104898,0.00016131022],"genre_scores_gemma":[0.29044285,0.0000014459371,0.70856446,0.0002952352,0.00037433705,0.00010480671,0.00009223715,0.00002751964,0.00009710943],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985305,0.00005551585,0.00067814457,0.00021723255,0.000110141846,0.000408478],"domain_scores_gemma":[0.9983958,0.00003650348,0.00042437215,0.0008425605,0.00016974998,0.00013103503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009625513,0.00026424666,0.00023537478,0.000059453723,0.00041601935,0.00014417569,0.00047619047,0.00029468272,0.00000901168],"category_scores_gemma":[0.00015744058,0.00019992093,0.00015667175,0.000100503385,0.00011820226,0.000039324168,0.00016045415,0.00041099734,0.000005435151],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012779352,0.000069364556,0.00012993842,0.00020094293,0.00008517008,2.4433405e-7,0.000569314,0.002760611,0.9887889,0.001536352,0.00007680777,0.0056545427],"study_design_scores_gemma":[0.00053162675,0.00019782232,0.00007497998,0.0000206426,0.000049792307,0.00006633325,0.00035774522,0.8849036,0.11074175,0.0010792573,0.0016840636,0.00029239908],"about_ca_topic_score_codex":0.00008299848,"about_ca_topic_score_gemma":0.0012632395,"teacher_disagreement_score":0.88214296,"about_ca_system_score_codex":0.000018632189,"about_ca_system_score_gemma":0.00021714499,"threshold_uncertainty_score":0.8152539},"labels":[],"label_agreement":null},{"id":"W2044267926","doi":"10.1186/1471-2105-8-136","title":"An adaptive bin framework search method for a beta-sheet protein homopolymer model","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Bin; Computer science; Context (archaeology); Set (abstract data type); Search algorithm; Exponential growth; Function (biology); Monte Carlo method; Algorithm; Mathematical optimization; Theoretical computer science; Mathematics","score_opus":0.02344821303907908,"score_gpt":0.32136390687974065,"score_spread":0.2979156938406616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044267926","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024466898,0.00013651203,0.9731126,0.000028079288,0.000060909748,0.0010092601,0.00015633713,0.00003435047,0.0009950426],"genre_scores_gemma":[0.07637845,0.0000065857007,0.9224396,0.0003842463,0.00020061606,0.00007354193,0.00022964572,0.000035411085,0.0002519502],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985464,0.00003614287,0.00042902987,0.00024905434,0.00022580712,0.000513528],"domain_scores_gemma":[0.99886155,0.000041103438,0.00013281245,0.0006114359,0.00016527595,0.00018780543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007989451,0.00024559294,0.00021971352,0.000091880414,0.00014742053,0.00005237246,0.0003577415,0.00045717286,0.000005849263],"category_scores_gemma":[0.00008319436,0.0002153004,0.00014975024,0.00014568039,0.00008627908,0.00002033925,0.000106576066,0.00019536515,0.000006594285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006705417,0.0007646095,0.00094200857,0.0017052419,0.00075919554,0.000008030763,0.005417821,0.11909246,0.4343885,0.20030668,0.002573481,0.22733657],"study_design_scores_gemma":[0.0004947788,0.00067163666,0.00003804115,0.000023308292,0.000028523915,0.0000102765525,0.00047083866,0.8371864,0.1557629,0.0043521025,0.00061633385,0.00034484305],"about_ca_topic_score_codex":0.000011704802,"about_ca_topic_score_gemma":0.000051283707,"teacher_disagreement_score":0.71809393,"about_ca_system_score_codex":0.000024339404,"about_ca_system_score_gemma":0.00020851006,"threshold_uncertainty_score":0.87796956},"labels":[],"label_agreement":null},{"id":"W2044833006","doi":"10.1186/1471-2105-12-s3-s1","title":"Building a biomedical tokenizer using the token lattice design pattern and the adapted Viterbi algorithm","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexical analysis; Computer science; Security token; Viterbi algorithm; Artificial intelligence; Domain (mathematical analysis); Classifier (UML); Natural language processing; Hidden Markov model","score_opus":0.060771486185793054,"score_gpt":0.2754870983270212,"score_spread":0.2147156121412281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044833006","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020104734,0.0006106107,0.9784506,0.00017860753,0.0001752586,0.0002596395,0.000012536549,0.00002877646,0.00017924503],"genre_scores_gemma":[0.058713447,0.00012281338,0.93968153,0.0011643781,0.00020717467,0.000022043117,0.000014557825,0.000019069941,0.000054999135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988673,0.00013997755,0.00034726123,0.00014662532,0.00019915539,0.00029973604],"domain_scores_gemma":[0.9992264,0.00013951802,0.00014073319,0.0003524943,0.000048424383,0.00009241896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008089528,0.0001746036,0.00017694593,0.000035726203,0.00021045664,0.00005395409,0.00036043953,0.00020373357,0.000015240043],"category_scores_gemma":[0.00022232402,0.0000885388,0.00007525865,0.00011899363,0.0007763137,0.000008549889,0.0002845423,0.00016211763,0.000006107407],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062356587,0.00018362983,0.0011379569,0.00024560635,0.00050467876,0.000014110964,0.010239351,0.000055933953,0.0049576657,0.00054029346,0.005721956,0.97577524],"study_design_scores_gemma":[0.0035557887,0.00043306279,0.0009230303,0.00009399501,0.00021252198,0.00035862156,0.0031483471,0.9531222,0.007332956,0.00054196385,0.029756922,0.0005206013],"about_ca_topic_score_codex":0.00004908171,"about_ca_topic_score_gemma":0.0000040961613,"teacher_disagreement_score":0.97525465,"about_ca_system_score_codex":0.000008133011,"about_ca_system_score_gemma":0.00006669334,"threshold_uncertainty_score":0.36105075},"labels":[],"label_agreement":null},{"id":"W2047165041","doi":"10.1186/1471-2105-9-55","title":"Designing multiple degenerate primers via consecutive pairwise alignments","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Tehran","keywords":"Degenerate energy levels; Primer (cosmetics); Computation; Pairwise comparison; Computer science; Algorithm; Cover (algebra); Reduction (mathematics); Computational biology; Theoretical computer science; Biology; Mathematics; Engineering; Physics; Artificial intelligence","score_opus":0.026146798081331638,"score_gpt":0.2254022577459897,"score_spread":0.19925545966465807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047165041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3722151,0.0003485558,0.62461233,0.00001628593,0.00022353389,0.0005923575,0.000035729012,0.000050946666,0.001905163],"genre_scores_gemma":[0.45825806,0.00022734837,0.53969365,0.00032443742,0.0001341893,0.000045829092,0.00033961725,0.000039683087,0.0009372106],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988401,0.000045684774,0.00035256823,0.00018535467,0.00021302131,0.000363257],"domain_scores_gemma":[0.99926716,0.000019098,0.00015867224,0.0003339327,0.000088403314,0.000132708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017138565,0.0002152136,0.00016250572,0.000061434075,0.00018210689,0.000019927349,0.00019678724,0.00013741422,0.000018261922],"category_scores_gemma":[0.00006680587,0.0002075203,0.000098167235,0.00010339492,0.0001276286,0.000011908336,0.00012717447,0.00007058785,0.00014144483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028564173,0.0003516608,0.103669465,0.0002917294,0.0006072514,0.000030081907,0.003775755,0.0053217467,0.8598585,0.00002895882,0.01859016,0.0071890582],"study_design_scores_gemma":[0.0030251618,0.00046693507,0.004246083,0.000028087432,0.000062301275,0.00015717778,0.0009842671,0.079054676,0.89748853,0.000022707683,0.013606645,0.00085745123],"about_ca_topic_score_codex":0.000010131671,"about_ca_topic_score_gemma":0.0000085679185,"teacher_disagreement_score":0.09942338,"about_ca_system_score_codex":0.000031995445,"about_ca_system_score_gemma":0.00012873224,"threshold_uncertainty_score":0.8462432},"labels":[],"label_agreement":null},{"id":"W2047300262","doi":"10.1186/1471-2105-14-141","title":"An automated graphics tool for comparative genomics: the Coulson plot generator","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta; Wellcome Trust","keywords":"Plot (graphics); Context (archaeology); Computer science; Comparative genomics; Genomics; Graphics; Representation (politics); File format; Software; Data mining; Computational biology; Genome; Biology; Genetics; Gene; Programming language; Computer graphics (images)","score_opus":0.026758218816336235,"score_gpt":0.2806950135405673,"score_spread":0.2539367947242311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047300262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761276,0.00042482722,0.021550937,0.000079661135,0.00020295107,0.0011630375,0.00021555307,0.000034057895,0.00020137818],"genre_scores_gemma":[0.90380937,0.0002196983,0.09344536,0.0013152553,0.0003160289,0.00038546952,0.00038468503,0.000028914294,0.00009523023],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999031,0.000033955275,0.00037399592,0.00016895548,0.00009686628,0.00029519133],"domain_scores_gemma":[0.9990309,0.000038835024,0.00015843112,0.00047121558,0.0002287188,0.00007190632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019020053,0.00020954138,0.00019080006,0.00003065184,0.00028000228,0.000115996925,0.00032619442,0.0001271673,0.0000072925786],"category_scores_gemma":[0.000027685912,0.000147517,0.00010644209,0.00007016132,0.0001316274,0.0000048415786,0.00008473457,0.000059435886,0.000039019553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025903017,0.00041045336,0.010393487,0.00039441156,0.0009795848,3.23795e-7,0.0074216146,0.016081734,0.787285,0.0034939703,0.16878301,0.0044973926],"study_design_scores_gemma":[0.0013236039,0.0009324345,0.013383755,0.000008330687,0.00008401093,0.000011461347,0.0023029163,0.8468709,0.053030975,0.0003514418,0.081012025,0.00068814727],"about_ca_topic_score_codex":0.000015281097,"about_ca_topic_score_gemma":0.000039714738,"teacher_disagreement_score":0.83078915,"about_ca_system_score_codex":0.000013662494,"about_ca_system_score_gemma":0.00010258732,"threshold_uncertainty_score":0.6015569},"labels":[],"label_agreement":null},{"id":"W2049268173","doi":"10.1186/1471-2105-8-444","title":"Insertions and the emergence of novel protein structure: a structure-based phylogenetic study of insertions","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic","keywords":"Phylogenetic tree; Biology; Protein domain; Domain (mathematical analysis); Computational biology; Inference; Similarity (geometry); Variable (mathematics); Protein structure; Genetics; Evolutionary biology; Phylogenetics; Structural similarity; Insert (composites); Sequence alignment; Structural alignment; Computer science; Artificial intelligence; Gene; Peptide sequence; Mathematics","score_opus":0.010725812650330126,"score_gpt":0.24453967665412163,"score_spread":0.2338138640037915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049268173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8765431,0.0001269356,0.1221396,0.000014050255,0.000054196324,0.0009306642,0.0001114012,0.000005928412,0.00007410658],"genre_scores_gemma":[0.9509578,0.0000058230867,0.048857685,0.00007113273,0.000030301253,0.000012599238,0.000043796495,0.000011072127,0.000009797126],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99882054,0.000034263758,0.0006090766,0.00013618407,0.00021339451,0.0001865305],"domain_scores_gemma":[0.9989179,0.000028063643,0.00034391685,0.00049466064,0.00016063097,0.000054879893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022099342,0.00017141941,0.00021484592,0.00008109184,0.00010437582,0.000011130958,0.00025261892,0.00013579143,0.0000074165814],"category_scores_gemma":[0.0001472783,0.00011719061,0.00006454951,0.00024164189,0.00029254123,0.000006859972,0.00011125557,0.00010505183,1.3693798e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00118853,0.00044882594,0.021939617,0.0005643413,0.00021952624,4.548723e-7,0.0024548178,0.010655015,0.95703006,0.002544685,0.00005604201,0.0028980852],"study_design_scores_gemma":[0.020352025,0.0030914443,0.120121114,0.00012482266,0.000403634,0.00005247721,0.007113643,0.13327065,0.71192765,0.0020903095,0.00039606547,0.0010561751],"about_ca_topic_score_codex":0.00005201104,"about_ca_topic_score_gemma":0.0010518746,"teacher_disagreement_score":0.24510242,"about_ca_system_score_codex":0.000004724438,"about_ca_system_score_gemma":0.00011087971,"threshold_uncertainty_score":0.47788945},"labels":[],"label_agreement":null},{"id":"W2050263604","doi":"10.1186/1471-2105-12-435","title":"PESCADOR, a web-based tool to assist text-mining of biointeractions extracted from PubMed queries","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; Ottawa Hospital Research Institute","keywords":"Computer science; Relevance (law); Function (biology); Set (abstract data type); Resource (disambiguation); Mechanism (biology); Biological network; Web resource; Focus (optics); Information retrieval; Interaction network; Computational biology; World Wide Web; Bioinformatics; Biology; Gene","score_opus":0.03956506832173659,"score_gpt":0.25544508606942734,"score_spread":0.21588001774769075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050263604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84859425,0.00014421067,0.14445023,0.00011118855,0.00049175776,0.00035777286,0.0002831833,0.00010739964,0.0054600155],"genre_scores_gemma":[0.565201,0.000010307293,0.43387964,0.00034371347,0.00007971277,0.00006831363,0.00015719961,0.000016878066,0.00024327342],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987221,0.000035673864,0.0005561406,0.00019017268,0.00017932939,0.00031661618],"domain_scores_gemma":[0.9989922,0.00007116292,0.00023731048,0.00044549466,0.000108522974,0.00014529654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020170404,0.00019443051,0.0002440674,0.0001169353,0.00007516358,0.00003016042,0.00028749398,0.0002450087,0.00009581108],"category_scores_gemma":[0.0007294727,0.00016609454,0.00013308068,0.00018605047,0.00018693633,0.000012575028,0.000117928765,0.0001028871,0.00003099956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026932992,0.0015958906,0.18170221,0.0008189416,0.0007939066,0.000015390042,0.0068332204,0.00011666136,0.084689364,0.00041938692,0.05474747,0.66557425],"study_design_scores_gemma":[0.0037305625,0.0015442128,0.58058846,0.00034600962,0.00022374373,0.000030682637,0.006577046,0.018940039,0.21567805,0.000108487526,0.17070886,0.0015238498],"about_ca_topic_score_codex":0.00006220765,"about_ca_topic_score_gemma":0.00017374777,"teacher_disagreement_score":0.6640504,"about_ca_system_score_codex":0.000016902768,"about_ca_system_score_gemma":0.00018814551,"threshold_uncertainty_score":0.6773139},"labels":[],"label_agreement":null},{"id":"W2050345155","doi":"10.1186/1471-2105-12-35","title":"VennDiagram: a package for the generation of highly-customizable Venn and Euler diagrams in R","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":3262,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Venn diagram; Computer science; Visualization; Process (computing); Data mining; Engineering drawing; Theoretical computer science; Programming language; Mathematics","score_opus":0.07426646512308042,"score_gpt":0.24697291885229222,"score_spread":0.17270645372921178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050345155","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008552843,0.00011949293,0.9904323,0.000056453377,0.00013072981,0.0002927179,0.00001565787,0.000022614351,0.00037718323],"genre_scores_gemma":[0.36286902,0.00008686276,0.63665706,0.00016931817,0.00004499404,0.000068633744,0.000034632703,0.000008695185,0.000060765266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918956,0.00002263628,0.00037212018,0.00010242726,0.00013733785,0.00017589683],"domain_scores_gemma":[0.99900025,0.00017139388,0.00018405265,0.0005535925,0.00005205018,0.00003863499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052707933,0.0000915918,0.000155377,0.00010472325,0.000060069007,0.00007819667,0.0005026483,0.00004872609,0.000003939677],"category_scores_gemma":[0.000113725684,0.00006156685,0.000046892023,0.00031161052,0.00005469313,0.000658184,0.00015097177,0.00005428112,0.000014266051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013777771,0.0009115135,0.074814305,0.0016386894,0.00040182486,0.000007791928,0.074651286,0.0027288776,0.0010939944,0.40999874,0.036266025,0.39734918],"study_design_scores_gemma":[0.0004094891,0.00005744044,0.0054924716,0.0000136191275,0.000022638116,0.0000025843165,0.0001367923,0.99042124,0.0014830922,0.0005983244,0.0012609141,0.00010139968],"about_ca_topic_score_codex":0.00006256139,"about_ca_topic_score_gemma":0.0002449992,"teacher_disagreement_score":0.98769236,"about_ca_system_score_codex":0.000016002943,"about_ca_system_score_gemma":0.000043402695,"threshold_uncertainty_score":0.25106233},"labels":[],"label_agreement":null},{"id":"W2050870676","doi":"10.1186/1471-2105-10-410","title":"Refining gene signatures: a Bayesian approach","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada; Douglas Mental Health University Institute; Natural Sciences and Engineering Research Council of Canada","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Bayesian probability; Context (archaeology); Data mining; Machine learning; DNA microarray; Artificial intelligence; Curse of dimensionality; Identification (biology); Microarray analysis techniques; Feature selection; Bayes' theorem; Pattern recognition (psychology); Gene; Biology; Genetics; Gene expression","score_opus":0.016360147667429287,"score_gpt":0.250817003064846,"score_spread":0.2344568553974167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050870676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010008259,0.00067475694,0.9250942,0.0001354941,0.00015629739,0.00017698825,0.000011471052,0.000062350686,0.063680165],"genre_scores_gemma":[0.5934507,0.000084905514,0.40230668,0.001801572,0.0002683132,0.00002020283,0.00039051945,0.00001626175,0.0016608017],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992537,0.00002004538,0.00024336329,0.00015190641,0.00014266702,0.00018833145],"domain_scores_gemma":[0.9993727,0.0000034531897,0.000111889,0.0003829913,0.000045421195,0.00008352066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012574348,0.00012613801,0.00009549161,0.00005624192,0.00008195678,0.000039444047,0.0001922154,0.00016764436,0.000008673568],"category_scores_gemma":[0.00004034236,0.00010881408,0.00006817891,0.000121137906,0.000023745215,0.0000070167384,0.000032317643,0.00008395725,0.0000138821115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026474858,0.0003141047,0.0011874818,0.00017688789,0.000055829845,0.0000010683275,0.0008773373,0.0065299543,0.8139915,0.0031140426,0.0731401,0.10034697],"study_design_scores_gemma":[0.0034503213,0.0011852668,0.013055514,0.00009271343,0.00007649211,0.00008288142,0.0016086122,0.25917363,0.33465883,0.00061617617,0.38429946,0.0017000996],"about_ca_topic_score_codex":6.957588e-7,"about_ca_topic_score_gemma":0.0000011173654,"teacher_disagreement_score":0.5834425,"about_ca_system_score_codex":0.000011584105,"about_ca_system_score_gemma":0.000079550846,"threshold_uncertainty_score":0.44373092},"labels":[],"label_agreement":null},{"id":"W2051873396","doi":"10.1186/1471-2105-8-227","title":"Relationship between insertion/deletion (indel) frequency of proteins and essentiality","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; Michael Smith Health Research BC","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Indel; Biology; In silico; Proteome; Computational biology; Genetics; INDEL Mutation; DNA microarray; Saccharomyces cerevisiae; Gene; Genotype; Single-nucleotide polymorphism","score_opus":0.02498220279781606,"score_gpt":0.2616971265343822,"score_spread":0.23671492373656614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051873396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5073461,0.000106761036,0.49048164,0.00002249167,0.000059648504,0.0002495192,0.000023501414,0.000010494669,0.0016998238],"genre_scores_gemma":[0.9072211,0.000013308238,0.0922775,0.00005486162,0.0001346351,0.0000044883855,0.00022081993,0.000009372822,0.00006394847],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988329,0.000020271742,0.00067896367,0.000102086204,0.00015012379,0.00021568249],"domain_scores_gemma":[0.9991665,0.000042694413,0.00030953897,0.00029193726,0.000096601776,0.000092740476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076544425,0.00013306194,0.0001508507,0.0000725398,0.000099341836,0.00002296904,0.00012074212,0.00024905044,0.0000046148184],"category_scores_gemma":[0.00011507371,0.00012489542,0.000063126005,0.00012170611,0.000118593845,0.000019154257,0.000084438,0.000116174975,0.000006009913],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007104138,0.000061528044,0.97514784,0.0007528039,0.0000577613,3.1850902e-7,0.00063544064,0.00015508497,0.004342314,0.009309429,0.0005585477,0.008907917],"study_design_scores_gemma":[0.001308528,0.00034579687,0.9676643,0.00006979086,0.000079553356,0.000020503103,0.0005789106,0.00674633,0.013302078,0.007525533,0.0018271916,0.0005314684],"about_ca_topic_score_codex":0.000019791238,"about_ca_topic_score_gemma":0.00007951891,"teacher_disagreement_score":0.39987496,"about_ca_system_score_codex":0.000014011463,"about_ca_system_score_gemma":0.00007121075,"threshold_uncertainty_score":0.50930876},"labels":[],"label_agreement":null},{"id":"W2052057394","doi":"10.1186/1471-2105-10-313","title":"Social tagging in the life sciences: characterizing a new metadata resource for bioinformatics","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Metadata; Computer science; World Wide Web; Information retrieval; Search engine indexing; Resource (disambiguation); Metadata repository; Annotation; Data science; Artificial intelligence","score_opus":0.07446472868360497,"score_gpt":0.32471233606516253,"score_spread":0.25024760738155755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052057394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061220832,0.0018306449,0.89776075,0.024770267,0.00038009678,0.0020420344,0.0001531489,0.00019299386,0.0116492305],"genre_scores_gemma":[0.083687894,0.00015979327,0.8741147,0.039419625,0.0013336267,0.000050040297,0.0006412677,0.000028649363,0.0005643939],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866426,0.00003621848,0.00050560175,0.00014141305,0.00024255543,0.0004099766],"domain_scores_gemma":[0.9993336,0.00008327309,0.00020972046,0.00026950423,0.000024835383,0.00007905938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009964195,0.0001710318,0.00020105389,0.00008944747,0.00028717972,0.00015115764,0.00065464235,0.00018692204,0.0000020091652],"category_scores_gemma":[0.00068127946,0.00011585873,0.00011002782,0.00026394034,0.0001800911,0.000032800068,0.00008637863,0.00012939103,0.0000056585477],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046163026,0.00032929756,0.0010619086,0.0007392189,0.00014006656,0.000003053944,0.021004468,0.00027643243,0.004221792,0.00988752,0.4438936,0.517981],"study_design_scores_gemma":[0.0017738222,0.0008665599,0.0025395479,0.00008206451,0.00005949564,0.00003315761,0.010234063,0.057630047,0.0010741327,0.00052787125,0.924634,0.00054526253],"about_ca_topic_score_codex":0.00000424649,"about_ca_topic_score_gemma":0.000009909053,"teacher_disagreement_score":0.5174357,"about_ca_system_score_codex":0.000009908031,"about_ca_system_score_gemma":0.0002520315,"threshold_uncertainty_score":0.47245818},"labels":[],"label_agreement":null},{"id":"W2052656210","doi":"10.1186/1471-2105-14-s15-s19","title":"The dynamics of functional classes of plant genes in rediploidized ancient polyploids","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Gene; Genetics; Gene family; Computational biology; Evolutionary dynamics; Evolutionary biology","score_opus":0.019255785105250056,"score_gpt":0.19619476762754154,"score_spread":0.17693898252229148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052656210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981693,0.000139156,0.00024434636,0.0003453986,0.00012263814,0.00021803343,0.00014831036,0.000010749857,0.00060208567],"genre_scores_gemma":[0.9948416,0.00013345486,0.004551108,0.000051043648,0.000057908175,0.000025734842,0.00016142658,6.0636944e-7,0.0001771676],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99925107,0.000016903177,0.0003833703,0.0000476348,0.00017262007,0.00012843119],"domain_scores_gemma":[0.99948114,0.00020331693,0.00015594784,0.000049771978,0.000079189136,0.000030650357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001262759,0.00006243274,0.00010335169,0.000011167459,0.00007619395,0.00001931618,0.00013573626,0.000047588324,0.000097790966],"category_scores_gemma":[0.000049727718,0.00001977791,0.000051743016,0.00021562948,0.00007129194,0.000073185234,0.000050356673,0.000039465027,0.00001266171],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002363461,0.0010108639,0.42499635,0.00035986444,0.00009274068,5.9923565e-7,0.0017887242,0.0039324015,0.27823624,0.064165175,0.0048695058,0.2203112],"study_design_scores_gemma":[0.00025544286,0.00015760632,0.76708007,0.000025685074,0.000008199397,0.0000048297875,0.0022556193,0.22516803,0.0014524191,0.0012417358,0.0022423202,0.000108022476],"about_ca_topic_score_codex":0.00015944093,"about_ca_topic_score_gemma":0.0024029724,"teacher_disagreement_score":0.34208372,"about_ca_system_score_codex":0.000015936019,"about_ca_system_score_gemma":0.000023730294,"threshold_uncertainty_score":0.1340915},"labels":[],"label_agreement":null},{"id":"W2053264599","doi":"10.1186/1471-2105-14-212","title":"Linear combination test for gene set analysis of a continuous phenotype","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary; University of Alberta","funders":"Canadian Institutes of Health Research; Department of Science and Technology, Ministry of Science and Technology, India; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Phenotype; Context (archaeology); Computational biology; Estimator; Computer science; Set (abstract data type); DNA microarray; Continuous variable; Gene expression profiling; Gene; Biology; Data mining; Genetics; Statistics; Gene expression; Mathematics","score_opus":0.01927340765702812,"score_gpt":0.26895499551251323,"score_spread":0.2496815878554851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053264599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38123253,0.00015674446,0.6158012,0.00010459528,0.00013991179,0.0008005803,0.00018899763,0.000021885859,0.0015535629],"genre_scores_gemma":[0.92405427,0.0000515157,0.07355802,0.00018517557,0.00005224908,0.00010000788,0.001376314,0.000010952014,0.00061149197],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993952,0.000010163376,0.0003039921,0.000091899696,0.00009216292,0.00010659286],"domain_scores_gemma":[0.9991889,0.00002497368,0.0002144105,0.00026636288,0.00026360585,0.000041736588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000101085185,0.000080455255,0.00014420062,0.0001049424,0.000035402616,0.000015730035,0.00011557208,0.00009381099,0.000029049444],"category_scores_gemma":[0.0001407453,0.000070552094,0.000108738444,0.00023243605,0.00003011127,0.0000072840576,0.000029991294,0.00002255138,0.000011931406],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010215319,0.0003649408,0.030569898,0.00034726286,0.0006435502,3.9972637e-8,0.000647173,0.0029688957,0.9094276,0.0006007316,0.039200198,0.015127598],"study_design_scores_gemma":[0.001461263,0.0005231082,0.0342501,0.000013599772,0.00044148613,8.9461196e-7,0.0006651666,0.68764794,0.25870293,0.0001342808,0.015857892,0.0003013588],"about_ca_topic_score_codex":0.000008181958,"about_ca_topic_score_gemma":0.000007110465,"teacher_disagreement_score":0.68467903,"about_ca_system_score_codex":0.000007495443,"about_ca_system_score_gemma":0.000047339363,"threshold_uncertainty_score":0.2877031},"labels":[],"label_agreement":null},{"id":"W2054353156","doi":"10.1186/1471-2105-11-s12-s7","title":"SADI, SHARE, and the in silico scientific method","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada; Genome Prairie; Canadian Institutes of Health Research; Genome Canada; Canarie; Microsoft Research","keywords":"Computer science; Workflow; Semantic Web; Social Semantic Web; Web service; World Wide Web; Set (abstract data type); Class (philosophy); Service (business); Data science; Semantic search; Artificial intelligence; Database","score_opus":0.10072184250704203,"score_gpt":0.387181686914727,"score_spread":0.28645984440768496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054353156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33106723,0.00015159823,0.58581513,0.0028769525,0.009670775,0.0014684778,0.000107102926,0.00017374304,0.068668984],"genre_scores_gemma":[0.21044038,0.0000041219823,0.77876765,0.00089751324,0.00012545145,0.00002293396,0.000028751343,0.000011702478,0.009701514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997475,0.00012537964,0.00075727655,0.00033225823,0.0010467131,0.0002633721],"domain_scores_gemma":[0.99587363,0.0022202223,0.00021693595,0.0014755806,0.00012525331,0.00008838039],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.022308353,0.00010553005,0.00019224305,0.0004111769,0.00035850576,0.0024141208,0.0012673198,0.000047611247,0.00017576027],"category_scores_gemma":[0.0061810086,0.000055954857,0.000060524155,0.0013788447,0.00050805736,0.0005001747,0.00080611254,0.00021966452,0.00047180837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006999005,0.00009123691,0.019709647,0.00006146261,0.000012380041,0.0000023918121,0.012386051,0.0014353498,0.000066552224,0.121642426,0.1582256,0.68629694],"study_design_scores_gemma":[0.0006521433,0.000005503569,0.013719024,0.00000769402,0.000004601361,0.000007878542,0.0017921756,0.8703969,0.000018532619,0.014904741,0.09839732,0.00009348882],"about_ca_topic_score_codex":0.000032956872,"about_ca_topic_score_gemma":0.0006274278,"teacher_disagreement_score":0.8689616,"about_ca_system_score_codex":0.000008114916,"about_ca_system_score_gemma":0.000065972206,"threshold_uncertainty_score":0.99862146},"labels":[],"label_agreement":null},{"id":"W2054958397","doi":"10.1186/1471-2105-9-25","title":"Using Generalized Procrustes Analysis (GPA) for normalization of cDNA microarray data","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Normalization (sociology); Quantile; Computer science; Data mining; Housekeeping gene; Statistics; Mathematics; Biology; Genetics; Gene expression","score_opus":0.14358390016491582,"score_gpt":0.3388302792023284,"score_spread":0.19524637903741257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054958397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09413444,0.000186324,0.90488446,0.0000162082,0.000064987325,0.0002629172,0.00020272432,0.000009122459,0.00023883884],"genre_scores_gemma":[0.26321015,0.00030044588,0.73034596,0.000197679,0.00013657183,0.000027108896,0.0053394465,0.000020400586,0.00042220633],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991873,0.000019861107,0.00038684273,0.00015718372,0.00012074924,0.0001280713],"domain_scores_gemma":[0.998848,0.0000073505926,0.00029109194,0.00064666977,0.00016509023,0.000041760068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014685313,0.00010063871,0.0001585543,0.00011392195,0.000092974464,0.000011613601,0.00027849496,0.00010084125,0.000009055266],"category_scores_gemma":[0.00007858631,0.00009063104,0.00009294208,0.00029740363,0.00005262904,0.000016833748,0.000095023264,0.000021307136,8.68128e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029181238,0.00016133336,0.043010686,0.00059711246,0.0005809052,1.5006484e-7,0.00055004854,0.028288752,0.89858466,0.0002553329,0.02624725,0.0014319372],"study_design_scores_gemma":[0.0009771908,0.00007140694,0.0023188938,0.000011997172,0.00031276388,0.000007742906,0.00018142213,0.6828229,0.27846965,0.000010370284,0.03457775,0.00023792332],"about_ca_topic_score_codex":0.000007407212,"about_ca_topic_score_gemma":0.000014509223,"teacher_disagreement_score":0.65453416,"about_ca_system_score_codex":0.000009349842,"about_ca_system_score_gemma":0.00014911804,"threshold_uncertainty_score":0.36958265},"labels":[],"label_agreement":null},{"id":"W2055029531","doi":"10.1186/1471-2105-13-s10-s17","title":"Gene network modular-based classification of microarray samples","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; York University","funders":"Canadian Institutes of Health Research","keywords":"Linear discriminant analysis; Modular design; DNA microarray; Discriminant; Computer science; Pattern recognition (psychology); Artificial intelligence; Computational biology; Data mining; Microarray analysis techniques; Biology; Gene; Genetics; Gene expression","score_opus":0.03825888650910341,"score_gpt":0.2668124748441448,"score_spread":0.22855358833504136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055029531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25114647,0.0010223852,0.74461097,0.000058738566,0.00041847138,0.0002841031,0.00003703117,0.000025624673,0.0023962122],"genre_scores_gemma":[0.84458685,0.00004357545,0.15433308,0.00017578705,0.0002677743,0.000023186307,0.00044564967,0.000013188333,0.00011089304],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913424,0.00003721266,0.00035286602,0.00009951134,0.00013976154,0.00023640489],"domain_scores_gemma":[0.99910873,0.000011692886,0.00025483157,0.00044763018,0.000087475935,0.00008965579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025380924,0.00011647385,0.00011401192,0.000044143315,0.000059023067,0.000012347519,0.00016147183,0.00014169286,0.000019924892],"category_scores_gemma":[0.00004688063,0.00010480967,0.0000821324,0.00013273768,0.000058588936,0.000010059489,0.000035973168,0.00004527092,0.000017414995],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077013756,0.0001279899,0.05368259,0.00014072994,0.000024771236,1.4724415e-8,0.00012777752,0.00367771,0.9278629,0.0005535635,0.009434212,0.0042907647],"study_design_scores_gemma":[0.0007363332,0.00011552605,0.11807799,0.000033755518,0.000036564532,0.0000039352894,0.00026137618,0.026734892,0.76868695,0.00005446499,0.08493504,0.0003231847],"about_ca_topic_score_codex":0.0000019000379,"about_ca_topic_score_gemma":0.0000034210987,"teacher_disagreement_score":0.5934404,"about_ca_system_score_codex":0.000011079515,"about_ca_system_score_gemma":0.00009496847,"threshold_uncertainty_score":0.42740142},"labels":[],"label_agreement":null},{"id":"W2055553856","doi":"10.1186/1471-2105-8-190","title":"Can Clustal-style progressive pairwise alignment of multiple sequences be used in RNA secondary structure prediction?","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multiple sequence alignment; Pairwise comparison; Protein secondary structure; Alignment-free sequence analysis; Structural alignment; Sequence alignment; Nucleic acid secondary structure; Nucleic acid structure; Sequence (biology); RNA; Computational biology; Conserved sequence; Computer science; Biology; Set (abstract data type); Consensus sequence; Phylogenetic tree; Bioinformatics; Genetics; Artificial intelligence; Peptide sequence; Gene; Biochemistry","score_opus":0.012431726598055248,"score_gpt":0.23945063842861142,"score_spread":0.22701891183055617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055553856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848555,0.0002931416,0.012749104,0.00006323011,0.00017581013,0.00070423645,0.00047505926,0.000019054145,0.00066491356],"genre_scores_gemma":[0.9576872,0.000025248013,0.041776024,0.000122066005,0.000066866814,0.00001765815,0.00021870137,0.000013570523,0.00007265597],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987664,0.000037391124,0.0005273375,0.0001502598,0.00024265639,0.00027590478],"domain_scores_gemma":[0.99924624,0.000034516965,0.0002712418,0.00029834837,0.00006288219,0.0000867733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038032437,0.00016894595,0.00018334706,0.000082752624,0.000054718817,0.000017567107,0.00019160662,0.00022448093,0.000043237946],"category_scores_gemma":[0.000095678246,0.0001451693,0.0000732609,0.000109554225,0.00009264342,0.000013140806,0.00008331236,0.000090602894,0.0000011368088],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042015497,0.00019491267,0.0518519,0.00087171356,0.000145025,0.000013929711,0.0042839665,0.0010692937,0.91873586,0.00029133528,0.00088920834,0.021232724],"study_design_scores_gemma":[0.0009730605,0.0003394597,0.00356383,0.00006572799,0.00001567635,0.000016541018,0.0027700802,0.0029663239,0.98740447,0.00018476584,0.0014839263,0.00021611345],"about_ca_topic_score_codex":0.000035419165,"about_ca_topic_score_gemma":0.000546521,"teacher_disagreement_score":0.068668656,"about_ca_system_score_codex":0.00003216345,"about_ca_system_score_gemma":0.00016795048,"threshold_uncertainty_score":0.5919832},"labels":[],"label_agreement":null},{"id":"W2056439952","doi":"10.1186/1471-2105-12-s9-s21","title":"Consistency-based detection of potential tumor-specific deletions in matched normal/tumor genomes","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"BC Cancer Agency; Natural Sciences and Engineering Research Council of Canada; Canada's Michael Smith Genome Sciences Centre","keywords":"Genome; Computational biology; Biology; Context (archaeology); Genetics; Cancer; Human genome; Consistency (knowledge bases); Computer science; Gene; Artificial intelligence","score_opus":0.015862311996866645,"score_gpt":0.20891035486141976,"score_spread":0.19304804286455313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056439952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8369711,0.00082086056,0.15854312,0.000011571695,0.00033964906,0.00036472507,0.00012339331,0.000018292265,0.002807259],"genre_scores_gemma":[0.9521609,0.0001495133,0.04733984,0.00015578445,0.000058230293,0.00002354063,0.00007818919,0.00001672649,0.000017278791],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99899596,0.000019100873,0.0005199738,0.00013232141,0.00010862434,0.0002240271],"domain_scores_gemma":[0.9992459,0.00001600005,0.0002207381,0.00034021435,0.00010866039,0.00006849915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014678747,0.00014567786,0.00017879499,0.000120602075,0.000052440108,0.000015899752,0.0001628752,0.00008651304,0.00003845541],"category_scores_gemma":[0.000042749434,0.00015163126,0.000111780646,0.00013523901,0.000112442285,0.000007816912,0.00006642271,0.000075312164,0.000019553623],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002655436,0.002167821,0.10011197,0.0019998814,0.00033429495,0.00006742549,0.0036227363,0.023122337,0.83531016,0.003357234,0.0026540316,0.024596691],"study_design_scores_gemma":[0.0045063687,0.0011477715,0.07087411,0.00008499898,0.00010434219,0.00011060967,0.0023610608,0.060891114,0.84436065,0.00042350797,0.014090048,0.0010454038],"about_ca_topic_score_codex":0.000061171144,"about_ca_topic_score_gemma":0.00034944125,"teacher_disagreement_score":0.115189776,"about_ca_system_score_codex":0.000029537265,"about_ca_system_score_gemma":0.00021677779,"threshold_uncertainty_score":0.6183343},"labels":[],"label_agreement":null},{"id":"W2057271915","doi":"10.1186/1471-2105-10-s8-s8","title":"Correlating protein function and stability through the analysis of single amino acid substitutions","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Mutation; Function (biology); Stability (learning theory); Genetics; Protein structure; Computational biology; Biology; Amino acid; Protein stability; Gene; Biochemistry; Computer science","score_opus":0.015728237680591565,"score_gpt":0.23258057050350625,"score_spread":0.2168523328229147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057271915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.585692,0.00022705922,0.41261944,0.000029896635,0.000027513563,0.00022087054,0.000025729822,0.0000088714505,0.0011486245],"genre_scores_gemma":[0.96866447,0.000008757215,0.031068463,0.00009762241,0.000021820388,0.0000051172656,0.00011601048,0.0000025131153,0.0000152210805],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993869,0.000023600773,0.00028166987,0.00009348076,0.00009928365,0.00011505259],"domain_scores_gemma":[0.9994284,0.00001083378,0.00016386734,0.0003054616,0.00006789147,0.000023540042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012877761,0.00009324914,0.00012798232,0.00003156996,0.000112641734,0.0000210803,0.00008530046,0.00010006739,0.000004802465],"category_scores_gemma":[0.00011079085,0.00006535538,0.00008199175,0.00025879976,0.00012054303,0.000014236711,0.000038808725,0.000062315994,6.38995e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035840177,0.0002704285,0.028808327,0.00028519123,0.00090045406,3.5439453e-7,0.002563179,0.007493585,0.90069616,0.027839009,0.00012387545,0.03066104],"study_design_scores_gemma":[0.002173624,0.0024122233,0.26860407,0.00008918908,0.002967419,0.000027552254,0.0047724918,0.3761437,0.32123774,0.017018223,0.003360692,0.001193092],"about_ca_topic_score_codex":0.000009127721,"about_ca_topic_score_gemma":0.00007103261,"teacher_disagreement_score":0.5794584,"about_ca_system_score_codex":0.000009727674,"about_ca_system_score_gemma":0.000036344372,"threshold_uncertainty_score":0.2665115},"labels":[],"label_agreement":null},{"id":"W2057279785","doi":"10.1186/1471-2105-9-s6-s12","title":"Genetic weighted k-means algorithm for clustering large-scale gene expression data","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Crossover; Computer science; Algorithm; Genetic algorithm; DNA microarray; Maxima and minima; Expression (computer science); Data mining; Gene; Computational biology; Gene expression; Mathematics; Artificial intelligence; Biology; Genetics; Machine learning","score_opus":0.03591019692004375,"score_gpt":0.27260320421340745,"score_spread":0.2366930072933637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057279785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010123509,0.0003440284,0.9880349,0.000024630326,0.00028098706,0.00038642518,0.0003309544,0.000035697776,0.0004388353],"genre_scores_gemma":[0.006680548,0.00048342953,0.9891907,0.0002626869,0.00040933347,0.00007360474,0.002041445,0.000033120727,0.00082512764],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876916,0.000025108871,0.0004014779,0.000307727,0.0001867656,0.00030978108],"domain_scores_gemma":[0.99850404,0.000011425069,0.00017318873,0.0010950504,0.0000970343,0.00011928416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015274085,0.00018001779,0.00014924724,0.000060286464,0.00024634553,0.000027480733,0.0005210932,0.00018144447,0.00001894029],"category_scores_gemma":[0.000029064415,0.00016073351,0.00007345686,0.00009765582,0.00004871772,0.000020020167,0.000368056,0.00006411471,0.000020442438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033724745,0.00057720154,0.0052927635,0.00059351465,0.00012550468,0.0000040656214,0.002051094,0.0023304722,0.62455374,0.000015987634,0.23618476,0.12793367],"study_design_scores_gemma":[0.0011304464,0.000092311435,0.00090657966,0.000022416005,0.00001685835,0.000039155282,0.00023786857,0.78017414,0.08677321,0.000011911291,0.13033411,0.00026101802],"about_ca_topic_score_codex":0.0000015738855,"about_ca_topic_score_gemma":0.000013798238,"teacher_disagreement_score":0.77784365,"about_ca_system_score_codex":0.000014949471,"about_ca_system_score_gemma":0.0001280663,"threshold_uncertainty_score":0.65545225},"labels":[],"label_agreement":null},{"id":"W2060064237","doi":"10.1186/1471-2105-12-139","title":"PeakRanger: A cloud-enabled peak caller for ChIP-seq data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":168,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Science Foundation","keywords":"Computer science; Cloud computing; Chromatin immunoprecipitation; Massively parallel; Software; Chip; Parallel computing; Multi-core processor; Data mining; Biology; Operating system","score_opus":0.05121050092748334,"score_gpt":0.2519177744359786,"score_spread":0.2007072735084953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060064237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37420952,0.0007147794,0.5858392,0.0000919933,0.001395662,0.0018461673,0.0016542646,0.00011157394,0.034136806],"genre_scores_gemma":[0.14872679,0.00035131976,0.84089196,0.0008003992,0.0007748466,0.00009349768,0.005704694,0.00010723729,0.0025492716],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998821,0.000015731845,0.00043506018,0.0002485232,0.000114765295,0.00036489384],"domain_scores_gemma":[0.9983308,0.000014391215,0.00018702888,0.0012578869,0.00009494361,0.00011498468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031552327,0.00021291689,0.00019083887,0.000040012204,0.0001173994,0.000043893542,0.00081337796,0.00019548608,0.00003899213],"category_scores_gemma":[0.00010328086,0.00019305533,0.00010506895,0.000061645995,0.00006458774,0.000014004506,0.0004883462,0.00007606987,0.000047866237],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004211164,0.0034739918,0.026549138,0.009951691,0.0034238724,0.000021651116,0.021384899,0.0021037175,0.11394055,0.028697798,0.7253834,0.060858097],"study_design_scores_gemma":[0.0047830003,0.0010517731,0.0053483425,0.00006826566,0.0002633137,0.00008836889,0.0022015665,0.6786373,0.007935799,0.0015320434,0.29637852,0.0017116609],"about_ca_topic_score_codex":0.000015748918,"about_ca_topic_score_gemma":0.00012547013,"teacher_disagreement_score":0.67653364,"about_ca_system_score_codex":0.000013463002,"about_ca_system_score_gemma":0.00014706932,"threshold_uncertainty_score":0.7872568},"labels":[],"label_agreement":null},{"id":"W2062584460","doi":"10.1186/s12859-014-0396-9","title":"Pathomx: an interactive workflow-based tool for the analysis of metabolomic data","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Research Council Canada; National Institute for Health and Care Research; Wellcome Trust","keywords":"Workflow; Computer science; Toolbox; Visualization; Scripting language; Plug-in; Software; Data visualization; Python (programming language); Software engineering; Metabolomics; Data integration; Data mining; Database; Data science; Bioinformatics; Programming language","score_opus":0.031130060562930013,"score_gpt":0.2978217137669514,"score_spread":0.2666916532040214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062584460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09815572,0.00038117447,0.9000464,0.000078229205,0.00018184909,0.00035095535,0.00059676124,0.000010252509,0.00019862963],"genre_scores_gemma":[0.7039552,0.00017648983,0.29331052,0.00041782134,0.00015074128,0.000044621345,0.0018624717,0.000017872033,0.00006430487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904,0.00004921365,0.00040357572,0.00019649821,0.00012159357,0.00018909921],"domain_scores_gemma":[0.9980979,0.00019924618,0.00028219822,0.0012566566,0.00012786563,0.000036116176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000797923,0.00014877657,0.00032707033,0.00012296678,0.00009140109,0.000034724508,0.00062408694,0.00007629285,0.00001129576],"category_scores_gemma":[0.00057279656,0.00009865271,0.0001821869,0.00029701885,0.00008378568,0.000015324807,0.00022415558,0.00005536993,0.0000016872359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065703653,0.00242621,0.07752022,0.001811796,0.04218814,7.4952567e-7,0.0038341053,0.108156815,0.18921468,0.024417853,0.028701609,0.51515746],"study_design_scores_gemma":[0.00069660647,0.0002094618,0.010002532,0.0000052759824,0.0017723294,4.608942e-7,0.0003880165,0.943197,0.009674737,0.00007730915,0.033762176,0.00021407622],"about_ca_topic_score_codex":0.000007731021,"about_ca_topic_score_gemma":0.000112665446,"teacher_disagreement_score":0.8350402,"about_ca_system_score_codex":0.000005653473,"about_ca_system_score_gemma":0.00005506483,"threshold_uncertainty_score":0.40229407},"labels":[],"label_agreement":null},{"id":"W2063430651","doi":"10.1186/1471-2105-8-270","title":"Recognizing protein–protein interfaces with empirical potentials and reduced amino acid alphabets","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"European Commission","keywords":"Decoy; Statistical potential; Parameterized complexity; Computer science; Protein structure; Computational biology; Protein structure prediction; Amino acid; Hierarchy; Biological system; Theoretical computer science; Bioinformatics; Algorithm; Biology; Biochemistry","score_opus":0.015598047749565039,"score_gpt":0.2640748466565687,"score_spread":0.2484767989070037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063430651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8524306,0.0003615513,0.145347,0.00005015382,0.000052512252,0.00059007533,0.000013874398,0.000032959495,0.0011213078],"genre_scores_gemma":[0.76532626,0.000014266455,0.2340455,0.00017647533,0.00010281304,0.000018853036,0.0000655592,0.00002231995,0.00022793675],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987134,0.000026630705,0.00043251467,0.00023946907,0.0001965944,0.00039142458],"domain_scores_gemma":[0.99919605,0.000009488415,0.00021129053,0.00033942497,0.00009645638,0.00014727311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003715993,0.0002503426,0.00021166443,0.00007504607,0.000119806245,0.00007805491,0.00018674915,0.0002534805,0.000006513369],"category_scores_gemma":[0.000108587985,0.00019391027,0.000049061,0.00011892728,0.00015107536,0.000022876036,0.00016821825,0.00015251728,0.000010333304],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005276963,0.00004442843,0.0019354798,0.00026787582,0.00009773296,0.000006057734,0.00038610137,0.00001833161,0.9611907,0.0000946811,0.00030858,0.035122346],"study_design_scores_gemma":[0.000888856,0.0006783321,0.0019810302,0.000100143836,0.00003235718,0.00011774547,0.00061338174,0.0013575238,0.9910463,0.00017190848,0.0025618374,0.00045059336],"about_ca_topic_score_codex":0.000005995249,"about_ca_topic_score_gemma":0.0000962809,"teacher_disagreement_score":0.088698514,"about_ca_system_score_codex":0.00001628102,"about_ca_system_score_gemma":0.00008744452,"threshold_uncertainty_score":0.7907431},"labels":[],"label_agreement":null},{"id":"W2064299963","doi":"10.1186/1471-2105-8-s10-s2","title":"Prediction of tissue-specific cis-regulatory modules using Bayesian networks and regression trees","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Transcription factor; Gene regulatory network; Computational biology; Regression; Bayesian network; Biology; DNA binding site; DNA microarray; Bayesian probability; Gene expression; Gene; Computer science; Tree (set theory); Data mining; Artificial intelligence; Genetics; Mathematics; Promoter; Statistics","score_opus":0.01523708875916004,"score_gpt":0.2288783935614113,"score_spread":0.21364130480225124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064299963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5251268,0.00054629735,0.4739133,0.0000017368061,0.0000965075,0.000092053044,0.00001631033,0.000007137743,0.00019981033],"genre_scores_gemma":[0.89868367,0.00030608018,0.10069172,0.000015107639,0.00013291095,9.974661e-7,0.00011847688,0.000016232467,0.00003478739],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991594,0.00001159302,0.00041341677,0.000117109455,0.00011252622,0.0001859617],"domain_scores_gemma":[0.9993633,0.000011029782,0.00021553392,0.00028380853,0.000054180204,0.000072115145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002621491,0.00013478668,0.00013908632,0.00005944381,0.00007782814,0.000019373208,0.000097132186,0.00019835438,0.0000034223872],"category_scores_gemma":[0.000010996656,0.00012017088,0.000043269854,0.000066530665,0.000095395495,0.00000885089,0.0000884627,0.000057263154,4.867727e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049187226,0.00024621142,0.050772548,0.0008991141,0.00017516222,0.0000039145434,0.0011987576,0.115172304,0.7085572,0.0018262356,0.0022881432,0.11836852],"study_design_scores_gemma":[0.000556137,0.00021291507,0.0325084,0.00008000303,0.000024320754,0.000039975563,0.00056121347,0.9359161,0.027890496,0.00009660851,0.0019020864,0.00021170829],"about_ca_topic_score_codex":0.0000030623742,"about_ca_topic_score_gemma":0.000024692306,"teacher_disagreement_score":0.82074386,"about_ca_system_score_codex":0.00001603976,"about_ca_system_score_gemma":0.000022799664,"threshold_uncertainty_score":0.49004263},"labels":[],"label_agreement":null},{"id":"W2064828432","doi":"10.1186/1471-2105-15-260","title":"Gene set enrichment analysis for multiple continuous phenotypes","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Department of Science and Technology, Ministry of Science and Technology, India; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Phenotype; Categorical variable; Gene; DNA microarray; Computational biology; Set (abstract data type); Genetics; Biology; Microarray; Continuous variable; Microarray analysis techniques; Computer science; Gene expression; Mathematics; Statistics; Machine learning","score_opus":0.01972766746154005,"score_gpt":0.2610992394118885,"score_spread":0.24137157195034845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064828432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053541113,0.0001100488,0.944714,0.00004318724,0.00013311283,0.00025733327,0.00007796457,0.000019998433,0.0011032092],"genre_scores_gemma":[0.89725673,0.00004318843,0.10029744,0.000396888,0.00016597852,0.000084953266,0.001001394,0.000011594977,0.00074180594],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929917,0.000021609565,0.00026376304,0.0001453924,0.00010360858,0.00016645744],"domain_scores_gemma":[0.99930185,0.000022403618,0.00014849483,0.0003658854,0.000093641705,0.000067703266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019345692,0.000110486784,0.00014513289,0.00007432005,0.00007590586,0.00003203211,0.00014857609,0.00009694551,0.000012265002],"category_scores_gemma":[0.00011601551,0.000095090894,0.0001432895,0.0001421441,0.000024443374,0.000004278304,0.000044171273,0.000026642232,0.000011397447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009169857,0.00047331664,0.19126447,0.00072507525,0.0020631037,2.0319374e-7,0.0016857287,0.03717915,0.5441938,0.0021366328,0.1241151,0.09524643],"study_design_scores_gemma":[0.0019051046,0.0003322413,0.012638789,0.000008001842,0.00033124827,0.0000018236616,0.00043769038,0.37832654,0.23816289,0.00010573063,0.36729807,0.0004518619],"about_ca_topic_score_codex":0.0000032173616,"about_ca_topic_score_gemma":0.000021206344,"teacher_disagreement_score":0.84441656,"about_ca_system_score_codex":0.000010532836,"about_ca_system_score_gemma":0.000034586352,"threshold_uncertainty_score":0.38776943},"labels":[],"label_agreement":null},{"id":"W2065925372","doi":"10.1186/1471-2105-15-170","title":"Ensemble analyses improve signatures of tumour hypoxia and reveal inter-platform differences","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer, Hypoxia, and Metabolism","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Center for Translational Molecular Medicine; Government of Ontario","keywords":"DNA microarray; Biomarker discovery; Computer science; Limiting; Biomarker; Transcriptome; Computational biology; Data mining; Bioinformatics; Artificial intelligence; Pattern recognition (psychology); Machine learning; Biology; Proteomics; Gene; Gene expression; Genetics","score_opus":0.02264884552033729,"score_gpt":0.2699888478312685,"score_spread":0.24734000231093117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065925372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95755786,0.0018793982,0.036657266,0.000017345903,0.00063051214,0.00020988114,0.000052749387,0.000016850769,0.0029781105],"genre_scores_gemma":[0.9799419,0.00039549524,0.018572895,0.00014968308,0.00045355372,0.00000821529,0.00004701495,0.000011836491,0.0004194104],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991223,0.000019837067,0.00037167655,0.00014435813,0.0001317749,0.00021005094],"domain_scores_gemma":[0.9993054,0.00003214791,0.00022214671,0.00026732893,0.000083718485,0.000089246205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017915273,0.00017243439,0.00027536464,0.000066985864,0.000052024683,0.000032937613,0.0001729972,0.00012983743,0.0000061574337],"category_scores_gemma":[0.00014550186,0.00013407161,0.000098871686,0.00006715475,0.0001144609,0.0000142696945,0.00012495677,0.00008818004,0.00000319754],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013130253,0.000053006857,0.0016685737,0.00048220207,0.00010188057,9.949504e-8,0.00041355813,0.00003895141,0.9529604,0.00045943458,0.0044755326,0.039215058],"study_design_scores_gemma":[0.0030563478,0.0013988734,0.050555933,0.00015495162,0.00034499072,0.000039499,0.0018184119,0.028154658,0.8491936,0.0013301319,0.06281368,0.0011389593],"about_ca_topic_score_codex":0.00003513212,"about_ca_topic_score_gemma":0.000099448116,"teacher_disagreement_score":0.10376683,"about_ca_system_score_codex":0.000004567378,"about_ca_system_score_gemma":0.000056642788,"threshold_uncertainty_score":0.54672813},"labels":[],"label_agreement":null},{"id":"W2065928355","doi":"10.1186/1471-2105-15-278","title":"Equivalent input produces different output in the UniFrac significance test","year":2014,"lang":"en","type":"letter","venue":"BMC Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Contango Strategies (Canada); University of Saskatchewan","funders":"Western Economic Diversification Canada; Genome Prairie","keywords":"UniFrac; Consistency (knowledge bases); Tree (set theory); Computer science; Statistical hypothesis testing; Statistics; Biology; Mathematics; Artificial intelligence; Genetics","score_opus":0.03544347977958179,"score_gpt":0.2396278816646724,"score_spread":0.2041844018850906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065928355","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10213683,0.00015326796,0.0046399357,0.76889706,0.0026006622,0.006934752,0.0003612275,0.00031591207,0.11396035],"genre_scores_gemma":[0.06154861,0.000087743,0.0029572367,0.93021387,0.0010000826,0.00015479804,0.0010102461,0.000045801415,0.0029816143],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979484,0.0004496814,0.0005845854,0.00021816646,0.00027404167,0.00052513456],"domain_scores_gemma":[0.9974156,0.0011378167,0.00036801092,0.0010373364,0.000009051856,0.000032195465],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000611932,0.00035618944,0.00040334277,0.000065111744,0.00021169546,0.000055029264,0.0015930317,0.0005928519,0.0007507238],"category_scores_gemma":[0.00018547394,0.00022837687,0.00010345024,0.00017396633,0.00048426288,0.00012234674,0.0004917164,0.0020485464,0.001480086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054658144,0.00008314004,0.005554222,0.00024710727,0.000006409393,0.000004310843,0.0013900899,0.00026231795,0.000025841855,0.000010854118,0.9918879,0.00052232685],"study_design_scores_gemma":[0.00022834045,0.00021705736,0.017962426,0.00005789508,0.000029189378,0.000019753637,0.00015076766,0.0036102093,0.000037375677,0.0005655358,0.97668827,0.0004332066],"about_ca_topic_score_codex":0.00011834436,"about_ca_topic_score_gemma":0.00091224146,"teacher_disagreement_score":0.1613168,"about_ca_system_score_codex":0.00014032895,"about_ca_system_score_gemma":0.000032267613,"threshold_uncertainty_score":0.9992974},"labels":[],"label_agreement":null},{"id":"W2066656905","doi":"10.1186/1471-2105-14-202","title":"MetaPathways: a modular pipeline for constructing pathway/genome databases from environmental sequence information","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; University of Alberta; Genome Canada; Tula Foundation; Western Canada Research Grid; Canadian Institute for Advanced Research","keywords":"KEGG; GenBank; Pipeline (software); Computer science; Annotation; Modular design; Computational biology; Database; Biology; Artificial intelligence; Genetics; Gene; Transcriptome; Programming language","score_opus":0.019750814503093676,"score_gpt":0.21109957472463892,"score_spread":0.19134876022154523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066656905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50453025,0.000226433,0.4928894,0.000020291513,0.0002741271,0.000565174,0.0013650036,0.00004010102,0.00008923493],"genre_scores_gemma":[0.49715707,0.00012898227,0.49305606,0.00025862738,0.0004893832,0.00009737247,0.008687139,0.000021068763,0.00010428737],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906504,0.000013239419,0.00043771986,0.00014639377,0.00010895224,0.00022867648],"domain_scores_gemma":[0.99933213,0.000008462292,0.0001805921,0.00035526315,0.000050232175,0.00007332746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014799024,0.00018046286,0.00015613153,0.000052584168,0.00007912604,0.00005926835,0.00014436278,0.00009165412,0.000035535813],"category_scores_gemma":[0.00014390353,0.00016433079,0.00008045109,0.000053001248,0.000059054637,0.000087984576,0.00008343351,0.00006488142,0.00008720883],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015302312,0.000017433511,0.00010717571,0.000081676655,0.000027502312,4.5099167e-8,0.0001425367,0.00099094,0.98220265,0.0000551244,0.00034574448,0.016013846],"study_design_scores_gemma":[0.0012463564,0.00012420146,0.0005574622,0.00003573301,0.00006478959,0.00004483153,0.0018042199,0.13620348,0.67789835,0.000060774186,0.18128408,0.0006756891],"about_ca_topic_score_codex":0.000042984913,"about_ca_topic_score_gemma":0.000003862625,"teacher_disagreement_score":0.3043043,"about_ca_system_score_codex":0.000018831437,"about_ca_system_score_gemma":0.00004377905,"threshold_uncertainty_score":0.6701215},"labels":[],"label_agreement":null},{"id":"W2067516565","doi":"10.1186/1471-2105-11-25","title":"Calibur: a tool for clustering large numbers of protein decoys","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Decoy; Cluster analysis; Bottleneck; Engineering; Artificial intelligence; Data mining; Computer science","score_opus":0.0061356032309906995,"score_gpt":0.24359543162986375,"score_spread":0.23745982839887306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067516565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38799375,0.000024361663,0.6100796,0.0000128343345,0.00015912077,0.0006404668,0.00014629551,0.00001464196,0.0009289051],"genre_scores_gemma":[0.44334498,0.000004920302,0.5557595,0.00013406806,0.00014296678,0.000076730954,0.00020076736,0.00002130383,0.00031476474],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923795,0.0000069102225,0.00032552466,0.000102593316,0.00009316686,0.00023382802],"domain_scores_gemma":[0.9993555,0.000010062521,0.00015405267,0.0003470648,0.00008364117,0.00004967498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019549172,0.00012540375,0.0001375964,0.000029230087,0.000055957873,0.000018615534,0.00018680883,0.00020588555,0.000009779759],"category_scores_gemma":[0.00016452039,0.000111863534,0.000106779735,0.000049015944,0.000047600788,0.000008505038,0.00011230872,0.00008819487,0.00000328708],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068908854,0.00019175271,0.009643976,0.0031550326,0.0001959245,0.0000011546176,0.0008167201,0.0007089664,0.9485918,0.012169339,0.0024859402,0.021350296],"study_design_scores_gemma":[0.0049920566,0.00082568167,0.0014267213,0.00009754288,0.00008321278,0.00007603078,0.00046278257,0.39560524,0.4470903,0.0020403552,0.14612938,0.0011707193],"about_ca_topic_score_codex":0.0000048583497,"about_ca_topic_score_gemma":0.0002388461,"teacher_disagreement_score":0.5015015,"about_ca_system_score_codex":0.0000046406985,"about_ca_system_score_gemma":0.00009184553,"threshold_uncertainty_score":0.45616627},"labels":[],"label_agreement":null},{"id":"W2068856084","doi":"10.1186/1471-2105-11-s1-s40","title":"New decoding algorithms for Hidden Markov Models using distance measures on labellings","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Decoding methods; Markov chain; Markov model; Hidden Markov model; Algorithm; Theoretical computer science; Artificial intelligence; Machine learning","score_opus":0.060008494598102875,"score_gpt":0.29085506612591827,"score_spread":0.2308465715278154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068856084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099288665,0.00007498852,0.8988376,0.00002975831,0.0003223301,0.00023856052,0.00002402794,0.000028249096,0.0011557875],"genre_scores_gemma":[0.16230279,0.00002485315,0.83658016,0.0002870962,0.00045874063,0.000005003578,0.00006581133,0.000016555437,0.00025901035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905163,0.000011583108,0.0003091897,0.00018772998,0.00013048941,0.00030936915],"domain_scores_gemma":[0.9993609,0.000044815322,0.00014090333,0.00025447714,0.000083564286,0.00011534619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002775153,0.00017740575,0.00015378998,0.000031195526,0.00015490338,0.000069574315,0.00025090654,0.0002128983,0.0000048477996],"category_scores_gemma":[0.00012588043,0.00013904316,0.00011427271,0.00006576696,0.00003904657,0.000011241611,0.0000863051,0.00013319527,0.000004005883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065052474,0.00016847905,0.0031581589,0.00042038338,0.00015361191,0.0000019162037,0.00044437833,0.008976023,0.27510324,0.007735134,0.008275,0.69491315],"study_design_scores_gemma":[0.0006627914,0.00024678904,0.000040636656,0.00003882055,0.000022343072,0.000010478552,0.00007599011,0.9430539,0.03848505,0.0014884458,0.015497353,0.00037743014],"about_ca_topic_score_codex":0.0000066974826,"about_ca_topic_score_gemma":0.00002360374,"teacher_disagreement_score":0.93407786,"about_ca_system_score_codex":0.000010526626,"about_ca_system_score_gemma":0.00008202744,"threshold_uncertainty_score":0.5670015},"labels":[],"label_agreement":null},{"id":"W2068916031","doi":"10.1186/1471-2105-14-s3-s15","title":"Characterizing the state of the art in the computational assignment of gene function: lessons from the first critical assessment of functional annotation (CAFA)","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health; Michael Smith Health Research BC","keywords":"Annotation; Function (biology); Task (project management); Computer science; Similarity (geometry); Gene ontology; Field (mathematics); Sequence (biology); Gene Annotation; Computational biology; Artificial intelligence; Gene; Biology; Genetics; Genome; Image (mathematics); Mathematics","score_opus":0.0205252854573285,"score_gpt":0.25658317216549725,"score_spread":0.23605788670816874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068916031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40975177,0.00021042096,0.57884717,0.0074144574,0.0006263029,0.0012261288,0.00039521875,0.000005631673,0.0015228898],"genre_scores_gemma":[0.9915244,0.000023294013,0.0069500464,0.0011177481,0.00008235453,0.00004140762,0.00023242095,0.0000061428323,0.000022188566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9987097,0.00007559851,0.00065362395,0.00007568533,0.0003450963,0.00014033246],"domain_scores_gemma":[0.9987782,0.0002820404,0.0003928817,0.00036462484,0.00016382104,0.000018399081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052117667,0.000114989125,0.00013473,0.000018579762,0.00013682818,0.000037873844,0.0003207641,0.00006614401,0.000027569242],"category_scores_gemma":[0.000045356606,0.000054859465,0.00010711998,0.00012179049,0.00024633118,0.000021201215,0.00010655332,0.00014119406,0.000004229062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047233084,0.0013897613,0.06258242,0.0011707599,0.0011421568,5.327205e-7,0.017141337,0.74436647,0.04126971,0.026413549,0.0683393,0.0357117],"study_design_scores_gemma":[0.0005799141,0.00015840784,0.5688146,0.0000689461,0.000057791094,0.0000071543313,0.0020575803,0.42089438,0.0015551493,0.0024345436,0.0032333313,0.00013820568],"about_ca_topic_score_codex":0.000023639897,"about_ca_topic_score_gemma":0.00005312082,"teacher_disagreement_score":0.5817726,"about_ca_system_score_codex":0.000015167177,"about_ca_system_score_gemma":0.00013469381,"threshold_uncertainty_score":0.22371042},"labels":[],"label_agreement":null},{"id":"W2069716529","doi":"10.1186/1471-2105-14-s16-s6","title":"Random forests on Hadoop for genome-wide association studies of multivariate neuroimaging phenotypes","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; Genentech; National Institutes of Health; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Imperial College London; Northern California Institute for Research and Education; Synarc; Engineering and Physical Sciences Research Council; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National University of Singapore; Medpace; Pfizer; Biogen; AstraZeneca; Bristol-Myers Squibb; Eli Lilly and Company; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; Amorfix Life Sciences; Alzheimer's Drug Discovery Foundation; Foundation for the National Institutes of Health","keywords":"Multivariate statistics; Random forest; Computer science; Artificial intelligence; Neuroimaging; Genome-wide association study; Machine learning; Genetic architecture; Genetic association; Quantitative trait locus; Population; Data mining; Computational biology; Biology; Single-nucleotide polymorphism; Genetics; Gene; Genotype","score_opus":0.02956429377384484,"score_gpt":0.29190146679685874,"score_spread":0.2623371730230139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069716529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8143353,0.0004270603,0.18163775,0.0009218225,0.00038598338,0.0012480373,0.00008670961,0.000024984878,0.0009323623],"genre_scores_gemma":[0.870077,0.00020805521,0.12635207,0.0016034038,0.00018500854,0.00018293508,0.00026870085,0.000028461187,0.0010943431],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99891895,0.0000633387,0.0005126183,0.0001321662,0.000104431696,0.00026847873],"domain_scores_gemma":[0.9982021,0.00071717997,0.0004875051,0.00021604421,0.00033506195,0.000042130858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005089861,0.00014140883,0.00028079544,0.000050773742,0.00009593461,0.00001634982,0.00012741692,0.00013103629,0.0000056853282],"category_scores_gemma":[0.0052190176,0.00011877688,0.00012702555,0.00005788387,0.000038532664,0.000009329611,0.00006669037,0.0000542204,0.00001775874],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003307265,0.00023463968,0.87947667,0.00079658336,0.00082831807,1.5286543e-7,0.0017917383,0.04219806,0.01023654,0.00040236805,0.057958063,0.0057461597],"study_design_scores_gemma":[0.006646939,0.0009820368,0.8280545,0.00005865613,0.00018077194,0.0000016041184,0.001527821,0.13910553,0.0044223364,0.002755261,0.015620477,0.00064411724],"about_ca_topic_score_codex":0.000014474382,"about_ca_topic_score_gemma":0.000039687187,"teacher_disagreement_score":0.09690747,"about_ca_system_score_codex":0.000037607275,"about_ca_system_score_gemma":0.000047030026,"threshold_uncertainty_score":0.6248028},"labels":[],"label_agreement":null},{"id":"W2070040136","doi":"10.1186/1471-2105-12-436","title":"clusterMaker: a multi-algorithm clustering plugin for Cytoscape","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":669,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Cluster analysis; Computer science; Interactome; Plug-in; Hierarchical clustering; Computational biology; Visualization; Dendrogram; Data mining; Bioinformatics; Biology; Machine learning; Genetics","score_opus":0.03728483425002162,"score_gpt":0.24980731058751915,"score_spread":0.21252247633749755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070040136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018152697,0.00016954653,0.99327093,0.000010678661,0.0004263948,0.0006651672,0.00011054746,0.00004490454,0.0034865635],"genre_scores_gemma":[0.010309697,0.00007728738,0.9873353,0.00067227904,0.00027942675,0.00009183679,0.00031057448,0.000046084035,0.0008774645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854785,0.000015277488,0.00062972977,0.00018993835,0.000118872995,0.00049832655],"domain_scores_gemma":[0.99896085,0.000016125687,0.00024667257,0.0005156308,0.00010321955,0.00015750776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031575907,0.00027835977,0.00023262562,0.00007188199,0.00015667733,0.000055533943,0.00036222287,0.0002859443,0.000023043349],"category_scores_gemma":[0.000036664103,0.0002577765,0.00020147728,0.00008293785,0.00008335086,0.00002038381,0.00025736,0.000111064735,0.000054539523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017950274,0.0013246102,0.0047464566,0.004384513,0.0012854207,0.00001008569,0.019065361,0.006338171,0.0074846772,0.0021812427,0.066945,0.8844394],"study_design_scores_gemma":[0.0019688492,0.00031819954,0.00036868433,0.000033672142,0.000041168263,0.00005005617,0.0006320843,0.9635848,0.002402573,0.000104739265,0.030002112,0.0004931051],"about_ca_topic_score_codex":0.000006990816,"about_ca_topic_score_gemma":0.000067088986,"teacher_disagreement_score":0.9572466,"about_ca_system_score_codex":0.000020163814,"about_ca_system_score_gemma":0.000094393945,"threshold_uncertainty_score":0.9999874},"labels":[],"label_agreement":null},{"id":"W2070739680","doi":"10.1186/1471-2105-8-s10-s1","title":"NIPS workshop on New Problems and Methods in Computational Biology","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Computational genomics; Presentation (obstetrics); Data science; Session (web analytics); Computational model; Modelling biological systems; Inference; Field (mathematics); Annotation; Systems biology; Machine learning; Computational biology; Biology; Genomics; Genome; Gene; World Wide Web; Mathematics","score_opus":0.05067414694382884,"score_gpt":0.37165532817481045,"score_spread":0.3209811812309816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070739680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03644714,0.0004130801,0.95599896,0.00030882366,0.00021125008,0.00045036254,0.000015020588,0.000020935122,0.0061344183],"genre_scores_gemma":[0.033134155,0.00052579015,0.9640119,0.0010214363,0.00023314875,0.000008353335,0.00029651148,0.000021149324,0.0007475651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838454,0.000054091244,0.00065797934,0.00018981828,0.000221643,0.000491945],"domain_scores_gemma":[0.9990505,0.00020606848,0.00012931217,0.00025372053,0.000074933174,0.00028546836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014303651,0.00019455863,0.00020508461,0.00022782525,0.000064242864,0.00004539599,0.00023310928,0.00032529148,0.00001631211],"category_scores_gemma":[0.0005819734,0.00016182137,0.000059382783,0.00021870554,0.00022407262,0.000009243596,0.00019783028,0.00021680449,0.000033373886],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045592288,0.00030454306,0.019774383,0.0006567852,0.00010572343,0.0000031837776,0.0020227896,0.0039850036,0.007636056,0.0032582746,0.008018894,0.95377845],"study_design_scores_gemma":[0.011255585,0.0039320276,0.07082605,0.00051530957,0.000057456466,0.00015548224,0.005032532,0.45051658,0.020367727,0.01727002,0.41749758,0.0025736357],"about_ca_topic_score_codex":0.000012065375,"about_ca_topic_score_gemma":0.00012916472,"teacher_disagreement_score":0.9512048,"about_ca_system_score_codex":0.000025304793,"about_ca_system_score_gemma":0.00017237428,"threshold_uncertainty_score":0.65988845},"labels":[],"label_agreement":null},{"id":"W2070791418","doi":"10.1186/1471-2105-13-206","title":"CaPSID: A bioinformatics platform for computational pathogen sequence identification in human genomes and transcriptomes","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Genome; Capsid; Biology; Computational biology; Transcriptome; DNA sequencing; Proteome; Reference genome; Identification (biology); Gene; Genetics; Gene expression","score_opus":0.0399281561811749,"score_gpt":0.28162911583535716,"score_spread":0.24170095965418226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070791418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93427825,0.0016850232,0.06252609,0.000029523146,0.00014951128,0.0006411055,0.00031535045,0.000008040615,0.00036710795],"genre_scores_gemma":[0.8918506,0.00021960233,0.107065715,0.00013696241,0.000089320834,0.00007097074,0.0004924227,0.000015319383,0.000059066766],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99894655,0.0000096486,0.0005184123,0.00010744845,0.000109006054,0.0003089115],"domain_scores_gemma":[0.9994882,0.000027429525,0.00015980253,0.00017259092,0.000069749105,0.00008227783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034607694,0.00016569164,0.00016487866,0.000092097696,0.00014469982,0.00004516763,0.00012550145,0.000110323,0.0000019850188],"category_scores_gemma":[0.000030928863,0.00015817226,0.000061682615,0.00007554778,0.000089711815,0.000014969621,0.00005899019,0.000046850724,0.000003753112],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027095294,0.0005477197,0.2938586,0.003716156,0.0004774319,7.595883e-7,0.033971105,0.01571227,0.57901406,0.017617999,0.0025392906,0.05227368],"study_design_scores_gemma":[0.00915361,0.0012268001,0.43858856,0.00015045625,0.0002937689,0.00018793716,0.017725768,0.425913,0.033409156,0.007782119,0.062454987,0.0031138475],"about_ca_topic_score_codex":0.0000053189165,"about_ca_topic_score_gemma":0.00002907961,"teacher_disagreement_score":0.5456049,"about_ca_system_score_codex":0.000021975617,"about_ca_system_score_gemma":0.00005016804,"threshold_uncertainty_score":0.6450078},"labels":[],"label_agreement":null},{"id":"W2071286514","doi":"10.1186/1471-2105-8-208","title":"Seahawk: moving beyond HTML in Web-based bioinformatics analysis","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Genome Alberta; Dalhousie University; Genome Canada","keywords":"Computer science; World Wide Web; Web service; Data Web; Web modeling; Semantic Web; XML; XSLT; Web standards; Information retrieval","score_opus":0.07830484163187579,"score_gpt":0.35560889294768033,"score_spread":0.27730405131580455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071286514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061310675,0.000027943332,0.8944927,0.00013143275,0.0006746507,0.00030485258,0.000060957445,0.00014430819,0.0428525],"genre_scores_gemma":[0.33347756,0.0000037282048,0.6635927,0.0012392765,0.00007376156,0.0000055501964,0.00015447933,0.000015827298,0.0014371519],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937034,0.00007754473,0.0025779242,0.00039811173,0.0024854185,0.00075760315],"domain_scores_gemma":[0.99484044,0.0018900553,0.0007526929,0.0019773524,0.0002800634,0.00025936513],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018604236,0.00027206613,0.00051812653,0.0036874006,0.00025110724,0.0010959973,0.0016907539,0.00012679618,0.000270937],"category_scores_gemma":[0.002880299,0.00021193865,0.000318927,0.00894758,0.00014814704,0.0010442713,0.0005808484,0.00022712034,0.0010727013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009769457,0.0003467229,0.3100862,0.00021750887,0.00019843224,0.000027392996,0.0073040985,0.28396782,0.000010690375,0.003774877,0.055153996,0.33881456],"study_design_scores_gemma":[0.00062300614,0.000025823401,0.026515497,0.00002040185,0.00007080579,0.0000017213106,0.0050990176,0.95162815,0.000033682925,0.0004950489,0.015211664,0.00027515297],"about_ca_topic_score_codex":0.00003559783,"about_ca_topic_score_gemma":0.0014469625,"teacher_disagreement_score":0.66766036,"about_ca_system_score_codex":0.00013647864,"about_ca_system_score_gemma":0.00021974584,"threshold_uncertainty_score":0.99994093},"labels":[],"label_agreement":null},{"id":"W2074131187","doi":"10.1186/1471-2105-15-78","title":"ShatterProof: operational detection and quantification of chromothripsis","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Domtar (Canada); University Health Network; University of British Columbia; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Government of Ontario; Ontario Institute for Cancer Research; Movember Foundation","keywords":"Chromothripsis; Computer science; Computational biology; Biology; Genetics; Genome instability","score_opus":0.009942496063046542,"score_gpt":0.2124061246202045,"score_spread":0.20246362855715797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074131187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5597387,0.00004941056,0.4388839,0.000034729714,0.00006815065,0.00009383568,0.000017432321,0.0000067737888,0.001107051],"genre_scores_gemma":[0.9742954,0.00002256469,0.025348078,0.00006694413,0.000061882456,0.000008306827,0.00007929717,0.0000049083365,0.00011262505],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99955165,0.000018044802,0.00022391629,0.000071765025,0.0000639315,0.000070680784],"domain_scores_gemma":[0.9996648,0.000008898163,0.00009284313,0.00014653736,0.00006219977,0.000024708608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014488495,0.000063837295,0.00006844041,0.000031092208,0.00006303975,0.000022184966,0.000054341857,0.000062800624,0.000011731265],"category_scores_gemma":[0.00004329708,0.000059135535,0.000026209651,0.000035327874,0.000042759944,0.0000099175595,0.00003314116,0.000021759262,0.0000063614616],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016936488,0.00022194619,0.05497607,0.0011656247,0.0001560012,8.7471555e-8,0.0019848736,0.006710085,0.84541,0.020273363,0.0009019914,0.068030626],"study_design_scores_gemma":[0.0010108897,0.0005856708,0.06340389,0.000032557422,0.000044964527,0.000047091235,0.0007265722,0.33272845,0.5831323,0.00042302322,0.017468996,0.00039555857],"about_ca_topic_score_codex":0.000008765967,"about_ca_topic_score_gemma":0.000030498557,"teacher_disagreement_score":0.41455668,"about_ca_system_score_codex":0.0000045097545,"about_ca_system_score_gemma":0.000025539048,"threshold_uncertainty_score":0.24114771},"labels":[],"label_agreement":null},{"id":"W2074656136","doi":"10.1186/1471-2105-7-s4-s13","title":"Determination of the minimum number of microarray experiments for discovery of gene expression patterns","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Cluster analysis; Expression (computer science); False discovery rate; Data mining; Microarray analysis techniques; Function (biology); Set (abstract data type); Similarity (geometry); Gene chip analysis; Computational biology; Interval (graph theory); Gene expression profiling; Microarray; Computer science; Hierarchical clustering; Microarray databases; Gene expression; Biology; Gene; Artificial intelligence; Mathematics; Genetics","score_opus":0.015086703780507608,"score_gpt":0.27456269834544395,"score_spread":0.25947599456493636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074656136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71092653,0.000051895015,0.28818458,0.0000064244887,0.00011405545,0.00021997135,0.00009220134,0.0000016108414,0.00040271867],"genre_scores_gemma":[0.94617957,0.000012115809,0.05327419,0.00001522092,0.000036482896,0.0000252593,0.00010934321,0.000007407643,0.0003404095],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931425,0.000017469249,0.0003967033,0.0000745407,0.00011989212,0.00007714698],"domain_scores_gemma":[0.99914783,0.000010105221,0.00044031887,0.00029726772,0.00009325797,0.000011245931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006947304,0.00007522582,0.000102919716,0.000021777945,0.000023499075,0.0000052782684,0.0001561049,0.000082517516,0.000003963156],"category_scores_gemma":[0.000020562284,0.00005312794,0.00010315226,0.000044479486,0.00004776706,0.000010431693,0.000045753917,0.00001658375,2.8743622e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004482732,0.00005884797,0.011627424,0.00018336921,0.0000034540483,3.6049108e-9,0.00010529496,0.000027571909,0.9869543,0.000028833141,0.0005796267,0.00038647096],"study_design_scores_gemma":[0.00045529744,0.00003881018,0.0053439224,0.000056551664,0.00000991758,9.221765e-7,0.00025106256,0.0010164093,0.99229735,0.000035701054,0.00043418005,0.00005988579],"about_ca_topic_score_codex":0.0000057364928,"about_ca_topic_score_gemma":0.000003521042,"teacher_disagreement_score":0.23525304,"about_ca_system_score_codex":0.0000065738527,"about_ca_system_score_gemma":0.000047021622,"threshold_uncertainty_score":0.21664946},"labels":[],"label_agreement":null},{"id":"W2074909362","doi":"10.1186/1471-2105-12-303","title":"Prototype semantic infrastructure for automated small molecule classification and annotation in lipidomics","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation; Canarie","keywords":"Ontology; Computer science; Annotation; Service (business); Information retrieval; Semantic Web; Web service; World Wide Web; Lipidomics; Bioinformatics; Artificial intelligence; Biology","score_opus":0.04138146981705494,"score_gpt":0.2698668574848378,"score_spread":0.22848538766778287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074909362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84155685,0.00012686434,0.15631483,0.000048424958,0.00013354409,0.0010340032,0.000024393405,0.00010474362,0.00065636844],"genre_scores_gemma":[0.52756685,0.000062007646,0.47174633,0.00016654517,0.00005018937,0.00012934828,0.00022287549,0.000015460902,0.000040390616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938214,0.000018009612,0.00026845236,0.0001231865,0.000049060236,0.0001591776],"domain_scores_gemma":[0.9996223,0.000015283822,0.00011138695,0.00015345032,0.00005446698,0.000043147855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015802615,0.00010506216,0.00010868933,0.00005938456,0.000037896516,0.000017069911,0.000095729236,0.0002170282,0.000001801686],"category_scores_gemma":[0.00020363841,0.00009069262,0.000027178381,0.00008179116,0.00008474408,0.000005555484,0.000039105955,0.000057060857,0.0000023541793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005812044,0.0010132891,0.36203265,0.008526121,0.00040946776,0.00000517254,0.025515275,0.0008151072,0.15583754,0.007203552,0.0181908,0.414639],"study_design_scores_gemma":[0.001996592,0.00088781136,0.15802519,0.00006680405,0.000028857428,0.000019754563,0.0014251855,0.82184154,0.011761553,0.00055660354,0.0030188218,0.00037126127],"about_ca_topic_score_codex":0.0000064637984,"about_ca_topic_score_gemma":0.000048417103,"teacher_disagreement_score":0.82102644,"about_ca_system_score_codex":0.000009102191,"about_ca_system_score_gemma":0.000063058724,"threshold_uncertainty_score":0.3698338},"labels":[],"label_agreement":null},{"id":"W2075326868","doi":"10.1186/1471-2105-8-197","title":"MASPECTRAS: a platform for management and analysis of proteomics LC-MS/MS data","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medizinische Universität Graz; Bundesministerium für Bildung, Wissenschaft und Kultur; Karl-Franzens-Universität Graz; University of Toronto; Österreichischen Akademie der Wissenschaften","keywords":"Computer science; Proteomics; Software; UniProt; Cluster analysis; Mascot; Data management; Proteome; Data mining; Database; Data science; Bioinformatics; Artificial intelligence; Biology","score_opus":0.03817860811772101,"score_gpt":0.3073214138576116,"score_spread":0.2691428057398906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075326868","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014708767,0.00003537036,0.9733768,0.000014070606,0.000006389945,0.0005928974,0.00063588115,0.00007623647,0.010553594],"genre_scores_gemma":[0.007044611,0.000117998614,0.99164355,0.00003227885,0.000021584046,0.0000864961,0.00080636144,0.000013673288,0.00023345556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891984,7.4566555e-7,0.0005621426,0.00016195055,0.00013271136,0.00022260017],"domain_scores_gemma":[0.99863964,0.00007567613,0.00030855936,0.0008676998,0.00004529075,0.00006313815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032070166,0.00013362803,0.00023462049,0.00015506966,0.00007834678,0.000026704938,0.00040432715,0.000096062286,0.000028816363],"category_scores_gemma":[0.000023250026,0.00012529719,0.00007235631,0.00032529456,0.000060481445,0.0002068723,0.0002482585,0.00008208679,0.0000014139164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016171571,0.0016067041,0.048578743,0.027641501,0.009493791,0.000007425314,0.005172217,0.003599826,0.03353237,0.6129574,0.0071172034,0.24867563],"study_design_scores_gemma":[0.0010109765,0.00005017736,0.00098037,0.00008816105,0.001393985,0.000006597212,0.0012313898,0.8876246,0.08071676,0.009281682,0.017106012,0.0005092731],"about_ca_topic_score_codex":0.0000072068915,"about_ca_topic_score_gemma":0.000040036226,"teacher_disagreement_score":0.8840248,"about_ca_system_score_codex":0.000039880702,"about_ca_system_score_gemma":0.00001674745,"threshold_uncertainty_score":0.51094705},"labels":[],"label_agreement":null},{"id":"W2075694192","doi":"10.1186/1471-2105-13-s1-s2","title":"SPARQL Assist language-neutral query composer","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canarie; Microsoft Research","keywords":"SPARQL; Computer science; Named graph; Semantics (computer science); World Wide Web; Identifier; Information retrieval; Semantic Web; Query language; Context (archaeology); Task (project management); RDF query language; SPARK (programming language); RDF; Web search query; Web query classification; Programming language; Search engine","score_opus":0.022859403368950572,"score_gpt":0.28317180680258563,"score_spread":0.26031240343363504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075694192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884607,0.0030863227,0.08338615,0.00019943612,0.001158296,0.00024932245,0.00006073668,0.00015663431,0.023242421],"genre_scores_gemma":[0.83832294,0.00006809138,0.1581334,0.0009599303,0.0007223969,0.000014253163,0.00026697226,0.000021952046,0.0014900449],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991393,0.000028179667,0.00024866473,0.000088454624,0.000113965005,0.00038142808],"domain_scores_gemma":[0.99941313,0.000022941867,0.00008572777,0.00029805402,0.000024763882,0.00015535804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023041257,0.00014112053,0.00013773757,0.000034030465,0.000069113135,0.000025756732,0.00018441014,0.00020713217,0.000021961228],"category_scores_gemma":[0.000087995606,0.00011239634,0.000088362656,0.00006774796,0.00013896891,0.000008123635,0.00008490383,0.00010151938,0.00015182064],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043443224,0.0012172274,0.3463103,0.0013309076,0.00049086986,0.000010322847,0.008086129,0.00017519032,0.04240037,0.0038938923,0.39211026,0.2035401],"study_design_scores_gemma":[0.0023950539,0.0006590981,0.09687769,0.00009864901,0.00011691247,0.0002361766,0.006620283,0.0057389457,0.115586005,0.00009902979,0.7700929,0.0014792256],"about_ca_topic_score_codex":0.000009243166,"about_ca_topic_score_gemma":0.0000208791,"teacher_disagreement_score":0.37798268,"about_ca_system_score_codex":0.000009258494,"about_ca_system_score_gemma":0.000039987804,"threshold_uncertainty_score":0.45833895},"labels":[],"label_agreement":null},{"id":"W2076017572","doi":"10.1186/1471-2105-12-247","title":"Dissecting protein loops with a statistical scalpel suggests a functional implication of some structural motifs","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Illinois Program for Research in the Humanities, University of Illinois at Urbana-Champaign; Institute of Pharmacy, Nirma University; Institute of Mountain Hazards and Environment; Institut de recherche en santé mentale; Centre for Earth Observation Instrumentation; Institut Pierre-Gilles de Gennes; Jinggangshan University; Institute for Global Prominent Research, Chiba University; Joint Fire Science Program; Critical Ecosystem Partnership Fund; Iran Polymer and Petrochemical Institute; International Pediatric Research Foundation; Josiah Macy Jr. Foundation; Institut de Physique du Globe de Paris; Japan Foundation Endowment Committee; Coalition for Epidemic Preparedness Innovations; James N. Kirby Foundation; Japan Health Sciences Foundation; ITP Foundation","keywords":"Structural motif; Computational biology; Biology; Structural Classification of Proteins database; Structural alignment; Sequence motif; Protein family; Protein function prediction; Hidden Markov model; Protein structure; Sequence alignment; Genetics; Protein function; Peptide sequence; Computer science; Gene; Artificial intelligence; Biochemistry","score_opus":0.01275364778276367,"score_gpt":0.2278553035764588,"score_spread":0.21510165579369514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076017572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7411683,0.000026700802,0.25745904,0.0000034610114,0.00004875044,0.00034139832,0.00007407505,0.000015755812,0.0008624654],"genre_scores_gemma":[0.8299736,0.0000010518003,0.16961494,0.00002099758,0.00006966861,0.000023832416,0.00021479686,0.000013132514,0.00006802905],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991416,0.000014005689,0.00032835963,0.00014404135,0.00016888128,0.00020313657],"domain_scores_gemma":[0.99925435,0.000009630976,0.00020667605,0.0002900789,0.00016297234,0.00007627054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000086558255,0.0001539262,0.00013983704,0.00004122958,0.00006712772,0.000014829925,0.00012829447,0.00012378657,0.000017362685],"category_scores_gemma":[0.00008144116,0.000117237396,0.000042659292,0.00006698732,0.00013114505,0.00001661597,0.00007124435,0.00008803815,0.0000033847152],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006053796,0.00041813272,0.19494161,0.0041656373,0.0008362508,0.000010797097,0.003987585,0.0020915142,0.46741045,0.2736382,0.0005407801,0.04590529],"study_design_scores_gemma":[0.0034236943,0.0025356729,0.5132271,0.00016726027,0.00015351176,0.00032459095,0.0013719145,0.08498482,0.373678,0.018672679,0.00017535767,0.0012854217],"about_ca_topic_score_codex":0.000019975285,"about_ca_topic_score_gemma":0.000028583232,"teacher_disagreement_score":0.31828547,"about_ca_system_score_codex":0.000012509255,"about_ca_system_score_gemma":0.00010937243,"threshold_uncertainty_score":0.4780802},"labels":[],"label_agreement":null},{"id":"W2076426906","doi":"10.1186/1471-2105-15-114","title":"Biological relevance of CNV calling methods using familial relatedness including monozygotic twins","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Copy-number variation; SNP array; Copy number analysis; SNP genotyping; Genotyping; Genetics; Biology; SNP; Computational biology; Computer science; Genomics; Single-nucleotide polymorphism; Genome; Gene; Genotype","score_opus":0.06364412042526461,"score_gpt":0.31840111189524806,"score_spread":0.25475699146998343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076426906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52351993,0.00009050013,0.47544935,0.0000047205717,0.00015196935,0.00007973753,0.000010671753,0.000011631379,0.0006814659],"genre_scores_gemma":[0.5710174,0.00005525513,0.42869446,0.000047185247,0.000092516115,0.0000030700376,0.000035325374,0.00000963421,0.000045176046],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883324,0.00011588385,0.00056404923,0.00014720848,0.00009629103,0.00024334961],"domain_scores_gemma":[0.9991918,0.000079763435,0.00026091322,0.0003058608,0.0001002482,0.00006141908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005781359,0.00016002412,0.0002319114,0.000053019256,0.00012821097,0.000019885036,0.00020922179,0.00022399279,0.000008093316],"category_scores_gemma":[0.0003929416,0.0001378994,0.00010721933,0.00011228197,0.00009993285,0.000012501211,0.00018966247,0.00009953048,0.000005650666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034588683,0.0003189174,0.054282244,0.0013751914,0.00036316342,0.0000018019138,0.0044617313,0.14105336,0.75952905,0.016360447,0.00022081229,0.021687375],"study_design_scores_gemma":[0.0011433425,0.0004941392,0.0029534856,0.00012163015,0.00008980099,0.00006409272,0.001942443,0.8315652,0.15262865,0.0011098288,0.007211971,0.00067545165],"about_ca_topic_score_codex":0.000024904431,"about_ca_topic_score_gemma":0.000006408584,"teacher_disagreement_score":0.6905118,"about_ca_system_score_codex":0.00002458296,"about_ca_system_score_gemma":0.000082640254,"threshold_uncertainty_score":0.56233746},"labels":[],"label_agreement":null},{"id":"W2076460489","doi":"10.1186/1471-2105-10-414","title":"Modular prediction of protein structural classes from sequences of twilight-zone identity with predicting sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Support vector machine; Modular design; Similarity (geometry); Feature selection; Feature (linguistics); Pattern recognition (psychology); Class (philosophy); Sequence (biology); Contrast (vision); Data mining; Machine learning; Biology; Image (mathematics)","score_opus":0.01020080503328411,"score_gpt":0.24509219230986357,"score_spread":0.23489138727657946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076460489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9133903,0.00019522218,0.08507766,0.00002325013,0.000066739645,0.00035809082,0.00019072679,0.000035362697,0.00066265016],"genre_scores_gemma":[0.80102205,0.000023608547,0.19853556,0.000029027326,0.00007373931,0.000005596295,0.00026921634,0.000008730897,0.000032473537],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982685,0.000049988237,0.0008198606,0.00015668826,0.00047536715,0.00022963212],"domain_scores_gemma":[0.99845505,0.000022830945,0.00080628664,0.00042990793,0.00021613693,0.00006977116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026419133,0.00022409607,0.00029418227,0.00008533739,0.000085494205,0.000045738103,0.00038162945,0.00018736244,0.000016100877],"category_scores_gemma":[0.000168725,0.00017295529,0.00008682906,0.00019235836,0.0002107022,0.00011408436,0.000080432925,0.00015757293,0.0000021523144],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050312,0.00013929702,0.24394216,0.0016667115,0.00031400358,0.0000023341172,0.0031564247,0.044262934,0.6989824,0.0015064604,0.00013263163,0.0053915],"study_design_scores_gemma":[0.0014770943,0.0026960147,0.08932839,0.0005441598,0.00014253272,0.00004517549,0.002105898,0.42936525,0.4725552,0.0008788293,0.00033870013,0.0005227565],"about_ca_topic_score_codex":0.00009971873,"about_ca_topic_score_gemma":0.000071660375,"teacher_disagreement_score":0.38510233,"about_ca_system_score_codex":0.000019330751,"about_ca_system_score_gemma":0.00016822964,"threshold_uncertainty_score":0.7052912},"labels":[],"label_agreement":null},{"id":"W2077350268","doi":"10.1186/1471-2105-15-s6-i1","title":"Knowledge Discovery and interactive Data Mining in Bioinformatics - State-of-the-Art, future challenges and research directions","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Discovery Centre; University Health Network","funders":"","keywords":"Data science; State (computer science); Computer science; World Wide Web; Bioinformatics; Biology","score_opus":0.06287523198941182,"score_gpt":0.34551861865405353,"score_spread":0.2826433866646417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077350268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.867849,0.027673973,0.0441788,0.002843943,0.002467442,0.0034735599,0.00088197604,0.00007807861,0.05055324],"genre_scores_gemma":[0.67032516,0.11614994,0.20541376,0.0004348239,0.0012511685,0.0001086057,0.0010058162,0.00012741983,0.0051832995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980276,0.00017319988,0.0006875014,0.00023002313,0.00041953987,0.0004621285],"domain_scores_gemma":[0.9982747,0.0002782798,0.00018952285,0.0008964622,0.00019740527,0.00016362702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019371038,0.00020507067,0.0002653303,0.0002601671,0.00016065064,0.00011016492,0.0006422213,0.0001927528,0.000001913262],"category_scores_gemma":[0.0012299818,0.00014779661,0.000046270285,0.00026873758,0.0006753905,0.0001003837,0.0018438397,0.0003461492,0.00000927897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016592923,0.00023104525,0.00414052,0.0026402078,0.00009897683,4.259811e-7,0.013712384,0.000016805896,0.00067105517,0.00033804195,0.006524145,0.97146046],"study_design_scores_gemma":[0.0030398767,0.0014336241,0.051076796,0.0008694528,0.00005597959,0.00008079785,0.033712894,0.40837988,0.0059415568,0.0006317917,0.49380872,0.00096862763],"about_ca_topic_score_codex":0.0000099768995,"about_ca_topic_score_gemma":0.00086801837,"teacher_disagreement_score":0.9704918,"about_ca_system_score_codex":0.000023382305,"about_ca_system_score_gemma":0.0002062599,"threshold_uncertainty_score":0.6026971},"labels":[],"label_agreement":null},{"id":"W2079137604","doi":"10.1186/1471-2105-11-s6-s14","title":"Discovering gene functional relationships using FAUN (Feature Annotation Using Nonnegative matrix factorization)","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; University of British Columbia; Oak Ridge National Laboratory; Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of Memphis","keywords":"Annotation; Non-negative matrix factorization; Computer science; Gene Annotation; Software; Feature (linguistics); Set (abstract data type); Genome; Field (mathematics); Data mining; Information retrieval; Computational biology; Gene; Matrix decomposition; Biology; Artificial intelligence; Genetics; Mathematics","score_opus":0.05097628625394497,"score_gpt":0.2947423372471521,"score_spread":0.24376605099320714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079137604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4699794,0.000039475795,0.5292953,0.000022864993,0.00041337535,0.00008916265,0.000037009468,0.000022816555,0.00010056721],"genre_scores_gemma":[0.49296674,0.000007287893,0.50600725,0.000041365394,0.00036251152,0.000003913889,0.0004286625,0.000015578238,0.00016668129],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991289,0.00003343691,0.0002802622,0.0001565734,0.0001946589,0.00020618952],"domain_scores_gemma":[0.9993358,0.000044709064,0.00019417991,0.00022461388,0.00012122635,0.000079451216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019232316,0.00016011072,0.00012110981,0.000076239514,0.00029695863,0.0000667024,0.00011181593,0.00033896323,0.000015450609],"category_scores_gemma":[0.000471454,0.00014168839,0.000070360424,0.00018177525,0.00012483845,0.000030729396,0.00007917969,0.00028237523,0.000010201413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016757622,0.00011688341,0.105030745,0.0002734133,0.0001668067,0.000002213862,0.0018441203,0.042307783,0.84349024,0.0011482047,0.0011430867,0.004308926],"study_design_scores_gemma":[0.0013257035,0.00015873485,0.049792185,0.00006244482,0.00011091649,0.00015211347,0.0026461633,0.87395245,0.059746664,0.00041715254,0.010807411,0.00082803983],"about_ca_topic_score_codex":0.000008998675,"about_ca_topic_score_gemma":0.000039741164,"teacher_disagreement_score":0.8316447,"about_ca_system_score_codex":0.00002426788,"about_ca_system_score_gemma":0.00016141377,"threshold_uncertainty_score":0.57778853},"labels":[],"label_agreement":null},{"id":"W2080569293","doi":"10.1186/1471-2105-10-442","title":"G+C content dominates intrinsic nucleosome occupancy","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":281,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Genome Canada; Ontario Genomics; Ontario Genomics Institute; Canadian Institute for Advanced Research; Howard Hughes Medical Institute","keywords":"Nucleosome; Chromatin; Linker DNA; Biology; DNA; Genome; Genetics; Histone; DNA sequencing; GC-content; Computational biology; DNA microarray; Sequence (biology); Biophysics; Biological system; Gene","score_opus":0.01536453061776141,"score_gpt":0.22552557151633804,"score_spread":0.21016104089857662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080569293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97514546,0.00032306515,0.017525524,0.00011634517,0.00020692372,0.00026854285,0.00003486549,0.00003702086,0.00634224],"genre_scores_gemma":[0.9158555,0.00021025252,0.081994355,0.0010006161,0.00015549104,0.0000062008535,0.00019640021,0.000016755444,0.0005643738],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991086,0.000011918738,0.00036408138,0.0001351383,0.00011180063,0.00026844346],"domain_scores_gemma":[0.9992939,0.00000761551,0.0001395503,0.00039082122,0.000074380165,0.00009370336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011286839,0.00017267912,0.00015829032,0.000043436285,0.00007619507,0.00005616419,0.00024298923,0.0001375685,0.000016305421],"category_scores_gemma":[0.000057006597,0.00015488823,0.000106489366,0.00006348342,0.000044706598,0.00000793044,0.00007797838,0.00007407281,0.00009994175],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012620948,0.0018230227,0.0562031,0.0012494375,0.00059014745,0.000028398983,0.0036493598,0.0028753963,0.41481113,0.045727238,0.052220274,0.4195604],"study_design_scores_gemma":[0.015403164,0.0067243925,0.36208597,0.00032807753,0.00032391772,0.00057498686,0.005945148,0.29962054,0.13432206,0.007670471,0.16149877,0.0055025043],"about_ca_topic_score_codex":0.0000022478175,"about_ca_topic_score_gemma":0.0000072581824,"teacher_disagreement_score":0.4140579,"about_ca_system_score_codex":0.000018181334,"about_ca_system_score_gemma":0.000061851766,"threshold_uncertainty_score":0.6316159},"labels":[],"label_agreement":null},{"id":"W2080867027","doi":"10.1186/1471-2105-12-s9-s9","title":"Detecting genomic regions associated with a disease using variability functions and Adjusted Rand Index","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Biology; Identification (biology); Functional genomics; DNA microarray; Genetics; Function (biology); Genomics; Bioinformatics; Genome; Gene","score_opus":0.03697424106330998,"score_gpt":0.2178551642141747,"score_spread":0.1808809231508647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080867027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93468356,0.00015653703,0.06406973,0.0000045659845,0.000057924975,0.00023304315,0.000044251814,0.000008759657,0.0007416083],"genre_scores_gemma":[0.98726076,0.000030416388,0.0125184255,0.000045447625,0.00003476732,0.0000124971775,0.000023743345,0.0000144890355,0.000059427846],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993005,0.000040332103,0.00023150482,0.00015870527,0.00006599429,0.00020299447],"domain_scores_gemma":[0.9993658,0.00002782963,0.0001395398,0.00026343364,0.00008722252,0.00011617828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020570293,0.0001476114,0.00013578136,0.00003772515,0.00022231867,0.000021289397,0.00007526062,0.00008520021,0.000004223629],"category_scores_gemma":[0.00018094313,0.0001249241,0.0000463349,0.00008845923,0.00012124132,0.0000028312666,0.00011555833,0.00006510058,0.0000011951943],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006555623,0.0001731756,0.98179907,0.00017616546,0.00047480577,0.0000021259036,0.0017540321,0.001680893,0.01158445,0.000115827395,0.00008329808,0.0015005714],"study_design_scores_gemma":[0.002181946,0.00030573257,0.9050403,0.000052679676,0.00034063042,0.000027670672,0.0016732268,0.08847499,0.00067542575,0.00031779046,0.00035241328,0.00055715686],"about_ca_topic_score_codex":0.000027688098,"about_ca_topic_score_gemma":0.00014539345,"teacher_disagreement_score":0.0867941,"about_ca_system_score_codex":0.000019184024,"about_ca_system_score_gemma":0.00011824594,"threshold_uncertainty_score":0.5094257},"labels":[],"label_agreement":null},{"id":"W2082220672","doi":"10.1186/1471-2105-8-358","title":"Combining classifiers to predict gene function in Arabidopsis thaliana using large-scale gene expression measurements","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Arabidopsis thaliana; DNA microarray; Computational biology; Gene expression; Biology; Gene; Genetics; Function (biology); Arabidopsis; Scale (ratio); Mutant; Geography; Cartography","score_opus":0.04853023466139118,"score_gpt":0.28517308430739813,"score_spread":0.23664284964600696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082220672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40208805,0.00010401998,0.5959606,0.0000127749045,0.0003595668,0.00026902175,0.0000126957,0.0000201283,0.0011731575],"genre_scores_gemma":[0.85962474,0.000026228869,0.139076,0.00053777394,0.00018657993,0.00002695488,0.00021656408,0.00003174858,0.00027343488],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983774,0.000054793636,0.0005429452,0.0002624754,0.0003541319,0.00040824493],"domain_scores_gemma":[0.99906987,0.000009696249,0.0001954154,0.00043482785,0.0001029864,0.00018722836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009590497,0.0001907388,0.00015973987,0.00020639123,0.00013064749,0.00003824569,0.00019214678,0.00022660242,0.000017009424],"category_scores_gemma":[0.00007788262,0.00018339252,0.000074663054,0.00031071433,0.000025370242,0.000022403623,0.00011308363,0.00010743058,0.000016955797],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032216488,0.00008700223,0.04096103,0.000045381217,0.000016158569,4.3329547e-7,0.00044290372,0.0024074842,0.9520893,0.00000795075,0.0015699796,0.0020502063],"study_design_scores_gemma":[0.0017416384,0.00020654748,0.033104565,0.00011694919,0.000033598888,0.000008459181,0.0021901322,0.01893952,0.935503,0.000032701704,0.007719243,0.00040362883],"about_ca_topic_score_codex":0.0000052759483,"about_ca_topic_score_gemma":0.000056174722,"teacher_disagreement_score":0.45753667,"about_ca_system_score_codex":0.00009409346,"about_ca_system_score_gemma":0.000106137864,"threshold_uncertainty_score":0.747853},"labels":[],"label_agreement":null},{"id":"W2082395827","doi":"10.1186/1471-2105-8-308","title":"Analysis of the role of retrotransposition in gene evolution in vertebrates","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Retrotransposon; Biology; Pseudogene; Gene; Genetics; Genome; Genome evolution; Human genome; Negative selection; Evolutionary biology; Transposable element","score_opus":0.008255408423635808,"score_gpt":0.19695447435050886,"score_spread":0.18869906592687305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082395827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99894375,0.000041088246,0.00032873722,0.000022220425,0.000014659527,0.00008216705,0.000031039977,0.000002787077,0.0005335406],"genre_scores_gemma":[0.998759,0.000005888848,0.0011877702,0.000007697618,0.0000065702675,0.0000011078777,0.000028963746,1.2203002e-7,0.00000290802],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994626,0.0000145678605,0.00030693898,0.000035200068,0.000101747886,0.000078935824],"domain_scores_gemma":[0.99977726,0.000052306426,0.000095988806,0.000035704288,0.000026850703,0.000011865969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001906597,0.00003599066,0.00009412038,0.000040450766,0.000019232171,0.0000028956683,0.00008764145,0.000045855944,0.00002655193],"category_scores_gemma":[0.000016915861,0.000013095669,0.0000646254,0.0013049366,0.000022034339,0.00004834461,0.000013246483,0.00003096506,9.532099e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009494719,0.00004815325,0.89588165,0.0000066524203,0.000010600848,2.7380786e-8,0.000359141,0.0014798697,0.09855041,0.00045848344,2.7039187e-7,0.0031952427],"study_design_scores_gemma":[0.000057183443,0.000024887118,0.9094036,0.000009823636,0.00002671371,1.9103804e-7,0.00043853084,0.076194055,0.013491199,0.00031715,0.0000086618065,0.000027994587],"about_ca_topic_score_codex":0.0003606341,"about_ca_topic_score_gemma":0.013480598,"teacher_disagreement_score":0.08505921,"about_ca_system_score_codex":0.00002126401,"about_ca_system_score_gemma":0.000006988047,"threshold_uncertainty_score":0.752249},"labels":[],"label_agreement":null},{"id":"W2082852695","doi":"10.1186/1471-2105-12-414","title":"Three-dimensional modeling of chromatin structure from interaction frequency data using Markov chain Monte Carlo sampling","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research","keywords":"Chromatin; Markov chain Monte Carlo; Chromosome conformation capture; Computational biology; Chromosome; Computer science; Monte Carlo method; Biology; Algorithm; Enhancer; Genetics; Artificial intelligence; DNA; Bayesian probability; Transcription factor; Gene; Mathematics; Statistics","score_opus":0.06652223994272753,"score_gpt":0.26597249007886103,"score_spread":0.1994502501361335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082852695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73973805,0.00015542365,0.259061,0.000001944765,0.00018818156,0.00012936066,0.00061750074,0.000009352175,0.00009917795],"genre_scores_gemma":[0.54302144,0.000009684613,0.45622596,0.000022301201,0.00006694168,9.50881e-7,0.0006348862,0.00001613913,0.0000017012003],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877954,0.000017143913,0.00060525275,0.00022822325,0.00016128102,0.00020857231],"domain_scores_gemma":[0.9986297,0.0000136215485,0.00034823196,0.0008412058,0.00010401835,0.000063217536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015357579,0.00020259709,0.0002121531,0.000056306628,0.000079877675,0.000023979115,0.00045578246,0.00019613968,0.000036623118],"category_scores_gemma":[0.000060291215,0.0001932611,0.000068267866,0.00006443141,0.000043289834,0.00003124416,0.00042900507,0.00012260713,0.0000021088954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032907768,0.0002273052,0.018727368,0.0007628732,0.00062031357,0.0000031712827,0.0025342526,0.55694866,0.41330934,0.00021295997,0.0002611491,0.006063516],"study_design_scores_gemma":[0.00030159118,0.000049381793,0.0005372069,0.000069096524,0.000045032164,0.000014299562,0.0003258194,0.99540174,0.0026007537,0.00043103856,0.000010157359,0.00021386932],"about_ca_topic_score_codex":0.0007356864,"about_ca_topic_score_gemma":0.0011279973,"teacher_disagreement_score":0.43845305,"about_ca_system_score_codex":0.000028000537,"about_ca_system_score_gemma":0.00013259429,"threshold_uncertainty_score":0.78809595},"labels":[],"label_agreement":null},{"id":"W2083274478","doi":"10.1186/1471-2105-14-354","title":"Balony:a software package for analysis of data generated by synthetic genetic array experiments","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Michael Smith Health Research BC; Canadian Institutes of Health Research; Tula Foundation","keywords":"Software package; Software; DNA microarray; R package; Computer science; Computational biology; Biology; Bioinformatics; Genetics; Programming language; Gene expression; Gene","score_opus":0.04914811403431144,"score_gpt":0.31499361420303784,"score_spread":0.2658455001687264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083274478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3819176,0.0010221258,0.61405754,0.000024189096,0.00007946797,0.0007597606,0.0018676756,0.000017588343,0.00025404003],"genre_scores_gemma":[0.42499602,0.00027403963,0.5622304,0.00022004177,0.00010985673,0.0002006894,0.010620204,0.000059650465,0.001289051],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99849206,0.000040770923,0.000519595,0.00030118314,0.000274747,0.0003716641],"domain_scores_gemma":[0.9981414,0.000041786854,0.00017287425,0.0012473144,0.00024490553,0.0001516836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017392074,0.00020177856,0.0002909224,0.00013551832,0.00007886721,0.00006337835,0.00077466347,0.00016753947,0.00012513211],"category_scores_gemma":[0.0001719308,0.00017384106,0.00014443924,0.0003469175,0.00010756743,0.00001745709,0.00028964083,0.000058139074,0.00004107083],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005488391,0.00015815582,0.0061614276,0.00023113479,0.0008753306,1.6529242e-7,0.00012053684,0.0007932961,0.9574604,0.0000041573708,0.028345816,0.0057946746],"study_design_scores_gemma":[0.00087353855,0.00040138548,0.0028055871,0.000019956768,0.00043704902,0.0000035579328,0.0002748507,0.19975151,0.7870321,0.000021080159,0.00789652,0.00048283985],"about_ca_topic_score_codex":0.000040576437,"about_ca_topic_score_gemma":0.00002653212,"teacher_disagreement_score":0.19895822,"about_ca_system_score_codex":0.000011501296,"about_ca_system_score_gemma":0.00010235436,"threshold_uncertainty_score":0.7089033},"labels":[],"label_agreement":null},{"id":"W2083366092","doi":"10.1186/1471-2105-10-222","title":"PCI-SS: MISO dynamic nonlinear protein secondary structure prediction","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Protein secondary structure; Conventional PCI; Interface (matter); Nonlinear system; Machine learning; Artificial intelligence; Data mining; Biology; Parallel computing; Physics","score_opus":0.0038572218742912727,"score_gpt":0.21592785593539401,"score_spread":0.21207063406110274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083366092","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7952151,0.00085743965,0.19392756,0.00021157267,0.00071168336,0.0016099797,0.0011732935,0.00018294931,0.006110446],"genre_scores_gemma":[0.49076408,0.00009230309,0.5008149,0.0014205108,0.0005503288,0.000023330114,0.0036057439,0.00005117276,0.0026776379],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877995,0.000022642356,0.00046399556,0.0002132219,0.00020257817,0.00031762745],"domain_scores_gemma":[0.99909836,0.0000041806124,0.00019020027,0.0005088827,0.00008770199,0.00011068816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010257903,0.00025355062,0.00017957055,0.00006703689,0.0001181004,0.000058046116,0.0002629106,0.00036414174,0.000031175834],"category_scores_gemma":[0.00007177009,0.00022392315,0.000107679385,0.00012148453,0.000062991305,0.000022043021,0.00006747486,0.0002310962,0.000015226476],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007042698,0.00021581756,0.0014362328,0.0009395423,0.00021974262,0.000009911801,0.00067289226,0.0038328513,0.8058157,0.0011474914,0.008038717,0.17696685],"study_design_scores_gemma":[0.004858378,0.0029709218,0.009731277,0.00019241718,0.00013334738,0.00048066312,0.00057183247,0.7399303,0.113445215,0.0059684175,0.119825326,0.001891909],"about_ca_topic_score_codex":0.0000021003348,"about_ca_topic_score_gemma":0.000035412264,"teacher_disagreement_score":0.73609746,"about_ca_system_score_codex":0.000029295314,"about_ca_system_score_gemma":0.0001918603,"threshold_uncertainty_score":0.9131321},"labels":[],"label_agreement":null},{"id":"W2084063783","doi":"10.1186/1471-2105-8-368","title":"Assessment of algorithms for high throughput detection of genomic copy number variation in oligonucleotide microarray data","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Children's Hospital; BC Cancer Agency","funders":"BC Cancer Agency; Michael Smith Health Research BC; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Copy-number variation; SNP genotyping; SNP array; Biology; DNA microarray; Genotyping; Single-nucleotide polymorphism; Computational biology; Copy number analysis; Genetics; SNP; Loss of heterozygosity; Genomics; Genome; Genotype; Gene; Allele","score_opus":0.022774831259624703,"score_gpt":0.29166617376329534,"score_spread":0.26889134250367064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084063783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5065093,0.000017994998,0.49258783,0.0000042635943,0.00011825169,0.00021675295,0.00021023004,0.000003388761,0.00033196426],"genre_scores_gemma":[0.7031054,0.000028074608,0.29634345,0.000018293802,0.00006068163,0.0000058478436,0.00040124374,0.00000851532,0.000028527302],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892175,0.000017101764,0.00065789785,0.00013534538,0.00009478906,0.00017312352],"domain_scores_gemma":[0.99903303,0.000035354846,0.00034914925,0.00044688483,0.000109343775,0.000026213165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006338487,0.00010747776,0.00017198465,0.000056332356,0.000039573664,0.000010952094,0.0002330074,0.00012440725,0.000011063351],"category_scores_gemma":[0.00003827058,0.000107603766,0.000046795372,0.000078783785,0.000042813568,0.000021178386,0.0001258906,0.000044990225,0.0000023057614],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019172613,0.00031294208,0.051478505,0.00094371446,0.0001741042,3.1311507e-7,0.0010540683,0.0029595403,0.9345085,0.003501376,0.00018415017,0.004691071],"study_design_scores_gemma":[0.0027202158,0.00042736527,0.45965812,0.000045083223,0.000091660004,0.000020666364,0.001511316,0.055118524,0.4774204,0.0005046921,0.0020771266,0.0004048297],"about_ca_topic_score_codex":0.00014627894,"about_ca_topic_score_gemma":0.0002512913,"teacher_disagreement_score":0.45708808,"about_ca_system_score_codex":0.000037593734,"about_ca_system_score_gemma":0.00013062936,"threshold_uncertainty_score":0.43879542},"labels":[],"label_agreement":null},{"id":"W2084339286","doi":"10.1186/s12859-015-0540-1","title":"OpenMS-Simulator: an open-source software for theoretical tandem mass spectrum prediction","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; University of Waterloo; National Natural Science Foundation of China","keywords":"Computer science; Computation; Software; Tandem mass spectrometry; Similarity (geometry); Simulation; Data mining; Artificial intelligence; Mass spectrometry; Algorithm; Chemistry","score_opus":0.03403832030887243,"score_gpt":0.3039335129003802,"score_spread":0.26989519259150774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084339286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003133657,0.000012374142,0.9867571,0.00008056823,0.000039525752,0.00073699333,0.0002368759,0.0004608266,0.008542083],"genre_scores_gemma":[0.046271767,0.000008692423,0.9519769,0.00015455198,0.00017141413,0.0003542063,0.00039632988,0.00004894715,0.000617207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988972,0.0000075387434,0.00044113523,0.00018324358,0.00018588726,0.0002850157],"domain_scores_gemma":[0.9987588,0.00007884193,0.00018231057,0.0006160448,0.00012458234,0.00023943404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003011714,0.00017836757,0.00019929191,0.000029379982,0.00017216771,0.00019432252,0.00066119747,0.00019343772,0.00010748191],"category_scores_gemma":[0.00017869241,0.0001630939,0.00004684885,0.000108224645,0.00011069641,0.00054847,0.0002135971,0.00016583309,0.000029725377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007687455,0.00061419775,0.013374483,0.0010731914,0.00012029752,0.0000014782321,0.0027719766,0.026313918,0.0030101675,0.90530354,0.022505838,0.02414218],"study_design_scores_gemma":[0.0013903955,0.00018760581,0.00001012384,0.000047392765,0.000037703427,0.000014467108,0.00078747846,0.76826894,0.022595491,0.140279,0.06602414,0.00035725458],"about_ca_topic_score_codex":0.0000035193477,"about_ca_topic_score_gemma":0.0000033517533,"teacher_disagreement_score":0.76502454,"about_ca_system_score_codex":0.0001252152,"about_ca_system_score_gemma":0.00014538209,"threshold_uncertainty_score":0.66507757},"labels":[],"label_agreement":null},{"id":"W2084455604","doi":"10.1186/1471-2105-10-115","title":"Most parsimonious haplotype allele sharing determination","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Agricultural Research Institute","keywords":"Haplotype; Genetics; Pedigree chart; Single-nucleotide polymorphism; Biology; Allele; Haplotype estimation; Genetic association; Linkage disequilibrium; Genotype; Computational biology; Gene","score_opus":0.01855987131325696,"score_gpt":0.26849910023989476,"score_spread":0.2499392289266378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084455604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6427387,0.0003777608,0.33213282,0.000497779,0.00025479007,0.00041173684,0.000023316057,0.0000812699,0.023481842],"genre_scores_gemma":[0.82538015,0.00016024953,0.17126055,0.0016131775,0.0001819647,0.0000097503835,0.00041769573,0.00001366716,0.0009628225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991961,0.00001905749,0.00032026775,0.00013555796,0.00008399863,0.0002449814],"domain_scores_gemma":[0.999407,0.0000127113035,0.00014644313,0.00028437722,0.00008676572,0.0000627057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023329977,0.00011677496,0.00012548569,0.000039267205,0.00009904136,0.000025793055,0.00017870251,0.00016975857,0.0000112760545],"category_scores_gemma":[0.00024914774,0.00011164911,0.00005156889,0.00009023341,0.00002401235,0.0000068736385,0.000058572405,0.000060205733,0.000053211897],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002589242,0.00069588044,0.40447024,0.00025815828,0.00023180306,0.000006932034,0.0018672434,0.022649694,0.02681392,0.004836153,0.115008265,0.42290276],"study_design_scores_gemma":[0.0014588435,0.0011237289,0.28028774,0.000023256396,0.00006147159,0.00005085677,0.0005111862,0.65146905,0.0038560536,0.0024427297,0.057896428,0.0008186227],"about_ca_topic_score_codex":0.0000050568806,"about_ca_topic_score_gemma":0.000028657974,"teacher_disagreement_score":0.6288194,"about_ca_system_score_codex":0.000018256373,"about_ca_system_score_gemma":0.000051931693,"threshold_uncertainty_score":0.45529187},"labels":[],"label_agreement":null},{"id":"W2084771278","doi":"10.1186/1471-2105-9-255","title":"Protein contact order prediction from primary sequences","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein Data Bank (RCSB PDB); Protein secondary structure; Protein structure prediction; Sequence (biology); Contact order; Protein structure; Protein folding; Matthews correlation coefficient; Protein Data Bank; Protein sequencing; Similarity (geometry); Computer science; Folding (DSP implementation); Order (exchange); Peptide sequence; Bioinformatics; Biology; Artificial intelligence; Genetics; Engineering; Biochemistry","score_opus":0.010084148967345701,"score_gpt":0.2092890452395811,"score_spread":0.19920489627223542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084771278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7977869,0.00034076144,0.19367415,0.000027351345,0.00018549415,0.00051239674,0.00022618179,0.000057119,0.0071896687],"genre_scores_gemma":[0.5917977,0.00022928002,0.40307763,0.0008049131,0.0005466371,0.000075894786,0.0024124633,0.000032616466,0.0010228545],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99919605,0.000020069627,0.00028910325,0.0001403945,0.00017006748,0.00018430705],"domain_scores_gemma":[0.9994121,0.00000717098,0.00012322738,0.00030940815,0.000081843806,0.00006625736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006615515,0.00014856145,0.00013142436,0.00002862114,0.000117432675,0.000019778303,0.00016546051,0.0001930102,0.000019567986],"category_scores_gemma":[0.000060059694,0.00012532153,0.000058578386,0.000081965525,0.000077527366,0.00001700367,0.000075831274,0.00009129242,0.000026909956],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009896146,0.0002719603,0.1018153,0.00073745375,0.00050125807,0.00003075434,0.0021980607,0.0022536388,0.85442585,0.0016681775,0.015768293,0.019339658],"study_design_scores_gemma":[0.009663176,0.0035157243,0.20878012,0.00036689005,0.00021886063,0.0007349065,0.001278828,0.18388075,0.40825298,0.0043235105,0.17545152,0.0035327498],"about_ca_topic_score_codex":0.00003725256,"about_ca_topic_score_gemma":0.000027070562,"teacher_disagreement_score":0.44617286,"about_ca_system_score_codex":0.000020329424,"about_ca_system_score_gemma":0.00021853934,"threshold_uncertainty_score":0.51104635},"labels":[],"label_agreement":null},{"id":"W2087450928","doi":"10.1186/1471-2105-10-184","title":"FuGEFlow: data model and markup language for flow cytometry","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; National Institutes of Health; Michael Smith Health Research BC","keywords":"Markup language; Computer science; Metadata; Data flow diagram; Database; World Wide Web; XML","score_opus":0.03626515090075776,"score_gpt":0.2830928028498879,"score_spread":0.24682765194913014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087450928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13182718,0.00066029775,0.86484706,0.00008812948,0.00011936959,0.00033596414,0.0005825963,0.000032815984,0.001506578],"genre_scores_gemma":[0.2669484,0.00021910171,0.7287356,0.0012843171,0.00022848153,0.000006547133,0.0019668406,0.000022006307,0.00058865355],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928224,0.0000071465074,0.00023448827,0.00017308809,0.00008947191,0.00021359237],"domain_scores_gemma":[0.9992635,0.000013490052,0.000056273264,0.0005520128,0.000034744164,0.00007995956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001810119,0.00013973146,0.00013261459,0.000042796837,0.00007118066,0.000050370207,0.00029427788,0.00014158485,0.000002767614],"category_scores_gemma":[0.00008003541,0.00012629689,0.000046856778,0.000055207398,0.00003562127,0.000016641512,0.000083054525,0.000056459336,0.0000035266048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016406574,0.00068477925,0.0035330302,0.0018196992,0.00026471843,0.000004429814,0.0026617679,0.012905929,0.4641148,0.0010569918,0.07100374,0.44030946],"study_design_scores_gemma":[0.0008757741,0.0001760266,0.0002613435,0.00001237847,0.000028339322,0.000009714211,0.00013588973,0.9886416,0.005187689,0.00009164364,0.0043653455,0.00021425636],"about_ca_topic_score_codex":0.0000017499397,"about_ca_topic_score_gemma":0.000016887028,"teacher_disagreement_score":0.97573566,"about_ca_system_score_codex":0.0000056258095,"about_ca_system_score_gemma":0.000055832894,"threshold_uncertainty_score":0.51502377},"labels":[],"label_agreement":null},{"id":"W2087932775","doi":"10.1186/1471-2105-11-403","title":"Data reduction for spectral clustering to analyze high throughput flow cytometry data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":166,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; Mitacs; National Institutes of Health; Michael Smith Health Research BC","keywords":"Throughput; Computer science; Cluster analysis; Reduction (mathematics); Flow cytometry; Data reduction; Data mining; Computational biology; Biology; Mathematics; Artificial intelligence; Molecular biology; Telecommunications","score_opus":0.054617542012774634,"score_gpt":0.3018674232321299,"score_spread":0.24724988121935526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087932775","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15700209,0.000033484954,0.8385878,0.00013509896,0.0015709138,0.0004158999,0.0019254246,0.000035959594,0.00029329796],"genre_scores_gemma":[0.16932994,0.000038940805,0.8192587,0.00022765697,0.0012968446,0.000009344732,0.009631853,0.000033253473,0.00017349106],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998796,0.000010279916,0.00038277853,0.00035903964,0.00014360601,0.00030830613],"domain_scores_gemma":[0.9976377,0.000015652937,0.00009637913,0.0020610187,0.00006862053,0.00012065877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710387,0.00018092502,0.00017348112,0.00007374451,0.00012221599,0.00010271146,0.0011608212,0.00019086807,0.000013743385],"category_scores_gemma":[0.000201757,0.00017157599,0.000051009534,0.00015436877,0.000050271166,0.00004847679,0.0005963115,0.00014379084,0.0000191837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007266365,0.0003039707,0.0024772412,0.0007762457,0.00027103216,0.0000013266679,0.00048371797,0.0040671253,0.8797627,0.0001701863,0.06212775,0.048832044],"study_design_scores_gemma":[0.0012647745,0.00033217075,0.0010088003,0.000026807325,0.0001079645,0.000061436236,0.00026201794,0.8421632,0.050618615,0.000051534473,0.10350365,0.0005990215],"about_ca_topic_score_codex":0.000039244907,"about_ca_topic_score_gemma":0.00081845117,"teacher_disagreement_score":0.8380961,"about_ca_system_score_codex":0.000012085198,"about_ca_system_score_gemma":0.00010376811,"threshold_uncertainty_score":0.69966656},"labels":[],"label_agreement":null},{"id":"W2087937056","doi":"10.1186/1471-2105-10-287","title":"Epitopia: a web-server for predicting B-cell epitopes","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":232,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Tel Aviv University; Killam Trusts","keywords":"Epitope; Computer science; Web server; Web application; Interface (matter); Sequence (biology); Computational biology; Graphical user interface; Data mining; Bioinformatics; Antigen; Biology; The Internet; Operating system; Immunology; Genetics","score_opus":0.015221118561711447,"score_gpt":0.2332089179338898,"score_spread":0.21798779937217833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087937056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.821418,0.0013394137,0.15245913,0.0003595496,0.0005994138,0.0017507591,0.00012633674,0.00013777969,0.021809636],"genre_scores_gemma":[0.6853251,0.0003737746,0.30914092,0.0014859615,0.00070790044,0.00007954496,0.000659318,0.00004491244,0.0021825645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987586,0.000011718821,0.0005658219,0.00014405747,0.00013879758,0.0003809762],"domain_scores_gemma":[0.9991137,0.000021852538,0.00022796866,0.0004543121,0.00009362228,0.00008859331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002858566,0.00022616268,0.00020572881,0.00005709556,0.00015679092,0.00009041433,0.00031039002,0.00019474732,0.0000075070357],"category_scores_gemma":[0.00011451762,0.00019492199,0.00019014317,0.00009316863,0.000023526867,0.000029991845,0.00008460007,0.00009021654,0.000024548852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002892345,0.0035921454,0.057839505,0.010482224,0.0010193539,0.000004814747,0.0100219,0.01641385,0.21932408,0.01985165,0.31231788,0.34624025],"study_design_scores_gemma":[0.007615739,0.003070684,0.006558337,0.00012289872,0.00016161986,0.00006953878,0.0026036652,0.639502,0.09975135,0.000774625,0.23825006,0.0015195013],"about_ca_topic_score_codex":0.0000016980957,"about_ca_topic_score_gemma":0.0000060361676,"teacher_disagreement_score":0.6230881,"about_ca_system_score_codex":0.0000135333685,"about_ca_system_score_gemma":0.000110946654,"threshold_uncertainty_score":0.7948688},"labels":[],"label_agreement":null},{"id":"W2090242275","doi":"10.1186/1471-2105-9-450","title":"Bluejay 1.0: genome browsing and comparison with rich customization provision and dynamic resource linking","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Calgary","funders":"Genome Canada; Genome Alberta; University of Calgary","keywords":"Personalization; Resource (disambiguation); Computer science; World Wide Web; Genome; DNA microarray; Computational biology; Biology; Data science; Genetics; Gene","score_opus":0.015214036059689802,"score_gpt":0.24463081578491097,"score_spread":0.22941677972522118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090242275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8731499,0.0010406718,0.12509844,0.000044687033,0.000020621274,0.00015054762,0.000004841251,0.00003616302,0.0004541482],"genre_scores_gemma":[0.8346997,0.00026102926,0.16454767,0.00012319251,0.000040848812,0.0000043350287,0.00014550616,0.000014297671,0.00016344634],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930286,0.00002319991,0.00023366018,0.00014580457,0.00012255822,0.00017188374],"domain_scores_gemma":[0.9995954,0.000023241164,0.00012241057,0.00015409976,0.000034836467,0.00007001423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013573036,0.00012524256,0.00014842743,0.00005125493,0.0001917677,0.00003372859,0.00007274527,0.0001598315,8.3981456e-7],"category_scores_gemma":[0.000058012956,0.000094929266,0.000014934311,0.00008421471,0.00023581149,0.000007956656,0.00010009178,0.00009333711,0.0000019183044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016017922,0.00044960747,0.4539279,0.003273923,0.00035432764,0.000027426997,0.027125495,0.0064450805,0.051486626,0.00009640422,0.004063177,0.45114824],"study_design_scores_gemma":[0.004921579,0.0024663615,0.09930302,0.00039444707,0.0001317619,0.0009998672,0.00610263,0.7703679,0.0053821467,0.000032425414,0.10854055,0.00135726],"about_ca_topic_score_codex":0.0000021914373,"about_ca_topic_score_gemma":0.000015306501,"teacher_disagreement_score":0.76392287,"about_ca_system_score_codex":0.000009612751,"about_ca_system_score_gemma":0.000044443444,"threshold_uncertainty_score":0.3871103},"labels":[],"label_agreement":null},{"id":"W2091244202","doi":"10.1186/1471-2105-13-199","title":"Normalization of ChIP-seq data with control","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Normalization (sociology); Chip; Computer science; False discovery rate; DNA microarray; Data mining; Computational biology; Biology; Genetics; Gene","score_opus":0.012600498616690542,"score_gpt":0.2263756072074164,"score_spread":0.21377510859072585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091244202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45702642,0.00023704162,0.5394139,0.000014144999,0.00011165313,0.00022663779,0.00024429685,0.000010806848,0.0027150859],"genre_scores_gemma":[0.9097644,0.00004686031,0.088809595,0.00010507272,0.0000952621,0.0000034184816,0.0010989008,0.000013669047,0.0000628271],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999366,0.000012493466,0.0002584154,0.00007203375,0.00010627586,0.00018482194],"domain_scores_gemma":[0.9990772,0.000007756002,0.0001872332,0.0006086734,0.00005728981,0.00006186636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019555159,0.00010015675,0.00011140373,0.0000248267,0.00003407938,0.000012533263,0.0002732289,0.00007906983,0.000008162392],"category_scores_gemma":[0.000034346504,0.000079882106,0.000023840978,0.000057047768,0.000047372163,0.000017836363,0.00012470021,0.000033212047,0.000008795474],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070174027,0.00090917264,0.87488806,0.0022001239,0.00073062937,7.1145695e-7,0.002162503,0.021339599,0.069144726,0.0075728544,0.009913508,0.010436354],"study_design_scores_gemma":[0.003961071,0.0006518401,0.053903036,0.000064618274,0.00021582132,0.0000772926,0.0010502044,0.89955366,0.016947689,0.00004375335,0.022722812,0.0008081877],"about_ca_topic_score_codex":0.0000038853814,"about_ca_topic_score_gemma":0.00002075806,"teacher_disagreement_score":0.87821406,"about_ca_system_score_codex":0.000005354055,"about_ca_system_score_gemma":0.00006341764,"threshold_uncertainty_score":0.32574975},"labels":[],"label_agreement":null},{"id":"W2091723965","doi":"10.1186/1471-2105-11-229","title":"GOAL: A software tool for assessing biological significance of genes groups","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"DNA microarray; Computational biology; Software; Biology; Gene; Genetics; Bioinformatics; Computer science; Gene expression; Programming language","score_opus":0.01928520424911289,"score_gpt":0.26124994545107205,"score_spread":0.24196474120195915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091723965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3434234,0.00013595766,0.65507656,0.000015184876,0.0003896938,0.00049065385,0.00009955549,0.00002601219,0.00034296996],"genre_scores_gemma":[0.3232757,0.000060087044,0.67563677,0.00021503754,0.00033354724,0.0000616758,0.00031426994,0.000021949065,0.00008100206],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876094,0.0000141465,0.00062475284,0.0001550024,0.00011623514,0.00032889945],"domain_scores_gemma":[0.99890995,0.000076068514,0.00034004863,0.0004428044,0.00015344341,0.000077671066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041712666,0.00020207369,0.00024515332,0.000043101503,0.00010858123,0.00006235323,0.00032325718,0.0003583302,0.0000131382085],"category_scores_gemma":[0.00020835921,0.0001654746,0.00018130857,0.00008571668,0.00017243426,0.000019266095,0.00013467282,0.00014467427,0.0000073643055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005083888,0.0004279677,0.054321237,0.002404964,0.0003054239,0.000001115225,0.0009215822,0.0019176789,0.6260863,0.00906168,0.013597462,0.29044622],"study_design_scores_gemma":[0.008745596,0.0027665084,0.028275885,0.00025674392,0.00028185936,0.00020807557,0.0032225857,0.34797344,0.28134412,0.009153857,0.31340986,0.00436146],"about_ca_topic_score_codex":0.0000020304772,"about_ca_topic_score_gemma":0.000017050017,"teacher_disagreement_score":0.34605575,"about_ca_system_score_codex":0.0000065243803,"about_ca_system_score_gemma":0.00014110621,"threshold_uncertainty_score":0.67478585},"labels":[],"label_agreement":null},{"id":"W2091810468","doi":"10.1186/1471-2105-9-s3-s1","title":"The Second International Symposium on Languages in Biology and Medicine (LBM) 2007","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computational biology; Biology; Data science; Computer science","score_opus":0.01740688202851943,"score_gpt":0.30610580208425237,"score_spread":0.28869892005573294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091810468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92192256,0.003737803,0.0050230063,0.0041207774,0.0012392396,0.0002894557,0.000056252302,0.000049560575,0.06356134],"genre_scores_gemma":[0.94694686,0.00718371,0.02690042,0.005342875,0.0013898442,0.000047152116,0.0003648086,0.00003201683,0.011792306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994576,0.000022424862,0.0002070682,0.00009220915,0.00007226273,0.00014841963],"domain_scores_gemma":[0.999643,0.00008156284,0.000060272385,0.00015380894,0.000021825834,0.000039500952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019820724,0.00008543997,0.0000910258,0.00003055499,0.00008134956,0.0000072112325,0.00016372719,0.00012599608,0.000025080777],"category_scores_gemma":[0.00021002072,0.000050591716,0.000019200597,0.000039165756,0.00039705096,0.0000023399955,0.00007545506,0.0000855984,0.0000107238075],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011836205,0.00036680227,0.2974913,0.00040035648,0.00040949858,0.000054780576,0.0076441034,0.00009653841,0.032905936,0.010731216,0.37741897,0.2712969],"study_design_scores_gemma":[0.0017055715,0.00079580076,0.026821243,0.00004690815,0.0000062274835,0.0001475687,0.0020678218,0.0035879402,0.0031543057,0.00023331137,0.9611828,0.0002505055],"about_ca_topic_score_codex":0.000008638256,"about_ca_topic_score_gemma":0.00010312527,"teacher_disagreement_score":0.58376384,"about_ca_system_score_codex":0.00000767249,"about_ca_system_score_gemma":0.000023050325,"threshold_uncertainty_score":0.20630702},"labels":[],"label_agreement":null},{"id":"W2092793778","doi":"10.1186/1471-2105-14-11","title":"An improved method to detect correct protein folds using partial clustering","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Alberta Prion Research Institute; Alberta Innovates","keywords":"Decoy; Cluster analysis; Data mining; Computer science; Selection (genetic algorithm); Protein structure prediction; Pattern recognition (psychology); Artificial intelligence; Algorithm; Protein structure","score_opus":0.012986935295008595,"score_gpt":0.27881630737906493,"score_spread":0.2658293720840563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092793778","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18547487,0.00002023516,0.8133064,0.000009509153,0.00011967806,0.0008286927,0.0000115661005,0.000031445088,0.0001976025],"genre_scores_gemma":[0.1696092,0.0000011492072,0.8296847,0.00030695245,0.00018408979,0.00007843718,0.00004028557,0.00002538769,0.00006983714],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889135,0.00005593298,0.00036324136,0.00020200512,0.00012053998,0.00036694584],"domain_scores_gemma":[0.9990783,0.0000073496053,0.00012782357,0.000499168,0.00009370003,0.00019365629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023030836,0.00021146401,0.00017761241,0.00005795699,0.00010636296,0.000115421295,0.00026808897,0.00021058775,0.000018343804],"category_scores_gemma":[0.00007083754,0.00018750074,0.00008132075,0.000111204674,0.000026224934,0.00002770948,0.0001778885,0.0000927366,0.000023877967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006377651,0.000010889798,0.00011669852,0.00008820513,0.000022778035,3.2214948e-7,0.00014551105,0.0062082508,0.9438843,0.000011876107,0.0000759485,0.049371414],"study_design_scores_gemma":[0.00029996678,0.00038450846,0.000104737665,0.000016082975,0.000013854433,0.000024215731,0.00011624986,0.7623477,0.23535243,0.00008025339,0.0009787785,0.0002811972],"about_ca_topic_score_codex":0.00011346297,"about_ca_topic_score_gemma":0.000090334,"teacher_disagreement_score":0.75613946,"about_ca_system_score_codex":0.00002522647,"about_ca_system_score_gemma":0.000100385,"threshold_uncertainty_score":0.7646058},"labels":[],"label_agreement":null},{"id":"W2094867507","doi":"10.1186/1471-2105-14-27","title":"Predicting PDZ domain mediated protein interactions from structure","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Hippo pathway signaling and YAP/TAZ","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"PDZ domain; Computational biology; Peptide; Peptide sequence; Domain (mathematical analysis); Sequence (biology); Biology; Protein sequencing; Protein domain; Computer science; Bioinformatics; Biochemistry; Gene; Mathematics","score_opus":0.00867511211621647,"score_gpt":0.21604297905403494,"score_spread":0.20736786693781847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094867507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9727996,0.0000647273,0.024793342,0.00007171243,0.00018004517,0.00038461824,0.00022297047,0.000054845405,0.0014281633],"genre_scores_gemma":[0.91533464,0.0000050014924,0.08241514,0.00022916435,0.00033928183,0.000051336243,0.001176476,0.000024096731,0.00042487532],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990432,0.000039366787,0.00036753798,0.00015337816,0.0001514522,0.00024506016],"domain_scores_gemma":[0.9992579,0.000027727378,0.00016377743,0.00033729413,0.00009495066,0.00011834129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008151947,0.00017180682,0.00013267434,0.000046513247,0.00011863384,0.0000793771,0.0001927932,0.0001769714,0.00025750292],"category_scores_gemma":[0.00016788162,0.00014584731,0.00007263852,0.00008814812,0.000049650374,0.00001992383,0.000088253335,0.0001689099,0.00021636726],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017619766,0.00002495866,0.0045603523,0.000045275578,0.000054563996,4.3620065e-7,0.0005967752,0.00014554379,0.99213237,0.000024706684,0.00080903375,0.0015883708],"study_design_scores_gemma":[0.0031286296,0.0006192758,0.008392041,0.00035235492,0.00008749107,0.000056205023,0.0053663114,0.14247294,0.7440391,0.0035927799,0.09025657,0.0016362892],"about_ca_topic_score_codex":0.00009749517,"about_ca_topic_score_gemma":0.0001121918,"teacher_disagreement_score":0.24809326,"about_ca_system_score_codex":0.00001517972,"about_ca_system_score_gemma":0.00008596097,"threshold_uncertainty_score":0.5947481},"labels":[],"label_agreement":null},{"id":"W2095632020","doi":"10.1186/1471-2105-7-333","title":"A methodology for global validation of microarray experiments","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"Génome Québec; Genome Canada","keywords":"DNA microarray; Replicate; Microarray; Computer science; Data mining; Concordance; Concordance correlation coefficient; Correlation; Microarray analysis techniques; Computational biology; Bioinformatics; Biology; Gene; Statistics; Genetics; Mathematics; Gene expression","score_opus":0.060875881693568064,"score_gpt":0.3393195170226023,"score_spread":0.27844363532903427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095632020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109097235,0.00018030552,0.8872059,0.000024735815,0.00017371656,0.00024533566,0.000037397862,0.000008565429,0.0030267953],"genre_scores_gemma":[0.37285876,0.000014383451,0.62586707,0.000099751305,0.00012527016,0.00006627614,0.00049905205,0.000008480488,0.0004609439],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994258,0.000029527273,0.00027984226,0.000090933245,0.00006720972,0.00010664286],"domain_scores_gemma":[0.9995136,0.000010393861,0.00017627893,0.00019464552,0.000083408566,0.0000216426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015385039,0.000073992625,0.00009195909,0.000022877091,0.00002986192,0.000008484681,0.000099990415,0.00010166268,0.0000056553727],"category_scores_gemma":[0.000046237088,0.000067632165,0.00006737055,0.00006080312,0.00003401564,0.000004140519,0.000027014446,0.000013125085,0.0000025371148],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011922918,0.00006040282,0.0030378662,0.00010365706,0.00001513172,1.39116105e-8,0.000060732375,0.000426593,0.98052657,0.0021567855,0.011281106,0.002211901],"study_design_scores_gemma":[0.0006035763,0.00009802103,0.0011781036,0.000006299987,0.000011153169,0.0000024310825,0.00016303807,0.0011253232,0.9738348,0.0005991267,0.022289382,0.00008876008],"about_ca_topic_score_codex":0.0000057391485,"about_ca_topic_score_gemma":0.0000043319337,"teacher_disagreement_score":0.26376152,"about_ca_system_score_codex":0.000013220649,"about_ca_system_score_gemma":0.0000611518,"threshold_uncertainty_score":0.27579597},"labels":[],"label_agreement":null},{"id":"W2095857517","doi":"10.1186/1471-2105-11-65","title":"Haplotype allelic classes for detecting ongoing positive selection","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Digestive system and related health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université de Montréal","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Biology; Haplotype; Genetics; Allele frequency; Locus (genetics); International HapMap Project; Linkage disequilibrium; Natural selection; Allele; Selection (genetic algorithm); Evolutionary biology; Computer science; Gene; Artificial intelligence","score_opus":0.012740858546409061,"score_gpt":0.27290535632370805,"score_spread":0.260164497777299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095857517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6870237,0.00011668475,0.2988856,0.00010938579,0.0010651465,0.0010440439,0.000034913308,0.00009586405,0.01162467],"genre_scores_gemma":[0.90463483,0.000031071908,0.09373069,0.00024506624,0.00046248938,0.000039779352,0.00012531735,0.00003256257,0.0006982193],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924374,0.00001699335,0.00027819787,0.00012757692,0.00008094953,0.00025251985],"domain_scores_gemma":[0.9994224,0.0000407817,0.00015400925,0.0001405195,0.00016491338,0.00007742944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025740542,0.00012426489,0.000113244256,0.000051118943,0.00020771606,0.00003848223,0.0000917938,0.00025447074,0.000004331604],"category_scores_gemma":[0.00022708574,0.00010792682,0.00007730115,0.00008050687,0.000034556142,0.000010333131,0.00003469217,0.0001471744,0.000024660108],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005337177,0.00024496118,0.025020435,0.0017663751,0.0003691312,0.0000010365353,0.0017876028,0.0013912846,0.91664493,0.0061965,0.0057821246,0.040261906],"study_design_scores_gemma":[0.0042944993,0.0033800362,0.018770862,0.00028832135,0.00017841507,0.0003820794,0.0025926044,0.1885815,0.6348492,0.00037454884,0.14467253,0.001635423],"about_ca_topic_score_codex":0.000015679834,"about_ca_topic_score_gemma":0.00032366675,"teacher_disagreement_score":0.28179574,"about_ca_system_score_codex":0.000013296339,"about_ca_system_score_gemma":0.00016266837,"threshold_uncertainty_score":0.4401128},"labels":[],"label_agreement":null},{"id":"W2096548036","doi":"10.1186/1471-2105-5-3","title":"VKCDB: Voltage-gated potassium channel database","year":2004,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Ion channel regulation and function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Potassium channel; Voltage-gated potassium channel; Ion channel; Voltage-gated ion channel; Inward-rectifier potassium ion channel; Biology; Database; Channel (broadcasting); GenBank; Potassium; Chemistry; Computer science; Biophysics; Biochemistry","score_opus":0.04418633462436138,"score_gpt":0.2961691965879071,"score_spread":0.2519828619635457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096548036","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.7243574e-7,0.866781,0.12712526,0.000007083756,0.001808588,0.00076826656,0.00055330864,0.000076400676,0.0028796208],"genre_scores_gemma":[0.0000013745943,0.97260284,0.0056222514,0.000107434,0.00080701325,0.000045227247,0.0133981975,0.00006976627,0.007345872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822325,0.000046084322,0.0008089343,0.00030890328,0.00025050555,0.00036232037],"domain_scores_gemma":[0.99846095,0.000016232529,0.0005072014,0.0007318713,0.00012118739,0.00016256],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025158923,0.0004892802,0.0006637035,0.0001942764,0.0001234858,0.000072671835,0.0003230964,0.00068796484,0.000088868524],"category_scores_gemma":[0.00012638635,0.00040525504,0.0004315766,0.00027406518,0.000076017095,0.000014566628,0.00020804931,0.0002452374,0.00079487346],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009803308,0.0003509619,0.000001823012,0.11301191,0.00063111144,0.000011259159,0.00021855583,0.0015360261,0.000033339744,0.0006918477,0.1276095,0.7558056],"study_design_scores_gemma":[0.00038619863,0.00008580359,3.5299536e-7,0.00227287,0.00019571818,0.0000743946,0.000044650344,0.0030008599,0.000039759427,0.000008360182,0.99340373,0.00048729664],"about_ca_topic_score_codex":0.000005293305,"about_ca_topic_score_gemma":0.000004876845,"teacher_disagreement_score":0.86579424,"about_ca_system_score_codex":0.00007729861,"about_ca_system_score_gemma":0.00059530616,"threshold_uncertainty_score":0.99998313},"labels":[],"label_agreement":null},{"id":"W2097593311","doi":"10.1186/1471-2105-11-243","title":"MOTIPS: Automated Motif Analysis for Predicting Targets of Modular Protein Domains","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Institute on Drug Abuse; National Institutes of Health","keywords":"Computational biology; Motif (music); Modular design; DNA microarray; Computer science; Bioinformatics; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.008454412933677317,"score_gpt":0.23456004819857065,"score_spread":0.22610563526489333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097593311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44647822,0.0000521816,0.55155694,0.000019450537,0.0001674427,0.0007362374,0.00019724567,0.000070505645,0.0007217999],"genre_scores_gemma":[0.6605363,0.0000074739687,0.33846208,0.000053906664,0.00013202005,0.000051899435,0.0005783696,0.000021188502,0.00015675717],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984272,0.000016346914,0.00081790827,0.00017227796,0.00018672,0.00037953176],"domain_scores_gemma":[0.99853176,0.000025058196,0.0004901136,0.00062031514,0.00020662698,0.00012610081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005340315,0.00023075327,0.00033924507,0.00015762863,0.00012481328,0.000043939304,0.0003398654,0.00034528173,0.000013801369],"category_scores_gemma":[0.00017576899,0.00020852702,0.00033049902,0.00030400563,0.000112306465,0.000017221631,0.00013684684,0.00015568918,0.000005473388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070223137,0.0008066936,0.06993539,0.004252347,0.00638552,0.000001854369,0.0033083232,0.21441899,0.6744887,0.006644152,0.008010601,0.011045198],"study_design_scores_gemma":[0.0007393605,0.00017871388,0.0019826991,0.000015562442,0.00019966443,0.0000042925876,0.00018467767,0.9712679,0.022488466,0.00019131492,0.0024959142,0.00025145127],"about_ca_topic_score_codex":0.00000786236,"about_ca_topic_score_gemma":0.00009634681,"teacher_disagreement_score":0.7568489,"about_ca_system_score_codex":0.000009318248,"about_ca_system_score_gemma":0.000109046334,"threshold_uncertainty_score":0.85034853},"labels":[],"label_agreement":null},{"id":"W2098478473","doi":"10.1186/1471-2105-7-534","title":"iHOPerator: user-scripting a personalized bioinformatics Web, starting with the iHOP website","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia; Providence Health Care","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Genome Alberta; Michael Smith Health Research BC; Genome Canada","keywords":"World Wide Web; Computer science; Scripting language; Web page; Web navigation; Client-side scripting; Web development; Dynamic web page; Context (archaeology); User interface; Web design; Web service; Static web page","score_opus":0.0658434519539109,"score_gpt":0.3047877373377604,"score_spread":0.2389442853838495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098478473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18631606,0.00015270172,0.7452836,0.0020348462,0.0011478137,0.0010706044,0.0001533249,0.00049620937,0.06334484],"genre_scores_gemma":[0.17187954,0.000009466436,0.797036,0.0040397397,0.00054535747,0.000047486363,0.00015476048,0.00006415339,0.02622352],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99450964,0.00013315953,0.0016361986,0.00038450744,0.0026225634,0.000713907],"domain_scores_gemma":[0.9957788,0.0010083138,0.00092099543,0.0017042605,0.000447231,0.00014041891],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0069218483,0.00033803657,0.00038559237,0.0003909792,0.0010908385,0.0032420394,0.0017266147,0.0000764915,0.00019713514],"category_scores_gemma":[0.0009830035,0.00017910932,0.00017120053,0.0019351012,0.00034726714,0.0014213845,0.0006941092,0.00026208462,0.0013836211],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010467119,0.00013747912,0.024313482,0.00018579396,0.00006959176,0.000009327985,0.008823227,0.02681224,0.000054400884,0.01362235,0.89465755,0.0312099],"study_design_scores_gemma":[0.0006848105,0.00004528916,0.001027802,0.000045932364,0.000029154779,0.000010766103,0.01496828,0.72594184,0.000022541488,0.00024984256,0.25670436,0.00026938773],"about_ca_topic_score_codex":0.000059307506,"about_ca_topic_score_gemma":0.00035143207,"teacher_disagreement_score":0.6991296,"about_ca_system_score_codex":0.000079435806,"about_ca_system_score_gemma":0.00023594788,"threshold_uncertainty_score":0.99939394},"labels":[],"label_agreement":null},{"id":"W2098927868","doi":"10.1186/1471-2105-13-s6-s11","title":"Challenges in estimating percent inclusion of alternatively spliced junctions from RNA-seq data","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Alternative splicing; Probabilistic logic; Computational biology; Exon; RNA-Seq; Focus (optics); Metric (unit); Artificial intelligence; Data mining; Machine learning; Biology; Genetics; Transcriptome; Gene; Gene expression; Physics","score_opus":0.13135979292320452,"score_gpt":0.3494587628119391,"score_spread":0.2180989698887346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098927868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9470921,0.0015857285,0.04849708,0.000095012525,0.00020154883,0.00020259205,0.00009612662,0.000009970776,0.0022198497],"genre_scores_gemma":[0.7955712,0.0008744058,0.20264311,0.00005090438,0.00024100154,0.000008175238,0.00051233335,0.000013832025,0.00008501124],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990003,0.00003947775,0.0003443089,0.00012911567,0.00021835238,0.00026843054],"domain_scores_gemma":[0.9991118,0.0000363141,0.00013527379,0.00057316484,0.00004705231,0.00009640742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049559854,0.00010773593,0.00013857325,0.00006881563,0.000086851804,0.000011631889,0.00040714396,0.00008821499,0.000011680222],"category_scores_gemma":[0.00030475808,0.000093835886,0.000032991826,0.00006541826,0.000042252494,0.00003806462,0.0015280457,0.00010116863,0.000012830558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038051308,0.00096309296,0.05103024,0.0011002755,0.00023319163,0.0000024007427,0.011764447,0.0036413977,0.63427556,0.0007343213,0.0025953176,0.29327926],"study_design_scores_gemma":[0.0014071773,0.00019753104,0.032680884,0.00021764867,0.00002449579,0.000009258735,0.0034668273,0.920067,0.036775667,0.00009830747,0.004689343,0.0003658416],"about_ca_topic_score_codex":0.00019203838,"about_ca_topic_score_gemma":0.00026977723,"teacher_disagreement_score":0.91642565,"about_ca_system_score_codex":0.000021705126,"about_ca_system_score_gemma":0.00006437148,"threshold_uncertainty_score":0.38265163},"labels":[],"label_agreement":null},{"id":"W2099003362","doi":"10.1186/s12859-015-0497-0","title":"GeneDig: a web application for accessing genomic and bioinformatics knowledge","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Montreal General Hospital","funders":"McGill University Health Centre; McGill University","keywords":"Computer science; World Wide Web; Genomic information; Usability; Genomics; Data science; Genome; Bioinformatics; Computational biology; Biology; Human–computer interaction; Gene; Genetics","score_opus":0.046363336134565385,"score_gpt":0.3213206243563992,"score_spread":0.2749572882218338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099003362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13250367,0.0019615474,0.8504955,0.00023604534,0.00058498606,0.0022191196,0.0002453563,0.000105034735,0.011648697],"genre_scores_gemma":[0.17856191,0.0011650382,0.81517375,0.0009143998,0.0011120604,0.00029359185,0.001465978,0.00009392988,0.0012193458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979979,0.000028629594,0.0008458206,0.00022361339,0.0003401516,0.00056388776],"domain_scores_gemma":[0.99818814,0.000058290116,0.00028201664,0.00053174264,0.00040347685,0.0005363622],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009608884,0.00030238437,0.0002878519,0.00018642057,0.00019197981,0.00019041791,0.00046001552,0.00034610598,0.000002712039],"category_scores_gemma":[0.000508942,0.00026304112,0.000115789066,0.0001935988,0.000300259,0.00004525218,0.0004514069,0.00013479036,0.00008957944],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011071054,0.00069749786,0.014660539,0.007951073,0.0004616878,0.0000012648803,0.008341922,0.0006908068,0.050009802,0.001783801,0.09407701,0.8202175],"study_design_scores_gemma":[0.0027419392,0.0006663394,0.0007494059,0.000043162923,0.00005490661,0.000038687453,0.0023557858,0.78363043,0.0050259656,0.00034968174,0.20375927,0.00058440823],"about_ca_topic_score_codex":0.000004560483,"about_ca_topic_score_gemma":0.00005076778,"teacher_disagreement_score":0.81963307,"about_ca_system_score_codex":0.000059856236,"about_ca_system_score_gemma":0.00079959264,"threshold_uncertainty_score":0.9999822},"labels":[],"label_agreement":null},{"id":"W2099753867","doi":"10.1186/1471-2105-12-491","title":"MAKER2: an annotation pipeline and genome-database management tool for second-generation genome projects","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2312,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Division of Integrative Organismal Systems; National Institute of General Medical Sciences; National Human Genome Research Institute; University of Utah; Agricultural Research Service; San Francisco State University; Michigan State University; College of Engineering, Michigan State University; U.S. Department of Agriculture; National Institutes of Health; National Science Foundation","keywords":"Annotation; Genome; Genome project; Gene Annotation; Computer science; DNA sequencing; Pipeline (software); Genome browser; Computational biology; Genomics; Database; Data mining; Biology; Gene; Genetics; Artificial intelligence","score_opus":0.04623520706017015,"score_gpt":0.24603221744344678,"score_spread":0.19979701038327663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099753867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8587013,0.0004689119,0.13766085,0.000009914281,0.00013745134,0.001100164,0.00039483956,0.000009951604,0.0015166125],"genre_scores_gemma":[0.540343,0.00041626615,0.45589247,0.00042103953,0.00031088133,0.0001868933,0.0015940479,0.00003077434,0.000804621],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991919,0.000015908128,0.00031334098,0.0002016441,0.00007191843,0.00020532947],"domain_scores_gemma":[0.9994278,0.000005368997,0.00011878363,0.000295952,0.000094764626,0.000057364028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022324642,0.0001609063,0.000117908465,0.000055925713,0.00012738966,0.00003614583,0.00010388469,0.000074987256,0.0000112363305],"category_scores_gemma":[0.000018260653,0.0001521323,0.00004139064,0.00004446413,0.00004015757,0.0000077029845,0.000106256724,0.000028547423,0.000005101242],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004428236,0.00032536912,0.003056918,0.0016484105,0.00031509149,0.0000023282148,0.006073337,0.00040859415,0.9678783,0.0023414374,0.001452264,0.016055137],"study_design_scores_gemma":[0.013834436,0.007578633,0.23136783,0.0000980104,0.0010027526,0.00017210825,0.013446174,0.22953622,0.25238544,0.0013179304,0.24373138,0.005529086],"about_ca_topic_score_codex":0.000002747331,"about_ca_topic_score_gemma":0.000078505844,"teacher_disagreement_score":0.71549284,"about_ca_system_score_codex":0.000009658479,"about_ca_system_score_gemma":0.000030620606,"threshold_uncertainty_score":0.6203775},"labels":[],"label_agreement":null},{"id":"W2099950456","doi":"10.1186/1471-2105-5-101","title":"Structural characterization of genomes by large scale sequence-structure threading: application of reliability analysis in structural genomics","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; BC Centre for Disease Control; Simon Fraser University; University of British Columbia","funders":"Genome Prairie; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Weibull distribution; Maintainability; Reliability (semiconductor); Structural genomics; Genome; Threading (protein sequence); Computational biology; Biology; Computer science; Reliability engineering; Genomics; Genetics; Data mining; Power (physics); Gene; Protein structure; Statistics; Engineering; Mathematics; Physics","score_opus":0.00539309504578688,"score_gpt":0.23219419528709262,"score_spread":0.22680110024130573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099950456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88600045,0.00007334376,0.1125069,0.000010496896,0.000040535895,0.0003269917,0.0010024987,0.000007723601,0.00003107347],"genre_scores_gemma":[0.95650166,0.000041647843,0.03965848,0.000033522356,0.000028664905,0.000006213953,0.0037118373,0.0000114089735,0.0000065660593],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986795,0.000022839029,0.00069058087,0.0002099715,0.00017167919,0.00022542741],"domain_scores_gemma":[0.9988218,0.0000062887657,0.00050146197,0.00048768774,0.0001297432,0.000053038086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013024228,0.00019240155,0.00034231335,0.00013156608,0.00004698794,0.000013923425,0.00026199518,0.0002533022,0.00000609762],"category_scores_gemma":[0.000028495855,0.00017232349,0.00013206125,0.00044753263,0.00012145313,0.000028546281,0.000092731185,0.00010022659,4.1084104e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014171335,0.000022324983,0.1653024,0.00035979936,0.00012108779,1.17108264e-7,0.0011005817,0.03358806,0.7969993,0.0005645589,0.0000016271091,0.0017984546],"study_design_scores_gemma":[0.0019203357,0.00024450247,0.17761819,0.000024280402,0.000258451,0.000012527351,0.00044008967,0.39721665,0.41787627,0.0035739723,0.00017966393,0.00063507794],"about_ca_topic_score_codex":0.000044145632,"about_ca_topic_score_gemma":0.00025064792,"teacher_disagreement_score":0.379123,"about_ca_system_score_codex":0.00007063565,"about_ca_system_score_gemma":0.00011413759,"threshold_uncertainty_score":0.7027148},"labels":[],"label_agreement":null},{"id":"W2100258314","doi":"10.1186/1471-2105-5-96","title":"Base-By-Base: Single nucleotide-level analysis of whole viral genome alignments","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Poxvirus research and outbreaks","field":"Immunology and Microbiology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Genome; Annotation; Biology; Computational biology; Java; Gene; Genome browser; Genetics; DNA microarray; Computer science; Software; Genomics; Programming language","score_opus":0.03318109257616441,"score_gpt":0.2569063753054517,"score_spread":0.22372528272928727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100258314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8902379,0.00187274,0.092276335,0.000229648,0.00043608042,0.0006820261,0.0065146997,0.00015950367,0.0075910287],"genre_scores_gemma":[0.97696775,0.00007410983,0.0168525,0.0005079802,0.00002434232,0.000015707577,0.0029225128,0.00002676271,0.0026083523],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99854535,0.0000568971,0.0006033284,0.00014968753,0.00012274692,0.0005220132],"domain_scores_gemma":[0.999112,0.00007073991,0.00022892073,0.00043596746,0.000081253216,0.00007109264],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002819468,0.00019131732,0.00041602858,0.00037287473,0.0001296557,0.00002650635,0.000362612,0.00019958658,0.00038377574],"category_scores_gemma":[0.00007993242,0.00016657622,0.00023956488,0.00051479385,0.0002524874,0.00022711269,0.0001392386,0.00017827083,0.0011705193],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027479287,0.001003237,0.004469845,0.0002423013,0.0032871475,0.00000553805,0.002215377,0.002340666,0.97134024,0.0006531204,0.008241554,0.005926163],"study_design_scores_gemma":[0.012739686,0.0017453922,0.028165175,0.00014811751,0.0022227105,0.000036466867,0.0031990577,0.0039573465,0.81606174,0.0006525149,0.1294791,0.0015926799],"about_ca_topic_score_codex":0.0001648991,"about_ca_topic_score_gemma":0.00009748817,"teacher_disagreement_score":0.1552785,"about_ca_system_score_codex":0.00011624788,"about_ca_system_score_gemma":0.000136151,"threshold_uncertainty_score":0.9996072},"labels":[],"label_agreement":null},{"id":"W2100284033","doi":"10.1186/1471-2105-15-344","title":"CIG-P: Circular Interaction Graph for Proteomics","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity Western University; Western University","funders":"Trinity Western University","keywords":"Visualization; Proteomics; Computer science; AKA; Computational biology; Graph; Data mining; Biology; Biochemistry; Theoretical computer science","score_opus":0.01974616961840828,"score_gpt":0.2766336423122025,"score_spread":0.2568874726937942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100284033","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0081981,0.0000063967054,0.9811743,0.000053178435,0.000036844747,0.0004296668,0.00003419243,0.00023544782,0.009831866],"genre_scores_gemma":[0.027466143,0.000015902144,0.9712891,0.00012731638,0.00011432486,0.0006248073,0.00012819697,0.000024287414,0.00020991685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992605,0.0000030542249,0.00034695558,0.00011205916,0.000088090004,0.00018935687],"domain_scores_gemma":[0.9992002,0.000068692185,0.00020840109,0.00038870948,0.00007551558,0.000058439688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012973804,0.00012890965,0.00013239679,0.0000455759,0.00013156715,0.00004660805,0.00018962167,0.00011809414,0.00003463994],"category_scores_gemma":[0.00009010274,0.00012574109,0.000108375534,0.00007645681,0.000034266453,0.00019739494,0.000040229297,0.00012838624,0.000026684656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044098627,0.00076969725,0.0044984543,0.012775926,0.00024041372,5.0352946e-7,0.002461912,0.012219162,0.32876644,0.439684,0.014395494,0.183747],"study_design_scores_gemma":[0.00065985596,0.000046372,0.000017218386,0.0000804951,0.00003351937,0.000014600745,0.0002757591,0.62441677,0.20331414,0.04668906,0.12404754,0.0004046815],"about_ca_topic_score_codex":0.0000026489074,"about_ca_topic_score_gemma":0.0000018410941,"teacher_disagreement_score":0.6121976,"about_ca_system_score_codex":0.000046799993,"about_ca_system_score_gemma":0.000022336231,"threshold_uncertainty_score":0.5127573},"labels":[],"label_agreement":null},{"id":"W2100744247","doi":"10.1186/1471-2105-11-484","title":"Protein network prediction and topological analysis in Leishmania major as a tool for drug target selection","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Research on Leishmaniasis Studies","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; National Institutes of Health; Universidad de Antioquia; McMaster University; Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Tropical disease; Computational biology; Betweenness centrality; Proteome; Interaction network; Drug discovery; Biology; Centrality; Drug; Leishmania; Computer science; Disease; Bioinformatics; Genetics; Medicine; Gene; Parasite hosting; Pharmacology; Mathematics","score_opus":0.016249164020894335,"score_gpt":0.28605494756141575,"score_spread":0.2698057835405214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100744247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9696459,0.000058454698,0.025495809,0.00076185464,0.00010076996,0.0023557171,0.000022347367,0.00010841563,0.0014506925],"genre_scores_gemma":[0.6085556,0.00003382006,0.38895392,0.0001933261,0.00036393583,0.00050562207,0.00008912603,0.000017648916,0.0012869891],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985959,0.000032607964,0.0005002904,0.0001772108,0.00029944722,0.00039455737],"domain_scores_gemma":[0.9992899,0.00012498819,0.00012013122,0.00019489674,0.00016427324,0.000105869934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089154736,0.00015653833,0.0003879164,0.00027528242,0.00016919377,0.000064270396,0.000074271105,0.00015432967,0.00007929889],"category_scores_gemma":[0.0008525619,0.00012190901,0.000114422175,0.0007348852,0.000111098074,0.00024639347,0.000073088326,0.00037067643,0.000015442653],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009127619,0.0002466932,0.98104215,0.00090966036,0.0005771224,0.000004555702,0.0012602723,0.00054449047,0.0008275473,0.0048475503,0.005539056,0.0032881158],"study_design_scores_gemma":[0.0026445256,0.00070023286,0.41635153,0.000063949585,0.00037789613,0.000045235316,0.000666672,0.56988734,0.0006757763,0.0017478516,0.0065961606,0.00024281479],"about_ca_topic_score_codex":0.000072913375,"about_ca_topic_score_gemma":0.0010402952,"teacher_disagreement_score":0.56934285,"about_ca_system_score_codex":0.00006360625,"about_ca_system_score_gemma":0.0001045939,"threshold_uncertainty_score":0.4971305},"labels":[],"label_agreement":null},{"id":"W2101212866","doi":"10.1186/1471-2105-10-45","title":"Comparison of small n statistical tests of differential expression applied to microarrays","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"","keywords":"DNA microarray; Bayes' theorem; Statistical hypothesis testing; Statistical power; Normalization (sociology); Statistics; False discovery rate; Sample size determination; Multiple comparisons problem; Computer science; Statistic; Data mining; Mathematics; Biology; Bayesian probability; Genetics; Gene expression; Gene","score_opus":0.029347025360879755,"score_gpt":0.3093103171116424,"score_spread":0.2799632917507627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101212866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35160723,0.000038768823,0.64562756,0.000020773074,0.00007370322,0.00022869723,0.000037939717,0.000008584061,0.0023567323],"genre_scores_gemma":[0.86075246,0.0000064026717,0.1389607,0.00006272729,0.000033193974,0.000006256922,0.00012819067,0.0000052761316,0.00004478954],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913776,0.000015310297,0.0004613992,0.00011406525,0.0001401959,0.00013127082],"domain_scores_gemma":[0.9993198,0.000012163246,0.00021063318,0.0003046401,0.00006882574,0.00008392015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058711124,0.00010719269,0.00019361335,0.000058548263,0.000026376913,0.000008530446,0.00017234944,0.00010758876,0.00001913439],"category_scores_gemma":[0.000046197765,0.00009138399,0.000043551794,0.000078938785,0.00003671358,0.0000022313284,0.00005269114,0.000046397396,0.00000590556],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001402518,0.00012845395,0.0012890847,0.00007273886,0.0000043081136,1.7060927e-8,0.00023932854,0.00025082912,0.9858766,0.0003508676,0.0038559684,0.00779153],"study_design_scores_gemma":[0.00045176805,0.00031991058,0.02081961,0.00003443589,0.000011766463,5.873584e-7,0.00026298582,0.0024545619,0.97372115,0.000058440703,0.0017420608,0.00012270639],"about_ca_topic_score_codex":8.247207e-7,"about_ca_topic_score_gemma":0.0000031969882,"teacher_disagreement_score":0.5091452,"about_ca_system_score_codex":0.000006439616,"about_ca_system_score_gemma":0.000052289528,"threshold_uncertainty_score":0.3726531},"labels":[],"label_agreement":null},{"id":"W2101348989","doi":"10.1186/1471-2105-11-s4-i1","title":"Proceedings of the ninth annual UT-ORNL-KBRIN Bioinformatics Summit 2010","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Vanderbilt University; University of British Columbia; National Institutes of Health; University of Memphis; University of Louisville","keywords":"Summit; Library science; Session (web analytics); Political science; Oak Ridge National Laboratory; Medical education; Informatics; Medicine; World Wide Web; Computer science; Geography","score_opus":0.014106414844126076,"score_gpt":0.2563653818904353,"score_spread":0.2422589670463092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101348989","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540724,0.000106632644,0.0061076065,0.00061582756,0.0025232735,0.0016905615,0.00066095666,0.00008850183,0.034134243],"genre_scores_gemma":[0.50445044,0.00074112666,0.47680676,0.0018826872,0.0016449733,0.000107458385,0.00052237156,0.00016576667,0.013678397],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99677444,0.000015647007,0.0012752967,0.00021643884,0.00096006755,0.0007581261],"domain_scores_gemma":[0.9974981,0.000049057897,0.00060723507,0.0007591755,0.00073362095,0.00035283045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009494513,0.00038767105,0.00036702686,0.00017479004,0.00022777272,0.0001207501,0.0014026467,0.0005769317,0.00006962531],"category_scores_gemma":[0.0010824853,0.0002650468,0.00031477876,0.00043543457,0.00096320955,0.000058348796,0.000883061,0.000638633,0.00012944512],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070545846,0.0012789265,0.121567555,0.0077027613,0.000660402,0.0000019311287,0.008230702,0.0001463246,0.18206392,0.0055475603,0.56762975,0.10446471],"study_design_scores_gemma":[0.004181329,0.0016818477,0.038323883,0.0002767395,0.00018396946,0.0001396841,0.012931902,0.085776895,0.37194523,0.0005630037,0.48198697,0.002008541],"about_ca_topic_score_codex":0.000018966773,"about_ca_topic_score_gemma":0.00014729386,"teacher_disagreement_score":0.47069916,"about_ca_system_score_codex":0.000020277683,"about_ca_system_score_gemma":0.0004278015,"threshold_uncertainty_score":0.99998015},"labels":[],"label_agreement":null},{"id":"W2102858485","doi":"10.1186/1471-2105-10-357","title":"AIR: A batch-oriented web program package for construction of supermatrices ready for phylogenomic analyses","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Norges Forskningsråd; Universitetet i Oslo","keywords":"Phylogenetic tree; Sequence (biology); Biology; Computational biology; Tree (set theory); Phylogenomics; DNA microarray; Evolutionary biology; Phylogenetics; R package; Computer science; Gene; Data mining; Bioinformatics; Genetics; Clade; Programming language","score_opus":0.0384095315106722,"score_gpt":0.3222790566447174,"score_spread":0.2838695251340452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102858485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.929397,0.00079894543,0.06634054,0.00006545139,0.00021351021,0.0017431413,0.00083571713,0.000018655232,0.00058703765],"genre_scores_gemma":[0.6058356,0.00021599956,0.3931408,0.0000909059,0.00013990144,0.00010242964,0.0004217994,0.000013160924,0.000039380266],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900854,0.000011920788,0.00048187902,0.00015811168,0.00008445364,0.00025510057],"domain_scores_gemma":[0.99914515,0.000033956705,0.00025207124,0.00028244196,0.00023242839,0.00005395765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000144287,0.00017880127,0.00025856998,0.00007282142,0.00010226935,0.000017000977,0.0001592088,0.00012592254,0.0000011341948],"category_scores_gemma":[0.00008113284,0.00015724132,0.00017628194,0.0001002246,0.00009147207,0.0000030632268,0.000037868333,0.00002897205,0.000001258404],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047038612,0.00026620395,0.0028479511,0.0006267839,0.0003206823,1.2114324e-7,0.0003616558,0.0004003271,0.9341606,0.0014274606,0.0026155144,0.056502316],"study_design_scores_gemma":[0.005539569,0.008910442,0.008094518,0.000047072102,0.0005838966,0.00003627315,0.0030944843,0.029273655,0.794049,0.0010548527,0.14828837,0.0010278375],"about_ca_topic_score_codex":0.0000028271907,"about_ca_topic_score_gemma":0.00001539977,"teacher_disagreement_score":0.32680026,"about_ca_system_score_codex":0.000011165119,"about_ca_system_score_gemma":0.000107441105,"threshold_uncertainty_score":0.6412115},"labels":[],"label_agreement":null},{"id":"W2103183338","doi":"10.1186/1471-2105-13-s19-s2","title":"Exploiting ancestral mammalian genomes for the prediction of human transcription factor binding sites","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"DNA binding site; Genome; Genomics; Biology; Computational biology; Comparative genomics; Transcription factor; Evolutionary biology; Genetics; Genome evolution; Gene; Promoter","score_opus":0.04655835942742874,"score_gpt":0.262063859411683,"score_spread":0.21550549998425422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103183338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9443085,0.00025339882,0.054555718,0.00000968978,0.00017070796,0.0002744437,0.00027030738,0.000009653564,0.00014756921],"genre_scores_gemma":[0.976488,0.00006858441,0.022664478,0.000018517238,0.00023721562,0.000023507295,0.00040006574,0.0000133652475,0.00008627436],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930656,0.000009342141,0.0003193741,0.00006326176,0.00008032459,0.00022114617],"domain_scores_gemma":[0.999543,0.000017108554,0.00017994651,0.00017442943,0.00004286537,0.000042667343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001560026,0.00010462287,0.000093901115,0.000029733803,0.00015230298,0.000024213883,0.00013141894,0.00008966135,0.0000068380355],"category_scores_gemma":[0.00001907378,0.00008104407,0.00010168082,0.000041075768,0.000045303557,0.000018594244,0.000025486279,0.000041040916,0.0000018633756],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002457184,0.000054483484,0.07659185,0.00046474772,0.00006572649,1.678545e-8,0.0019856559,0.00045106618,0.9166201,0.000591977,0.00024741745,0.0029024081],"study_design_scores_gemma":[0.003070474,0.0014406431,0.1418348,0.000109949746,0.00031423356,0.00003622892,0.01817541,0.22349538,0.5991332,0.00021548054,0.011195606,0.0009786119],"about_ca_topic_score_codex":0.000002677329,"about_ca_topic_score_gemma":0.000013679976,"teacher_disagreement_score":0.31748688,"about_ca_system_score_codex":0.000013852627,"about_ca_system_score_gemma":0.000020807653,"threshold_uncertainty_score":0.33048812},"labels":[],"label_agreement":null},{"id":"W2103592640","doi":"10.1186/1471-2105-15-229","title":"SnowyOwl: accurate prediction of fungal genes by using RNA-Seq and homology information to select among ab initio models","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Concordia University","funders":"Genome Alberta; Genome Canada; McGill University","keywords":"Gene prediction; Genome; Computational biology; Gene; Biology; Genetics; Homology (biology); Gene Annotation; RNA-Seq; Genomics; DNA microarray; Transcriptome; Gene expression","score_opus":0.020085814343212993,"score_gpt":0.2237495654642957,"score_spread":0.2036637511210827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103592640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8166954,0.00020690066,0.18174018,0.000011226377,0.000096441436,0.00020533132,0.00015128752,0.000005647619,0.00088760076],"genre_scores_gemma":[0.9752532,0.00029334842,0.02404748,0.00017199827,0.000063283376,0.000013998842,0.0001287595,0.000010399236,0.000017501805],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991393,0.000029216153,0.00043743054,0.000100210156,0.00009743752,0.00019637829],"domain_scores_gemma":[0.999368,0.000017696488,0.00020545158,0.00018706311,0.00014725125,0.000074553966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019764889,0.0001480621,0.00017521175,0.000074379364,0.000092576156,0.00003047209,0.00010223488,0.00014233736,0.0000014919353],"category_scores_gemma":[0.00005657111,0.00014184839,0.00004137795,0.00008366888,0.00008123734,0.00001724997,0.00013316426,0.000048192218,0.0000023865227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056228763,0.00019396214,0.08365949,0.0017566729,0.0007003292,4.5101604e-7,0.007052136,0.23082018,0.58779204,0.0016044959,0.009986224,0.07587173],"study_design_scores_gemma":[0.0011102422,0.00083094684,0.011075125,0.000036793364,0.00008753091,0.00003458588,0.0006553748,0.91612226,0.06338218,0.00032794112,0.0059158904,0.00042110344],"about_ca_topic_score_codex":0.000032452626,"about_ca_topic_score_gemma":0.000020191224,"teacher_disagreement_score":0.6853021,"about_ca_system_score_codex":0.000011612696,"about_ca_system_score_gemma":0.000050747138,"threshold_uncertainty_score":0.57844096},"labels":[],"label_agreement":null},{"id":"W2104239076","doi":"10.1186/1471-2105-10-241","title":"Multi-level learning: improving the prediction of protein, domain and residue interactions by allowing information flow between levels","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institutes of Health; Yale University","keywords":"Computer science; Computational biology; Domain (mathematical analysis); DNA microarray; Bioinformatics; Chemistry; Biology; Biochemistry; Mathematics; Gene expression; Gene","score_opus":0.017120454248524975,"score_gpt":0.24037328422694504,"score_spread":0.22325282997842005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104239076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25936204,0.000074184005,0.73952013,0.000077815115,0.000046886806,0.00046298068,0.00019860154,0.000021943342,0.00023543021],"genre_scores_gemma":[0.76961535,0.000014495498,0.22956668,0.000110268906,0.000072746174,0.000014586505,0.00047632577,0.000007454878,0.00012207043],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991508,0.000035525973,0.00043295653,0.000083589686,0.00013741202,0.0001596969],"domain_scores_gemma":[0.9993826,0.000016567199,0.00025959066,0.00020757741,0.00008691147,0.00004672824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002409665,0.00013383133,0.00012124223,0.000049364044,0.00017187202,0.000055193952,0.0001319089,0.00013615825,0.0000015821871],"category_scores_gemma":[0.0001817023,0.000102064514,0.00005238255,0.00007944523,0.00005653496,0.00007330669,0.00007109875,0.00017755303,0.0000016613538],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020491316,0.00007882732,0.0112461625,0.0006688409,0.00021010001,3.4704317e-7,0.0054423218,0.0035673103,0.5308749,0.00032718855,0.001457894,0.4459212],"study_design_scores_gemma":[0.004746118,0.0015676455,0.13813998,0.0002905822,0.00018609408,0.000068749614,0.005079681,0.5635317,0.2473544,0.0007157998,0.037255913,0.0010633275],"about_ca_topic_score_codex":0.00001146127,"about_ca_topic_score_gemma":0.000012294816,"teacher_disagreement_score":0.5599644,"about_ca_system_score_codex":0.000015411248,"about_ca_system_score_gemma":0.000056645866,"threshold_uncertainty_score":0.41620702},"labels":[],"label_agreement":null},{"id":"W2105074464","doi":"10.1186/1471-2105-15-s7-s8","title":"Population substructure in Cache County, Utah: the Cache County study","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; National Human Genome Research Institute; National Institute on Aging; University of California, San Diego; Genentech; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"International HapMap Project; Population; Cache; Population stratification; Geography; Demography; Computer science; Biology; Genetics; Genotype; Genotyping; Sociology","score_opus":0.015173799726650868,"score_gpt":0.27276204595015485,"score_spread":0.25758824622350396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105074464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933143,0.0001215093,0.0038876582,0.000086562235,0.00016479974,0.00057789544,0.000026520622,0.00001095046,0.0018097948],"genre_scores_gemma":[0.9966828,0.000023658753,0.0024243782,0.00023594173,0.00015520606,0.000021317554,0.00020580302,0.00001484504,0.00023599749],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986715,0.00011964221,0.00038267634,0.00016612707,0.00035945338,0.00030059976],"domain_scores_gemma":[0.9991267,0.000038415215,0.00010844241,0.0005757884,0.00008920885,0.000061496816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085134746,0.00016689049,0.00016258977,0.00004812517,0.00012279743,0.00006519851,0.0003258219,0.00016775877,0.00001372842],"category_scores_gemma":[0.00019148912,0.00010994929,0.000056286342,0.00016095495,0.00010312226,0.0000080575965,0.00014101814,0.00018404279,0.0000179411],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029067538,0.00030917983,0.9437743,0.00030060072,0.00012331949,0.0000026100154,0.0046030413,0.0097712185,0.001572445,0.0010946228,0.015227014,0.022930982],"study_design_scores_gemma":[0.0024610676,0.0007257087,0.8299988,0.000025013152,0.000046220808,0.00003599737,0.0057185497,0.13583764,0.001572026,0.00079993263,0.022221133,0.0005579381],"about_ca_topic_score_codex":0.00026701996,"about_ca_topic_score_gemma":0.0019197889,"teacher_disagreement_score":0.12606643,"about_ca_system_score_codex":0.00002796502,"about_ca_system_score_gemma":0.00007622315,"threshold_uncertainty_score":0.4483602},"labels":[],"label_agreement":null},{"id":"W2105612251","doi":"10.1186/1471-2105-12-s8-s12","title":"A linear classifier based on entity recognition tools and a statistical approach to method extraction in the protein-protein interaction literature","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Fundação Luso-Americana para o Desenvolvimento; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Computer science; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Relationship extraction; Machine learning; Ranking (information retrieval); Natural language processing; Data mining; Information extraction","score_opus":0.09354681556915123,"score_gpt":0.32892828978095134,"score_spread":0.2353814742118001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105612251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05422936,0.000019259007,0.94084865,0.00007654943,0.0000579558,0.00065727776,0.00007802178,0.000017877557,0.004015048],"genre_scores_gemma":[0.12980327,0.0000043502973,0.86914814,0.00044885383,0.000059351863,0.00015859242,0.00031681792,0.0000075281578,0.000053103224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991258,0.00016177936,0.0002473913,0.0001667524,0.00014254233,0.0001557848],"domain_scores_gemma":[0.9995611,0.000053845542,0.00008146054,0.0002009066,0.00004638278,0.000056318495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057367276,0.000124254,0.00010691101,0.00007937176,0.000054420663,0.00006649477,0.00010287561,0.00021575813,0.00000841002],"category_scores_gemma":[0.00060233905,0.000083875086,0.00003399988,0.00013907453,0.000048956706,0.000016814487,0.000031195348,0.0002346639,0.0000118599555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036855054,0.0018393885,0.0009020021,0.0014970799,0.000070372225,0.000014514366,0.008531946,0.00010449981,0.03271637,0.0016601803,0.002924794,0.9460533],"study_design_scores_gemma":[0.00473913,0.0066320766,0.027978592,0.00132699,0.00011728085,0.00022668007,0.011003254,0.82000643,0.077006444,0.002476376,0.046822954,0.0016637866],"about_ca_topic_score_codex":0.000011535327,"about_ca_topic_score_gemma":0.000016755856,"teacher_disagreement_score":0.9443896,"about_ca_system_score_codex":0.00001339845,"about_ca_system_score_gemma":0.00003502347,"threshold_uncertainty_score":0.34203267},"labels":[],"label_agreement":null},{"id":"W2105896055","doi":"10.1186/1471-2105-6-186","title":"Nonparametric tests for differential gene expression and interaction effects in multi-factorial microarray experiments","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Outlier; DNA microarray; Parametric statistics; Covariate; Microarray analysis techniques; Robustness (evolution); Statistical hypothesis testing; Gene expression profiling; Computational biology; Computer science; Data mining; Biology; Statistics; Gene expression; Mathematics; Genetics; Gene","score_opus":0.03083952188263326,"score_gpt":0.31633714419032416,"score_spread":0.2854976223076909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105896055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6306704,0.00023041922,0.367962,0.00001113903,0.0005654971,0.00048086134,0.000009371041,0.000011478741,0.00005879509],"genre_scores_gemma":[0.85442257,0.00006239928,0.14483935,0.00005764932,0.00025785688,0.000111543995,0.00012809328,0.000012919024,0.00010760454],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992749,0.000025273852,0.00027379318,0.00017266837,0.000088474924,0.00016490574],"domain_scores_gemma":[0.9995503,0.00002773849,0.00012889091,0.0001915807,0.000036161706,0.00006535847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006786804,0.00013554787,0.000116731804,0.00012055101,0.000053107437,0.00004065646,0.00009011087,0.00015314158,0.000004926981],"category_scores_gemma":[0.00010492057,0.00011862317,0.000046844856,0.00007543367,0.000021256783,0.00001954992,0.000058442,0.00005767189,0.000004730659],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015651125,0.00010479199,0.0018112856,0.000070045135,0.0000055467517,3.8873452e-8,0.0002249795,0.00009093485,0.99042684,0.00000421267,0.0008599529,0.006244888],"study_design_scores_gemma":[0.0028522965,0.00013905737,0.00521777,0.00003976085,0.0000079907995,0.0000027019519,0.00009969643,0.024193997,0.9599666,0.000005219667,0.0072970977,0.00017781617],"about_ca_topic_score_codex":0.0000021743365,"about_ca_topic_score_gemma":0.000010747044,"teacher_disagreement_score":0.22375216,"about_ca_system_score_codex":0.00003354059,"about_ca_system_score_gemma":0.00003139682,"threshold_uncertainty_score":0.48373124},"labels":[],"label_agreement":null},{"id":"W2106017862","doi":"10.1186/1471-2105-9-375","title":"Critical assessment of alignment procedures for LC-MS proteomics and metabolomics measurements","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":191,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Cancer Research UK","keywords":"Proteomics; Metabolomics; Computational biology; DNA microarray; Computer science; Bioinformatics; Data science; Biology; Genetics","score_opus":0.042791251933404335,"score_gpt":0.310214925530109,"score_spread":0.26742367359670466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106017862","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57486033,0.0015847813,0.41897306,0.00014710729,0.00027823,0.0015834459,0.0001873447,0.000019336132,0.0023663926],"genre_scores_gemma":[0.3823165,0.0010153597,0.61618805,0.00013068362,0.00007953024,0.00011848744,0.00005052503,0.000016854725,0.000083983985],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884915,0.00001960957,0.00047220135,0.00017881187,0.00021850687,0.00026170755],"domain_scores_gemma":[0.9992523,0.00003196139,0.00017206132,0.00024094206,0.0002209926,0.00008170585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034462704,0.00018450979,0.00030411457,0.00006206064,0.00014555846,0.000017384975,0.00013478004,0.000108451495,0.0000033738006],"category_scores_gemma":[0.00049294345,0.0001577227,0.00009892549,0.00006508156,0.00018791464,0.000011360294,0.00013669627,0.000051551815,5.5784324e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006281335,0.0011522403,0.13116333,0.0052174814,0.0013971123,0.000001286214,0.0011229758,0.0004556373,0.8131938,0.03135704,0.01259501,0.0017159316],"study_design_scores_gemma":[0.008109339,0.0035089438,0.07237986,0.00013915081,0.0006619539,0.00017619184,0.001470569,0.046559505,0.8315009,0.0022142325,0.03142688,0.0018524885],"about_ca_topic_score_codex":0.0000027569768,"about_ca_topic_score_gemma":0.00000989055,"teacher_disagreement_score":0.19721502,"about_ca_system_score_codex":0.00001621212,"about_ca_system_score_gemma":0.00020062251,"threshold_uncertainty_score":0.64317447},"labels":[],"label_agreement":null},{"id":"W2106606545","doi":"10.1186/1471-2105-5-201","title":"A novel Mixture Model Method for identification of differentially expressed genes from DNA microarray data","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Repeatability; Nonparametric statistics; Set (abstract data type); Sensitivity (control systems); Computer science; Data set; Data mining; DNA microarray; Microarray analysis techniques; Algorithm; Pattern recognition (psychology); Statistics; Mathematics; Gene; Biology; Artificial intelligence; Genetics; Gene expression","score_opus":0.04615492341010959,"score_gpt":0.3068764359789374,"score_spread":0.2607215125688278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106606545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016701974,0.000218035,0.980961,0.000099115765,0.00014048615,0.00033849987,0.0014724972,0.000013003358,0.00005537119],"genre_scores_gemma":[0.072665036,0.00011406097,0.92163736,0.00015919004,0.00012184108,0.00005507255,0.005047346,0.0000219603,0.00017810754],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891806,0.000014419055,0.0005136448,0.0002640534,0.000147622,0.00014218903],"domain_scores_gemma":[0.99836653,0.000019565576,0.00037219524,0.0010463983,0.00014066917,0.000054609387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018904785,0.00014459736,0.0001564784,0.00004888988,0.000059866154,0.00003753333,0.000567997,0.00018200408,0.000003351545],"category_scores_gemma":[0.000106946594,0.00012942681,0.00008068347,0.00006657487,0.000036116853,0.00001955082,0.00015695204,0.0000418935,0.0000022980435],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075557706,0.000079131874,0.000014258374,0.000096995536,0.00003128661,7.804352e-9,0.0001784175,0.0069865454,0.9879899,0.00014144808,0.0014285636,0.0029778911],"study_design_scores_gemma":[0.00097275764,0.000025472113,0.00013124543,0.00001997914,0.000043376258,7.418398e-7,0.00013477112,0.26323715,0.7320954,0.00045399895,0.002751164,0.00013391335],"about_ca_topic_score_codex":0.000011197685,"about_ca_topic_score_gemma":0.00002849211,"teacher_disagreement_score":0.25625062,"about_ca_system_score_codex":0.000012550967,"about_ca_system_score_gemma":0.00019776147,"threshold_uncertainty_score":0.5277872},"labels":[],"label_agreement":null},{"id":"W2107815233","doi":"10.1186/1471-2105-9-101","title":"Prediction of mucin-type O-glycosylation sites in mammalian proteins using the composition of k-spaced amino acid pairs","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Program for New Century Excellent Talents in University; China Agricultural University; University of Alberta","keywords":"Glycosylation; Threonine; Computational biology; Serine; Encoding (memory); Binary classification; Support vector machine; Mucin; Computer science; Amino acid; Biology; Bioinformatics; Artificial intelligence; Biochemistry; Phosphorylation","score_opus":0.05543503999968876,"score_gpt":0.2762255201344427,"score_spread":0.2207904801347539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107815233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96239614,0.00007173923,0.03646628,0.00002793294,0.00003964661,0.00060770777,0.000034257606,0.000007739214,0.0003485618],"genre_scores_gemma":[0.9771332,0.00004557976,0.02246224,0.000016431783,0.00003434255,0.000008881698,0.00023705863,0.000009207349,0.000053052827],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998942,0.000074197706,0.0004577692,0.00009781005,0.0002689661,0.00015923587],"domain_scores_gemma":[0.999208,0.000014142512,0.00023780916,0.00028517746,0.0002184106,0.00003646356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028321563,0.00010546615,0.00013605428,0.00012566072,0.00008493366,0.0000082531615,0.00012917112,0.00013278335,0.000016277545],"category_scores_gemma":[0.00010772489,0.0000839408,0.000060671653,0.00030229366,0.000132697,0.000020981834,0.00006148944,0.00009156271,0.0000035387113],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029130373,0.00011035671,0.06946338,0.00027351725,0.000020422827,6.830886e-7,0.00083519,0.0050853654,0.9232892,0.000078923935,0.00013730704,0.00041438607],"study_design_scores_gemma":[0.0008175485,0.00040054883,0.052967653,0.000042730415,0.00000965184,0.000025480747,0.00033553105,0.18354985,0.7614574,0.000014211136,0.00027676774,0.00010265954],"about_ca_topic_score_codex":0.00005703436,"about_ca_topic_score_gemma":0.00007782375,"teacher_disagreement_score":0.17846449,"about_ca_system_score_codex":0.00002593052,"about_ca_system_score_gemma":0.00012750407,"threshold_uncertainty_score":0.34230065},"labels":[],"label_agreement":null},{"id":"W2109203567","doi":"10.1186/s12859-015-0805-8","title":"Revisiting operons: an analysis of the landscape of transcriptional units in E. coli","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Andlinger Center for Energy and the Environment, Princeton University; U.S. Department of Energy; Canadian Association for the Study of the Liver; National Science Foundation","keywords":"Operon; Computational biology; DNA microarray; Biology; Genetics; Escherichia coli; Gene; Gene expression","score_opus":0.04254395801968929,"score_gpt":0.26151269206273164,"score_spread":0.21896873404304235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109203567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9861371,0.00022875662,0.0121953655,0.000020633992,0.000039952953,0.00013885334,0.000058364356,0.0000024695855,0.0011785326],"genre_scores_gemma":[0.98714966,0.00002556256,0.012623756,0.00004987574,0.000022114762,0.0000052229298,0.000072689996,0.0000044924695,0.000046609246],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930555,0.00006683208,0.00033425455,0.000059931495,0.00014572912,0.00008769424],"domain_scores_gemma":[0.9994235,0.000011628139,0.00014850328,0.00025848488,0.000120171906,0.000037712318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044956154,0.000065850865,0.00015717806,0.00007910754,0.000016839782,0.0000067504066,0.00019615736,0.000077487195,0.000011063986],"category_scores_gemma":[0.00014405581,0.00004712184,0.000069896225,0.0004032267,0.00003426388,0.000008048381,0.000034716388,0.000030725576,7.008739e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006209496,0.0003353651,0.27277687,0.00087285315,0.000987573,8.356926e-7,0.007914798,0.07152759,0.6171441,0.010437668,0.000404644,0.016976763],"study_design_scores_gemma":[0.0026502146,0.0008133422,0.10732619,0.0003047129,0.00086912845,0.00000968413,0.015637504,0.3582092,0.5091246,0.0003332315,0.0040670154,0.0006552009],"about_ca_topic_score_codex":0.000017307859,"about_ca_topic_score_gemma":0.000073848045,"teacher_disagreement_score":0.28668162,"about_ca_system_score_codex":0.000005099154,"about_ca_system_score_gemma":0.00012659522,"threshold_uncertainty_score":0.19215728},"labels":[],"label_agreement":null},{"id":"W2109327803","doi":"10.1186/1471-2105-3-35","title":"FunSpec: a web-based cluster interpreter for yeast","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":409,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Genome Canada","keywords":"Cluster analysis; Categorical variable; Interpreter; Gene; Computational biology; Computer science; Exposition (narrative); Interpretation (philosophy); DNA microarray; Biology; Genetics; Artificial intelligence; Gene expression; Machine learning","score_opus":0.01484499009857399,"score_gpt":0.22456440291573057,"score_spread":0.2097194128171566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109327803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012581263,0.00030610088,0.9618547,0.00024077218,0.00064393814,0.0009799658,0.00025139228,0.00006694281,0.023074906],"genre_scores_gemma":[0.5805234,0.00008248194,0.4061393,0.0075046346,0.0008340181,0.000180926,0.00061335723,0.000085375425,0.0040365555],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988454,0.000014276626,0.0004878202,0.0001503239,0.00012249497,0.000379697],"domain_scores_gemma":[0.99912864,0.000024804405,0.0001705208,0.00047253515,0.00008380745,0.00011969396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019310285,0.00022189917,0.00017883208,0.0000648291,0.00009730881,0.00008310643,0.00027875003,0.00022699122,0.00009924559],"category_scores_gemma":[0.000049153787,0.00019521898,0.00021142699,0.000072057424,0.00007753382,0.000012534396,0.00009853778,0.00009438193,0.00016714894],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007205938,0.0003668204,0.002254962,0.0016523824,0.00031048025,0.0000012197021,0.0012736011,0.009354972,0.0047442107,0.0012939877,0.90134144,0.07668534],"study_design_scores_gemma":[0.0014958063,0.00023215341,0.0000332407,0.000027316219,0.000021634763,0.000009195222,0.000076305114,0.7882516,0.0008832996,0.000055513767,0.20864142,0.00027254532],"about_ca_topic_score_codex":6.5931005e-7,"about_ca_topic_score_gemma":0.0000187832,"teacher_disagreement_score":0.7788966,"about_ca_system_score_codex":0.000018998624,"about_ca_system_score_gemma":0.00004460746,"threshold_uncertainty_score":0.7960799},"labels":[],"label_agreement":null},{"id":"W2109429447","doi":"10.1186/1471-2105-12-486","title":"Constructing a semantic predication gold standard from the biomedical literature","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Unified Medical Language System; Computer science; Information retrieval; Annotation; Terminology; Natural language processing; Biomedical text mining; Ontology; Task (project management); Semantic similarity; Controlled vocabulary; Artificial intelligence; Text mining; Linguistics","score_opus":0.023971190296094843,"score_gpt":0.24545670248368603,"score_spread":0.2214855121875912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109429447","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3362449,0.003320761,0.6426624,0.0010787122,0.001596228,0.00076225575,0.0013152612,0.00026874323,0.012750719],"genre_scores_gemma":[0.4109987,0.00022339012,0.58431476,0.0011389555,0.0007719934,0.000033981356,0.002168985,0.000030137082,0.00031908572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990197,0.000045899258,0.00033831268,0.00015140153,0.00021966705,0.00022504995],"domain_scores_gemma":[0.9992341,0.00005943364,0.00015040746,0.00039468973,0.0000665492,0.00009486608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026960825,0.00014174885,0.00013723534,0.000028240034,0.000083046616,0.000048508973,0.00033488122,0.0002816901,0.000032724925],"category_scores_gemma":[0.0004709978,0.00008753873,0.00007559605,0.0001464844,0.0004095775,0.000006965219,0.00014374725,0.000170636,0.00002397524],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008547199,0.00028782518,0.10847363,0.0005950453,0.00061559695,0.00001861033,0.021396799,0.0000034699328,0.0037043293,0.003382863,0.19117263,0.6694945],"study_design_scores_gemma":[0.009496952,0.00397347,0.060023375,0.0019403547,0.00062241976,0.00067487906,0.053024713,0.057018068,0.045113057,0.00658309,0.7585659,0.0029637378],"about_ca_topic_score_codex":0.000017631457,"about_ca_topic_score_gemma":0.000033885768,"teacher_disagreement_score":0.6665307,"about_ca_system_score_codex":0.000012026247,"about_ca_system_score_gemma":0.00010693844,"threshold_uncertainty_score":0.35697255},"labels":[],"label_agreement":null},{"id":"W2110845345","doi":"10.1186/1471-2105-7-244","title":"Identification of consensus RNA secondary structures using suffix arrays","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nucleic acid secondary structure; Protein secondary structure; Computational biology; Suffix array; Conserved sequence; Suffix; Structural motif; DNA microarray; Computer science; Sequence alignment; RNA; Data structure; Biology; Genetics; DNA; Gene; Base sequence; Peptide sequence","score_opus":0.014567914469078996,"score_gpt":0.2406418170439644,"score_spread":0.2260739025748854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110845345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7821165,0.00026398746,0.21523753,0.000009994496,0.00017664177,0.00020425144,0.00006979203,0.000012776753,0.0019085647],"genre_scores_gemma":[0.8861554,0.000011486966,0.113406114,0.00003529335,0.00011672833,0.0000037331056,0.00008500228,0.000013643223,0.0001725999],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911183,0.00002926147,0.00048574887,0.000100044934,0.00012798028,0.00014512436],"domain_scores_gemma":[0.9992489,0.000014007477,0.00032218327,0.0003031005,0.00008259805,0.000029206052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019084601,0.00011538392,0.0001274479,0.000049242753,0.000063619445,0.000024652141,0.00013407554,0.0001368971,0.00002225725],"category_scores_gemma":[0.00005172532,0.00010716911,0.000076640004,0.000061427825,0.00007098423,0.0000050925028,0.000039501883,0.0000422105,0.0000061922897],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023818464,0.000013951862,0.00016724972,0.00012005116,0.000014068864,2.1484718e-7,0.00003556794,0.0011960741,0.9955482,0.0010894461,0.00038671395,0.0014046398],"study_design_scores_gemma":[0.00023396737,0.000043512056,0.00053773617,0.000010803677,0.000019455621,0.000017141874,0.00016707568,0.009346033,0.98716223,0.0014669885,0.00085317617,0.00014190108],"about_ca_topic_score_codex":0.00002072118,"about_ca_topic_score_gemma":0.000012401246,"teacher_disagreement_score":0.10403894,"about_ca_system_score_codex":0.000008166662,"about_ca_system_score_gemma":0.00010035986,"threshold_uncertainty_score":0.43702292},"labels":[],"label_agreement":null},{"id":"W2111112354","doi":"10.1186/1471-2105-14-s12-s1","title":"Using context-specific effect of miRNAs to identify functional associations between miRNAs and gene signatures","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"microRNA; Biology; Context (archaeology); Computational biology; Gene regulatory network; Gene; Regulation of gene expression; DNA microarray; Genetics; Gene expression","score_opus":0.03031355083459365,"score_gpt":0.2895462607782136,"score_spread":0.25923270994361997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111112354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95843244,0.0005487174,0.040251933,0.000023034494,0.0000896905,0.00045126965,0.00011532525,0.000009510189,0.00007805414],"genre_scores_gemma":[0.9805446,0.000013803837,0.018728895,0.0000629946,0.00015065784,0.000014076187,0.00041928343,0.0000141020255,0.000051581235],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99915874,0.00004664086,0.00035133454,0.00012024087,0.00016872588,0.00015431589],"domain_scores_gemma":[0.99929154,0.000056790723,0.00019255644,0.0001991636,0.00016115372,0.00009881407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018192988,0.00013241557,0.00017435929,0.00007713621,0.00008497545,0.000051094325,0.00009045242,0.00015738183,0.000027933069],"category_scores_gemma":[0.00011988049,0.000121009994,0.0000791608,0.000095272626,0.00005080205,0.00001870575,0.000091487535,0.00005346734,0.000024254869],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042472464,0.000023262075,0.05129261,0.00015092074,0.00014374127,1.2635958e-7,0.00014197818,0.00094535534,0.93682134,0.00006818761,0.0070363763,0.0033336424],"study_design_scores_gemma":[0.00094751286,0.00019538462,0.62685835,0.000041352327,0.00008880665,0.000004565787,0.000079731035,0.0042045093,0.36507595,0.00007531471,0.0021387995,0.0002897089],"about_ca_topic_score_codex":0.000019623161,"about_ca_topic_score_gemma":0.000006813303,"teacher_disagreement_score":0.57556576,"about_ca_system_score_codex":0.000027628965,"about_ca_system_score_gemma":0.000050051087,"threshold_uncertainty_score":0.49346444},"labels":[],"label_agreement":null},{"id":"W2111492198","doi":"10.1186/1471-2105-7-423","title":"Detection of prokaryotic promoters from the genomic distribution of hexanucleotide pairs","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Université de Sherbrooke","keywords":"Promoter; Biology; Genetics; Computational biology; Bacterial genome size; Genome; Gene; Intergenic region; Transcription (linguistics); DNA sequencing; Regulatory sequence; DNA microarray; Transcription factor; Gene expression","score_opus":0.0061610793041830285,"score_gpt":0.18525158885705942,"score_spread":0.1790905095528764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111492198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731541,0.00013439069,0.0260254,0.00004435807,0.000121582445,0.00025020834,0.00017631052,0.000009783348,0.000083832085],"genre_scores_gemma":[0.9941735,0.00004044184,0.0052032154,0.000017263186,0.00009032257,0.0000053967005,0.00044538872,0.000008027249,0.000016442282],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926406,0.00002458621,0.0003986645,0.00009642103,0.00008262737,0.00013364169],"domain_scores_gemma":[0.9993205,0.000012649974,0.00026798536,0.0003197459,0.00006274093,0.000016352225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001237726,0.00010296341,0.00012593738,0.000017677636,0.000039580755,0.00000973203,0.00018745488,0.00017531686,0.0000027759977],"category_scores_gemma":[0.00003836182,0.00007489974,0.000079493904,0.00008296416,0.00015511831,0.0000035195417,0.00009317065,0.000056108795,0.0000031691782],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000566377,0.00004234201,0.004883271,0.00005364596,0.000023546547,6.494353e-8,0.000025814592,0.00017791921,0.9910315,0.000059965718,0.00018809165,0.0034571819],"study_design_scores_gemma":[0.0003593679,0.00027842485,0.076638244,0.000016578322,0.00003530521,0.0000041567114,0.00008862045,0.0047807912,0.9149039,0.00017606284,0.002603507,0.00011505647],"about_ca_topic_score_codex":0.00015893271,"about_ca_topic_score_gemma":0.0001534691,"teacher_disagreement_score":0.07612763,"about_ca_system_score_codex":0.000011061913,"about_ca_system_score_gemma":0.00004496582,"threshold_uncertainty_score":0.30543226},"labels":[],"label_agreement":null},{"id":"W2111607030","doi":"10.1186/1471-2105-10-202","title":"NLStradamus: a simple Hidden Markov Model for nuclear localization signal prediction","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":719,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Nuclear localization sequence; NLS; Hidden Markov model; Nuclear transport; Markov chain; Computational biology; Simple (philosophy); Computer science; Set (abstract data type); Markov model; Artificial intelligence; Biology; Machine learning; Genetics; Cell nucleus; Gene","score_opus":0.010340648857877142,"score_gpt":0.2196102180540038,"score_spread":0.20926956919612666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111607030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023410652,0.000027080681,0.97422355,0.000043017437,0.0000977616,0.0003253476,0.00008895742,0.000055392862,0.0017282481],"genre_scores_gemma":[0.7820001,0.000040574334,0.21417639,0.0015346926,0.0004325156,0.00000774197,0.001449674,0.000034973815,0.00032330427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993367,0.000008112066,0.0002495621,0.00012429887,0.00010764481,0.00017364486],"domain_scores_gemma":[0.999579,0.0000039618662,0.00009477082,0.000193809,0.00007029054,0.000058159894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000081654085,0.00012133507,0.00009190753,0.000038391354,0.0001296215,0.000043046417,0.00009594805,0.00017676357,0.000019420855],"category_scores_gemma":[0.000025400997,0.0001146512,0.000082663675,0.000057273963,0.000022799186,0.000018549443,0.000020337158,0.000048168706,0.000008588839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025982081,0.00035070942,0.0011551016,0.0006926798,0.00021215019,7.4293945e-7,0.002192993,0.12793419,0.06004418,0.0064682225,0.35327268,0.44507816],"study_design_scores_gemma":[0.00052572286,0.00041706907,0.0003963802,0.000006337794,0.000028385733,0.000009579596,0.00011190037,0.9812803,0.00085181894,0.0007320359,0.015502292,0.00013816911],"about_ca_topic_score_codex":9.882262e-7,"about_ca_topic_score_gemma":0.000003858069,"teacher_disagreement_score":0.8533461,"about_ca_system_score_codex":0.000016571832,"about_ca_system_score_gemma":0.000038009493,"threshold_uncertainty_score":0.46753404},"labels":[],"label_agreement":null},{"id":"W2111931353","doi":"10.1186/1471-2105-10-s12-i1","title":"Trends in modeling Biomedical Complex Systems","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca; World Anti-Doping Agency","keywords":"Computer science; Data science; Multidisciplinary approach; Inference; Informatics; Management science; Complex system; Health informatics; Artificial intelligence; Engineering; Medicine","score_opus":0.028375283573716284,"score_gpt":0.2678424997625228,"score_spread":0.2394672161888065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111931353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5026902,0.0011079789,0.48877102,0.0001838211,0.0002385775,0.00022030532,0.000022061962,0.00006154755,0.0067044757],"genre_scores_gemma":[0.97845125,0.000035689452,0.020566542,0.00014601508,0.00016676485,0.0000038042267,0.00041115523,0.000008844973,0.00020991768],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988966,0.000029778774,0.00046367163,0.00014018005,0.00019039559,0.0002793966],"domain_scores_gemma":[0.9994246,0.0000038127866,0.00008338309,0.00034939565,0.00003646928,0.0001023703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022416192,0.00014352614,0.00019644288,0.00021708898,0.000042256528,0.000033631248,0.0001930877,0.00016555462,0.000013047676],"category_scores_gemma":[0.00001621206,0.00013095688,0.00010775926,0.00035160076,0.000032476168,0.000005525665,0.000045152545,0.00006798049,0.000016710836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074033014,0.00023004554,0.003553949,0.00010814576,0.000092580914,0.000004428596,0.0002794179,0.9337648,0.009984666,0.0005127583,0.01442504,0.036970098],"study_design_scores_gemma":[0.0003709184,0.000094752104,0.0012923316,0.000013550568,0.000015108601,0.000013546633,0.00016109107,0.9928091,0.00007769756,0.000019111752,0.004967002,0.00016575218],"about_ca_topic_score_codex":0.000008149133,"about_ca_topic_score_gemma":0.000021582593,"teacher_disagreement_score":0.47576106,"about_ca_system_score_codex":0.000023034163,"about_ca_system_score_gemma":0.000040741023,"threshold_uncertainty_score":0.5340266},"labels":[],"label_agreement":null},{"id":"W2114857957","doi":"10.1186/1471-2105-4-16","title":"Domain fusion analysis by applying relational algebra to protein sequence and domain databases","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Computer science; Domain (mathematical analysis); UniProt; Protein domain; Sequence database; Hidden Markov model; Computational biology; Relational database; Database; Protein structure database; Sequence (biology); Protein sequencing; Data mining; Artificial intelligence; Biology; Peptide sequence; Gene; Genetics; Mathematics","score_opus":0.018481855168488638,"score_gpt":0.24497772610081245,"score_spread":0.22649587093232382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114857957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21479279,0.0002740301,0.7816766,0.000054978755,0.00004156262,0.0006083878,0.00017963303,0.00001599877,0.0023560186],"genre_scores_gemma":[0.08800323,0.000065526794,0.90914315,0.0007692515,0.00006192128,0.00011200446,0.0013921654,0.000021760477,0.00043096958],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986978,0.000047231268,0.00050623424,0.00021288128,0.00021636633,0.00031945412],"domain_scores_gemma":[0.9991238,0.000021893215,0.00018127309,0.0004259988,0.000054835553,0.00019219285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005504126,0.00021517617,0.00020984349,0.00011699424,0.00020067664,0.00006599651,0.00014653885,0.00013917299,0.000032674263],"category_scores_gemma":[0.00005621259,0.00019719885,0.00008810125,0.00036705422,0.00007827564,0.000024968454,0.00015423873,0.000108548185,0.000026785241],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008142187,0.0006412505,0.049284518,0.0020469849,0.003091687,0.000012026953,0.0065633394,0.019505369,0.4554582,0.32952824,0.08863075,0.04442343],"study_design_scores_gemma":[0.002415591,0.00046769882,0.001148619,0.00014050058,0.00031508066,0.000087260385,0.0032051406,0.051313102,0.016359417,0.004453251,0.9181909,0.0019034308],"about_ca_topic_score_codex":0.000008557455,"about_ca_topic_score_gemma":0.000044305987,"teacher_disagreement_score":0.82956016,"about_ca_system_score_codex":0.000023182172,"about_ca_system_score_gemma":0.00008486524,"threshold_uncertainty_score":0.8041536},"labels":[],"label_agreement":null},{"id":"W2114864966","doi":"10.1186/s12859-015-0469-4","title":"An evidence-based approach to identify aging-related genes in Caenorhabditis elegans","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Instituto Milenio en Inmunología e Inmunoterapia; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Caenorhabditis elegans; Model organism; Gene; Organism; Biology; Computational biology; Knowledge base; DNA microarray; Genetics; Computer science; World Wide Web","score_opus":0.04925741564619464,"score_gpt":0.2981212473397274,"score_spread":0.24886383169353277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114864966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64372754,0.0008358666,0.35342506,0.00012136543,0.00033322655,0.0005209244,0.00002461409,0.000055645523,0.0009557728],"genre_scores_gemma":[0.8659763,0.000072275536,0.1325369,0.00076373084,0.0001469182,0.000033528595,0.00025068744,0.000039040817,0.00018063954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824643,0.000098194454,0.0005641872,0.00031687607,0.00033294444,0.00044137385],"domain_scores_gemma":[0.99856424,0.000016376718,0.00013889647,0.0007463241,0.00018072379,0.00035342664],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006771428,0.000264292,0.00023887982,0.0001798406,0.00006871663,0.00013112485,0.00053955556,0.00025660958,0.000007270857],"category_scores_gemma":[0.00019022936,0.0002667874,0.00008117263,0.0002741783,0.00008202596,0.000039736322,0.00011890129,0.00014222926,0.00008429654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028584077,0.0012525392,0.14461482,0.0010204443,0.00013922693,0.000014912609,0.019201169,0.72308844,0.08500206,0.00044297974,0.013499852,0.011437694],"study_design_scores_gemma":[0.004664143,0.0020843646,0.039467786,0.00031144152,0.00014902069,0.00010983344,0.006101073,0.7913159,0.13717204,0.0003911098,0.015743226,0.0024900225],"about_ca_topic_score_codex":0.00013674113,"about_ca_topic_score_gemma":0.00023109248,"teacher_disagreement_score":0.22224875,"about_ca_system_score_codex":0.000057455105,"about_ca_system_score_gemma":0.0003566832,"threshold_uncertainty_score":0.9999784},"labels":[],"label_agreement":null},{"id":"W2115044025","doi":"10.1186/1471-2105-14-s9-s4","title":"Classification and assessment tools for structural motif discovery algorithms","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University; University of Ottawa","keywords":"Motif (music); Computer science; Structural motif; Benchmark (surveying); Sequence motif; DNA microarray; Data mining; Computational biology; Drug discovery; Machine learning; Algorithm; Artificial intelligence; Bioinformatics; Biology; DNA; Genetics; Gene","score_opus":0.021244962799292395,"score_gpt":0.26984898610286223,"score_spread":0.24860402330356984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115044025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76262283,0.000058726917,0.23587175,0.00006422783,0.00012566715,0.000527396,0.00008366492,0.000009722175,0.0006359905],"genre_scores_gemma":[0.52458704,0.000095047915,0.4740565,0.00013027097,0.0001018569,0.000084388885,0.0006520483,0.0000154442,0.00027738503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936074,0.000008361571,0.00026229993,0.00012328719,0.00007462413,0.000170685],"domain_scores_gemma":[0.99949324,0.000023008342,0.00012430856,0.00023237157,0.00007194948,0.000055114335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082027975,0.00012164646,0.000102544174,0.000021845772,0.00008946676,0.00028629837,0.000113563045,0.00010215485,0.00000472536],"category_scores_gemma":[0.000040007824,0.0001037566,0.000052202504,0.000026201045,0.00004652115,0.0000410294,0.000078282814,0.000045730558,0.00000461618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121063626,0.00022138859,0.10856074,0.0028047618,0.0005531902,5.2831643e-7,0.0011771097,0.0038600408,0.2680203,0.034977753,0.017579358,0.5621238],"study_design_scores_gemma":[0.00051484077,0.00014981964,0.11291845,0.00000749334,0.000016295931,0.000009122324,0.000608779,0.88164204,0.0007874524,0.0007563028,0.002377276,0.0002120987],"about_ca_topic_score_codex":0.0000054919315,"about_ca_topic_score_gemma":0.000007675889,"teacher_disagreement_score":0.87778205,"about_ca_system_score_codex":0.000017987435,"about_ca_system_score_gemma":0.00006689465,"threshold_uncertainty_score":0.42310715},"labels":[],"label_agreement":null},{"id":"W2115059509","doi":"10.1186/1471-2105-15-47","title":"PSEUDOMARKER 2.0: efficient computation of likelihoods using NOMAD","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"FP7 Health; Air Force Office of Scientific Research; National Institute of Mental Health; National Institute on Aging; National Institutes of Health; Academy of Finland; European Commission","keywords":"Computation; Computer science; Computational biology; DNA microarray; Biology; Algorithm; Genetics; Gene expression; Gene","score_opus":0.017862716838259705,"score_gpt":0.2715878407092353,"score_spread":0.2537251238709756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115059509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47879997,0.000034965116,0.5197091,0.000010325488,0.000086884895,0.000065146,0.000004824139,0.0000047018357,0.0012841058],"genre_scores_gemma":[0.73756623,0.0000064030464,0.2621925,0.00009537188,0.00005737216,0.0000019683364,0.00004802904,0.0000070900956,0.000025024354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991523,0.0000705501,0.00041954315,0.00009580562,0.000092301634,0.00016950755],"domain_scores_gemma":[0.99935526,0.000033954027,0.0002684739,0.00018989037,0.000106877626,0.000045540488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004686921,0.000097530035,0.00016033501,0.000045977242,0.000056415076,0.000007421327,0.00009496069,0.000132131,0.0000040456785],"category_scores_gemma":[0.00025790522,0.00008958381,0.000080142025,0.00007998635,0.000054588563,0.0000019560182,0.00006982328,0.00003822533,0.000010377448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100019475,0.00026729752,0.1741921,0.0004640228,0.00016988732,1.5731237e-7,0.00056466414,0.7626061,0.032800227,0.0009502261,0.0040536067,0.023831675],"study_design_scores_gemma":[0.00040294993,0.00011334233,0.033767983,0.0000126971145,0.000020937774,0.0000063558136,0.000112736016,0.96338814,0.0012220154,0.00008661652,0.0007473948,0.000118836426],"about_ca_topic_score_codex":0.000008994463,"about_ca_topic_score_gemma":0.000004655099,"teacher_disagreement_score":0.2587663,"about_ca_system_score_codex":0.000011415431,"about_ca_system_score_gemma":0.000055584816,"threshold_uncertainty_score":0.36531216},"labels":[],"label_agreement":null},{"id":"W2115427074","doi":"10.1186/1471-2105-14-186","title":"MITE Digger, an efficient and accurate algorithm for genome wide discovery of miniature inverted repeat transposable elements","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Electric (Canada); University of Toronto","funders":"University of Toronto","keywords":"Transposable element; Mite; Genome; Inverted repeat; Computational biology; Computer science; Algorithm; Biology; Genetics; Gene; Ecology","score_opus":0.017332050745270177,"score_gpt":0.215296391470711,"score_spread":0.19796434072544083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115427074","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99263644,0.00007666964,0.0056429296,0.00014791853,0.00007125885,0.0007119133,0.00057506515,0.00002499238,0.000112829985],"genre_scores_gemma":[0.7508491,0.00012398863,0.24559943,0.00059561385,0.00018051047,0.00014470179,0.0017247596,0.000004070624,0.00077779964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913716,0.000015483525,0.00038593163,0.00012140642,0.00013142911,0.00020856613],"domain_scores_gemma":[0.9994989,0.00011198136,0.00015041755,0.000071338356,0.000081603925,0.00008577848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096539305,0.000121424266,0.00015908595,0.000012869321,0.00013575837,0.00009577033,0.00014048064,0.000078578865,0.000051520656],"category_scores_gemma":[0.000023289957,0.000048947695,0.000065158136,0.00015143963,0.00004619816,0.00031670954,0.000033538214,0.000041230007,0.0000076235883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021357417,0.0023555094,0.09558422,0.0011895439,0.0004091074,0.0000018041499,0.011466966,0.0024205684,0.15146048,0.0010967526,0.0019979943,0.7318035],"study_design_scores_gemma":[0.00071086164,0.0005582048,0.17598893,0.000036287107,0.000051120776,0.0000044223357,0.0011201691,0.8159245,0.0021556823,0.000425374,0.0027208715,0.00030354227],"about_ca_topic_score_codex":0.00004171145,"about_ca_topic_score_gemma":0.00013443634,"teacher_disagreement_score":0.813504,"about_ca_system_score_codex":0.000009338314,"about_ca_system_score_gemma":0.000012121427,"threshold_uncertainty_score":0.19960292},"labels":[],"label_agreement":null},{"id":"W2116096983","doi":"10.1186/1471-2105-13-102","title":"Workflows for microarray data processing in the Kepler environment","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; National Science Foundation","keywords":"Workflow; Computer science; Python (programming language); Graphical user interface; Pipeline (software); Java; Software engineering; Database; Programming language","score_opus":0.07304841262008531,"score_gpt":0.30161588278825785,"score_spread":0.22856747016817253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116096983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04444521,0.004299223,0.94379777,0.00064535195,0.0003829451,0.0013949914,0.000102713064,0.00001881467,0.0049129906],"genre_scores_gemma":[0.7619696,0.0002762521,0.23324712,0.0016368977,0.00058970926,0.00021199205,0.001448669,0.000025173193,0.0005945342],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940217,0.000020575457,0.00019756184,0.0000971239,0.00009255294,0.00019002313],"domain_scores_gemma":[0.99930245,0.000007827826,0.00008460286,0.0005623583,0.00000957939,0.000033174503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041312503,0.00007975884,0.000055487104,0.000022035749,0.000061269406,0.000029623958,0.00036338388,0.00007183147,0.000008001387],"category_scores_gemma":[0.0000325626,0.000054051397,0.000024478353,0.000047566053,0.000027474183,0.000016801847,0.000091663554,0.00004227916,0.000013384768],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041036404,0.001029911,0.053717617,0.0011411868,0.000048351507,1.8933626e-7,0.010136985,0.0011935872,0.2349127,0.0006249865,0.31717494,0.3796092],"study_design_scores_gemma":[0.0005614556,0.000039016842,0.00640152,0.00002159958,0.000015923511,0.0000056363083,0.0016721503,0.017719937,0.0074695842,0.000024843383,0.9658836,0.00018472463],"about_ca_topic_score_codex":6.344133e-7,"about_ca_topic_score_gemma":0.000004023962,"teacher_disagreement_score":0.71752447,"about_ca_system_score_codex":0.0000094535035,"about_ca_system_score_gemma":0.000038582493,"threshold_uncertainty_score":0.2204152},"labels":[],"label_agreement":null},{"id":"W2116128456","doi":"10.1186/1471-2105-15-s3-a1","title":"Highlights from the ISCB Student Council Symposium 2013","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Oxford; Genome Canada; National Science Foundation","keywords":"Library science; Computational biology; Computer science; Data science; Biology","score_opus":0.026457790260734238,"score_gpt":0.26145885002145786,"score_spread":0.2350010597607236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116128456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4261004,0.003286784,0.3955605,0.017848367,0.006265047,0.0040201894,0.00082779943,0.0003370376,0.14575386],"genre_scores_gemma":[0.72049415,0.016146401,0.20239878,0.022925602,0.009747265,0.00031206533,0.0035612534,0.0002704662,0.024144016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722546,0.000087946115,0.0006804788,0.00022795468,0.0012223871,0.00055578374],"domain_scores_gemma":[0.99802196,0.00014090369,0.00020354362,0.0009814057,0.00038262492,0.00026953305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091297,0.0002857418,0.0002391144,0.000033871613,0.00025243862,0.00019481436,0.0009881138,0.0002823156,0.000061604784],"category_scores_gemma":[0.00038453352,0.00017686866,0.00016148893,0.00012266535,0.00033127837,0.000015769323,0.00049606286,0.00020088705,0.0006644217],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027961694,0.0005048373,0.008987367,0.00046461858,0.0004885688,0.0000021335215,0.006102769,0.00070330594,0.018360756,0.0018442809,0.94177425,0.020487467],"study_design_scores_gemma":[0.0010922002,0.00042863714,0.0040095886,0.00003699168,0.000044259745,0.0000067324386,0.0009129358,0.034052458,0.005735456,0.0001777594,0.95310915,0.00039386447],"about_ca_topic_score_codex":0.000103513914,"about_ca_topic_score_gemma":0.00044521253,"teacher_disagreement_score":0.29439375,"about_ca_system_score_codex":0.0000655186,"about_ca_system_score_gemma":0.0003932456,"threshold_uncertainty_score":0.8540018},"labels":[],"label_agreement":null},{"id":"W2116676712","doi":"10.1186/1471-2105-7-480","title":"RiboSubstrates: a web application addressing the cleavage specificities of ribozymes in designated genomes","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Atlantic Cancer Research Institute; Université de Moncton; Université de Sherbrooke","funders":"Canadian Institutes of Health Research; Atlantic Canada Opportunities Agency; Université de Sherbrooke","keywords":"Ribozyme; Computational biology; Mammalian CPEB3 ribozyme; Biology; Ligase ribozyme; RNA; Gene silencing; Functional genomics; DNA microarray; Hammerhead ribozyme; Computer science; Genome; Gene; Genomics; Genetics; Gene expression","score_opus":0.03215291938696927,"score_gpt":0.24609796270677625,"score_spread":0.213945043319807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116676712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7902841,0.003499913,0.18896107,0.000075018164,0.00010064967,0.0010666191,0.00007638806,0.000039884246,0.015896387],"genre_scores_gemma":[0.9777417,0.000104946565,0.021785242,0.000037069356,0.00007236523,0.000038261274,0.00008222,0.000012643613,0.00012554898],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991509,0.00004700803,0.00041608035,0.000098646415,0.00012293525,0.0001644875],"domain_scores_gemma":[0.99941146,0.00003437968,0.00020615941,0.00028840188,0.000041528805,0.000018079409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030144688,0.00012145006,0.00013099285,0.000055392156,0.00006232194,0.000032676006,0.00021430776,0.00011758055,0.0000075567254],"category_scores_gemma":[0.00002156485,0.00008918379,0.000057452555,0.0001256392,0.00009366313,0.000009108426,0.000040193256,0.000050534036,0.000009280366],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009864869,0.00008354423,0.0050365697,0.0002353634,0.000021991775,6.10019e-7,0.00030170375,0.0017770682,0.97919804,0.003945509,0.0008941315,0.008406809],"study_design_scores_gemma":[0.000374464,0.0000769954,0.0026506465,0.000048953374,0.000012821819,0.000006173518,0.0013776196,0.015588478,0.9754579,0.0011331749,0.0030788565,0.00019391083],"about_ca_topic_score_codex":0.000027352593,"about_ca_topic_score_gemma":0.00012221775,"teacher_disagreement_score":0.18745764,"about_ca_system_score_codex":0.000010345191,"about_ca_system_score_gemma":0.00006861391,"threshold_uncertainty_score":0.36368093},"labels":[],"label_agreement":null},{"id":"W2117044793","doi":"10.1186/1471-2105-6-128","title":"Integrative analysis of multiple gene expression profiles with quality-adjusted effect size models","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Weighting; Data mining; Computer science; Consistency (knowledge bases); DNA microarray; R package; Data quality; Statistical power; Computational biology; Gene; Biology; Statistics; Gene expression; Mathematics; Artificial intelligence; Genetics; Metric (unit)","score_opus":0.023493328889068035,"score_gpt":0.2824609765342343,"score_spread":0.2589676476451663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117044793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6154275,0.00016840949,0.38227472,0.00002609632,0.000030039075,0.0003692032,0.00007463571,0.000022500913,0.0016068956],"genre_scores_gemma":[0.87263805,0.000048362894,0.1264736,0.000066424705,0.000039597668,0.000057262063,0.00032241835,0.000011274634,0.00034298407],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988862,0.000097408134,0.00044574187,0.00018322469,0.00023086682,0.00015651587],"domain_scores_gemma":[0.99886334,0.00007258437,0.00035434868,0.00047114675,0.00016657985,0.00007197639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023631306,0.00017957314,0.00029215385,0.00012278718,0.000055502147,0.000017770506,0.00017909009,0.00014095865,0.000018896628],"category_scores_gemma":[0.00013545231,0.00011673084,0.00014577773,0.00037743844,0.00006950943,0.000020742806,0.000061818755,0.000069595495,0.000003439561],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081753056,0.00013901686,0.015288899,0.00018464508,0.00042478114,1.04916005e-7,0.0012068844,0.05908128,0.9163667,0.000108682136,0.0011266076,0.005254904],"study_design_scores_gemma":[0.0008518414,0.00021083746,0.0045359167,0.000036391895,0.00017109583,8.49301e-7,0.0005636445,0.1963395,0.7965271,0.000005646882,0.0005824163,0.00017477381],"about_ca_topic_score_codex":0.000009598196,"about_ca_topic_score_gemma":0.00008404299,"teacher_disagreement_score":0.25721058,"about_ca_system_score_codex":0.000020269545,"about_ca_system_score_gemma":0.000077644225,"threshold_uncertainty_score":0.47601452},"labels":[],"label_agreement":null},{"id":"W2117463702","doi":"10.1186/1471-2105-9-279","title":"Identifying a few foot-and-mouth disease virus signature nucleotide strings for computational genotyping","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Animal Disease Management and Epidemiology","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Genotyping; Foot-and-mouth disease virus; Computational biology; Biology; Signature (topology); DNA microarray; Genetics; Genotype; Virus; Gene; Mathematics","score_opus":0.06867020602029669,"score_gpt":0.25867838621071254,"score_spread":0.19000818019041585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117463702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735554,0.00043601682,0.024053834,0.00048845896,0.000102098,0.00059868617,0.00019954976,0.0001460678,0.00041992837],"genre_scores_gemma":[0.9672775,0.00009634848,0.030480055,0.0013462296,0.00020154002,0.000027817652,0.0003838377,0.0000020951663,0.00018456911],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99912155,0.000023125256,0.0003047903,0.00015037309,0.00013336814,0.0002668167],"domain_scores_gemma":[0.99933356,0.00027614663,0.00013748101,0.00003704572,0.000049526487,0.00016624817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016842016,0.00013699514,0.00016687473,0.000020437048,0.00043790552,0.00005223478,0.00014938877,0.00006130047,0.00004785528],"category_scores_gemma":[0.00013938436,0.000062594736,0.00011330719,0.00012432148,0.00007818444,0.00023393627,0.00010864148,0.0000730009,0.00003330547],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037301057,0.00097454496,0.49691316,0.0047509857,0.00070459046,0.00007126048,0.006047408,0.025407152,0.0060283816,0.14125326,0.098817326,0.21530183],"study_design_scores_gemma":[0.00037083792,0.00008464238,0.79497075,0.000041479474,0.000057616406,0.0000036564713,0.0005944908,0.19218642,0.000007799475,0.004724842,0.00664725,0.00031019776],"about_ca_topic_score_codex":0.000023480607,"about_ca_topic_score_gemma":0.000036672198,"teacher_disagreement_score":0.29805762,"about_ca_system_score_codex":0.000016631915,"about_ca_system_score_gemma":0.000013393702,"threshold_uncertainty_score":0.33680597},"labels":[],"label_agreement":null},{"id":"W2117980752","doi":"10.1186/1471-2105-13-s19-s11","title":"Linearization of ancestral multichromosomal genomes","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Row; Combinatorics; Linearization; Mathematics; Biology; Genetics; Computer science; Gene; Physics; Nonlinear system","score_opus":0.021088227291032657,"score_gpt":0.25444365989167667,"score_spread":0.233355432600644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117980752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8634479,0.0012451793,0.13095772,0.000012007104,0.0003454442,0.00033604598,0.000043322663,0.000022219798,0.0035901575],"genre_scores_gemma":[0.74861896,0.00010761576,0.2505093,0.000033024597,0.00026926096,0.0000068076506,0.00021578856,0.00001257921,0.00022668076],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993453,0.0000125694305,0.0002549426,0.000056362172,0.000115714494,0.00021507991],"domain_scores_gemma":[0.9995503,0.0000055604505,0.00012415346,0.00019860928,0.000055391276,0.00006602459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012633753,0.000093189,0.000095036834,0.00003599452,0.000027641267,0.000009004944,0.00010827831,0.000085385975,0.000022282768],"category_scores_gemma":[0.000034429813,0.00008570489,0.000053360705,0.000074657684,0.000047638092,0.000013062582,0.00006100167,0.000032132386,0.00003265784],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001058758,0.0005943042,0.71501666,0.0012279961,0.00024547498,4.2245406e-7,0.0030110944,0.0033787685,0.2408195,0.000714394,0.001598724,0.03328681],"study_design_scores_gemma":[0.0040236292,0.0010762907,0.19024706,0.000073906354,0.00018668246,0.00006630269,0.002280305,0.16480869,0.55763155,0.000051862597,0.07816115,0.0013925692],"about_ca_topic_score_codex":0.0000017338093,"about_ca_topic_score_gemma":0.0000021498104,"teacher_disagreement_score":0.5247696,"about_ca_system_score_codex":0.000007172881,"about_ca_system_score_gemma":0.00003693889,"threshold_uncertainty_score":0.3494944},"labels":[],"label_agreement":null},{"id":"W2119722989","doi":"10.1186/1471-2105-7-391","title":"Probe-level linear model fitting and mixture modeling results in high accuracy detection of differential gene expression","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Replicate; False positive paradox; Computer science; DNA microarray; Linear model; Replication (statistics); Set (abstract data type); Mixture model; Data set; Expression (computer science); Pattern recognition (psychology); Data mining; Gaussian; Computational biology; Artificial intelligence; Mathematics; Statistics; Gene expression; Gene; Biology; Genetics; Machine learning","score_opus":0.025785161643324863,"score_gpt":0.25112015716946995,"score_spread":0.22533499552614508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119722989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49567208,0.00006954883,0.5039999,0.000010701462,0.000036344278,0.000115439114,0.000025863748,0.000006610072,0.000063506384],"genre_scores_gemma":[0.89419043,0.00008108306,0.10534025,0.000014013593,0.00008519398,0.000014451018,0.00019006403,0.000009883049,0.00007461029],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904865,0.000022371596,0.0004938899,0.00016281614,0.00013147162,0.00014078915],"domain_scores_gemma":[0.99942404,0.000009708546,0.0002287334,0.0002301662,0.000074223,0.000033135948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000120537705,0.00012229849,0.0001209116,0.00006564523,0.000054494743,0.000016780938,0.0000914225,0.00018513411,7.0253424e-7],"category_scores_gemma":[0.000082868435,0.000106014326,0.000037499227,0.00007900537,0.000022332353,0.000016588037,0.00008350652,0.00008467055,5.2987895e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015491429,0.000033890436,0.00016907814,0.000094915194,0.0000023008204,5.1305634e-8,0.000100243094,0.088009775,0.9094454,0.000015503383,0.00005243568,0.0019215108],"study_design_scores_gemma":[0.0006490836,0.000025845764,0.00046195742,0.00003388364,0.0000045584225,0.0000012895038,0.00005925825,0.59753317,0.40103734,0.00009035966,0.000022138034,0.00008108931],"about_ca_topic_score_codex":0.000021410653,"about_ca_topic_score_gemma":0.000037579193,"teacher_disagreement_score":0.5095234,"about_ca_system_score_codex":0.000012003572,"about_ca_system_score_gemma":0.000049531645,"threshold_uncertainty_score":0.43231386},"labels":[],"label_agreement":null},{"id":"W2119886845","doi":"10.1186/1471-2105-5-13","title":"SeeGH – A software tool for visualization of whole genome array comparative genomic hybridization data","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Genome browser; Computer science; Context (archaeology); Genome; Visualization; Chromosome; DNA microarray; Reference genome; Human genome; Comparative genomic hybridization; Software; Genome project; Copy number analysis; Annotation; Computational biology; Biology; Genetics; Data mining; Genomics; Copy-number variation; Gene","score_opus":0.03524230117997183,"score_gpt":0.278305355110992,"score_spread":0.24306305393102018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119886845","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16746597,0.00010463419,0.8304626,0.000013835088,0.00007367663,0.00042399432,0.0012752045,0.00001565405,0.00016445557],"genre_scores_gemma":[0.6103074,0.000044592452,0.3725961,0.00011731652,0.00016266637,0.000037659007,0.016440073,0.00002312215,0.00027108894],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990766,0.000015654297,0.00047593378,0.00016180048,0.00010113952,0.00016889682],"domain_scores_gemma":[0.998998,0.00001449675,0.00027717245,0.0004996581,0.00017511054,0.000035560544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017292546,0.00013829525,0.0001741551,0.000050365976,0.000104793624,0.00003625192,0.00030018072,0.0000891659,0.000007384046],"category_scores_gemma":[0.00007465753,0.00013657483,0.000057200028,0.00008568825,0.00005254204,0.00003335238,0.00012375519,0.000027053537,0.00001369167],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062097743,0.0008453756,0.013025858,0.003122323,0.0007270708,6.2289973e-7,0.012496197,0.29619572,0.65205234,0.016150134,0.003411283,0.0013521095],"study_design_scores_gemma":[0.018003324,0.0035956125,0.029376268,0.00032481737,0.000747625,0.00015476022,0.012978592,0.09996941,0.59910667,0.0061435774,0.22583543,0.0037639095],"about_ca_topic_score_codex":0.0000064199144,"about_ca_topic_score_gemma":0.000022568822,"teacher_disagreement_score":0.45786646,"about_ca_system_score_codex":0.000030741186,"about_ca_system_score_gemma":0.00024977888,"threshold_uncertainty_score":0.556936},"labels":[],"label_agreement":null},{"id":"W2119894516","doi":"10.1186/1471-2105-8-286","title":"CLUSS: Clustering of protein sequences based on a new similarity measure","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Cluster analysis; Similarity (geometry); Phylogenetic tree; Biological data; Similarity measure; Computer science; Matching (statistics); Protein sequencing; Measure (data warehouse); Data mining; Protein family; Computational biology; Artificial intelligence; Bioinformatics; Biology; Genetics; Peptide sequence; Mathematics; Gene","score_opus":0.018123837303283746,"score_gpt":0.26742335716123616,"score_spread":0.24929951985795243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119894516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026815407,0.000058209716,0.950364,0.000096708005,0.00013604152,0.0005706084,0.00002223953,0.00005153245,0.021885263],"genre_scores_gemma":[0.33865976,0.0000061880123,0.6598012,0.0007280024,0.00017669602,0.000006917991,0.00011893521,0.000029546658,0.00047273506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983229,0.000036148645,0.00071488245,0.00014017621,0.00043239165,0.00035351026],"domain_scores_gemma":[0.99872065,0.000044454453,0.00040586846,0.00055598683,0.00011686977,0.00015618085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010173133,0.00023766354,0.00022332006,0.00012631419,0.00008456973,0.000034433873,0.00036663958,0.0002616708,0.00002540363],"category_scores_gemma":[0.00059484923,0.00020705047,0.0001323712,0.00018878092,0.00009909893,0.000014858552,0.00012302294,0.00021930276,0.000020397767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057573793,0.0012165839,0.07344097,0.011888614,0.0005380636,0.000018618226,0.0065598125,0.5918657,0.09511126,0.0032541542,0.017870257,0.1924786],"study_design_scores_gemma":[0.0016140767,0.0010714341,0.0021811158,0.00030287183,0.000029800018,0.000016831018,0.00043808165,0.9236535,0.055108942,0.00006741103,0.014965409,0.0005505423],"about_ca_topic_score_codex":0.000028377424,"about_ca_topic_score_gemma":0.00015451352,"teacher_disagreement_score":0.3317878,"about_ca_system_score_codex":0.0000297473,"about_ca_system_score_gemma":0.00030421015,"threshold_uncertainty_score":0.84432733},"labels":[],"label_agreement":null},{"id":"W2120027330","doi":"10.1186/1471-2105-10-306","title":"A methodology for the analysis of differential coexpression across the human lifespan","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Biology; DNA microarray; Similarity (geometry); Differential (mechanical device); Computational biology; Gene; Microarray analysis techniques; Gene expression; Genetics; Computer science; Artificial intelligence","score_opus":0.04775446544068047,"score_gpt":0.34034123617324125,"score_spread":0.2925867707325608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120027330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.163247,0.0002593733,0.8352045,0.00020595851,0.00016890194,0.0005018458,0.0001245315,0.000010063958,0.0002778602],"genre_scores_gemma":[0.958703,0.000086646694,0.039492138,0.00081615086,0.00024012574,0.000030296567,0.0003624776,0.000010816732,0.00025837906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988411,0.000057603047,0.0005714913,0.00010603484,0.0001308778,0.00029290406],"domain_scores_gemma":[0.9986629,0.00018800737,0.0003755802,0.0006329589,0.00009465294,0.00004592589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007229,0.00015875585,0.00027697586,0.00004449066,0.0003359794,0.00004764584,0.00050749787,0.00018504153,0.000011267116],"category_scores_gemma":[0.000096306976,0.0000839161,0.0003602073,0.00021060764,0.000156863,0.0000060438047,0.00013402876,0.000104377905,0.0000013904644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002331568,0.0009369343,0.009420879,0.00094725844,0.013343424,7.250544e-7,0.034222085,0.10139659,0.2692196,0.035928745,0.08344042,0.44881177],"study_design_scores_gemma":[0.002275117,0.00089549314,0.04273501,0.00003429854,0.0022929963,0.00001032481,0.004485891,0.8892426,0.022382483,0.0015375003,0.033470854,0.0006374313],"about_ca_topic_score_codex":0.0000073915676,"about_ca_topic_score_gemma":0.000067989335,"teacher_disagreement_score":0.79571235,"about_ca_system_score_codex":0.000006336613,"about_ca_system_score_gemma":0.000032913063,"threshold_uncertainty_score":0.34219992},"labels":[],"label_agreement":null},{"id":"W2120865704","doi":"10.1186/1471-2105-10-s13-o5","title":"Functionally informative tag SNP selection using a pareto-optimal approach: playing the game of life","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Single-nucleotide polymorphism; SNP; SNP genotyping; Genotyping; Selection (genetic algorithm); Tag SNP; Computational biology; Biology; DNA microarray; Genomics; Genetics; Computer science; Genome; Genotype; Gene; Artificial intelligence","score_opus":0.035381251315872116,"score_gpt":0.24991471195998424,"score_spread":0.21453346064411213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120865704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23858765,0.00012610276,0.7574302,0.00002852721,0.00007942081,0.00036829332,0.000016466864,0.000019837064,0.0033434762],"genre_scores_gemma":[0.7795534,0.000031083804,0.21955936,0.000528869,0.00015705323,0.000014955578,0.0000668969,0.000011479208,0.0000768867],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989091,0.0000518159,0.00048060637,0.00010191806,0.0002340928,0.00022245804],"domain_scores_gemma":[0.9992031,0.000025016021,0.00035211915,0.0002323165,0.00012176895,0.00006572116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004023465,0.00016841658,0.00017190854,0.000059159614,0.00016584386,0.000041630356,0.00019961732,0.0001678626,0.0000125664055],"category_scores_gemma":[0.00015638472,0.00012187064,0.000118189324,0.00015435273,0.000059551418,0.000030486248,0.00005103326,0.00010250338,0.000007583216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025674123,0.0006209451,0.006520459,0.0011788482,0.0008384085,7.5334407e-7,0.010154568,0.2995379,0.6224646,0.010721948,0.0043811374,0.041013017],"study_design_scores_gemma":[0.0012022796,0.0009650563,0.0036509894,0.00007194058,0.00009992391,0.00008973414,0.0037086804,0.8714075,0.113561474,0.00031232074,0.004303455,0.0006266545],"about_ca_topic_score_codex":0.000005137638,"about_ca_topic_score_gemma":0.000002123509,"teacher_disagreement_score":0.5718696,"about_ca_system_score_codex":0.000017226326,"about_ca_system_score_gemma":0.00019684964,"threshold_uncertainty_score":0.49697405},"labels":[],"label_agreement":null},{"id":"W2120895683","doi":"10.1186/1471-2105-12-8","title":"Flexible taxonomic assignment of ambiguous sequencing reads","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics","keywords":"Metagenomics; Computer science; Set (abstract data type); False positive paradox; Data mining; Computational biology; Matching (statistics); Phylogenetic tree; Biology; Information retrieval; Artificial intelligence; Statistics; Genetics; Mathematics; Gene","score_opus":0.062467156920103004,"score_gpt":0.23166582566858296,"score_spread":0.16919866874847994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120895683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8807783,0.0005437234,0.070733756,0.0000056831695,0.0002566512,0.00029429706,0.00004656133,0.000010001502,0.047331035],"genre_scores_gemma":[0.8700585,0.00016207628,0.12933677,0.00007699159,0.00004888615,0.000013695904,0.000015813266,0.000012140414,0.00027512366],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992523,0.000012816098,0.00035449213,0.00010887171,0.000078935685,0.00019257041],"domain_scores_gemma":[0.9993821,0.00000454915,0.00017757415,0.0003308026,0.000053030075,0.00005195473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000150311,0.00012829875,0.0001536102,0.000036924666,0.00004730259,0.0000071013674,0.00017266869,0.00008607834,0.000016681694],"category_scores_gemma":[0.000023919774,0.00011659835,0.00008119791,0.000044736822,0.000078333745,0.0000013969819,0.00013811565,0.000037587182,0.000017398159],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040619244,0.0003118805,0.050437823,0.00090427557,0.0006902136,0.000002836388,0.006354378,0.002944452,0.90016985,0.0034072672,0.0064863437,0.027884487],"study_design_scores_gemma":[0.00089891284,0.00086307497,0.020138869,0.000037496917,0.00007225456,0.000024990137,0.0025637425,0.0035855814,0.96034265,0.00038957916,0.010560434,0.00052239175],"about_ca_topic_score_codex":0.000057581194,"about_ca_topic_score_gemma":0.000017886074,"teacher_disagreement_score":0.06017282,"about_ca_system_score_codex":0.000020607393,"about_ca_system_score_gemma":0.00010672708,"threshold_uncertainty_score":0.47547427},"labels":[],"label_agreement":null},{"id":"W2121109569","doi":"10.1186/1471-2105-9-261","title":"Probe-specific mixed-model approach to detect copy number differences using multiplex ligation-dependent probe amplification (MLPA)","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Instituto de Salud Carlos III; Generalitat de Catalunya; European Commission","keywords":"Multiplex ligation-dependent probe amplification; Normalization (sociology); Mixed model; Multiplex; Computer science; Copy-number variation; Bivariate analysis; Statistics; Algorithm; Mathematics; Biology; Machine learning; Bioinformatics; Genetics; Genome","score_opus":0.0513519044060402,"score_gpt":0.24780123376166083,"score_spread":0.19644932935562062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121109569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40724337,0.00003371002,0.59102535,0.000009416354,0.00007195511,0.00043544197,0.00004713461,0.000024597804,0.0011090456],"genre_scores_gemma":[0.60703105,0.00004463029,0.39219305,0.000051872965,0.000088202934,0.00006983128,0.00017336645,0.000016053395,0.00033196047],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985996,0.000034064346,0.0005382622,0.00026230162,0.00025188428,0.0003139146],"domain_scores_gemma":[0.9990346,0.00001206177,0.00021307962,0.00044145455,0.00017446831,0.00012432633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015770206,0.0002378084,0.00019534437,0.00006216971,0.00032552538,0.000078582045,0.00027731835,0.00018103847,0.000011151128],"category_scores_gemma":[0.00003611376,0.00021680817,0.00009258196,0.00013895919,0.00007763118,0.000027798396,0.00012937638,0.00009203864,0.000067123045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007168929,0.0017359564,0.26325125,0.002085734,0.00053794845,0.0000035701837,0.027692499,0.2817417,0.3925803,0.0147239035,0.008314481,0.006615774],"study_design_scores_gemma":[0.0023341796,0.0003421871,0.03190166,0.00009015259,0.00009066647,0.00041645684,0.004464404,0.7621084,0.19076756,0.0010347537,0.004474493,0.0019751266],"about_ca_topic_score_codex":0.00001988268,"about_ca_topic_score_gemma":0.000017009932,"teacher_disagreement_score":0.48036668,"about_ca_system_score_codex":0.000054752356,"about_ca_system_score_gemma":0.00019175232,"threshold_uncertainty_score":0.8841181},"labels":[],"label_agreement":null},{"id":"W2121776973","doi":"10.1186/1471-2105-15-148","title":"Improvement of domain-level ortholog clustering by optimizing domain-specific sum-of-pairs score","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute for Basic Biology; National Bioscience Database Center; Institute of Genetics; Research Organization of Information and Systems","keywords":"Cluster analysis; Pipeline (software); Pairwise comparison; Domain (mathematical analysis); Computer science; DNA microarray; Data mining; Genome; Computational biology; Architecture domain; Biology; Pattern recognition (psychology); Artificial intelligence; Gene; Genetics; Software; Mathematics","score_opus":0.02150140156673435,"score_gpt":0.22381527533736278,"score_spread":0.20231387377062843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121776973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6803179,0.00061048253,0.31660622,0.00001616561,0.00016418305,0.00021609289,0.00008415747,0.000004011397,0.0019807902],"genre_scores_gemma":[0.5943989,0.00051082723,0.40473732,0.00009305574,0.00007646064,0.000015010596,0.00007671811,0.00002348683,0.00006821409],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987686,0.000020036605,0.0006200594,0.00016768124,0.00015213479,0.00027147165],"domain_scores_gemma":[0.9990255,0.000024245746,0.00034640555,0.00043877904,0.000101729536,0.00006332887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033496102,0.00019786619,0.00028432807,0.00004992016,0.00007504136,0.000013942318,0.00025125858,0.00012793386,0.0000053141202],"category_scores_gemma":[0.000016601665,0.00017944085,0.0001294734,0.00007119444,0.00015531036,0.000002188484,0.000297277,0.000058977035,0.0000030474075],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120034514,0.00010012357,0.0075021223,0.0005699209,0.00015030663,2.654542e-7,0.0010252162,0.0021402282,0.9736172,0.00074599247,0.002709345,0.011319255],"study_design_scores_gemma":[0.006022215,0.003389729,0.011879167,0.00024701047,0.00010707494,0.000036136225,0.007298447,0.0085291285,0.7732441,0.0009970989,0.18654926,0.0017006202],"about_ca_topic_score_codex":0.0000064669475,"about_ca_topic_score_gemma":0.000017985905,"teacher_disagreement_score":0.20037308,"about_ca_system_score_codex":0.00001228543,"about_ca_system_score_gemma":0.000037748527,"threshold_uncertainty_score":0.7317385},"labels":[],"label_agreement":null},{"id":"W2121981832","doi":"10.1186/1471-2105-13-s9-s2","title":"Modeling and mining term association for improving biomedical information retrieval performance","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Term (time); Term Discrimination; Set (abstract data type); Index (typography); Sentence; Association rule learning; Data mining; Paragraph; Baseline (sea); Artificial intelligence; Search engine; Concept search; Web search query; World Wide Web","score_opus":0.01922306671104155,"score_gpt":0.25661114349442515,"score_spread":0.2373880767833836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121981832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75931376,0.00020489443,0.23964027,0.000043726046,0.0003197777,0.0001855988,0.000024205765,0.000036178026,0.00023160774],"genre_scores_gemma":[0.8185873,0.00006673942,0.18038127,0.0001957435,0.00034757485,0.000015942447,0.00029392936,0.000009701699,0.00010180381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989725,0.000013351256,0.00037809738,0.00007582819,0.00019210346,0.0003681323],"domain_scores_gemma":[0.99945694,0.000042783155,0.00016377743,0.0001298509,0.00008245758,0.00012420327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007527504,0.00012407287,0.00012782965,0.000067825225,0.00014171211,0.000052107716,0.00009758494,0.00030107415,0.0000016675755],"category_scores_gemma":[0.0008668316,0.00010730676,0.000046879366,0.00007457,0.000048900893,0.000060297814,0.00009549344,0.00007801052,0.0000061887736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091975095,0.00022890627,0.19530307,0.004451427,0.00024154526,1.591567e-7,0.009529247,0.0010011422,0.015664473,0.00023316282,0.006003228,0.7664239],"study_design_scores_gemma":[0.0012561587,0.0004054496,0.004159686,0.0000414629,0.000050149374,0.000016655451,0.0014236913,0.9732263,0.0024472773,0.0000072071016,0.016637955,0.00032798498],"about_ca_topic_score_codex":0.0000016930652,"about_ca_topic_score_gemma":9.824346e-7,"teacher_disagreement_score":0.9722252,"about_ca_system_score_codex":0.00003673736,"about_ca_system_score_gemma":0.00006464949,"threshold_uncertainty_score":0.43758428},"labels":[],"label_agreement":null},{"id":"W2122545386","doi":"10.1186/1471-2105-14-s5-s3","title":"Joint genotype inference with germline and somatic mutations","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Foreign Affairs and International Trade Canada; Canadian Institutes of Health Research; Terry Fox Research Institute; Government of Canada","keywords":"Genetics; Biology; Genome; 1000 Genomes Project; Germline; Germline mutation; Exome sequencing; Exome; Computational biology; DNA sequencing; Cancer genome sequencing; Genotype; Whole genome sequencing; Mutation; Gene; Single-nucleotide polymorphism","score_opus":0.012273740109208165,"score_gpt":0.22595126737810664,"score_spread":0.21367752726889847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122545386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84122604,0.0003131732,0.15547146,0.0001325759,0.000068136564,0.00043834897,0.00003345314,0.000020182524,0.0022966515],"genre_scores_gemma":[0.8229252,0.0002436531,0.17578135,0.00050071755,0.000089517576,0.00005514947,0.00017483438,0.000018663864,0.0002109222],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942803,0.0000068784225,0.00022714134,0.00009787099,0.00007852973,0.00016156131],"domain_scores_gemma":[0.9994619,0.000027634658,0.000094584706,0.0002352722,0.00008835971,0.00009225986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000049412265,0.000116571915,0.00010529584,0.00003489439,0.000068856156,0.0000784969,0.000072660194,0.00006570068,0.000037505954],"category_scores_gemma":[0.000092484675,0.00009300858,0.000023538521,0.000048879072,0.00008060827,0.000010671309,0.00007836134,0.00004739663,0.0000754267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005170431,0.0014923752,0.33447155,0.00674597,0.0011871782,0.00002021532,0.013802312,0.05111637,0.2878262,0.02365336,0.056316998,0.22285043],"study_design_scores_gemma":[0.0070852297,0.0034634073,0.27985308,0.00028911632,0.00034296184,0.00031393307,0.00405629,0.6089666,0.055456918,0.0056397174,0.03160784,0.0029249184],"about_ca_topic_score_codex":0.00003526785,"about_ca_topic_score_gemma":0.00009202046,"teacher_disagreement_score":0.55785024,"about_ca_system_score_codex":0.000008825159,"about_ca_system_score_gemma":0.00011719078,"threshold_uncertainty_score":0.37927797},"labels":[],"label_agreement":null},{"id":"W2122656565","doi":"10.1186/1471-2105-11-344","title":"Error, reproducibility and sensitivity: a pipeline for data processing of Agilent oligonucleotide expression arrays","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Biotechnology and Biological Sciences Research Council; University College London Hospitals NHS Foundation Trust; National Institute for Health and Care Research; Wellcome Trust","keywords":"Pipeline (software); DNA microarray; Oligonucleotide; Sensitivity (control systems); Reproducibility; Computational biology; Computer science; Bioinformatics; Biology; Gene expression; Genetics; Engineering; Chemistry; DNA; Gene; Chromatography; Programming language; Electronic engineering","score_opus":0.04951004012177882,"score_gpt":0.31344069538670294,"score_spread":0.2639306552649241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122656565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28182858,0.00019133727,0.7161068,0.0001787521,0.0002545936,0.0006448144,0.00018061323,0.000026132506,0.00058838684],"genre_scores_gemma":[0.7408152,0.000045721485,0.25810623,0.000115308234,0.00016040825,0.000019640194,0.0006101185,0.000015108199,0.00011224203],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989471,0.000026299855,0.0003647399,0.00041190724,0.000113416674,0.00013653716],"domain_scores_gemma":[0.99793625,0.00002127651,0.00025689535,0.0015782095,0.00013987855,0.0000674996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010892823,0.00011334863,0.00013871769,0.000035082034,0.000077429075,0.000023712546,0.00013845363,0.00012981614,0.0000031865502],"category_scores_gemma":[0.000793443,0.0000950955,0.000030610736,0.000055992125,0.00009506992,0.00002140603,0.000235796,0.00008865065,8.053887e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010327845,0.000060303322,0.0010829557,0.0004039665,0.000004151274,6.3382736e-8,0.00015454128,0.000030737705,0.96560574,0.0000257973,0.004207073,0.028321374],"study_design_scores_gemma":[0.0007000356,0.00006739622,0.0015760682,0.00006416331,0.000026622094,0.000017052189,0.00039812058,0.27589312,0.686971,0.00009652292,0.033983503,0.00020636951],"about_ca_topic_score_codex":0.0000042618535,"about_ca_topic_score_gemma":0.00004103981,"teacher_disagreement_score":0.45898664,"about_ca_system_score_codex":0.0000032575779,"about_ca_system_score_gemma":0.00011216449,"threshold_uncertainty_score":0.3877882},"labels":[],"label_agreement":null},{"id":"W2123076448","doi":"10.1186/1471-2105-11-383","title":"The oligodeoxynucleotide sequences corresponding to never-expressed peptide motifs are mainly located in the non-coding strand","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computational biology; Genetics; Biology; DNA microarray; Coding region; Molecular biology; Gene; Gene expression","score_opus":0.013192514968809728,"score_gpt":0.24217249296437277,"score_spread":0.22897997799556305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123076448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93684864,0.00003188708,0.059995804,0.00043816163,0.00035967803,0.00071097567,0.000032036143,0.000018802806,0.0015639872],"genre_scores_gemma":[0.9802419,0.00005907182,0.01853956,0.000654513,0.00013361758,0.000060742295,0.000021401594,0.000019887095,0.00026932053],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986675,0.00008288659,0.00041501984,0.00017705884,0.00024994576,0.00040763358],"domain_scores_gemma":[0.9989144,0.00015439882,0.00018301146,0.00059604004,0.000062667124,0.00008945444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011178361,0.00020742319,0.00015846346,0.000066415,0.00032259777,0.00022696592,0.0007743226,0.00016628634,0.0000106840025],"category_scores_gemma":[0.0004358613,0.00012636068,0.00008508078,0.00019883587,0.00007823859,0.000025554287,0.000112152906,0.00019707852,0.000034073568],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017804278,0.00003230744,0.0019483026,0.00009437916,0.000026192549,0.0000053409176,0.0013766944,0.0009446902,0.98998463,0.0009018752,0.001402323,0.0031052185],"study_design_scores_gemma":[0.0009347568,0.0002728664,0.011129871,0.00020108708,0.00003543474,0.000058911017,0.011626799,0.024877602,0.9237733,0.0005356402,0.025852535,0.00070121925],"about_ca_topic_score_codex":0.000027991544,"about_ca_topic_score_gemma":0.0006002046,"teacher_disagreement_score":0.06621136,"about_ca_system_score_codex":0.000011295373,"about_ca_system_score_gemma":0.00009332328,"threshold_uncertainty_score":0.5152839},"labels":[],"label_agreement":null},{"id":"W2123808880","doi":"10.1186/1471-2105-6-273","title":"Ancestral sequence alignment under optimal conditions","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Phylogenetic tree; Pairwise comparison; Multiple sequence alignment; Alignment-free sequence analysis; Maximum parsimony; Heuristic; Sequence (biology); Tree (set theory); Biology; Sequence alignment; Algorithm; Computational biology; Computer science; Artificial intelligence; Clade; Mathematics; Genetics; Combinatorics; Gene","score_opus":0.034718946190375424,"score_gpt":0.2832690485862361,"score_spread":0.24855010239586067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123808880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9629477,0.00042901994,0.031140672,0.00024422826,0.00015580845,0.00020428772,0.00013364447,0.000010074807,0.0047345157],"genre_scores_gemma":[0.8741838,0.00019277545,0.12420275,0.0006528293,0.00020643805,0.000018665489,0.000094113835,0.000009400239,0.0004392624],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99934524,0.000009067074,0.00022677865,0.0001096917,0.00009229867,0.00021691917],"domain_scores_gemma":[0.99959534,0.0000073728897,0.00007151605,0.00022042045,0.00003926529,0.00006608282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007021659,0.00012124858,0.00009009818,0.000020375845,0.00010222666,0.000025537118,0.0001348065,0.000070299844,0.000021614933],"category_scores_gemma":[0.000010198518,0.00011190431,0.000062938365,0.00003841803,0.00009166109,0.0000023193593,0.00008146356,0.000039290622,0.00006149702],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001358141,0.00045872518,0.023262046,0.0002576555,0.0005920496,0.0000028472314,0.002036844,0.40344346,0.49528366,0.015387039,0.045690604,0.013449239],"study_design_scores_gemma":[0.0040322663,0.0013840601,0.0666056,0.00006920614,0.00019580113,0.0002438897,0.0044422,0.14779569,0.23736504,0.00096248346,0.534551,0.0023527446],"about_ca_topic_score_codex":0.0000029247951,"about_ca_topic_score_gemma":0.000025432893,"teacher_disagreement_score":0.4888604,"about_ca_system_score_codex":0.000018025392,"about_ca_system_score_gemma":0.000071803435,"threshold_uncertainty_score":0.4563325},"labels":[],"label_agreement":null},{"id":"W2125076371","doi":"10.1186/1471-2105-15-61","title":"CDSbank: taxonomy-aware extraction, selection, renaming and formatting of protein-coding DNA or amino acid sequences","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"GenBank; Computer science; Disk formatting; Sequence database; Redundancy (engineering); Web server; Data mining; Information retrieval; Database; Computational biology; Biology; The Internet; Genetics; World Wide Web","score_opus":0.024829442139633295,"score_gpt":0.24259199304970877,"score_spread":0.2177625509100755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125076371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8681948,0.0002691013,0.12987238,0.000023014758,0.00009771456,0.00040899034,0.000015748525,0.000010975451,0.0011072237],"genre_scores_gemma":[0.91484624,0.000118793745,0.084672086,0.00005036038,0.00011559573,0.000044314875,0.000015335221,0.000011302321,0.0001259547],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990533,0.00002577157,0.00044324342,0.00014290141,0.00010986897,0.00022489335],"domain_scores_gemma":[0.9992796,0.000026278949,0.00031972132,0.00017053714,0.00014698307,0.000056834644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003223131,0.00016165129,0.00018397206,0.0000651661,0.00019875521,0.00004248389,0.000118790434,0.00011053172,0.0000043857854],"category_scores_gemma":[0.00016234767,0.00013281177,0.000049383892,0.00010346718,0.00008749513,0.000009280365,0.00011060205,0.00006452326,0.0000021969793],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017049677,0.000060462196,0.032372266,0.0017341771,0.00019654965,3.9683945e-7,0.0013428207,0.00043927145,0.89375573,0.00044838857,0.0006885353,0.06879091],"study_design_scores_gemma":[0.0010644144,0.0008783423,0.0074874964,0.00018777102,0.000074071104,0.00013284806,0.0031133783,0.048712574,0.901896,0.0001685139,0.03561785,0.0006667195],"about_ca_topic_score_codex":0.000013370995,"about_ca_topic_score_gemma":0.00008389018,"teacher_disagreement_score":0.06812419,"about_ca_system_score_codex":0.0000136068675,"about_ca_system_score_gemma":0.00008197153,"threshold_uncertainty_score":0.54159063},"labels":[],"label_agreement":null},{"id":"W2125456570","doi":"10.1186/1471-2105-11-461","title":"Pan-genome sequence analysis using Panseq: an online tool for the rapid analysis of core and accessory genomic regions","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Escherichia coli research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":306,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada; Canadian Food Inspection Agency","keywords":"Genome; Biology; Genetics; Multilocus sequence typing; Locus (genetics); Population; Phylogenetic tree; Bacterial genome size; Reference genome; Whole genome sequencing; Computational biology; Gene; Genotype","score_opus":0.11340474752202609,"score_gpt":0.35653608672141324,"score_spread":0.24313133919938715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125456570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9482881,0.00033135235,0.050347276,0.000032699314,0.000036014702,0.0003311243,0.0006034302,0.000007675214,0.000022359069],"genre_scores_gemma":[0.9115314,0.0006292742,0.086901285,0.00012094299,0.00007601946,0.000027500746,0.00064334885,0.000012789798,0.000057442157],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989987,0.000029518005,0.00039697034,0.00017731253,0.000151783,0.0002457403],"domain_scores_gemma":[0.99867475,0.00012478007,0.00024414482,0.00065594236,0.00023479326,0.000065597655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004480929,0.00015125271,0.00031592062,0.00021536714,0.00021503684,0.000047721885,0.00036385894,0.00011750636,0.000009120797],"category_scores_gemma":[0.00028580928,0.00010840085,0.0002434858,0.00076498673,0.00031537615,0.000018116207,0.00021676549,0.000121637204,2.391671e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014258693,0.00012728914,0.0661876,0.0002189346,0.007857469,4.4726846e-7,0.00101851,0.009854112,0.9091824,0.00021288429,0.000038386966,0.005159339],"study_design_scores_gemma":[0.00032037048,0.00015437213,0.1571519,0.0000032797905,0.0038756148,0.0000030303438,0.0011034587,0.8344489,0.0011006171,0.000022892862,0.0015829412,0.00023264285],"about_ca_topic_score_codex":0.00004794443,"about_ca_topic_score_gemma":0.001528589,"teacher_disagreement_score":0.9080818,"about_ca_system_score_codex":0.000011739054,"about_ca_system_score_gemma":0.00014268955,"threshold_uncertainty_score":0.44204584},"labels":[],"label_agreement":null},{"id":"W2125816119","doi":"10.1186/1471-2105-6-34","title":"Atlas – a data warehouse for integrative bioinformatics","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":163,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research","keywords":"Atlas (anatomy); Data warehouse; Bioinformatics; Computational biology; Data science; Computer science; Biology; Data mining","score_opus":0.030515866595186156,"score_gpt":0.27606820481453165,"score_spread":0.2455523382193455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125816119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002562372,0.00044321574,0.98625386,0.00026741604,0.0003745966,0.0011285197,0.00096023444,0.0000861098,0.007923666],"genre_scores_gemma":[0.014482518,0.00031122993,0.9754982,0.001757157,0.0010102349,0.00007815007,0.0050617117,0.00006666124,0.0017341106],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781656,0.000020666206,0.0010390456,0.00027217294,0.00024116535,0.000610389],"domain_scores_gemma":[0.99745536,0.00007336321,0.0004278517,0.0016341952,0.00019819115,0.00021106204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062160584,0.0004085742,0.0003463328,0.00010791819,0.00022860403,0.00016294724,0.0012066812,0.00034049412,0.000024184295],"category_scores_gemma":[0.00025051608,0.00033370472,0.00018074967,0.00016289535,0.0001506758,0.0000934035,0.0007030188,0.00019148346,0.00019288191],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005634443,0.00032573886,0.0005299027,0.0010233126,0.000514809,6.4618933e-7,0.0038675065,0.012455985,0.0005749587,0.0043637976,0.71648175,0.25929815],"study_design_scores_gemma":[0.0010001162,0.00021306383,0.0000239532,0.000033011926,0.000043698292,0.000022993661,0.0008553925,0.61184555,0.000889368,0.0001230591,0.38455692,0.0003929028],"about_ca_topic_score_codex":0.000004251376,"about_ca_topic_score_gemma":0.00018041697,"teacher_disagreement_score":0.59938955,"about_ca_system_score_codex":0.000043264856,"about_ca_system_score_gemma":0.0002820126,"threshold_uncertainty_score":0.9999115},"labels":[],"label_agreement":null},{"id":"W2126698259","doi":"10.1186/1471-2105-15-s9-s12","title":"ARYANA: Aligning Reads by Yet Another Approach","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Institute for Research in Fundamental Sciences; Royan Institute; Sharif University of Technology; National Science Foundation","keywords":"Computer science; Search engine indexing; Hash function; Software; Hash table; Scalability; Theoretical computer science; Algorithm; Computer engineering; Information retrieval; Programming language; Database","score_opus":0.011428203836682409,"score_gpt":0.20909785854690072,"score_spread":0.1976696547102183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126698259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25529796,0.0015826477,0.5702083,0.00011451803,0.00045443684,0.00051695644,0.00011833386,0.00003423463,0.17167263],"genre_scores_gemma":[0.7213987,0.00028617564,0.27318764,0.0018483081,0.00031168415,0.00003827638,0.00033000356,0.00005591812,0.0025432918],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992386,0.000023983768,0.00024762287,0.00015040585,0.000100887744,0.0002384781],"domain_scores_gemma":[0.99944824,0.000014175267,0.00010000993,0.0003469714,0.000038874623,0.000051710504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020785944,0.00015773001,0.0001460946,0.00002421261,0.00009018701,0.00003137645,0.00018522792,0.00011678817,0.000005001149],"category_scores_gemma":[0.00005083532,0.00013731567,0.0000685893,0.000052738633,0.00006464873,0.0000013194426,0.00011630049,0.00004749315,0.000027027474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014401639,0.00036321822,0.04260701,0.0006977643,0.00054961414,4.1986672e-7,0.002192647,0.0030731952,0.34557354,0.0035495434,0.57116854,0.03008046],"study_design_scores_gemma":[0.0014922719,0.00050028565,0.0028808862,0.000021997734,0.00006806963,0.000025257625,0.00086884544,0.061474368,0.05874135,0.00032742633,0.8726633,0.0009359265],"about_ca_topic_score_codex":0.0000075098947,"about_ca_topic_score_gemma":0.0000049393175,"teacher_disagreement_score":0.46610075,"about_ca_system_score_codex":0.0000061731625,"about_ca_system_score_gemma":0.00002445263,"threshold_uncertainty_score":0.5599571},"labels":[],"label_agreement":null},{"id":"W2126957930","doi":"10.1186/1471-2105-13-15","title":"The EnzymeTracker: an open-source laboratory information management system for sample tracking","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Espace pour la vie; Concordia University","funders":"","keywords":"Computer science; Data management; Interface (matter); Sample (material); Ajax; Data sharing; Tracking system; Data science; World Wide Web; Web application; Database; Filter (signal processing)","score_opus":0.02994307694206483,"score_gpt":0.2968691113282399,"score_spread":0.26692603438617507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126957930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011512122,0.00042957882,0.9799994,0.0000975049,0.0009859789,0.0023379354,0.00040779248,0.00008542338,0.0041442313],"genre_scores_gemma":[0.24183974,0.0009050332,0.7493604,0.0015444764,0.0014049765,0.000666241,0.003330615,0.00009787886,0.0008506471],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977198,0.00006751425,0.00081826193,0.00012283416,0.00048562794,0.00078595185],"domain_scores_gemma":[0.9981329,0.00013207506,0.00031181698,0.0007334337,0.00032700994,0.00036278015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022783705,0.00023868389,0.00019099274,0.00010173375,0.0006110378,0.000609882,0.0010744636,0.0002241181,0.0000051370343],"category_scores_gemma":[0.00047190615,0.00017120205,0.00008898291,0.00021402941,0.00016127908,0.00020313816,0.0005110689,0.0001288998,0.00008054132],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000993446,0.0005389955,0.0052240873,0.006046096,0.0005348353,3.838758e-7,0.004862701,0.00047475233,0.0017127596,0.014902818,0.07098821,0.8937209],"study_design_scores_gemma":[0.001212615,0.00043128105,0.0010999818,0.000045288634,0.000043609878,0.000008362715,0.011176634,0.02618919,0.0074746176,0.000036747384,0.95190924,0.00037240115],"about_ca_topic_score_codex":0.000013151491,"about_ca_topic_score_gemma":0.000028997727,"teacher_disagreement_score":0.8933485,"about_ca_system_score_codex":0.00006643995,"about_ca_system_score_gemma":0.00013521468,"threshold_uncertainty_score":0.69814163},"labels":[],"label_agreement":null},{"id":"W2127147859","doi":"10.1186/1471-2105-9-158","title":"Improving the prediction of mRNA extremities in the parasitic protozoan Leishmania","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Wilfrid Laurier University; Centre hospitalier de l'Université Laval; Centre hospitalier universitaire de Québec","funders":"Canadian Institutes of Health Research; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Polyadenylation; RNA splicing; Biology; DNA microarray; Computational biology; splice; In silico; Genetics; Alternative splicing; Expressed sequence tag; Polypyrimidine tract; Untranslated region; Gene; Messenger RNA; RNA; Gene expression","score_opus":0.026698459540062093,"score_gpt":0.2490251544614015,"score_spread":0.2223266949213394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127147859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99207795,0.00012070114,0.0056146597,0.00004320987,0.000029501236,0.00055834994,0.000012464494,0.000005744295,0.0015374471],"genre_scores_gemma":[0.99742174,0.00008882287,0.0019852247,0.00010020596,0.00007110939,0.000066780034,0.000026026404,0.000005965738,0.00023414256],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992283,0.000050085746,0.00026796683,0.000064939384,0.00020107302,0.00018762861],"domain_scores_gemma":[0.9994958,0.000042477204,0.00009046544,0.00030281206,0.000045451558,0.000023011815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035338814,0.00007758355,0.00007653438,0.000033478947,0.00012312601,0.00001910236,0.00025943096,0.000060225735,0.0000027634585],"category_scores_gemma":[0.00018638393,0.000043307256,0.000050283772,0.00009419184,0.00013918526,0.000011158637,0.00004136181,0.00010807578,0.000003108696],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004114245,0.0003831884,0.3939586,0.001480664,0.00011102065,0.000013955176,0.013525578,0.001693839,0.56020266,0.0011241114,0.00989409,0.017200867],"study_design_scores_gemma":[0.0032876043,0.0019354929,0.2821245,0.00021134486,0.000048487713,0.0006566561,0.02107004,0.40816167,0.27324292,0.00014653729,0.008503102,0.00061163545],"about_ca_topic_score_codex":0.00006722418,"about_ca_topic_score_gemma":0.00006385172,"teacher_disagreement_score":0.40646785,"about_ca_system_score_codex":0.00000907403,"about_ca_system_score_gemma":0.000103242215,"threshold_uncertainty_score":0.17660187},"labels":[],"label_agreement":null},{"id":"W2127314261","doi":"10.1186/1471-2105-13-318","title":"On the contributions of topological features to transcriptional regulatory network robustness","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Robustness (evolution); Gene regulatory network; Computational biology; DNA microarray; Topology (electrical circuits); Computer science; Biology; Systems biology; Gene; Genetics; Gene expression; Mathematics; Combinatorics","score_opus":0.0145162027474679,"score_gpt":0.24526934500809067,"score_spread":0.23075314226062277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127314261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84380436,0.001002448,0.15273446,0.00045865963,0.0003169811,0.00035425244,0.00006181155,0.00001801208,0.0012490202],"genre_scores_gemma":[0.9865897,0.000016351234,0.011986449,0.0006077554,0.00041978838,0.000021701355,0.00008811628,0.000008637912,0.00026147597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9990127,0.00007402497,0.00029355055,0.000089970585,0.00020337131,0.0003263647],"domain_scores_gemma":[0.99921376,0.00005554355,0.00010402649,0.00040568638,0.00009865726,0.00012231276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004766456,0.0001350311,0.00015993239,0.00003132702,0.0001388506,0.0000117619975,0.00021635629,0.00016168132,0.00005675756],"category_scores_gemma":[0.00011552885,0.00008943795,0.00017336062,0.00018298786,0.00011599277,0.0000055191313,0.00006135471,0.00008699689,0.00001444224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027432558,0.00027776006,0.012558034,0.000075283344,0.00038822542,2.3064341e-7,0.0003144593,0.64866215,0.014760057,0.17618968,0.14568907,0.00081072276],"study_design_scores_gemma":[0.002970143,0.0017243003,0.6430773,0.00022595726,0.0008732675,0.00013636984,0.0022489794,0.059787378,0.15454037,0.002624559,0.12938923,0.0024021512],"about_ca_topic_score_codex":0.0000010594774,"about_ca_topic_score_gemma":0.0000079840665,"teacher_disagreement_score":0.6305193,"about_ca_system_score_codex":0.000017967714,"about_ca_system_score_gemma":0.00004986085,"threshold_uncertainty_score":0.36471736},"labels":[],"label_agreement":null},{"id":"W2127325366","doi":"10.1186/1471-2105-4-65","title":"Statistical extraction of Drosophila cis-regulatory modules using exhaustive assessment of local word frequency","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; York University","keywords":"Genome; DNA microarray; Coding (social sciences); Computational biology; Gene; Locus (genetics); Biology; Coding region; Regulatory sequence; Cis-regulatory module; Genetics; Computer science; Regulation of gene expression; Gene expression; Statistics; Mathematics; Enhancer","score_opus":0.01464972971313742,"score_gpt":0.28023106684270627,"score_spread":0.26558133712956883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127325366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48952568,0.000045783643,0.50936544,9.499715e-7,0.00007028602,0.00009119197,0.000060609374,0.000002835743,0.0008372347],"genre_scores_gemma":[0.6399721,0.000021067146,0.35989255,0.000008143287,0.000014602302,0.0000022594493,0.00006927741,0.0000098724695,0.00001012855],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891543,0.000030844414,0.0005701833,0.00012118235,0.00018789075,0.00017448027],"domain_scores_gemma":[0.999117,0.000021406751,0.00035561583,0.0003060493,0.00013688559,0.00006302699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021719669,0.00014657243,0.00021024278,0.000054296816,0.000043460557,0.00001002652,0.00010996793,0.00015980449,0.000019651108],"category_scores_gemma":[0.000037173366,0.00014455551,0.00007666244,0.00007355887,0.00018678524,0.000009736208,0.000043711774,0.00007919884,0.0000011432131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012666553,0.0008414956,0.04414722,0.0021886325,0.00039392975,0.000004148707,0.00043203952,0.13494956,0.6953043,0.11472853,0.0002921564,0.0065913456],"study_design_scores_gemma":[0.0013857516,0.00058408844,0.0733507,0.00010628524,0.0001423754,0.000075400225,0.0024189134,0.8279811,0.08957,0.0036155125,0.00018729057,0.0005825498],"about_ca_topic_score_codex":0.00001038388,"about_ca_topic_score_gemma":0.000011095545,"teacher_disagreement_score":0.69303155,"about_ca_system_score_codex":0.000045744026,"about_ca_system_score_gemma":0.0002446141,"threshold_uncertainty_score":0.5894802},"labels":[],"label_agreement":null},{"id":"W2128104809","doi":"10.1186/1471-2105-11-s1-s64","title":"Predicting protein functions by relaxation labelling protein interaction network","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Labelling; Computational biology; Protein–protein interaction; DNA microarray; Computer science; Relaxation (psychology); Biology; Bioinformatics; Genetics; Neuroscience; Biochemistry; Gene expression; Gene","score_opus":0.008306784005993129,"score_gpt":0.21799601741548452,"score_spread":0.2096892334094914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128104809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5924437,0.00009060253,0.39808872,0.00008207962,0.00085577363,0.0010560959,0.000044725366,0.00008968728,0.0072486117],"genre_scores_gemma":[0.7908924,0.000024374953,0.20095058,0.00030205396,0.0016586436,0.00022685672,0.0014744577,0.00006570834,0.004404903],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986349,0.000026071892,0.00061107427,0.00017341212,0.00017321495,0.00038136833],"domain_scores_gemma":[0.99890876,0.00001487996,0.00042417605,0.0004229967,0.00011124026,0.00011796777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004683946,0.00021747878,0.00014542876,0.00004396937,0.00030543926,0.00012187338,0.00019810651,0.0003468165,0.000037391266],"category_scores_gemma":[0.0001144339,0.0002070225,0.00009298267,0.00015563627,0.0000624944,0.000042233525,0.00011443881,0.00044710844,0.00008855271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006370612,0.00044356115,0.016868467,0.0011174703,0.00037033166,0.0000012811776,0.0014645944,0.035571065,0.7272601,0.0038844154,0.12948763,0.082894],"study_design_scores_gemma":[0.0012362441,0.00046872694,0.00030857467,0.00017164391,0.00005421463,0.000044783377,0.0007777786,0.7574846,0.023600686,0.00059882365,0.21442237,0.00083151815],"about_ca_topic_score_codex":0.000013685854,"about_ca_topic_score_gemma":0.00014516783,"teacher_disagreement_score":0.7219136,"about_ca_system_score_codex":0.000018974379,"about_ca_system_score_gemma":0.000088206834,"threshold_uncertainty_score":0.8442133},"labels":[],"label_agreement":null},{"id":"W2128374023","doi":"10.1186/1471-2105-5-40","title":"Pegasys: software for executing and integrating analyses of biological sequences","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Computer science; Workflow; Database; Software; File format; Interface (matter); SQL; Disk formatting; Software framework; Sequence diagram; Source code; Programming language; Data mining; Software system; Operating system; Component-based software engineering; Unified Modeling Language","score_opus":0.06584168856376765,"score_gpt":0.31367912502923484,"score_spread":0.2478374364654672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128374023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83843654,0.0012385253,0.15983889,0.000015444286,0.000047358288,0.0001760936,0.000049168586,0.0000044515914,0.00019352064],"genre_scores_gemma":[0.6152856,0.00016856224,0.3844197,0.000044420616,0.000037440182,0.000009478865,0.000024489105,0.000004178404,0.0000061588526],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994102,0.000008092385,0.00028613737,0.00010471915,0.000047374044,0.000143442],"domain_scores_gemma":[0.9995699,0.00003864111,0.00014355034,0.00011468493,0.000100801764,0.00003242085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001362665,0.00010755214,0.0001551099,0.00002707162,0.0000835618,0.00001533096,0.000092944196,0.00008065823,5.9472023e-7],"category_scores_gemma":[0.0003710982,0.00007888656,0.000062812476,0.00005652541,0.000117521085,0.0000014002395,0.00008835747,0.000027694537,3.6726613e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015652977,0.00010241051,0.07621231,0.0011069317,0.00037908435,6.1258123e-7,0.0024624593,0.0064621195,0.890408,0.0032315876,0.00017929035,0.019298716],"study_design_scores_gemma":[0.003879782,0.0034891572,0.022181708,0.00035558685,0.0002159122,0.00008368622,0.018224545,0.010008338,0.9288488,0.007673976,0.0037732387,0.001265241],"about_ca_topic_score_codex":0.000016602298,"about_ca_topic_score_gemma":0.000022472459,"teacher_disagreement_score":0.22458082,"about_ca_system_score_codex":0.0000054140864,"about_ca_system_score_gemma":0.000061020168,"threshold_uncertainty_score":0.32169002},"labels":[],"label_agreement":null},{"id":"W2129978006","doi":"10.1186/1471-2105-9-329","title":"Evaluation of genomic island predictors using a comparative genomics approach","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":284,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Genome Canada; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Genome; Identification (biology); Comparative genomics; Genomics; Computational biology; Precision and recall; Computer science; Sequence (biology); Data mining; Biology; Genetics; Artificial intelligence; Gene; Ecology","score_opus":0.10055274526987305,"score_gpt":0.2917008819532804,"score_spread":0.19114813668340735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129978006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89628476,0.0004488592,0.0993044,8.383773e-7,0.000059016846,0.00048224014,0.000046887213,0.0000068131585,0.0033661807],"genre_scores_gemma":[0.8089316,0.00007856076,0.19048314,0.000013157276,0.00010148844,0.000014608124,0.00030493023,0.000015033303,0.000057477548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998863,0.000067457746,0.00038274433,0.00012755951,0.0003822313,0.00017700411],"domain_scores_gemma":[0.99914193,0.00000604198,0.00023616946,0.00029351327,0.00027088023,0.000051481267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056251086,0.00014279541,0.00018553829,0.00007335793,0.000077574034,0.000009155508,0.00016052536,0.00010603372,0.0000151321065],"category_scores_gemma":[0.0000283122,0.00013591898,0.00007826338,0.00008275979,0.00011397254,0.000008922517,0.000089267516,0.000051528306,0.000010426092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023485244,0.00067627954,0.053456314,0.0006661546,0.0012899151,8.285951e-7,0.02007513,0.51341707,0.40460765,0.0000558897,0.0031247716,0.0023951153],"study_design_scores_gemma":[0.0012608216,0.00013403552,0.0083569195,0.000005453959,0.00015531763,0.00004250646,0.0008964478,0.9764179,0.011675484,0.000016301869,0.00083297637,0.00020580892],"about_ca_topic_score_codex":0.000008225478,"about_ca_topic_score_gemma":0.000010919612,"teacher_disagreement_score":0.46300083,"about_ca_system_score_codex":0.000068660214,"about_ca_system_score_gemma":0.00036525997,"threshold_uncertainty_score":0.5542615},"labels":[],"label_agreement":null},{"id":"W2130138427","doi":"10.1186/s12859-015-0791-x","title":"The Gap Procedure: for the identification of phylogenetic clusters in HIV-1 sequence data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Centre Hospitalier de l’Université de Montréal; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Phylogenetic tree; Computational biology; Identification (biology); Sequence (biology); Human immunodeficiency virus (HIV); Biology; DNA microarray; Evolutionary biology; Genetics; Virology; Gene","score_opus":0.13240220328288554,"score_gpt":0.3364065460040913,"score_spread":0.20400434272120577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130138427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27992734,0.0605393,0.5954594,0.015809484,0.0043307925,0.026055865,0.01228961,0.0002703527,0.0053178193],"genre_scores_gemma":[0.98822755,0.00047435652,0.007367326,0.00008847859,0.000023590455,0.00025799673,0.0017475601,0.000012369138,0.001800754],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992629,0.0000485501,0.00036344051,0.000075752796,0.00004981846,0.00019950447],"domain_scores_gemma":[0.9988084,0.00035947902,0.00014644163,0.0005916621,0.00007888382,0.000015128955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088412716,0.000065987995,0.00008265733,0.00003121865,0.00011640517,0.00002217836,0.0005851048,0.000055425862,0.0000029570106],"category_scores_gemma":[0.000546893,0.00003366893,0.000021654127,0.00010198969,0.00022242925,0.00009082548,0.0001310842,0.00007453382,0.00017874216],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004266753,0.0014707439,0.13418987,0.0030313106,0.001918444,0.0000039483584,0.036790065,0.008266171,0.03658323,0.01189106,0.47618258,0.2854058],"study_design_scores_gemma":[0.015168131,0.0011383086,0.033124626,0.00019312128,0.00031733591,0.0001568145,0.030470831,0.64437795,0.025472585,0.0016093515,0.24724936,0.000721605],"about_ca_topic_score_codex":0.000015189309,"about_ca_topic_score_gemma":0.0001582097,"teacher_disagreement_score":0.70830023,"about_ca_system_score_codex":0.000031440086,"about_ca_system_score_gemma":0.00023717615,"threshold_uncertainty_score":0.22974284},"labels":[],"label_agreement":null},{"id":"W2130948145","doi":"10.1186/1471-2105-7-448","title":"Gene function classification using Bayesian models with hierarchy-based priors","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Public Health","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prior probability; Bayesian probability; Hierarchy; DNA microarray; Computational biology; Computer science; Function (biology); Artificial intelligence; Data mining; Biology; Gene; Genetics; Gene expression","score_opus":0.027646690329334797,"score_gpt":0.24136193798693564,"score_spread":0.21371524765760086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130948145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07826648,0.000077427714,0.9187909,0.000039846964,0.00007927947,0.00022944437,0.0000101621,0.000033388555,0.0024730898],"genre_scores_gemma":[0.79755694,0.000009205139,0.20138718,0.00017624076,0.00013889595,0.000028074419,0.00045566095,0.000022000704,0.00022579153],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990706,0.000029603061,0.00030748546,0.00018914099,0.0002088621,0.00019432808],"domain_scores_gemma":[0.9992002,0.0000048321176,0.00021128397,0.0004049292,0.000116716124,0.000061984174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011408871,0.00015481339,0.00009761838,0.000099510136,0.0001286742,0.00005191453,0.000119817596,0.00014525752,0.00000824371],"category_scores_gemma":[0.000006468239,0.00013023728,0.00005412834,0.00018368821,0.00005991535,0.000021344773,0.000021049043,0.00006302988,0.000006326884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072372355,0.0003010033,0.008296558,0.00024141703,0.000043337186,5.5332873e-7,0.00010933429,0.36267576,0.61397976,0.002982213,0.003906217,0.006740147],"study_design_scores_gemma":[0.0008141641,0.00018887132,0.0030994385,0.00002365122,0.00003399805,0.0000066058287,0.00014296855,0.9235716,0.06717585,0.00026298163,0.004420968,0.00025891422],"about_ca_topic_score_codex":0.000012321367,"about_ca_topic_score_gemma":0.00002291888,"teacher_disagreement_score":0.7192905,"about_ca_system_score_codex":0.000040985895,"about_ca_system_score_gemma":0.00024860245,"threshold_uncertainty_score":0.5310922},"labels":[],"label_agreement":null},{"id":"W2131414388","doi":"10.1186/1471-2105-10-s1-s5","title":"ComPhy: prokaryotic composite distance phylogenies inferred from whole-genome gene sets","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Missouri; University of Maryland, Baltimore County; National Science Foundation","keywords":"Genome; Phylogenetic tree; Biology; Phylogenetics; Computational biology; Gene; Distance matrices in phylogeny; Bacterial genome size; Distance matrix; Genetics; Evolutionary biology; Bioinformatics; Computer science; Algorithm","score_opus":0.013734137712329139,"score_gpt":0.2341514672249999,"score_spread":0.22041732951267076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131414388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80870694,0.0026034352,0.1823835,0.00020552574,0.00032645446,0.0010232734,0.0010568793,0.0001206058,0.0035733723],"genre_scores_gemma":[0.77461416,0.000150442,0.21845339,0.00073121046,0.00028828546,0.000020764222,0.0053244,0.000035103745,0.00038222005],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99857175,0.000032279077,0.00048054184,0.00025348127,0.0002570348,0.00040492436],"domain_scores_gemma":[0.9989442,0.000011905421,0.00019911237,0.000611519,0.000092441864,0.00014080427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011009567,0.00029975662,0.00027335063,0.00006571109,0.0001262248,0.000094815674,0.00039259443,0.0001599057,0.000016033036],"category_scores_gemma":[0.000019589008,0.0002876834,0.0001313783,0.00014021934,0.00008885885,0.000018021059,0.00012437256,0.00010861108,0.00016340277],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002777004,0.00044887612,0.01960936,0.00023772828,0.00036078956,0.00001209158,0.0015140944,0.005073528,0.9565291,0.00011611006,0.0021118778,0.013708744],"study_design_scores_gemma":[0.008612321,0.0023358886,0.5349775,0.00016692869,0.00039053799,0.00010324371,0.0010430121,0.13865201,0.10761555,0.0018632876,0.20040387,0.0038358471],"about_ca_topic_score_codex":0.000006532988,"about_ca_topic_score_gemma":0.000016813421,"teacher_disagreement_score":0.84891355,"about_ca_system_score_codex":0.00003522571,"about_ca_system_score_gemma":0.000068972564,"threshold_uncertainty_score":0.9999575},"labels":[],"label_agreement":null},{"id":"W2131619859","doi":"10.1186/1471-2105-7-29","title":"Recrafting the neighbor-joining method","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Phylogenetic tree; Implementation; Construct (python library); k-nearest neighbors algorithm; Algorithm; Running time; Data mining; Theoretical computer science; Artificial intelligence; Biology","score_opus":0.015895730640615214,"score_gpt":0.2535508975119469,"score_spread":0.2376551668713317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131619859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2598333,0.003012619,0.62658143,0.0005362432,0.0006821942,0.0006281301,0.00005070307,0.000031704618,0.10864369],"genre_scores_gemma":[0.32485107,0.00013174888,0.6717126,0.0010276617,0.00078232225,0.000032451844,0.000066673216,0.000032418367,0.0013630706],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992318,0.00003312154,0.00029634597,0.000112325826,0.00009673926,0.00022965325],"domain_scores_gemma":[0.9994381,0.000046086097,0.00012443097,0.00031159024,0.00005329408,0.000026476006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034867733,0.0001313381,0.00010865533,0.000020474556,0.00020060124,0.00004563165,0.00019447497,0.000077235,0.0000054956354],"category_scores_gemma":[0.00006144223,0.00009012804,0.00008604056,0.000076979486,0.000047503727,0.0000010630508,0.00015470189,0.00006560694,0.000018133143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025798738,0.00028616795,0.16400924,0.00062078447,0.00069643086,0.0000046737255,0.0039529433,0.061699353,0.46299765,0.025918402,0.13293745,0.14661893],"study_design_scores_gemma":[0.0015753183,0.00037026347,0.050805297,0.00004259234,0.00013512996,0.000105982974,0.0030111668,0.14807723,0.06650617,0.0025912465,0.72567624,0.0011033716],"about_ca_topic_score_codex":0.000028535205,"about_ca_topic_score_gemma":0.000054221447,"teacher_disagreement_score":0.5927388,"about_ca_system_score_codex":0.000006824067,"about_ca_system_score_gemma":0.00004563341,"threshold_uncertainty_score":0.36753148},"labels":[],"label_agreement":null},{"id":"W2132548846","doi":"10.1186/1471-2105-13-31","title":"PANDAseq: paired-end assembler for illumina sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":2221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Amplicon; Computer science; Sequence (biology); Error detection and correction; k-mer; Amplicon sequencing; Sequence assembly; Computational biology; DNA sequencing; Biology; Genetics; Algorithm; DNA; 16S ribosomal RNA; Polymerase chain reaction; Gene","score_opus":0.039292586530235186,"score_gpt":0.2637107171785696,"score_spread":0.2244181306483344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132548846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9446518,0.00003598182,0.020571077,0.00013397358,0.00059385103,0.00054202636,0.000059604885,0.00008571318,0.03332596],"genre_scores_gemma":[0.8885947,0.000014929323,0.109369636,0.0010105318,0.00008647506,0.000034765533,0.00011197794,0.000009893317,0.0007671366],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992252,0.000055086715,0.00022186029,0.000057413312,0.000068482295,0.00037194727],"domain_scores_gemma":[0.99935526,0.0002170951,0.000100800804,0.00023098082,0.0000066827315,0.00008917871],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00045216247,0.000108853186,0.00013330166,0.000019263125,0.0002547201,0.000012927355,0.00024254815,0.00011990677,0.0027686353],"category_scores_gemma":[0.00006869195,0.00009035718,0.000061728424,0.00008238534,0.00023226943,0.00043777146,0.00015922882,0.00008162004,0.0010453566],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021642275,0.0007774482,0.5860749,0.0005997251,0.00010147432,7.375145e-7,0.021982763,0.0020418502,0.016373828,0.0047732084,0.3408138,0.026243884],"study_design_scores_gemma":[0.0017124119,0.0007426052,0.2585676,0.00004065657,0.00009889065,0.00007507234,0.0042137257,0.07457469,0.0052126893,0.004660578,0.64876354,0.0013375208],"about_ca_topic_score_codex":0.00004740276,"about_ca_topic_score_gemma":0.00028787705,"teacher_disagreement_score":0.32750726,"about_ca_system_score_codex":0.000056276105,"about_ca_system_score_gemma":0.000016213186,"threshold_uncertainty_score":0.99973243},"labels":[],"label_agreement":null},{"id":"W2132626965","doi":"10.1186/s12859-015-0720-z","title":"PROKARYO: an illustrative and interactive computational model of the lactose operon in the bacterium Escherichia coli","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Operon; Computational biology; Computer science; Biological system; Biology; Escherichia coli; Gene; Genetics","score_opus":0.031199008765802526,"score_gpt":0.2582938359164607,"score_spread":0.22709482715065818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132626965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926755,0.000023632068,0.0063164295,0.00018468623,0.00006914034,0.00030076358,0.000046332705,0.000003541068,0.0003799675],"genre_scores_gemma":[0.9703038,0.000012051753,0.029291825,0.00026314927,0.000023871631,0.000011064671,0.00005536135,0.0000058424494,0.000033041968],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993872,0.00006314663,0.00023642743,0.000096197655,0.00010118215,0.000115829505],"domain_scores_gemma":[0.99950814,0.000011218877,0.00013217355,0.00022125978,0.00009279838,0.000034429853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020563015,0.00010452416,0.000103292405,0.00002259219,0.00003352495,0.000028569804,0.00025052202,0.00014479413,9.998016e-7],"category_scores_gemma":[0.00005297055,0.00006091234,0.000026676453,0.00008136018,0.00018528244,0.000013753038,0.0001532429,0.00011219071,7.8351627e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020648795,0.0014274856,0.018880803,0.00043053352,0.00022667798,0.0000016424226,0.040411483,0.11648917,0.7994555,0.00678611,0.0025989988,0.011226663],"study_design_scores_gemma":[0.0015494426,0.0010745203,0.01788743,0.000031773045,0.000027006326,0.000021730752,0.007390656,0.91360176,0.05571942,0.0008836778,0.0015034742,0.00030911068],"about_ca_topic_score_codex":0.000011572643,"about_ca_topic_score_gemma":0.00010480058,"teacher_disagreement_score":0.7971126,"about_ca_system_score_codex":0.000009356184,"about_ca_system_score_gemma":0.00016812167,"threshold_uncertainty_score":0.24839331},"labels":[],"label_agreement":null},{"id":"W2133103440","doi":"10.1186/1471-2105-13-s19-s15","title":"Gene trees and species trees: irreconcilable differences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Gene duplication; Biology; Tree (set theory); Gene; Inference; Phylogenetic tree; Tree rearrangement; Extant taxon; Function (biology); Phylogenomics; Phylogenetics; Evolutionary biology; Set (abstract data type); Computational biology; Genetics; Computer science; Mathematics; Combinatorics; Artificial intelligence","score_opus":0.023805937387694338,"score_gpt":0.2215970825356099,"score_spread":0.19779114514791554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133103440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9019874,0.0048068874,0.056980174,0.0000825102,0.00081225904,0.00044891244,0.000116060975,0.00005725237,0.03470859],"genre_scores_gemma":[0.91859394,0.0011551286,0.075103834,0.00049530435,0.000727982,0.000019538851,0.00019068763,0.000024445368,0.0036891268],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988954,0.000017419323,0.00040147267,0.00010772254,0.00013273861,0.0004452291],"domain_scores_gemma":[0.9992756,0.000019088939,0.00015679156,0.00032035436,0.000039167076,0.00018899875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025634427,0.00021716587,0.00020671135,0.00004845393,0.0001331518,0.00008272864,0.00018143558,0.0001845694,0.000050814884],"category_scores_gemma":[0.00003530232,0.00017546877,0.00007491692,0.00007083637,0.00013767145,0.00003150782,0.00017187512,0.0000889283,0.00005497686],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032326122,0.0006411273,0.70172375,0.0011439822,0.0007917133,0.0000017799111,0.011517157,0.0006483428,0.031520348,0.008582461,0.11890153,0.12420456],"study_design_scores_gemma":[0.004502582,0.0013102817,0.40488213,0.00015225005,0.00028018735,0.00035213868,0.010731357,0.12148389,0.03501777,0.0008497294,0.4171484,0.0032892632],"about_ca_topic_score_codex":0.000004952951,"about_ca_topic_score_gemma":0.000059161117,"teacher_disagreement_score":0.2982469,"about_ca_system_score_codex":0.00001220712,"about_ca_system_score_gemma":0.000047452842,"threshold_uncertainty_score":0.7155408},"labels":[],"label_agreement":null},{"id":"W2133554582","doi":"10.1186/1471-2105-13-326","title":"A computational pipeline for the development of multi-marker bio-signature panels and ensemble classifiers","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Institute of Infection and Immunity; St. Paul's Hospital; Simon Fraser University; University of British Columbia; Prevention of Organ Failure","funders":"Astellas Pharma; Genome British Columbia; St. Paul's Foundation; Novartis Pharma; Genome Canada","keywords":"Pipeline (software); Computer science; Ensemble learning; Artificial intelligence; Machine learning; Random subspace method; Biomarker discovery; DNA microarray; Biomarker; Data mining; Big data; Receiver operating characteristic; Pattern recognition (psychology); Support vector machine; Proteomics; Biology; Gene","score_opus":0.04168584868854552,"score_gpt":0.2975414227229967,"score_spread":0.2558555740344512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133554582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003764235,0.00013221959,0.9951841,0.000045003602,0.000015663178,0.00026895662,0.00005525063,0.000035093995,0.000499428],"genre_scores_gemma":[0.11628142,0.000013700429,0.8832306,0.000051245,0.000024802523,0.000109778084,0.00006564082,0.000008557554,0.00021421516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993756,0.0000021305536,0.0003292778,0.00005283843,0.00008865293,0.00015151368],"domain_scores_gemma":[0.9993646,0.00020568859,0.00017489026,0.0001365516,0.000070115995,0.000048163765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001659798,0.00009307176,0.000096753014,0.00001984544,0.00013783154,0.0000118330645,0.000102886326,0.000088771485,0.000014340838],"category_scores_gemma":[0.000038964325,0.00006530493,0.000034849916,0.00005204252,0.0000592266,0.00009304008,0.000050933468,0.00008701538,0.0000026059288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005076181,0.0013785783,0.023267904,0.008559163,0.00051857956,1.667881e-7,0.039138693,0.01406033,0.059389714,0.058486585,0.013578021,0.78111464],"study_design_scores_gemma":[0.00059915986,0.000005033359,0.0006685424,0.000045247943,0.000029902778,0.0000049381442,0.0014336242,0.90521175,0.062180225,0.0008114743,0.028817102,0.00019303053],"about_ca_topic_score_codex":4.359994e-7,"about_ca_topic_score_gemma":0.000001194008,"teacher_disagreement_score":0.89115137,"about_ca_system_score_codex":0.000021158046,"about_ca_system_score_gemma":0.000051455096,"threshold_uncertainty_score":0.26630577},"labels":[],"label_agreement":null},{"id":"W2134425468","doi":"10.1186/1471-2105-13-s10-s9","title":"Gene order in rosid phylogeny, inferred from pairwise syntenies among extant genomes","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extant taxon; Phylogenetics; Biology; Evolutionary biology; Genome; Pairwise comparison; DNA microarray; Computational biology; Gene; Genetics; Computer science; Gene expression; Artificial intelligence","score_opus":0.016163955662212754,"score_gpt":0.22764341752703593,"score_spread":0.21147946186482316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134425468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808698,0.0032941857,0.013958527,0.00001584549,0.00028641525,0.00040146074,0.000095171556,0.000031810858,0.0010467779],"genre_scores_gemma":[0.89108264,0.0005350047,0.10692526,0.00014497277,0.0003373369,0.000057669702,0.0005729714,0.000040022656,0.000304115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985257,0.00004251947,0.00049894146,0.00017491679,0.0002077532,0.0005501666],"domain_scores_gemma":[0.99908614,0.000020794954,0.00016464911,0.0004966773,0.0000762017,0.00015553024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026496281,0.00026276257,0.00024152716,0.00010930011,0.00005870976,0.0000485501,0.00026867975,0.00021584895,0.00006294993],"category_scores_gemma":[0.0000917441,0.00024062798,0.00009484306,0.00018847326,0.00009765255,0.00003127438,0.00024533647,0.00010922621,0.00010880984],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007581915,0.00029109456,0.8717564,0.00015111393,0.00017995441,0.00000278155,0.0025641362,0.0007102893,0.113889694,0.000024591824,0.0010083985,0.00934572],"study_design_scores_gemma":[0.0030719105,0.0002901339,0.84237957,0.000063406296,0.000102708356,0.000022188531,0.003302441,0.028903602,0.09986559,0.00011246847,0.020354358,0.0015315943],"about_ca_topic_score_codex":0.0000564332,"about_ca_topic_score_gemma":0.00014276452,"teacher_disagreement_score":0.09296673,"about_ca_system_score_codex":0.000039495993,"about_ca_system_score_gemma":0.00007281918,"threshold_uncertainty_score":0.98125243},"labels":[],"label_agreement":null},{"id":"W2134591904","doi":"10.1186/1471-2105-5-170","title":"PhyME: A probabilistic algorithm for finding motifs in sets of orthologous sequences","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":204,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Human Genome Research Institute; W. M. Keck Foundation; National Institutes of Health; National Science Foundation","keywords":"Probabilistic logic; Phylogenetic tree; Motif (music); Expectation–maximization algorithm; Computer science; Computational biology; Biology; Data mining; Algorithm; Gene; Genetics; Artificial intelligence; Maximum likelihood; Mathematics","score_opus":0.0151012122346998,"score_gpt":0.2562718729200442,"score_spread":0.24117066068534443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134591904","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78213876,0.00011670861,0.21661521,0.000024266954,0.00010713932,0.00052532816,0.00015218515,0.000009770303,0.00031060257],"genre_scores_gemma":[0.45337433,0.0000401214,0.5462078,0.000057356956,0.000028804148,0.00003807752,0.00020567313,0.000014205203,0.00003364772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913716,0.000009042445,0.00042178194,0.00012554487,0.00008396082,0.00022248513],"domain_scores_gemma":[0.9994767,0.000016887032,0.00018419912,0.00022039127,0.00006283669,0.000038989925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016014448,0.0001293745,0.00016991828,0.000060438288,0.000038003865,0.000016087639,0.00018032118,0.00013743638,0.000001574037],"category_scores_gemma":[0.00009505766,0.00012075783,0.00008050939,0.00009500909,0.00008045487,0.0000062039994,0.00006723018,0.00005126831,0.000002410886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030813046,0.0016903684,0.019659303,0.0077509354,0.00039256577,0.000020367153,0.011641462,0.64606863,0.10726982,0.012169156,0.00048259817,0.19254665],"study_design_scores_gemma":[0.0042088763,0.001204541,0.0044758283,0.00021147149,0.000055839424,0.00010974481,0.0023261977,0.94195443,0.035754472,0.008425359,0.0004977447,0.0007754979],"about_ca_topic_score_codex":0.0000122436895,"about_ca_topic_score_gemma":0.00010552806,"teacher_disagreement_score":0.3295926,"about_ca_system_score_codex":0.000034124605,"about_ca_system_score_gemma":0.00019744372,"threshold_uncertainty_score":0.49243614},"labels":[],"label_agreement":null},{"id":"W2135398177","doi":"10.1186/1471-2105-14-s15-s5","title":"Gene tree correction guided by orthology","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Tree (set theory); Synteny; Ensembl; Set (abstract data type); Gene; Clade; Biology; Phylogenetic tree; Computer science; Computational biology; Mathematics; Genetics; Combinatorics; Genomics; Genome; Programming language","score_opus":0.012322689451228852,"score_gpt":0.22914997419534575,"score_spread":0.2168272847441169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135398177","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6785019,0.0006110576,0.28767163,0.00021549537,0.0016401085,0.0011671323,0.000040813142,0.000114551876,0.030037338],"genre_scores_gemma":[0.31604248,0.00093610166,0.6230793,0.0028750096,0.0010662797,0.00045154395,0.0041179787,0.00016065907,0.05127064],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914354,0.000023384213,0.0003150436,0.00013755212,0.00011763326,0.00026282397],"domain_scores_gemma":[0.99935865,0.0000072436237,0.00011865662,0.00033742937,0.00009619171,0.00008182051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110102905,0.00014742241,0.00012095073,0.00004686024,0.000061186176,0.00003912703,0.00016873586,0.00016494645,0.00012581052],"category_scores_gemma":[0.00005592528,0.00013534114,0.00006851213,0.00008428608,0.00005297369,0.000010899824,0.00009309748,0.00006152007,0.0005625338],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016569415,0.0000966537,0.01021359,0.000068259724,0.00008398179,5.68235e-7,0.00020808594,0.00023687365,0.20453298,0.000012285886,0.73396605,0.05056411],"study_design_scores_gemma":[0.003988043,0.0013537419,0.024865717,0.000024491212,0.00011205054,0.00034496107,0.0014382392,0.15870397,0.44020066,0.00016994399,0.3671286,0.0016695759],"about_ca_topic_score_codex":0.000024878542,"about_ca_topic_score_gemma":0.000019726987,"teacher_disagreement_score":0.3668374,"about_ca_system_score_codex":0.000016824717,"about_ca_system_score_gemma":0.000039834198,"threshold_uncertainty_score":0.72304213},"labels":[],"label_agreement":null},{"id":"W2135526239","doi":"10.1186/1471-2105-8-262","title":"False positive reduction in protein-protein interaction predictions using gene ontology annotations","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Ranking (information retrieval); Gene ontology; Computer science; Protein–protein interaction; Data mining; Set (abstract data type); Measure (data warehouse); Reduction (mathematics); Protein function prediction; Function (biology); Ontology; Computational biology; Machine learning; Protein function; Artificial intelligence; Gene; Bioinformatics; Biology; Mathematics; Genetics; Gene expression","score_opus":0.017851863187489957,"score_gpt":0.27350107672319923,"score_spread":0.2556492135357093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135526239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48071495,0.00006757528,0.5164888,0.00003467683,0.00023086142,0.0005826289,0.000028821316,0.000019672312,0.0018320337],"genre_scores_gemma":[0.8080485,0.000013973999,0.19106808,0.000086721775,0.0002673683,0.000032636268,0.00030883934,0.000019987976,0.00015393457],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985577,0.000036126952,0.0007157087,0.00016564845,0.00015749199,0.00036731522],"domain_scores_gemma":[0.99916506,0.000011723797,0.00029182446,0.00029060766,0.00014637005,0.00009440726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005000693,0.00018859729,0.00016126932,0.0002069567,0.00015328465,0.00004247435,0.00012963123,0.00028186626,0.000007295019],"category_scores_gemma":[0.00006706566,0.00019587376,0.00008145364,0.00024215475,0.00008540553,0.000044205684,0.00007870226,0.00021294657,0.000014035489],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096249976,0.0005134038,0.0017975701,0.00032703244,0.00022309418,0.00000858404,0.0037472728,0.051969226,0.91342634,0.0036994333,0.00076116563,0.0225644],"study_design_scores_gemma":[0.0031674958,0.0008981542,0.0071746367,0.00035408844,0.00009538844,0.0006877112,0.006890012,0.7045006,0.26941475,0.0013829791,0.0041675935,0.0012665596],"about_ca_topic_score_codex":0.000059504535,"about_ca_topic_score_gemma":0.0004940363,"teacher_disagreement_score":0.6525314,"about_ca_system_score_codex":0.000112214846,"about_ca_system_score_gemma":0.00015011089,"threshold_uncertainty_score":0.79875},"labels":[],"label_agreement":null},{"id":"W2135842485","doi":"10.1186/1471-2105-9-507","title":"MetaboMiner – semi-automated identification of metabolites from 2D NMR spectra of complex biofluids","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":199,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Genome Alberta; Ministry of Advanced Education, Government of Alberta","keywords":"Metabolomics; Heteronuclear single quantum coherence spectroscopy; NMR spectra database; Proton NMR; Two-dimensional nuclear magnetic resonance spectroscopy; Nuclear magnetic resonance spectroscopy; Chemistry; Heteronuclear molecule; Nuclear magnetic resonance; Spectral line; Biological system; Analytical Chemistry (journal); Chromatography; Stereochemistry; Biology; Physics","score_opus":0.025207410916275246,"score_gpt":0.2568409985779328,"score_spread":0.23163358766165756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135842485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9662277,0.0031553595,0.028112663,0.00002057181,0.00015285339,0.00025229133,0.00058966776,0.000045637025,0.0014432251],"genre_scores_gemma":[0.9277614,0.0019699738,0.06925501,0.000049763676,0.00009262316,0.000009748315,0.00062152045,0.000019003668,0.0002209833],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835634,0.00003910363,0.0009651676,0.00018204446,0.00024016756,0.00021719404],"domain_scores_gemma":[0.9985934,0.00003490955,0.00054065074,0.00054395397,0.00022813515,0.000058957376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022462793,0.000207329,0.00048048623,0.00014405858,0.000070452064,0.000010630164,0.00027561712,0.00012832232,0.000051515653],"category_scores_gemma":[0.0001891357,0.00017907219,0.00019113554,0.00029104808,0.00022930492,0.000014425144,0.00013669232,0.00005722701,0.000013095698],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004266656,0.000093986935,0.0058013387,0.00009174928,0.0002585323,2.5865506e-7,0.00022570134,0.00010433308,0.98917603,0.00063669373,0.0034322655,0.00013644788],"study_design_scores_gemma":[0.00071260525,0.0000958947,0.060101777,0.000008669302,0.00014186432,0.000008354389,0.00033894816,0.022337653,0.9088959,0.00010142528,0.0070165712,0.0002403574],"about_ca_topic_score_codex":0.00004926149,"about_ca_topic_score_gemma":0.000014618309,"teacher_disagreement_score":0.08028015,"about_ca_system_score_codex":0.0000075453027,"about_ca_system_score_gemma":0.00007451668,"threshold_uncertainty_score":0.7302352},"labels":[],"label_agreement":null},{"id":"W2136671508","doi":"10.1186/1471-2105-11-507","title":"Proteome scanning to predict PDZ domain interactions using support vector machines","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Hippo pathway signaling and YAP/TAZ","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"PDZ domain; Computational biology; Proteome; Protein–protein interaction; Support vector machine; DNA microarray; Domain (mathematical analysis); Computer science; Protein Array Analysis; Biology; Human proteome project; Proteomics; Bioinformatics; Artificial intelligence; Genetics; Gene; Gene expression; Mathematics","score_opus":0.017073109368465934,"score_gpt":0.27795528179319323,"score_spread":0.2608821724247273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136671508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8983578,0.00000878379,0.098458074,0.000053232445,0.0005906958,0.0003453025,0.00007777536,0.00004650223,0.0020618069],"genre_scores_gemma":[0.6416087,0.0000015780026,0.35658336,0.00031750518,0.0006078146,0.00004173705,0.00017817899,0.000035040375,0.0006260507],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998976,0.000021269012,0.00036900706,0.00016992608,0.0001597401,0.00030407598],"domain_scores_gemma":[0.9992014,0.0000128944985,0.000118945674,0.00038752294,0.00009228163,0.00018691164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002801463,0.00018453388,0.00014734083,0.00010272581,0.00017237297,0.000075783864,0.00021950793,0.00013849529,0.00008097514],"category_scores_gemma":[0.0001568957,0.00016643835,0.000097457334,0.00013627636,0.000050447572,0.000016639522,0.00012631396,0.00021421214,0.00010459383],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003889547,0.00003349131,0.002878389,0.000068445195,0.000024319907,0.0000013203395,0.00062877015,0.00060626736,0.9941168,0.00003238725,0.0004728845,0.0010980637],"study_design_scores_gemma":[0.0017922607,0.0011243504,0.005209227,0.00020810701,0.000106304324,0.00058084744,0.0012010944,0.15485111,0.6013646,0.00016101915,0.23178391,0.001617137],"about_ca_topic_score_codex":0.000025308103,"about_ca_topic_score_gemma":0.00010987967,"teacher_disagreement_score":0.39275214,"about_ca_system_score_codex":0.000013932252,"about_ca_system_score_gemma":0.0001779415,"threshold_uncertainty_score":0.6787159},"labels":[],"label_agreement":null},{"id":"W2136850043","doi":"10.1186/1471-2105-4-2","title":"An automated method for finding molecular complexes in large protein interaction networks","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6293,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Tree traversal; Cluster analysis; Protein Interaction Networks; Protein–protein interaction; Interaction network; Data mining; False positive paradox; Computational biology; Theoretical computer science; Algorithm; Artificial intelligence; Biology; Genetics","score_opus":0.017041386901073357,"score_gpt":0.31358256104532667,"score_spread":0.2965411741442533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136850043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041470405,0.00009914846,0.9562183,0.000011656019,0.00016867854,0.0008847251,0.000032799464,0.000064451306,0.0010498284],"genre_scores_gemma":[0.4136006,0.000010542012,0.5852294,0.00033663385,0.00006444182,0.000110258894,0.000560301,0.000032461838,0.00005538687],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984769,0.00009401135,0.0006365868,0.00019102039,0.00010668148,0.00049479934],"domain_scores_gemma":[0.9991334,0.000028407758,0.0002508106,0.0004041817,0.00007530789,0.000107865075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089973427,0.00023639013,0.00023717941,0.00010878511,0.000115025156,0.00009465058,0.00021472253,0.0002888567,0.00001179752],"category_scores_gemma":[0.00009233052,0.00023153561,0.00011436489,0.00016861015,0.000026222295,0.000032027376,0.00005118409,0.00015686259,0.000006476537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009009779,0.0010996615,0.0044452916,0.0016294288,0.00038767236,0.0000071392865,0.0023973903,0.76308626,0.12714624,0.06600556,0.008904559,0.023989825],"study_design_scores_gemma":[0.0011766304,0.00023676698,0.00012217362,0.000043880078,0.000013795819,0.000016996215,0.0005656385,0.97779644,0.010382317,0.0003127588,0.0090159755,0.00031664083],"about_ca_topic_score_codex":0.00000542931,"about_ca_topic_score_gemma":0.00008420008,"teacher_disagreement_score":0.3721302,"about_ca_system_score_codex":0.000036684556,"about_ca_system_score_gemma":0.000081888946,"threshold_uncertainty_score":0.9441748},"labels":[],"label_agreement":null},{"id":"W2136961946","doi":"10.1186/1471-2105-11-441","title":"Relations as patterns: bridging the gap between OBO and OWL","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Ontology; Open Biomedical Ontologies; Web Ontology Language; Ontology components; Semantics (computer science); Ontology language; OWL-S; Description logic; Programming language; Software; Automated reasoning; Protégé; Natural language processing; Bridging (networking); Information retrieval; Semantic Web; Artificial intelligence; Semantic Web Stack","score_opus":0.02210392464390946,"score_gpt":0.2746213768207904,"score_spread":0.25251745217688093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136961946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.954064,0.0001370165,0.042355068,0.0005727413,0.00016464731,0.00012579563,0.000034457284,0.000034081135,0.0025121598],"genre_scores_gemma":[0.9637311,0.00005905711,0.034522973,0.00048891216,0.00038888573,0.000010524212,0.00010992027,0.000011061864,0.00067757274],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.999415,0.000016366452,0.00020838506,0.00009299288,0.00010001496,0.00016725392],"domain_scores_gemma":[0.9995005,0.000060845843,0.00007795919,0.00026821555,0.00002472518,0.00006776716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022884391,0.00009601464,0.0000860283,0.00002311569,0.00015702087,0.000050315815,0.0001660695,0.0001762366,0.000017892919],"category_scores_gemma":[0.00030427467,0.00006296816,0.00004025743,0.000048051723,0.00018324102,0.000004983312,0.0001299728,0.00018969156,0.000037920032],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003069257,0.000052041516,0.60759646,0.0002317591,0.00015821701,0.0000021862816,0.0018813523,0.000019955467,0.01246703,0.0016470025,0.02525102,0.3506623],"study_design_scores_gemma":[0.0018351671,0.0006362294,0.43165883,0.000114036935,0.000180581,0.00022466878,0.0038498896,0.019895863,0.019944016,0.0014760458,0.5191023,0.0010823781],"about_ca_topic_score_codex":0.000014181787,"about_ca_topic_score_gemma":0.000039459785,"teacher_disagreement_score":0.49385127,"about_ca_system_score_codex":0.0000025210327,"about_ca_system_score_gemma":0.000048527556,"threshold_uncertainty_score":0.2567767},"labels":[],"label_agreement":null},{"id":"W2136992683","doi":"10.1186/1471-2105-7-41","title":"Discovering semantic features in the literature: a foundation for building functional associations","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Context (archaeology); DNA microarray; Non-negative matrix factorization; Data mining; Semantic similarity; Interpretation (philosophy); Information retrieval; Computational biology; Natural language processing; Gene; Artificial intelligence; Biology; Matrix decomposition; Gene expression; Genetics","score_opus":0.016823192533370328,"score_gpt":0.2701781252555171,"score_spread":0.25335493272214676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136992683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30917433,0.0007048431,0.6872745,0.00071594503,0.00040849549,0.00048702012,0.00007863371,0.000035115434,0.001121079],"genre_scores_gemma":[0.88104564,0.00002584675,0.1160169,0.00040403067,0.0005345407,0.00007899509,0.0014847262,0.000010522517,0.00039877035],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99942315,0.000020548492,0.00020124712,0.000083516585,0.00011669985,0.00015485522],"domain_scores_gemma":[0.9996646,0.00007944268,0.00008307071,0.00012416458,0.000036790876,0.000011935914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027802383,0.00008229551,0.000072728384,0.00004318744,0.00011676924,0.000105569154,0.000109032626,0.000121268306,0.0000011603354],"category_scores_gemma":[0.00024141891,0.000056467037,0.00006499448,0.00013135707,0.000038556973,0.000009470302,0.000027374348,0.000073428724,0.0000019088782],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010323484,0.0017676469,0.21984424,0.003556841,0.00054269156,0.000010432097,0.015093278,0.041863307,0.07719495,0.12708344,0.33404514,0.17796567],"study_design_scores_gemma":[0.0046721306,0.00066322385,0.72029555,0.00034690803,0.00012860248,0.00012060732,0.004456914,0.08077957,0.007816113,0.011964208,0.16760059,0.0011555811],"about_ca_topic_score_codex":0.000013586544,"about_ca_topic_score_gemma":0.00018469224,"teacher_disagreement_score":0.57187134,"about_ca_system_score_codex":0.000015944132,"about_ca_system_score_gemma":0.000040652376,"threshold_uncertainty_score":0.23026589},"labels":[],"label_agreement":null},{"id":"W2137751072","doi":"10.1186/1471-2105-8-s5-s1","title":"Articles selected from posters presented at the Tenth Annual International Conference on Research in Computational Biology – Preface","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Università degli Studi di Palermo; Università degli Studi di Udine; International Business Machines Corporation; Broad Institute; Università degli Studi di Padova; U.S. Department of Energy; National Science Foundation","keywords":"Library science; Convention; Operations research; History; Political science; Computer science; Law; Engineering","score_opus":0.06454478139956638,"score_gpt":0.36266369236069484,"score_spread":0.29811891096112847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137751072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97123796,0.000088062545,0.019085418,0.002283531,0.00036570092,0.0006779033,0.0004978014,0.000024586556,0.005739061],"genre_scores_gemma":[0.98496485,0.000135045,0.012068015,0.0004080972,0.00018612652,0.000016609376,0.0016606656,0.000014794904,0.0005458182],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976843,0.00014231083,0.0006149931,0.00023263031,0.0007204548,0.00060530275],"domain_scores_gemma":[0.9984941,0.0003029171,0.00012565787,0.0003554277,0.00054995046,0.0001719647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013967736,0.00017227598,0.00014601389,0.00022993798,0.00016369732,0.00007168886,0.0006342789,0.00023754081,0.00007593757],"category_scores_gemma":[0.00055039243,0.000121561374,0.00005696499,0.00034338143,0.00059638015,0.000016122789,0.00053722033,0.00033280737,0.00016034552],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011952315,0.003391719,0.44333416,0.0007002564,0.0013188672,0.000037632613,0.02073104,0.011634141,0.1775904,0.00868194,0.14491622,0.1757113],"study_design_scores_gemma":[0.0072784326,0.0027740174,0.27741966,0.00023512924,0.000027847807,0.000049374743,0.020213712,0.55181915,0.075559504,0.0027321149,0.060734738,0.0011563395],"about_ca_topic_score_codex":0.000097577555,"about_ca_topic_score_gemma":0.0010177252,"teacher_disagreement_score":0.540185,"about_ca_system_score_codex":0.000093339615,"about_ca_system_score_gemma":0.00024242079,"threshold_uncertainty_score":0.4957129},"labels":[],"label_agreement":null},{"id":"W2137820961","doi":"10.1186/1471-2105-8-340","title":"Impact of image segmentation on high-content screening data quality for SK-BR-3 cells","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"High-content screening; Computer science; Segmentation; Content (measure theory); Information retrieval; Data science; Computational biology; Artificial intelligence; Biology; Genetics; Mathematics","score_opus":0.07732888352285805,"score_gpt":0.3812900083304241,"score_spread":0.30396112480756604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137820961","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25505283,0.000019533712,0.7439991,0.000004918216,0.000015878237,0.0003204792,0.00017229884,0.000017157508,0.00039774974],"genre_scores_gemma":[0.2939382,0.000038283022,0.7026333,0.00010550922,0.00008151316,0.000007770162,0.0030410404,0.000018848888,0.00013553402],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987695,0.000024030198,0.00062674546,0.0001806074,0.00017792654,0.000221183],"domain_scores_gemma":[0.9983855,0.00006177441,0.00040850605,0.0009045749,0.0001769279,0.00006270834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010612009,0.0001531388,0.0002016794,0.0000872552,0.00004615285,0.00003139904,0.00035239515,0.00010842411,0.000009770354],"category_scores_gemma":[0.00018303959,0.0001301839,0.00017836764,0.00009142176,0.000056684607,0.000028220571,0.00017418322,0.00005441407,0.0000045172446],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030558772,0.00012763256,0.0024540932,0.0001576292,0.00014810065,2.5716176e-7,0.00008066768,0.000118489595,0.9759986,0.000025616362,0.0072767194,0.013306654],"study_design_scores_gemma":[0.00071748364,0.0004807697,0.007452563,0.000019162304,0.00006299288,0.0000012725894,0.00030372347,0.0091317585,0.98118037,0.000015186768,0.00043857793,0.00019613562],"about_ca_topic_score_codex":0.00012720551,"about_ca_topic_score_gemma":0.0000707578,"teacher_disagreement_score":0.041365825,"about_ca_system_score_codex":0.000027519101,"about_ca_system_score_gemma":0.000049860486,"threshold_uncertainty_score":0.5308745},"labels":[],"label_agreement":null},{"id":"W2139251761","doi":"10.1186/1471-2105-13-s19-s8","title":"A consolidation algorithm for genomes fractionated after higher order polyploidization","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Deutscher Akademischer Austauschdienst","keywords":"Genome; Algorithm; Gene duplication; Consolidation (business); Biology; Fractionation; Computer science; Computational biology; Gene; Genetics; Chemistry","score_opus":0.015573472473317742,"score_gpt":0.25466988657805234,"score_spread":0.2390964141047346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139251761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0113223335,0.0010039398,0.98533213,0.000051202856,0.00055903936,0.0006337859,0.00010521096,0.000038615297,0.0009537576],"genre_scores_gemma":[0.065059274,0.00018701638,0.928033,0.00055429904,0.0009263175,0.0002961765,0.0022800849,0.00005252208,0.0026113335],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999172,0.000017460668,0.00027247972,0.00010552157,0.00013349597,0.00029905664],"domain_scores_gemma":[0.99936706,0.000014484674,0.00013035671,0.00020969662,0.00019239706,0.00008600742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016623148,0.00014736601,0.0001041036,0.000069911635,0.000073586816,0.00003705665,0.00008269647,0.00015643975,0.00013255465],"category_scores_gemma":[0.000033925502,0.00013994254,0.000062068735,0.00012799875,0.00003496257,0.000033809385,0.00004843625,0.000041989464,0.00008974608],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091551134,0.0021231954,0.12303025,0.0019069684,0.0019098762,0.0000014104171,0.0043853363,0.0026541124,0.08202413,0.0017295711,0.06025903,0.7190606],"study_design_scores_gemma":[0.0031966115,0.00035533306,0.026276104,0.000023460932,0.00017994118,0.000023927603,0.0005791609,0.14762954,0.025999215,0.00011864475,0.7945789,0.0010391765],"about_ca_topic_score_codex":0.0000018659885,"about_ca_topic_score_gemma":0.0000019566585,"teacher_disagreement_score":0.73431987,"about_ca_system_score_codex":0.000027340946,"about_ca_system_score_gemma":0.000054987806,"threshold_uncertainty_score":0.5706691},"labels":[],"label_agreement":null},{"id":"W2139259976","doi":"10.1186/1471-2105-4-11","title":"PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":340,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; National Research Council Canada; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Directorate for Biological Sciences; Genome Canada","keywords":"Computer science; Support vector machine; Set (abstract data type); Task (project management); Interaction information; Precision and recall; Recall; Data curation; Interaction network; Artificial intelligence; Protein–protein interaction; Data mining; Machine learning; Database; Information retrieval; Biology","score_opus":0.027212083889263005,"score_gpt":0.29671629648987846,"score_spread":0.26950421260061547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139259976","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61417294,0.0012955919,0.38041776,0.0005390355,0.00041982462,0.0017996259,0.00031441226,0.00006521505,0.00097559736],"genre_scores_gemma":[0.4667232,0.000013674645,0.53080755,0.00032501738,0.0002158819,0.00016091645,0.00035760613,0.000029347188,0.0013667941],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990563,0.000047653586,0.00032083213,0.00016702867,0.00013129179,0.00027689076],"domain_scores_gemma":[0.999403,0.000040208182,0.00012915012,0.00025873035,0.00006314738,0.00010576633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033885927,0.00017371387,0.00015181267,0.0000546101,0.00020823239,0.000091609174,0.00014958497,0.00020097305,0.000017064745],"category_scores_gemma":[0.00065190473,0.00011191134,0.00008044734,0.00013332568,0.00023016747,0.000011002373,0.00007879123,0.00014621436,0.000003065898],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016730425,0.0013979528,0.0076728314,0.0069752303,0.0014554852,0.000030920306,0.022267858,0.000081066595,0.6320181,0.008468716,0.04537751,0.27258128],"study_design_scores_gemma":[0.0030914678,0.0015215806,0.00053036923,0.00047158342,0.0001226679,0.0005854395,0.0026776893,0.049787283,0.04521612,0.0004898623,0.89467555,0.00083036756],"about_ca_topic_score_codex":0.0000030600143,"about_ca_topic_score_gemma":0.00001119694,"teacher_disagreement_score":0.84929806,"about_ca_system_score_codex":0.000011450683,"about_ca_system_score_gemma":0.00013096347,"threshold_uncertainty_score":0.45636117},"labels":[],"label_agreement":null},{"id":"W2140058398","doi":"10.1186/1471-2105-11-47","title":"BSSF: a fingerprint based ultrafast binding site similarity search and function analysis server","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; McGill University","keywords":"Computer science; Similarity (geometry); Structural genomics; Information retrieval; Data mining; Fingerprint (computing); Genomics; Nearest neighbor search; Function (biology); Computational biology; Genome; Biology; Genetics; Artificial intelligence; Protein structure; Gene; Image (mathematics)","score_opus":0.0262463177668005,"score_gpt":0.2816497731573805,"score_spread":0.25540345539058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140058398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4193305,0.0000026405783,0.5800937,0.00009074198,0.00013639499,0.00008798284,0.000011551367,0.00007067922,0.00017582097],"genre_scores_gemma":[0.3720742,0.0000012940191,0.6276175,0.00020991098,0.000028880073,0.0000047379726,0.000033868087,0.000005179536,0.0000244399],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985719,0.00009314117,0.00036675713,0.0002309567,0.00047114684,0.00026615395],"domain_scores_gemma":[0.9985719,0.00050359167,0.00010706837,0.0005358937,0.00013802084,0.00014352913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013282328,0.00015734369,0.00020208629,0.00047408964,0.00019780487,0.0004614021,0.00038064137,0.00009407721,0.000030991498],"category_scores_gemma":[0.00015442805,0.00014700003,0.00013038727,0.0013270362,0.000062429295,0.00096668047,0.00028075624,0.0003235844,0.00006670242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050623203,0.0001815217,0.11738072,0.0004535009,0.00029269722,0.0000041834214,0.0031405722,0.8109746,0.0018649232,0.014672354,0.00011731479,0.050867],"study_design_scores_gemma":[0.00021907852,0.00002625545,0.10283903,0.00000744086,0.000057023775,0.0000041156623,0.00003523969,0.8955651,0.0006175623,0.00021173965,0.00025505075,0.00016239517],"about_ca_topic_score_codex":0.000035684854,"about_ca_topic_score_gemma":0.00020730343,"teacher_disagreement_score":0.08459049,"about_ca_system_score_codex":0.000034157998,"about_ca_system_score_gemma":0.00017714704,"threshold_uncertainty_score":0.59944874},"labels":[],"label_agreement":null},{"id":"W2140106205","doi":"10.1186/1471-2105-11-63","title":"Validation of differential gene expression algorithms: Application comparing fold-change estimation to hypothesis testing","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Computer science; Bayes' theorem; DNA microarray; Algorithm; Nonparametric statistics; Data mining; Replicate; Cross-validation; Statistical hypothesis testing; Machine learning; Bayesian probability; Artificial intelligence; Statistics; Mathematics; Biology; Gene; Gene expression; Genetics","score_opus":0.05775399429316948,"score_gpt":0.27967853765939465,"score_spread":0.2219245433662252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140106205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48479307,0.000007019285,0.5144804,0.000016366645,0.00012252278,0.00030284125,0.000009215392,0.000019336523,0.0002492076],"genre_scores_gemma":[0.6549387,0.0000036219656,0.34466,0.00003121194,0.00013193591,0.000096060445,0.000113467904,0.000010612886,0.0000143872785],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990883,0.000020411146,0.00038500418,0.0001703045,0.0001952223,0.00014076248],"domain_scores_gemma":[0.9990464,0.000027326581,0.00028701752,0.00040529144,0.00015026006,0.00008371523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014664493,0.00012837781,0.00012878951,0.00010105222,0.00008415442,0.000030927233,0.00018249654,0.00013562854,0.000007809958],"category_scores_gemma":[0.00023972218,0.00012062645,0.00004687701,0.00016553033,0.000025828223,0.000021077545,0.000094320756,0.00006988532,0.000015921898],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022680666,0.000036688896,0.003184465,0.000060152564,0.000004087138,1.27723885e-8,0.00015478664,0.0007677133,0.95726633,0.000019554991,0.00014995375,0.0383336],"study_design_scores_gemma":[0.0002585898,0.00005397857,0.010536741,0.000027109441,0.000013445348,0.000002356481,0.000061364124,0.16529156,0.82325953,0.000058336846,0.00030228953,0.00013468335],"about_ca_topic_score_codex":0.00001150785,"about_ca_topic_score_gemma":0.000007823656,"teacher_disagreement_score":0.1701456,"about_ca_system_score_codex":0.000011239113,"about_ca_system_score_gemma":0.00003770104,"threshold_uncertainty_score":0.49190038},"labels":[],"label_agreement":null},{"id":"W2140424919","doi":"10.1186/s12859-015-0622-0","title":"Using Gene Ontology to describe the role of the neurexin-neuroligin-SHANK complex in human, mouse and rat and its relevance to autism","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Autism Spectrum Disorder Research","field":"Neuroscience","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; Centre for Addiction and Mental Health","funders":"National Human Genome Research Institute; University College London; British Heart Foundation; Parkinson's UK; National Institute for Health and Care Research","keywords":"Neuroligin; Neurexin; Autism; Gene ontology; Autism spectrum disorder; Annotation; Biology; Computational biology; Gene; Genetics; Psychology; Developmental psychology; Gene expression","score_opus":0.14624088114181524,"score_gpt":0.3374047741527832,"score_spread":0.19116389301096795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140424919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9949609,0.00013277052,0.00093396625,0.0023118944,0.00006565327,0.0009018399,0.000020433274,0.000023496003,0.00064904167],"genre_scores_gemma":[0.99417573,0.000023637887,0.00432019,0.0013482702,0.000008605388,0.000014786074,4.911264e-7,0.00001621888,0.00009204963],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984727,0.00017017043,0.0003852285,0.00019759488,0.0003752944,0.00039900854],"domain_scores_gemma":[0.9991002,0.00018354642,0.00011892977,0.0004194605,0.000020192048,0.0001576751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003267455,0.0001517474,0.00020697206,0.00013862985,0.00018822147,0.00007117096,0.00052766065,0.000055139433,0.0000032052321],"category_scores_gemma":[0.0006599188,0.00010234507,0.000022917084,0.000506892,0.00017579073,0.00020572466,0.0007155393,0.00022165597,0.000012542269],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031358137,0.000204383,0.020022333,0.00029935208,0.0000092504715,0.000014905877,0.033567373,0.012837471,0.8088431,0.12070775,0.00068165886,0.0024988572],"study_design_scores_gemma":[0.0015155886,0.00045308436,0.01740476,0.000058808128,0.000016251424,0.00027998709,0.001022487,0.70425576,0.25918514,0.009534388,0.005820257,0.00045349798],"about_ca_topic_score_codex":0.0000947379,"about_ca_topic_score_gemma":0.00047967146,"teacher_disagreement_score":0.6914183,"about_ca_system_score_codex":0.000046355803,"about_ca_system_score_gemma":0.00010155361,"threshold_uncertainty_score":0.41735107},"labels":[],"label_agreement":null},{"id":"W2140572608","doi":"10.1186/1471-2105-11-s1-s4","title":"Better score function for peptide identification with ETD MS/MS spectra","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Bioinformatics Solutions (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Electron-transfer dissociation; Tandem mass spectrometry; Proteomics; Peptide; Mass spectrometry; Database search engine; Computer science; Computational biology; Tandem mass tag; Bioinformatics; Chemistry; Chromatography; Quantitative proteomics; Search engine; Biology; Information retrieval; Biochemistry","score_opus":0.015368112956873332,"score_gpt":0.25119998308449154,"score_spread":0.23583187012761822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140572608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08586935,0.0000035756545,0.9042176,0.00012535931,0.00004821312,0.00041697174,0.000066842964,0.00022784126,0.00902423],"genre_scores_gemma":[0.062204495,0.000007001179,0.93522996,0.0001542543,0.0002537995,0.00051302026,0.00036316298,0.00003353634,0.0012407457],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991905,0.0000013329527,0.00034469634,0.00013917251,0.00013057416,0.00019372725],"domain_scores_gemma":[0.9990347,0.0000401458,0.00025506827,0.000506344,0.00010509194,0.00005864034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000102136466,0.00014153728,0.000109497916,0.00004127904,0.00016478683,0.000079477606,0.00018233918,0.00013354827,0.00014077795],"category_scores_gemma":[0.000025810115,0.000121120895,0.000060136925,0.00009427451,0.00006282588,0.00029007747,0.000025459707,0.00023450892,0.000052649713],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047610936,0.0003893487,0.016854981,0.0031017594,0.0001343317,7.073864e-7,0.0011187211,0.00054863276,0.7960458,0.10770978,0.018871807,0.054748055],"study_design_scores_gemma":[0.0013346084,0.00012256333,0.002349605,0.00011132852,0.0001485452,0.0000443405,0.0003180641,0.103595056,0.7310668,0.02650104,0.13354743,0.0008605824],"about_ca_topic_score_codex":0.0000041411627,"about_ca_topic_score_gemma":0.000055365494,"teacher_disagreement_score":0.11467561,"about_ca_system_score_codex":0.000028609704,"about_ca_system_score_gemma":0.000040179508,"threshold_uncertainty_score":0.49391666},"labels":[],"label_agreement":null},{"id":"W2140818786","doi":"10.1186/1471-2105-13-22","title":"Analysis of energy-based algorithms for RNA secondary structure prediction","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Algorithm; Computer science; Harmonic mean; Function (biology); Data mining; Mathematics; Artificial intelligence; Statistics; Biology","score_opus":0.014537501140611066,"score_gpt":0.2395444029647138,"score_spread":0.22500690182410274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140818786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061839134,0.00027945434,0.9361558,0.000007688965,0.00020792976,0.00017108647,0.0008896317,0.000012352078,0.0004369397],"genre_scores_gemma":[0.7376363,0.000018762385,0.26029524,0.00018276124,0.00019799794,0.000031393236,0.0015137632,0.000015514135,0.0001082495],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992691,0.000021072316,0.00031171856,0.00008371051,0.00011936543,0.00019498056],"domain_scores_gemma":[0.99935204,0.000022860237,0.00019484208,0.00028238568,0.000076298995,0.000071563154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018545214,0.000118592696,0.00018219552,0.00012312438,0.000049984552,0.000010648559,0.000118670716,0.00018543132,0.000048443282],"category_scores_gemma":[0.00004409699,0.000102579,0.00020175941,0.00016614389,0.000028566928,0.000011154285,0.000025920937,0.000029378893,7.4255144e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053610717,0.0002851856,0.023561755,0.0011030483,0.0031283884,1.4837234e-7,0.000566583,0.009757314,0.81298345,0.002375628,0.0035251863,0.14217722],"study_design_scores_gemma":[0.0004866041,0.00020558912,0.002211777,0.000009720983,0.0005375571,0.0000013261063,0.000105680454,0.1184876,0.86615074,0.00007635755,0.011542102,0.00018494746],"about_ca_topic_score_codex":0.000003105025,"about_ca_topic_score_gemma":0.000009146057,"teacher_disagreement_score":0.6758605,"about_ca_system_score_codex":0.000008282962,"about_ca_system_score_gemma":0.00006874919,"threshold_uncertainty_score":0.418305},"labels":[],"label_agreement":null},{"id":"W2142056356","doi":"10.1186/1471-2105-3-2","title":"The Comparative RNA Web (CRW) Site: an online database of comparative sequence and structure information for ribosomal, intron, and other RNAs","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1643,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"National Institute of General Medical Sciences; University of Texas at Austin; Welch Foundation; National Institutes of Health; National Science Foundation","keywords":"Intron; RNA; Biology; Phylogenetic tree; Nucleic acid structure; Computational biology; Ribosomal RNA; Genetics; Nucleic acid secondary structure; Sequence (biology); Database; Gene; Computer science","score_opus":0.06946269515937568,"score_gpt":0.2973266295758393,"score_spread":0.22786393441646358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142056356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9583225,0.00088561786,0.036902655,0.00006633882,0.000070416565,0.0008514258,0.0025662666,0.000012510962,0.00032224372],"genre_scores_gemma":[0.8926252,0.00034080967,0.10602422,0.00028957668,0.000079314814,0.000025689409,0.0005523161,0.000009465443,0.000053387488],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921227,0.000046843183,0.00036795673,0.00009861321,0.00011302614,0.00016128739],"domain_scores_gemma":[0.99919677,0.00006302892,0.00028060717,0.00027128658,0.000117894415,0.000070411406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014575619,0.00015954504,0.00018625545,0.000032892207,0.00016897389,0.000065083455,0.00014492299,0.00010124502,0.000010204122],"category_scores_gemma":[0.00004791582,0.00011028643,0.000029219349,0.000053014177,0.00019371297,0.00006691465,0.00007280901,0.00006249106,0.0000021620674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009602933,0.0001844733,0.0014862204,0.0010626351,0.00028244592,2.997416e-7,0.01621181,0.00060267514,0.9309926,0.009886715,0.0061573028,0.03217251],"study_design_scores_gemma":[0.002187353,0.0013442187,0.00042450745,0.00009851771,0.00007899643,0.000041769257,0.006977678,0.49190852,0.4217196,0.0005174453,0.0741449,0.00055647164],"about_ca_topic_score_codex":0.000006128728,"about_ca_topic_score_gemma":0.00014687641,"teacher_disagreement_score":0.509273,"about_ca_system_score_codex":0.0000060863576,"about_ca_system_score_gemma":0.000029545015,"threshold_uncertainty_score":0.44973505},"labels":[],"label_agreement":null},{"id":"W2142664740","doi":"10.1186/1471-2105-13-s9-s3","title":"Inference of gene regulatory subnetworks from time course gene expression data","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Inference; Gene regulatory network; Computer science; Identification (biology); Computational biology; Block (permutation group theory); Data mining; Set (abstract data type); DNA microarray; Scale (ratio); Gene; Artificial intelligence; Gene expression; Biology; Genetics; Mathematics","score_opus":0.02317497161639883,"score_gpt":0.2607738370857789,"score_spread":0.23759886546938006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142664740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8164983,0.005392691,0.17673402,0.000009656808,0.00025505104,0.00022459168,0.00034534856,0.000031813186,0.0005085741],"genre_scores_gemma":[0.7773105,0.00019311093,0.21725723,0.00007275189,0.00065779465,0.0000057442026,0.0042496207,0.000030390425,0.00022283506],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984407,0.00007084386,0.00057339994,0.00022636335,0.0003015787,0.0003871189],"domain_scores_gemma":[0.99721855,0.0000378316,0.000397745,0.0020502422,0.00010179231,0.00019381594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004610383,0.00022933986,0.00029653116,0.000044935547,0.000069816975,0.00001921581,0.00071734434,0.0002895702,0.0000887198],"category_scores_gemma":[0.00006812413,0.00020957482,0.00010754665,0.00014588423,0.00012310056,0.000038117214,0.00057185616,0.000091799346,0.00007080368],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001423403,0.00039321985,0.097788654,0.00010970666,0.00046390446,7.4503424e-7,0.000421569,0.012456353,0.8404173,0.000027538446,0.03885704,0.0089216],"study_design_scores_gemma":[0.0008000667,0.000091368776,0.035134457,0.000079873316,0.000373138,0.000010347846,0.00016857385,0.23304573,0.7237038,0.000030221232,0.005884492,0.00067792996],"about_ca_topic_score_codex":0.0000076016495,"about_ca_topic_score_gemma":0.000007974243,"teacher_disagreement_score":0.22058937,"about_ca_system_score_codex":0.000013198588,"about_ca_system_score_gemma":0.00012411515,"threshold_uncertainty_score":0.8546213},"labels":[],"label_agreement":null},{"id":"W2143416770","doi":"10.1186/1471-2105-15-s13-s2","title":"RiboFSM: Frequent subgraph mining for the discovery of RNA structures and interactions","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Simon Fraser University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal; King Saud University","keywords":"Computational biology; Graph; Computer science; Theoretical computer science; Biology; RNA; DNA microarray; Combinatorics; Genetics; Mathematics; Gene; Gene expression","score_opus":0.01668141282398036,"score_gpt":0.2508486031466072,"score_spread":0.2341671903226268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143416770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2590341,0.00030524758,0.739304,0.000069053785,0.00021608928,0.00027937375,0.000042994176,0.0000056168105,0.0007435324],"genre_scores_gemma":[0.88227326,0.00009247555,0.11718435,0.00013725355,0.000105640924,0.000030441854,0.000029350012,0.000009599397,0.00013765387],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995408,0.000018046283,0.0002050867,0.00006915171,0.00006284955,0.00010405441],"domain_scores_gemma":[0.99948204,0.00010654595,0.00013353961,0.00021955691,0.00003515464,0.000023177841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018088387,0.00008439752,0.00009206236,0.00002481297,0.00008830064,0.000033069064,0.00011709818,0.00005387772,0.0000031294717],"category_scores_gemma":[0.00015126057,0.00005464189,0.00006995013,0.000027704184,0.000060241422,0.000010469801,0.000048135913,0.000027099022,4.3781307e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025846146,0.000045034518,0.0022178316,0.00066600274,0.00025700603,7.856156e-8,0.0011343997,0.00037093752,0.8866408,0.032759495,0.0025727195,0.07307723],"study_design_scores_gemma":[0.0006148512,0.000371142,0.0016006865,0.000053288637,0.0000905951,0.000016503976,0.0015540997,0.014073149,0.9564951,0.0041559795,0.02071489,0.0002596892],"about_ca_topic_score_codex":0.000006440595,"about_ca_topic_score_gemma":0.000029997702,"teacher_disagreement_score":0.62323916,"about_ca_system_score_codex":0.0000022822992,"about_ca_system_score_gemma":0.0000193471,"threshold_uncertainty_score":0.22282316},"labels":[],"label_agreement":null},{"id":"W2144030303","doi":"10.1186/1471-2105-15-341","title":"FastMG: a simple, fast, and accurate maximum likelihood procedure to estimate amino acid replacement rate matrices from large data sets","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Inference; Phylogenetic tree; Sequence (biology); Matrix (chemical analysis); Algorithm; Sequence alignment; Computer science; Protein sequencing; Similarity (geometry); Distance matrix; Data mining; Peptide sequence; Biology; Genetics; Artificial intelligence; Gene","score_opus":0.018077665721101796,"score_gpt":0.28126252376126315,"score_spread":0.26318485804016134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144030303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8845456,0.0011518602,0.11074876,0.00019199404,0.00019014484,0.0006922695,0.0017006648,0.00002359025,0.0007551022],"genre_scores_gemma":[0.8200965,0.0004956096,0.17528799,0.0015409406,0.00026653594,0.00005956778,0.0021018446,0.000052725103,0.000098293065],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845064,0.00004017415,0.0004657858,0.0004283951,0.00014680291,0.00046819673],"domain_scores_gemma":[0.9985194,0.000031689284,0.00021607171,0.00096034317,0.00008189096,0.00019058163],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004347833,0.00030071108,0.0002716859,0.000051503284,0.00017698463,0.00013219335,0.0004882469,0.00013101562,0.000008907963],"category_scores_gemma":[0.00019351691,0.00026055408,0.00004148227,0.000098470315,0.0000395447,0.000009163457,0.0013222946,0.00007741636,0.000043399705],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027117892,0.0010317109,0.23874049,0.00444003,0.0024269659,0.000011557384,0.010285567,0.0036901727,0.33695966,0.0006040346,0.18475069,0.21434735],"study_design_scores_gemma":[0.006325406,0.0022265362,0.10743866,0.00018088093,0.0004569774,0.00005381032,0.003015864,0.5034401,0.043100923,0.0022101637,0.32898614,0.0025645478],"about_ca_topic_score_codex":0.000015260513,"about_ca_topic_score_gemma":0.00023149823,"teacher_disagreement_score":0.4997499,"about_ca_system_score_codex":0.000009501776,"about_ca_system_score_gemma":0.00007394063,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W2144326360","doi":"10.1186/1471-2105-14-s6-s2","title":"Simulating the decentralized processes of the human immune system in a virtual anatomy model","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Artificial Immune Systems Applications","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Replicate; Immune system; Distributed computing; Visualization; Human–computer interaction; Artificial intelligence; Biology","score_opus":0.016378069319878806,"score_gpt":0.23870325032892034,"score_spread":0.22232518100904153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144326360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8164992,0.00029484602,0.17680785,0.000030526076,0.000120101424,0.001986012,0.000012563198,0.00025430723,0.0039946414],"genre_scores_gemma":[0.99660015,0.00000286875,0.003199965,0.000006110256,0.000008957451,0.00013287521,0.0000031215393,0.000017276374,0.000028653221],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988224,0.000018774248,0.00075862673,0.000045705914,0.0001637128,0.00019081478],"domain_scores_gemma":[0.99921405,0.00008929199,0.00016181893,0.00042806685,0.000086147935,0.000020627202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018063675,0.00011555263,0.00017408577,0.00004616163,0.00012850208,0.00004598005,0.00036620925,0.000057799054,0.0000044774633],"category_scores_gemma":[0.00005682557,0.0000703571,0.000049509814,0.00039509297,0.0000539599,0.00022952538,0.00006986482,0.00011696093,0.00002993577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.4006133e-7,0.00001061975,0.00080774166,0.00079477,0.000012589438,1.6709867e-8,0.0038232373,0.98615587,0.0012203067,0.0067009656,0.00006191457,0.0004113224],"study_design_scores_gemma":[0.00015814858,0.000003119557,0.00087674044,0.00015155428,0.000007933991,0.0000012765166,0.0045256545,0.9916989,0.0023448176,0.0000911711,0.00005665552,0.0000839929],"about_ca_topic_score_codex":0.00012548547,"about_ca_topic_score_gemma":0.00009897469,"teacher_disagreement_score":0.18010102,"about_ca_system_score_codex":0.0000682657,"about_ca_system_score_gemma":0.0000479529,"threshold_uncertainty_score":0.2869079},"labels":[],"label_agreement":null},{"id":"W2144811782","doi":"10.1186/1471-2105-12-225","title":"Binding Site Prediction for Protein-Protein Interactions and Novel Motif Discovery using Re-occurring Polypeptide Sequences","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Binding site; Proteome; Computational biology; Protein–protein interaction; Plasma protein binding; Sequence motif; Protein Array Analysis; Binding domain; Biology; Sequence (biology); Bioinformatics; DNA microarray; Genetics; Biochemistry; Gene","score_opus":0.045870827510556725,"score_gpt":0.2596847144328296,"score_spread":0.21381388692227288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144811782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46645024,0.00005158973,0.5319445,0.0000052972227,0.00014646538,0.0005643824,0.00024344264,0.000018455059,0.0005756001],"genre_scores_gemma":[0.61635256,0.000015657222,0.3825448,0.00010031605,0.000249946,0.00007665013,0.00023058498,0.000030277533,0.00039922234],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988772,0.0000111400595,0.0005189759,0.00017435913,0.000104164435,0.0003141574],"domain_scores_gemma":[0.999253,0.00001057543,0.00030280172,0.00027376393,0.00006716575,0.00009272563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025853675,0.00020909458,0.00016455908,0.000093829345,0.00024064198,0.00012613114,0.00013975501,0.00015110036,0.0000060603625],"category_scores_gemma":[0.0000561884,0.00019219387,0.00009605178,0.0000893659,0.00009249545,0.00010654861,0.00015462092,0.00012039055,0.0000063846505],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046016526,0.0001640961,0.008369904,0.0015000809,0.00029732427,8.518961e-7,0.0030295523,0.0020493728,0.9739837,0.0027287481,0.0006351841,0.006781021],"study_design_scores_gemma":[0.0021602612,0.0006680054,0.001012591,0.00075033604,0.00015835765,0.00011602633,0.0029492825,0.8605511,0.122599885,0.00083411555,0.0071170777,0.0010829167],"about_ca_topic_score_codex":0.000042196607,"about_ca_topic_score_gemma":0.00006583792,"teacher_disagreement_score":0.8585018,"about_ca_system_score_codex":0.00003277103,"about_ca_system_score_gemma":0.00008501629,"threshold_uncertainty_score":0.78374386},"labels":[],"label_agreement":null},{"id":"W2144847592","doi":"10.1186/1471-2105-15-35","title":"Inferring clonal evolution of tumors from single nucleotide somatic mutations","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genetics; Biology; Somatic cell; DNA microarray; Somatic evolution in cancer; Computational biology; Mutation; Nucleotide; Gene; Gene expression","score_opus":0.010037905264403343,"score_gpt":0.21691627519172957,"score_spread":0.20687836992732622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144847592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74573475,0.000105990795,0.2516134,0.00001269294,0.00016391973,0.00010486646,0.000084243125,0.0000118441685,0.002168287],"genre_scores_gemma":[0.9246954,0.000012738023,0.07473799,0.000075903175,0.00019026222,0.000006197439,0.0002448597,0.000013348838,0.000023325932],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922734,0.000012909804,0.00039446677,0.00009658092,0.0001175936,0.00015112743],"domain_scores_gemma":[0.9993205,0.000068512694,0.00020431174,0.00027611374,0.000067549816,0.00006300597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010333181,0.00010858191,0.00013687676,0.000049547263,0.000054761204,0.000022439526,0.00013409281,0.0000772809,0.000013965662],"category_scores_gemma":[0.0002508591,0.00011212663,0.00007646469,0.00005988619,0.00006782092,0.000008222251,0.00008700718,0.000044541855,0.000028288196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002911541,0.0010577905,0.28195003,0.0015052188,0.00042577193,0.0000018969163,0.0035551223,0.093743995,0.5589092,0.020783968,0.0068689245,0.030906985],"study_design_scores_gemma":[0.002938571,0.001028361,0.0858464,0.00026930077,0.00018987297,0.000017932909,0.0020125257,0.7062094,0.17407648,0.011634273,0.014735048,0.0010418252],"about_ca_topic_score_codex":0.000071856346,"about_ca_topic_score_gemma":0.00015405606,"teacher_disagreement_score":0.61246544,"about_ca_system_score_codex":0.00003682816,"about_ca_system_score_gemma":0.000114294315,"threshold_uncertainty_score":0.45723912},"labels":[],"label_agreement":null},{"id":"W2145021813","doi":"10.1186/1471-2105-13-245","title":"An algorithm for chemical genomic profiling that minimizes batch effects: bucket evaluations","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cluster analysis; DNA microarray; Profiling (computer programming); Normalization (sociology); Genomics; Gene expression profiling; Computational biology; Data mining; Drug discovery; Algorithm; Artificial intelligence; Bioinformatics; Gene; Biology; Gene expression; Genome; Genetics","score_opus":0.03323431744631187,"score_gpt":0.3219691730689637,"score_spread":0.28873485562265183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145021813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14132154,0.00043789207,0.85654366,0.000024899888,0.00040002423,0.0007284181,0.000056334437,0.000032393673,0.00045483754],"genre_scores_gemma":[0.26963314,0.000056891648,0.7276809,0.00029592778,0.00061311363,0.0003674852,0.001172228,0.000029585506,0.00015070163],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991516,0.000035686015,0.00024918452,0.00014002946,0.00014149169,0.00028200916],"domain_scores_gemma":[0.99923646,0.000031379765,0.00013514391,0.00037311218,0.000081869584,0.00014203596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031539926,0.00014395284,0.0001206377,0.000043320215,0.00009475722,0.00003822481,0.0001842516,0.00017114745,0.000009472644],"category_scores_gemma":[0.000076488424,0.00012782188,0.0000860961,0.000058927057,0.000039288345,0.000023974302,0.0000455335,0.000053203024,0.000017847395],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007188676,0.00021288717,0.002937716,0.00027702822,0.000050774473,2.8990227e-8,0.0007794829,0.00008568921,0.88030434,0.00020489078,0.006124818,0.108950466],"study_design_scores_gemma":[0.0010888593,0.00013978645,0.0013681648,0.000018308152,0.000059501752,0.000006195252,0.0009134022,0.13103208,0.85493827,0.00006860029,0.010075318,0.00029151348],"about_ca_topic_score_codex":7.2090745e-7,"about_ca_topic_score_gemma":5.474671e-7,"teacher_disagreement_score":0.13094638,"about_ca_system_score_codex":0.000027159133,"about_ca_system_score_gemma":0.00010262564,"threshold_uncertainty_score":0.52124256},"labels":[],"label_agreement":null},{"id":"W2145063082","doi":"10.1186/1471-2105-10-118","title":"ACID: annotation of cassette and integron data","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Antibiotic Resistance in Bacteria","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Health and Medical Research Council; Medical Research Council; Australian Research Council; Canadian Institutes of Health Research; Macquarie University","keywords":"Integron; Annotation; Integrase; Gene cassette; Computer science; Computational biology; Genome; Genetic genealogy; Biology; Gene; Genetics; Plasmid; Population","score_opus":0.025123547859322238,"score_gpt":0.28154666715376697,"score_spread":0.2564231192944447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145063082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.882828,0.00038648047,0.11431378,0.00008975597,0.000087984365,0.00016638055,0.000131125,0.000011437983,0.0019850743],"genre_scores_gemma":[0.831276,0.00022298133,0.16735445,0.00020132551,0.000053973406,3.5341944e-7,0.0008046259,0.0000057847287,0.000080512575],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994704,0.000011331937,0.00024443708,0.0000991236,0.00007547022,0.00009920906],"domain_scores_gemma":[0.9993136,0.000006390312,0.00013122114,0.00047728568,0.00004101847,0.000030478735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011217276,0.000079564255,0.000094393945,0.000024458448,0.000022710768,0.000018988532,0.00019523587,0.00008169261,0.0000033933507],"category_scores_gemma":[0.000106415806,0.00006966892,0.000015565454,0.000043957723,0.000055997312,0.000016578837,0.000087131,0.000035628225,0.0000038458425],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005681896,0.00023035011,0.055536795,0.0010193029,0.00012777005,0.0000032006046,0.001115423,0.00009483013,0.7229159,0.0016945588,0.049233634,0.16746005],"study_design_scores_gemma":[0.0032969667,0.0021020975,0.44535646,0.0003387481,0.0001802685,0.00014659029,0.0037259103,0.15030451,0.32055375,0.00074626616,0.07182333,0.0014250828],"about_ca_topic_score_codex":0.0000021852495,"about_ca_topic_score_gemma":0.000010198668,"teacher_disagreement_score":0.40236214,"about_ca_system_score_codex":0.000003683036,"about_ca_system_score_gemma":0.00003772765,"threshold_uncertainty_score":0.2841016},"labels":[],"label_agreement":null},{"id":"W2145428772","doi":"10.1186/1471-2105-12-481","title":"U-Compare bio-event meta-service: compatible BioNLP event extraction services","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Brain Injury Research Center; U.S. National Library of Medicine; National Institute of General Medical Sciences; Precursory Research for Embryonic Science and Technology; National Institute on Drug Abuse; Directorate for Biological Sciences; National Institutes of Health; Fonds Wetenschappelijk Onderzoek; China Scholarship Council; Joint Information Systems Committee; Vlaamse regering; Biotechnology and Biological Sciences Research Council; University of Tokyo; Korea Institute of Science and Technology Information; University of Massachusetts Amherst; Korea Institute of Science and Technology; Norges Teknisk-Naturvitenskapelige Universitet; Japan Society for the Promotion of Science; Academy of Finland; Ministry of Education, Culture, Sports, Science and Technology; National Institute of Advanced Industrial Science and Technology","keywords":"Computer science; Event (particle physics); Biomedical text mining; Interoperability; Service (business); Task (project management); Data mining; Extraction (chemistry); Information extraction; Information retrieval; Text mining; World Wide Web; Systems engineering; Engineering","score_opus":0.0833120254126558,"score_gpt":0.30913784916280196,"score_spread":0.22582582375014615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145428772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6993409,0.005261891,0.27818736,0.0005671975,0.0018499951,0.001177386,0.00025636228,0.00044842684,0.012910484],"genre_scores_gemma":[0.7975474,0.00022502251,0.19962251,0.001288885,0.00020050818,0.00007543276,0.0005737812,0.000033338343,0.00043310755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986082,0.00004863911,0.00054765475,0.00021898544,0.00023964475,0.00033690908],"domain_scores_gemma":[0.99891585,0.000019193389,0.0002863968,0.0004959756,0.00013214722,0.00015041034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028583748,0.00025998717,0.00031182173,0.00008260984,0.0001301453,0.00003604261,0.00038666438,0.00021783632,0.00019923692],"category_scores_gemma":[0.000028498269,0.00019657951,0.00021592683,0.00019132205,0.0000872649,0.000016655453,0.00017658509,0.00012472144,0.00020011773],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042554163,0.0107052885,0.22771856,0.0227753,0.021214189,0.000075095006,0.04975076,0.0047839843,0.086972944,0.0045544477,0.13792789,0.42926612],"study_design_scores_gemma":[0.004209244,0.0020914315,0.07348914,0.00029859034,0.0025602877,0.0002668444,0.019357251,0.13552395,0.16655539,0.0009026467,0.5918979,0.0028473493],"about_ca_topic_score_codex":0.00013567523,"about_ca_topic_score_gemma":0.00039692273,"teacher_disagreement_score":0.45397,"about_ca_system_score_codex":0.00001644103,"about_ca_system_score_gemma":0.00007603686,"threshold_uncertainty_score":0.80162793},"labels":[],"label_agreement":null},{"id":"W2145664842","doi":"10.1186/1471-2105-13-s3-s4","title":"Combining automated peak tracking in SAR by NMR with structure-based backbone assignment from 15N-NOESY","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Two-dimensional nuclear magnetic resonance spectroscopy; Biological system; Computer science; Drug discovery; Chemistry; Algorithm; Stereochemistry; Biology","score_opus":0.007970372992195376,"score_gpt":0.2326558932292477,"score_spread":0.22468552023705232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145664842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8832527,0.00046673778,0.11475653,0.000026000898,0.00012737577,0.00039136596,0.0002571876,0.00009088844,0.00063124613],"genre_scores_gemma":[0.9016256,0.000008138523,0.09651119,0.00034249783,0.000075923366,0.000007384913,0.0013801963,0.000028282237,0.0000208328],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986587,0.000044962577,0.00042083635,0.0001698121,0.0002445202,0.00046112234],"domain_scores_gemma":[0.99917835,0.000026373056,0.00022187282,0.00039263282,0.000042254786,0.0001385239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015355284,0.00027175463,0.00024209432,0.000059614038,0.00007378872,0.000056600067,0.00020990612,0.0002607338,0.000024980822],"category_scores_gemma":[0.000039087186,0.00022131045,0.00005286407,0.00013407311,0.000073512696,0.00002921119,0.00007268894,0.00017131449,0.000007651619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013148091,0.0007155168,0.5108263,0.0008484473,0.0004928517,0.000011806504,0.0036222823,0.04121608,0.41682604,0.0005316545,0.00783694,0.015757263],"study_design_scores_gemma":[0.008650892,0.00081996596,0.0797996,0.00029470416,0.00014293386,0.000045485314,0.0013055775,0.63372946,0.26291174,0.00017724573,0.010221281,0.0019011087],"about_ca_topic_score_codex":0.000041379488,"about_ca_topic_score_gemma":0.00008731133,"teacher_disagreement_score":0.5925134,"about_ca_system_score_codex":0.000050528903,"about_ca_system_score_gemma":0.000105979685,"threshold_uncertainty_score":0.9024778},"labels":[],"label_agreement":null},{"id":"W2145683333","doi":"10.1186/1471-2105-8-324","title":"Mining and state-space modeling and verification of sub-networks from large-scale biomolecular networks","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Component (thermodynamics); Context (archaeology); Cluster analysis; Biological network; Function (biology); Network model; Distributed computing; Gene regulatory network; DNA microarray; Systems biology; Data mining; Artificial intelligence; Bioinformatics; Biology","score_opus":0.008122024849831223,"score_gpt":0.21986943049142804,"score_spread":0.21174740564159683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145683333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48256135,0.0017863798,0.51550835,0.0000037946982,0.000028081964,0.00006785124,0.0000060095813,0.0000066889165,0.000031463074],"genre_scores_gemma":[0.919093,0.00078116026,0.07973776,0.000046547986,0.00008232753,0.0000024479689,0.00022277942,0.000019521149,0.00001442621],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886405,0.00002920535,0.000462972,0.00020863274,0.0001324962,0.00030263865],"domain_scores_gemma":[0.99919504,0.000025775653,0.00021450361,0.00035406236,0.00008925589,0.000121370584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051087135,0.00017443472,0.00021424428,0.00006955254,0.000085184576,0.00003146941,0.000103333026,0.00020590036,0.0000015417633],"category_scores_gemma":[0.00002392248,0.00017651008,0.000064610154,0.00016748715,0.00007780726,0.000011852855,0.00012917239,0.00006395998,4.5258346e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002358184,0.00007558948,0.06132728,0.0001448115,0.00030800045,0.0000018668094,0.0012164395,0.8795457,0.041358568,0.000043759257,0.00033967127,0.015402537],"study_design_scores_gemma":[0.0003955923,0.000051353545,0.002161405,0.000025235142,0.000069302136,0.00000369645,0.00068013684,0.9854831,0.010709901,0.000015775458,0.0002111267,0.00019335649],"about_ca_topic_score_codex":0.000012472919,"about_ca_topic_score_gemma":0.00016027289,"teacher_disagreement_score":0.4365317,"about_ca_system_score_codex":0.000009700389,"about_ca_system_score_gemma":0.000025774913,"threshold_uncertainty_score":0.7197872},"labels":[],"label_agreement":null},{"id":"W2145757848","doi":"10.1186/1471-2105-10-s1-s2","title":"Genome aliquoting with double cut and join","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Royal Society; Royal Society of Canada","keywords":"Genome; Sign (mathematics); Heuristic; Combinatorics; Genetics; Biology; Gene; Human genome; Computational biology; Mathematics; Computer science; Artificial intelligence","score_opus":0.012803395977688994,"score_gpt":0.2268005749068623,"score_spread":0.2139971789291733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145757848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9192895,0.0006457091,0.061633706,0.0001717425,0.000056092318,0.00053561846,0.0000123966565,0.000051665247,0.017603539],"genre_scores_gemma":[0.6640418,0.00027127963,0.3327975,0.00069502933,0.00026487408,0.000014541653,0.00024378495,0.000032947486,0.0016382261],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993229,0.000007224119,0.00019552158,0.0001239975,0.00011870646,0.00023168004],"domain_scores_gemma":[0.9995493,0.0000030955339,0.00008590897,0.00023669995,0.0000434313,0.00008152412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012674025,0.00013749815,0.00011147141,0.0000425385,0.00007074678,0.00005360029,0.00010658757,0.0000778548,0.000008060942],"category_scores_gemma":[0.0000057703655,0.00011168527,0.000028814362,0.000073399555,0.00003948029,0.0000095317955,0.0000520753,0.00005431332,0.000019249115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027712737,0.0010739627,0.079717904,0.0025880027,0.0013829252,0.000047399506,0.0111239515,0.009583924,0.7777722,0.0048961253,0.005452507,0.10358983],"study_design_scores_gemma":[0.036597464,0.014266641,0.25129667,0.00038504848,0.0007347377,0.0015661247,0.008488043,0.10880211,0.24500977,0.000958173,0.3247843,0.0071109207],"about_ca_topic_score_codex":0.0000021140959,"about_ca_topic_score_gemma":0.0000120568,"teacher_disagreement_score":0.5327624,"about_ca_system_score_codex":0.000008622177,"about_ca_system_score_gemma":0.00003998547,"threshold_uncertainty_score":0.4554393},"labels":[],"label_agreement":null},{"id":"W2146003645","doi":"10.1186/1471-2105-5-75","title":"Interaction profile-based protein classification of death domain","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"In silico; Protein–protein interaction; Computational biology; Computer science; Protein structure prediction; Protein structure; Homology modeling; Protein function prediction; Structural genomics; Protein domain; Protein family; Docking (animal); Macromolecular docking; Protein sequencing; Artificial intelligence; Bioinformatics; Biology; Peptide sequence; Genetics; Protein function; Biochemistry; Gene","score_opus":0.018933649688083556,"score_gpt":0.2507077440627499,"score_spread":0.23177409437466637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146003645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34455052,0.00004336056,0.64874107,0.000072258874,0.000113740076,0.0005644694,0.000026997766,0.000019727726,0.0058678696],"genre_scores_gemma":[0.73362625,0.000005013723,0.26575115,0.00010749426,0.0000759371,0.00004033215,0.0003086796,0.000013573534,0.00007158632],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900645,0.000016492895,0.00053037953,0.00010579393,0.0001475253,0.00019337732],"domain_scores_gemma":[0.99910206,0.0000064710057,0.00035484682,0.0003729272,0.000099779674,0.00006392469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022760271,0.00014828703,0.0001383824,0.000067942645,0.000059433947,0.00002680754,0.00017458624,0.00018015095,0.000011008537],"category_scores_gemma":[0.00003077533,0.00013279481,0.00009792184,0.0001008183,0.00006120378,0.000015123438,0.000048565093,0.00009596976,0.00003451197],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025054566,0.0018004257,0.0075689103,0.0054373085,0.0004939643,0.000004016696,0.0034401377,0.091030665,0.703801,0.1099845,0.0049546547,0.06897897],"study_design_scores_gemma":[0.008879742,0.0022382042,0.008903669,0.00065628806,0.000096310345,0.000071565955,0.0030699973,0.33868003,0.60043454,0.007535559,0.027868468,0.0015656148],"about_ca_topic_score_codex":0.0000070646747,"about_ca_topic_score_gemma":0.00001979686,"teacher_disagreement_score":0.3890757,"about_ca_system_score_codex":0.000039423936,"about_ca_system_score_gemma":0.00021454923,"threshold_uncertainty_score":0.5415215},"labels":[],"label_agreement":null},{"id":"W2146389940","doi":"10.1186/1471-2105-6-151","title":"AutoFACT: An Auto matic F unctional A nnotation and C lassification T ool","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":189,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Université de Montréal","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Perl; Annotation; Computer science; Software; Unix; Genomics; Functional genomics; Bioconductor; Computational biology; Information retrieval; Data mining; Programming language; Biology; Artificial intelligence; Genetics; Genome; Gene","score_opus":0.014767438856832656,"score_gpt":0.24020079870371533,"score_spread":0.22543335984688267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146389940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26548347,0.00028251077,0.72504383,0.00048364108,0.00029225825,0.0006524811,0.00006482346,0.000102229365,0.0075947647],"genre_scores_gemma":[0.66843516,0.0001041535,0.32792178,0.0009563377,0.00052594166,0.00004304252,0.0010489871,0.000030381088,0.0009342149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990202,0.000020775135,0.00044853482,0.00013931253,0.00015375977,0.00021739247],"domain_scores_gemma":[0.9992838,0.000011461246,0.00019256565,0.00031477198,0.00007339057,0.00012402124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026252476,0.00016657544,0.000121159195,0.00006321217,0.00013971527,0.000100278914,0.00012853833,0.00017781684,0.000032679123],"category_scores_gemma":[0.00003263434,0.00015336766,0.000047191497,0.00007731368,0.00006895676,0.000051137937,0.0000612017,0.00009061038,0.00008037572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054210506,0.00072902226,0.009468141,0.001377353,0.0003573374,0.0000010003745,0.0073683057,0.033957433,0.032401524,0.038784496,0.037093252,0.83792],"study_design_scores_gemma":[0.0007000092,0.00017126944,0.008722006,0.000015524385,0.000026310227,0.000037388985,0.00046531207,0.94940853,0.0006000809,0.0003878802,0.039181717,0.00028394346],"about_ca_topic_score_codex":0.0000025501352,"about_ca_topic_score_gemma":0.000042144584,"teacher_disagreement_score":0.9154511,"about_ca_system_score_codex":0.00002653783,"about_ca_system_score_gemma":0.00009549822,"threshold_uncertainty_score":0.62541515},"labels":[],"label_agreement":null},{"id":"W2146494984","doi":"10.1186/1471-2105-13-s19-s16","title":"A graph-theoretic approach for inparalog detection","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Gene duplication; Biology; Heuristic; Gene; Comparative genomics; Computational biology; Graph; Event (particle physics); Function (biology); Genome; Genetic algorithm; DNA microarray; Cluster analysis; Set (abstract data type); Evolutionary biology; Genomics; Genetics; Computer science; Theoretical computer science; Artificial intelligence","score_opus":0.017883537988364544,"score_gpt":0.2323048496636832,"score_spread":0.21442131167531867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146494984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20963569,0.0009101639,0.7843333,0.000006430101,0.00026016287,0.00045622545,0.000032774245,0.000008775225,0.0043564946],"genre_scores_gemma":[0.81995904,0.000094283874,0.1793204,0.00012079637,0.0002473216,0.0000932349,0.00006465914,0.000014458984,0.000085779895],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99932134,0.00001362323,0.00021194314,0.00009234857,0.00006366834,0.00029707744],"domain_scores_gemma":[0.9995568,0.0000136020135,0.00008414217,0.00022290612,0.000049196424,0.00007340077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022016808,0.00013058388,0.000111372174,0.00003875277,0.00010927983,0.000016727294,0.00010798012,0.000111233785,0.000001685487],"category_scores_gemma":[0.000053724434,0.00011361508,0.000107839915,0.000060730294,0.0000681862,0.0000020298266,0.000065186054,0.000036094592,0.000006759263],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001642814,0.0016955615,0.13545008,0.004571251,0.0015006922,2.3663277e-7,0.009521164,0.009105416,0.6911344,0.03193413,0.015624567,0.09781967],"study_design_scores_gemma":[0.008136842,0.003250884,0.049049955,0.00004017496,0.0006632004,0.0002203412,0.007107664,0.18624696,0.5134523,0.006106903,0.22200961,0.0037151624],"about_ca_topic_score_codex":0.0000014126927,"about_ca_topic_score_gemma":0.0000030209642,"teacher_disagreement_score":0.61032337,"about_ca_system_score_codex":0.0000074791296,"about_ca_system_score_gemma":0.000019008621,"threshold_uncertainty_score":0.46330884},"labels":[],"label_agreement":null},{"id":"W2148362397","doi":"10.1186/1471-2105-12-s8-s8","title":"Benchmarking of the 2010 BioCreative Challenge III text-mining competition by the BioGRID and MINT interaction databases","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Associazione Italiana per la Ricerca sul Cancro; Canadian Institutes of Health Research; European Commission","keywords":"Computer science; Annotation; Benchmarking; Identification (biology); Test set; Information retrieval; Normalization (sociology); Data curation; Named-entity recognition; Natural language processing; Set (abstract data type); Information extraction; Artificial intelligence; Database; Data mining; Task (project management)","score_opus":0.050830729813296054,"score_gpt":0.26690982688537845,"score_spread":0.2160790970720824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148362397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9364148,0.0024999348,0.048864916,0.0003722928,0.0009339366,0.00049821637,0.00023585216,0.00003557886,0.010144505],"genre_scores_gemma":[0.97034746,0.0006438484,0.028447898,0.00016129916,0.00009442329,0.000014921907,0.000151089,0.000008811549,0.00013021725],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993517,0.000044096945,0.00026689703,0.00010354047,0.00010380034,0.00012997874],"domain_scores_gemma":[0.99938226,0.00006255759,0.00022089902,0.00026110795,0.000041511325,0.000031675852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021278912,0.000109885,0.00010795686,0.000025702831,0.0001217517,0.000011947048,0.00017190416,0.000084129606,0.000020309666],"category_scores_gemma":[0.00010687807,0.000060539118,0.00005044866,0.00006846113,0.00038535247,0.000009949292,0.0002037945,0.00008833489,0.0000016604246],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011592057,0.0010614498,0.067469485,0.0015258268,0.00089688407,0.000002309684,0.043484915,0.000026999196,0.058795974,0.0057251686,0.091360345,0.7284914],"study_design_scores_gemma":[0.004551442,0.0035410668,0.09111501,0.0016246829,0.00046953114,0.00027683255,0.110049084,0.041834507,0.4450838,0.00029178595,0.29941884,0.0017434128],"about_ca_topic_score_codex":0.00008696426,"about_ca_topic_score_gemma":0.00011583664,"teacher_disagreement_score":0.72674805,"about_ca_system_score_codex":0.0000057079997,"about_ca_system_score_gemma":0.000027858789,"threshold_uncertainty_score":0.24687135},"labels":[],"label_agreement":null},{"id":"W2149205772","doi":"10.1186/1471-2105-12-328","title":"Classifying short genomic fragments from novel lineages using composition and homology","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic; Killam Trusts; Canada Research Chairs; Government of Canada; Genome Canada; Ontario Genomics; Ontario Genomics Institute","keywords":"Metagenomics; Taxonomic rank; Classifier (UML); Naive Bayes classifier; Artificial intelligence; Biology; Computer science; Rank (graph theory); Genome; Computational biology; Homology (biology); Bayes' theorem; Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Genetics; Support vector machine; Bayesian probability; Gene; Ecology","score_opus":0.06827311741666486,"score_gpt":0.25665656560547695,"score_spread":0.18838344818881209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149205772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9319423,0.0005723845,0.066450566,0.0000031579377,0.00015240387,0.0001259086,0.00007236974,0.0000045224606,0.0006763816],"genre_scores_gemma":[0.7523073,0.00018484548,0.24719971,0.00012651333,0.00008913083,0.000004151194,0.00006657157,0.000011795909,0.000009983369],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993372,0.000012018245,0.00026719173,0.00014895939,0.000054131084,0.00018052153],"domain_scores_gemma":[0.9996181,0.0000103297825,0.00008088483,0.00019749405,0.000036641904,0.000056551286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007107451,0.00014381547,0.00014620232,0.00003510783,0.000113466966,0.000019211659,0.000107063475,0.0001297639,0.000005779951],"category_scores_gemma":[0.000008313782,0.0001385823,0.000044121578,0.000027196947,0.000092347895,0.000002315734,0.00020237334,0.000053761007,0.0000041916173],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006013586,0.00007093243,0.10341615,0.00004825017,0.00015560156,8.182577e-7,0.0009172566,0.00020473127,0.89324147,0.00007190226,0.000047588277,0.0017651663],"study_design_scores_gemma":[0.0025637515,0.0006324041,0.6400582,0.00007757086,0.00034354063,0.00014335994,0.0023259942,0.14704785,0.2014248,0.00034982018,0.0036597345,0.0013729278],"about_ca_topic_score_codex":0.000039486626,"about_ca_topic_score_gemma":0.000017295008,"teacher_disagreement_score":0.6918167,"about_ca_system_score_codex":0.000011274384,"about_ca_system_score_gemma":0.00003127518,"threshold_uncertainty_score":0.5651222},"labels":[],"label_agreement":null},{"id":"W2149954962","doi":"10.1186/1471-2105-7-228","title":"A stable gene selection in microarray data analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene selection; Selection (genetic algorithm); Microarray analysis techniques; DNA microarray; Support vector machine; Computer science; Gene; Data mining; Significance analysis of microarrays; Microarray; Sample (material); Computational biology; Biology; Artificial intelligence; Genetics; Gene expression","score_opus":0.02232773026539993,"score_gpt":0.26402948074815574,"score_spread":0.2417017504827558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149954962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22373916,0.00044526963,0.76994807,0.000058837824,0.00009340797,0.00023847513,0.00009645036,0.000027940237,0.0053524175],"genre_scores_gemma":[0.8086453,0.00012397968,0.18448594,0.0001869585,0.00020097836,0.000025720177,0.004087811,0.00001668662,0.0022265825],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999253,0.000022869885,0.000285208,0.00018254714,0.00010119328,0.00015521444],"domain_scores_gemma":[0.9993722,0.0000037380023,0.00010728214,0.0004492078,0.000038873266,0.000028741586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001926141,0.000087891975,0.00010081171,0.00015437847,0.000041940126,0.000035843717,0.00023167927,0.00009625354,0.000022457974],"category_scores_gemma":[0.00001981122,0.00008275922,0.00004197379,0.00053280755,0.000018462022,0.000012565086,0.00008988152,0.00004562709,0.000013417548],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008675913,0.00017894134,0.12824573,0.00007781985,0.00011757364,3.2092754e-7,0.000082472405,0.022484738,0.805485,0.00014051661,0.040566187,0.0025339643],"study_design_scores_gemma":[0.0012237991,0.00007928676,0.11524057,0.000013007172,0.00019067351,0.000008668841,0.0002888941,0.46968597,0.27878827,0.000101252146,0.13387689,0.00050274783],"about_ca_topic_score_codex":0.00008793709,"about_ca_topic_score_gemma":0.0009769851,"teacher_disagreement_score":0.5854621,"about_ca_system_score_codex":0.00002043673,"about_ca_system_score_gemma":0.00008718816,"threshold_uncertainty_score":0.33748233},"labels":[],"label_agreement":null},{"id":"W2150756255","doi":"10.1186/1471-2105-10-106","title":"flowCore: a Bioconductor package for high throughput flow cytometry","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":651,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Terry Fox Research Institute; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Data mining; Data management; Throughput; Automation; Data science; Data flow diagram; Software engineering; Database; Operating system; Engineering","score_opus":0.021869838695404036,"score_gpt":0.2510222181838827,"score_spread":0.22915237948847866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150756255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2506156,0.00027719277,0.7462328,0.00014629826,0.0006794593,0.00066267006,0.0002748834,0.0000714894,0.0010395709],"genre_scores_gemma":[0.5172663,0.000110968314,0.4787593,0.0017133066,0.00064714893,0.000026338392,0.000916654,0.00003612833,0.00052385876],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987882,0.00001650545,0.00042931517,0.00022246774,0.00015409716,0.00038943463],"domain_scores_gemma":[0.9991469,0.000024248855,0.00011694233,0.00048957055,0.0001053571,0.000117021795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017380071,0.00025157156,0.00023805545,0.00007370491,0.00012628452,0.00007210846,0.00029134203,0.00027110055,0.000018596318],"category_scores_gemma":[0.00012326558,0.00022172563,0.00018740485,0.00015816004,0.00006438914,0.000017558828,0.000035573667,0.00009433247,0.000033213444],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000920502,0.0007132714,0.0026220137,0.0008249846,0.00023253387,0.0000037516172,0.00082263106,0.00052473566,0.8889667,0.0032914479,0.04044103,0.060636397],"study_design_scores_gemma":[0.0065405928,0.0033107148,0.003986221,0.000092111935,0.00016118707,0.00005532229,0.00040135244,0.055247184,0.8594603,0.0021091283,0.06694614,0.0016897795],"about_ca_topic_score_codex":0.0000042803226,"about_ca_topic_score_gemma":0.000011395328,"teacher_disagreement_score":0.26747352,"about_ca_system_score_codex":0.000021224698,"about_ca_system_score_gemma":0.000105424966,"threshold_uncertainty_score":0.9041709},"labels":[],"label_agreement":null},{"id":"W2150951857","doi":"10.1186/1471-2105-12-380","title":"iCTNet: A Cytoscape plugin to produce and analyze integrative complex traits networks","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Ontario Ministry of Research and Innovation; Multiple Sclerosis Society; National Multiple Sclerosis Society","keywords":"Plug-in; Biological network; Identification (biology); Computer science; Data integration; Visualization; Computational biology; Systems biology; Interface (matter); Data science; Biology; Data mining","score_opus":0.026278439747076315,"score_gpt":0.23801105044177925,"score_spread":0.21173261069470295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150951857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09318373,0.00043856353,0.8842378,0.000093704766,0.00023121353,0.0010856694,0.000077826284,0.000061026614,0.020590423],"genre_scores_gemma":[0.69221264,0.00016453813,0.30439803,0.0019576426,0.00031963628,0.000053865853,0.00024950146,0.000045923207,0.0005981844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856925,0.000033898687,0.00056717155,0.00024549014,0.00013519533,0.0004490064],"domain_scores_gemma":[0.9990157,0.000015733687,0.00019032216,0.0003999478,0.00011278489,0.00026553607],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032139526,0.0003175685,0.0002894898,0.00009453867,0.00013046847,0.000067863206,0.00031241516,0.00021959042,0.000041562304],"category_scores_gemma":[0.00005483449,0.00026128453,0.00009492104,0.00021585966,0.00012647745,0.000019371319,0.00026183046,0.00016664038,0.000037889513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003254029,0.0010988568,0.023611799,0.001630543,0.0019279949,0.000017048345,0.06795973,0.014214903,0.021454927,0.015858063,0.27552772,0.57344437],"study_design_scores_gemma":[0.0026588952,0.0021716075,0.05486779,0.00018856121,0.00018548762,0.00018903059,0.0050614276,0.8320484,0.0050182464,0.0006464543,0.09474998,0.0022141258],"about_ca_topic_score_codex":0.000012969504,"about_ca_topic_score_gemma":0.00016250872,"teacher_disagreement_score":0.8178335,"about_ca_system_score_codex":0.000016029291,"about_ca_system_score_gemma":0.000074229014,"threshold_uncertainty_score":0.99998397},"labels":[],"label_agreement":null},{"id":"W2151109259","doi":"10.1186/1471-2105-14-58","title":"Prediction of a time-to-event trait using genome wide SNP data","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute","keywords":"Single-nucleotide polymorphism; SNP; Genome-wide association study; Computational biology; Trait; Computer science; Event (particle physics); Biology; DNA microarray; Genome; Quantitative trait locus; Data mining; Genetics; Genotype; Gene","score_opus":0.054842597824317746,"score_gpt":0.2739561777448809,"score_spread":0.21911357992056316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151109259","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61160725,0.000081340724,0.38575006,0.000117535696,0.000087129374,0.00049018016,0.00048079825,0.00001379436,0.0013718997],"genre_scores_gemma":[0.36463964,0.000066656576,0.6296061,0.0008927159,0.0002652091,0.00003443217,0.0030385887,0.00003521392,0.0014214115],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902236,0.00003765285,0.0004902347,0.00014248797,0.00009712646,0.00021014483],"domain_scores_gemma":[0.9990028,0.000024422501,0.00020793827,0.00058113114,0.00009912748,0.00008456819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003308605,0.0001062664,0.00016901044,0.000050009825,0.00004873886,0.0000125768365,0.0003039106,0.00013807796,0.00013266875],"category_scores_gemma":[0.00030807563,0.0000976798,0.000051383522,0.00008740437,0.000037166414,0.0000113880205,0.00026313736,0.000043827167,0.00015504242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011858496,0.0006035118,0.21219759,0.0008021523,0.00089127035,6.4436665e-7,0.0016664376,0.14862135,0.41526443,0.000060494596,0.19599494,0.023778612],"study_design_scores_gemma":[0.00055075006,0.0003318401,0.19204898,0.000024329376,0.00006863518,0.000014281993,0.0003131536,0.77889556,0.0010759461,0.00008678609,0.026328608,0.00026115493],"about_ca_topic_score_codex":0.000037992537,"about_ca_topic_score_gemma":0.00000799806,"teacher_disagreement_score":0.6302742,"about_ca_system_score_codex":0.000017135455,"about_ca_system_score_gemma":0.00009511025,"threshold_uncertainty_score":0.39832667},"labels":[],"label_agreement":null},{"id":"W2151432781","doi":"10.1186/1471-2105-7-516","title":"Integrated siRNA design based on surveying of features associated with high RNAi effectiveness","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Interference and Gene Delivery","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Graduate School, University of Minnesota; Ryerson University; University of Minnesota","keywords":"RNA interference; Computational biology; DNA microarray; Computer science; Interference (communication); Biology; Bioinformatics; Genetics; Gene; Telecommunications; Gene expression; RNA","score_opus":0.014586936844769409,"score_gpt":0.22038578861930821,"score_spread":0.2057988517745388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151432781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7581559,0.000041280582,0.24048626,0.000005384249,0.000072258365,0.0002546951,0.000060760827,0.000020370166,0.0009031287],"genre_scores_gemma":[0.98684615,0.000004691656,0.012368987,0.000074258896,0.000026521593,0.0000128327865,0.0005348793,0.000016129728,0.000115537965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990743,0.0001570929,0.00026350355,0.00013332261,0.00017493704,0.00019688529],"domain_scores_gemma":[0.99916345,0.00013529848,0.00019836173,0.00025655128,0.00021326542,0.00003305426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000412179,0.00018530923,0.0002058378,0.00007866558,0.000051910574,0.00002838536,0.00016650707,0.00016900797,0.000005901021],"category_scores_gemma":[0.00015886471,0.00013643851,0.00006920266,0.00016764211,0.000070005844,0.000007935966,0.000023954844,0.000093523544,0.0000051536454],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068181735,0.0013816612,0.13407518,0.00085369596,0.0005975219,0.000015480928,0.00017816306,0.554166,0.28351462,0.00039010393,0.012272075,0.0057373163],"study_design_scores_gemma":[0.0021441136,0.002329517,0.19377932,0.0004331566,0.000056064837,0.000005085609,0.0000991794,0.05869575,0.74187005,0.00005324472,0.00009367418,0.00044083755],"about_ca_topic_score_codex":0.00013031432,"about_ca_topic_score_gemma":0.00014830405,"teacher_disagreement_score":0.49547026,"about_ca_system_score_codex":0.000026502552,"about_ca_system_score_gemma":0.00014647351,"threshold_uncertainty_score":0.5563801},"labels":[],"label_agreement":null},{"id":"W2152436336","doi":"10.1186/1471-2105-11-105","title":"Free energy estimation of short DNA duplex hybridizations","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"DNA microarray; Duplex (building); DNA; Computational biology; Biology; Genetics; Gene; Gene expression","score_opus":0.012044819640651365,"score_gpt":0.24810138362208925,"score_spread":0.23605656398143787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152436336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17612162,0.000045205597,0.81476665,0.000075337004,0.00036388752,0.00012564148,0.00006494178,0.000026406691,0.008410307],"genre_scores_gemma":[0.91568285,0.000041832966,0.08323415,0.00011253801,0.000088608846,0.000021024553,0.00042141668,0.000011633036,0.00038593807],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993612,0.000010491406,0.00029691117,0.00009440257,0.00013253359,0.00010444996],"domain_scores_gemma":[0.9991848,0.0000073615583,0.000112863236,0.0005384926,0.00010031592,0.00005618934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008875747,0.00008807854,0.000080990016,0.00006146615,0.000052962616,0.000016730268,0.00021418034,0.000112969195,0.000037244306],"category_scores_gemma":[0.00014136884,0.000081664606,0.000053541382,0.000111527166,0.000057843765,0.000009860403,0.0000749965,0.000049171416,0.000004212214],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030758372,0.00009320209,0.0013242061,0.000096684,0.000024350775,8.916115e-8,0.000118832824,0.0052035265,0.92877364,0.008118226,0.030486664,0.02572984],"study_design_scores_gemma":[0.00036287145,0.000073967785,0.0030279215,0.00001244535,0.000019552415,0.000008833363,0.00009563653,0.2504516,0.6969464,0.00035267186,0.04845147,0.00019664897],"about_ca_topic_score_codex":0.0000045267884,"about_ca_topic_score_gemma":0.00004790212,"teacher_disagreement_score":0.73956126,"about_ca_system_score_codex":0.000004712045,"about_ca_system_score_gemma":0.00011788895,"threshold_uncertainty_score":0.3330186},"labels":[],"label_agreement":null},{"id":"W2152809196","doi":"10.1186/1471-2105-12-s9-s10","title":"The evolution of the tape measure protein: units, duplications and losses","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Gene duplication; Heuristic; Measure (data warehouse); Sequence (biology); Genome; Lineage (genetic); Biology; Computational biology; Genetics; Divergence (linguistics); Similarity (geometry); Genomics; Gene; Algorithm; Computer science; Artificial intelligence; Data mining; Image (mathematics)","score_opus":0.021874249157548,"score_gpt":0.1984610059880758,"score_spread":0.17658675683052782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152809196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88790745,0.00020125424,0.030188058,0.0005560549,0.00032859851,0.0015384365,0.00006361348,0.000058316597,0.07915823],"genre_scores_gemma":[0.9903718,0.000015726466,0.008560576,0.0000332366,0.000007948185,0.000017979171,0.0000011592739,0.000003883351,0.000987661],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999626,0.000015754582,0.0001626538,0.000038942042,0.00007214192,0.00008450289],"domain_scores_gemma":[0.9995899,0.000019161418,0.000117338175,0.0002310503,0.000020297428,0.000022252723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009660181,0.000050167466,0.000038662212,0.0000072753464,0.00026600566,0.0000190976,0.00016723087,0.0000285698,0.00009799655],"category_scores_gemma":[0.000054495827,0.000026751073,0.00002122275,0.00016786646,0.00023287168,0.00018842454,0.000116858275,0.000062428335,0.000058392827],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026477603,0.0009332593,0.15850109,0.0007438347,0.00025024623,6.013666e-7,0.05394629,0.0005326515,0.49405316,0.09574112,0.03564013,0.15939285],"study_design_scores_gemma":[0.00027258042,0.00007959229,0.9248954,0.000088038796,0.00005349793,0.000036913458,0.004967856,0.009301029,0.015141955,0.0009834291,0.04395939,0.00022030833],"about_ca_topic_score_codex":0.0003365515,"about_ca_topic_score_gemma":0.0006714654,"teacher_disagreement_score":0.7663943,"about_ca_system_score_codex":0.000044487908,"about_ca_system_score_gemma":0.000022629432,"threshold_uncertainty_score":0.20459273},"labels":[],"label_agreement":null},{"id":"W2153531183","doi":"10.1186/1471-2105-14-82","title":"Learning a peptide-protein binding affinity predictor with kernel ridge regression","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Government of Ontario; Compute Canada","keywords":"Kernel (algebra); Affinities; Regression; Ridge; Kernel method; Binding affinities; Value (mathematics)","score_opus":0.013916969751074464,"score_gpt":0.21455401098658966,"score_spread":0.2006370412355152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153531183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97809434,0.00008094479,0.015852563,0.00003944798,0.000058435617,0.00060057634,0.000015567752,0.00006301461,0.0051951236],"genre_scores_gemma":[0.8590168,0.00007474091,0.13621682,0.000111692076,0.00017434137,0.00015190785,0.0006090881,0.00005776661,0.003586875],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986564,0.00003368617,0.0004944309,0.00016497575,0.00024319589,0.00040732356],"domain_scores_gemma":[0.9989319,0.000015028074,0.0003395887,0.00044468054,0.00013330557,0.00013551614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023287868,0.00028788485,0.00022129479,0.00008186563,0.00023390121,0.00017118744,0.0002901192,0.00019788093,0.000057736324],"category_scores_gemma":[0.00011386079,0.00019901663,0.00009642689,0.00015329152,0.000062177394,0.00006308327,0.00023035721,0.00024142743,0.00023287506],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022555238,0.0015680959,0.22243579,0.009512624,0.0017852392,0.000012200159,0.015724983,0.017281424,0.5472124,0.0022827694,0.10700855,0.07292037],"study_design_scores_gemma":[0.010015309,0.0064244247,0.041328408,0.001532446,0.00020498419,0.000329906,0.031611815,0.60534495,0.25056294,0.00016469744,0.04872343,0.0037566994],"about_ca_topic_score_codex":0.000020325113,"about_ca_topic_score_gemma":0.000007560768,"teacher_disagreement_score":0.5880635,"about_ca_system_score_codex":0.0000219354,"about_ca_system_score_gemma":0.00010696564,"threshold_uncertainty_score":0.8115663},"labels":[],"label_agreement":null},{"id":"W2153542855","doi":"10.1186/1471-2105-13-s19-s5","title":"Medians seek the corners, and other conjectures","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational biology; Biology","score_opus":0.017517362560641996,"score_gpt":0.2381653842075965,"score_spread":0.22064802164695452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153542855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8358201,0.011308549,0.102556445,0.00059185096,0.0011667339,0.0015900286,0.0001875253,0.000097752265,0.04668101],"genre_scores_gemma":[0.9240016,0.00038041742,0.068183325,0.004382892,0.0010938077,0.00004574665,0.000116260446,0.000055024528,0.0017409376],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994672,0.000019521187,0.00013665509,0.00005703911,0.00009537008,0.00022424741],"domain_scores_gemma":[0.99961036,0.000015988026,0.000059106776,0.00022245424,0.000018627688,0.000073441784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002067534,0.0001015643,0.000069399124,0.000018124372,0.00006732573,0.000026967115,0.00011674041,0.00007776143,0.000025595304],"category_scores_gemma":[0.00003909303,0.00006422785,0.000033716602,0.000039012382,0.0001024436,0.000005254334,0.00007929298,0.000050995484,0.000042497995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002380535,0.0004306763,0.64921474,0.0011896875,0.0010836826,0.0000018112526,0.029141374,0.0005515237,0.048659198,0.0063808705,0.19102699,0.0720814],"study_design_scores_gemma":[0.001136361,0.00020197302,0.02131391,0.000015088864,0.00008545859,0.00010274249,0.0043733506,0.007058533,0.009944755,0.00009558969,0.9551529,0.000519312],"about_ca_topic_score_codex":0.000005355294,"about_ca_topic_score_gemma":0.0000140778275,"teacher_disagreement_score":0.76412594,"about_ca_system_score_codex":0.0000045226952,"about_ca_system_score_gemma":0.000021523323,"threshold_uncertainty_score":0.26191357},"labels":[],"label_agreement":null},{"id":"W2154003902","doi":"10.1186/s12859-015-0788-5","title":"Evaluation of shotgun metagenomics sequence classification methods using in silico and in vitro simulated communities","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Public Health Agency; Michael Smith Health Research BC; Public Health Agency of Canada; Canadian Institutes of Health Research; University of Connecticut; Genome Canada; Genome British Columbia","keywords":"In silico; Metagenomics; Shotgun; Computational biology; Shotgun sequencing; Biology; DNA microarray; Bioinformatics; Sequence (biology); Computer science; Data mining; Genetics; DNA sequencing; Gene","score_opus":0.2892683905235093,"score_gpt":0.40553302523698453,"score_spread":0.11626463471347526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154003902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99204504,0.0011573776,0.006238217,0.0000062528497,0.000042580727,0.00023420546,0.000016007492,0.0000012878918,0.000259055],"genre_scores_gemma":[0.8592702,0.000116310184,0.14053227,0.000021418055,0.000008199878,0.000004771251,0.00003862672,0.0000060014245,0.0000021843637],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905056,0.00023824733,0.00038752606,0.00007196833,0.00013621649,0.00011545602],"domain_scores_gemma":[0.9993382,0.000039515973,0.00015008873,0.00022087063,0.00021979242,0.00003152463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022125873,0.000096950964,0.00016373734,0.00009322071,0.000023178192,0.00001251763,0.000098650184,0.00009207546,5.8437604e-7],"category_scores_gemma":[0.0001958385,0.00009618868,0.000022564951,0.00011025326,0.00008820327,0.00000391511,0.00009959427,0.00005386538,2.742753e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011616065,0.00004984572,0.015768865,0.00007991403,0.000044628803,7.9535845e-8,0.004212593,0.1430095,0.8231382,0.000034767698,0.000003394487,0.013542074],"study_design_scores_gemma":[0.0007294579,0.000040308143,0.006704669,0.000010707606,0.00004193608,0.0000027186668,0.005153257,0.93972176,0.047158573,0.00025946257,0.00006907407,0.000108071865],"about_ca_topic_score_codex":0.00012067527,"about_ca_topic_score_gemma":0.00021466592,"teacher_disagreement_score":0.7967123,"about_ca_system_score_codex":0.000053531516,"about_ca_system_score_gemma":0.00019856283,"threshold_uncertainty_score":0.39224607},"labels":[],"label_agreement":null},{"id":"W2154496386","doi":"10.1186/s12859-015-0770-2","title":"Whole genome SNP genotype piecemeal imputation","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Imputation (statistics); SNP; Genotype; Single-nucleotide polymorphism; Biology; Genome-wide association study; SNP genotyping; Computational biology; Genetics; Statistics; Computer science; Mathematics; Missing data; Gene","score_opus":0.03597789474738615,"score_gpt":0.2812938896453417,"score_spread":0.24531599489795552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154496386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4408313,0.0005581458,0.5442134,0.00031384567,0.00048698625,0.00035944305,0.000090365356,0.00005024988,0.013096249],"genre_scores_gemma":[0.6085464,0.0000860735,0.3846892,0.0013546047,0.00060981367,0.000032479467,0.002196707,0.000036184538,0.0024485225],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990803,0.000046674064,0.00035975728,0.00012725402,0.0001230452,0.0002629448],"domain_scores_gemma":[0.9992492,0.000013716816,0.0001690153,0.00026569664,0.00016362549,0.0001387345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043489668,0.00012467954,0.00014045625,0.000043846918,0.000067148016,0.000023401297,0.0001526095,0.00018505128,0.000010144114],"category_scores_gemma":[0.00029497544,0.000115648785,0.00006397495,0.000090776906,0.000044166933,0.0000069319353,0.000099540564,0.00006252787,0.00030520142],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063448295,0.0006790202,0.31568733,0.000512363,0.00078433915,0.000006465962,0.008649947,0.24087018,0.07112277,0.002778829,0.31073588,0.047538396],"study_design_scores_gemma":[0.0035359776,0.0014949192,0.16724426,0.0000128147685,0.0001046433,0.00007569722,0.0033035232,0.2222269,0.00094130775,0.00243657,0.5974972,0.0011261522],"about_ca_topic_score_codex":0.000012480429,"about_ca_topic_score_gemma":0.000036252393,"teacher_disagreement_score":0.28676137,"about_ca_system_score_codex":0.000032989134,"about_ca_system_score_gemma":0.00019716781,"threshold_uncertainty_score":0.47160205},"labels":[],"label_agreement":null},{"id":"W2154714551","doi":"10.1186/1471-2105-11-114","title":"OrgConv: detection of gene conversion using consensus sequences and its application in plant mitochondrial and chloroplast homologs","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Photosynthetic Processes and Mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Lilly Endowment; Eli Lilly and Company","keywords":"Genome; Biology; Gene; Computational biology; Chloroplast; Phylogenetic tree; Genetics; Homologous recombination; Plastid; Mitochondrial DNA; Sequence alignment; Homologous chromosome; Peptide sequence","score_opus":0.010293527756984836,"score_gpt":0.22312425727802512,"score_spread":0.2128307295210403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154714551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828263,0.00006896127,0.016703717,0.0000056830927,0.00013219847,0.0001962777,0.000035735815,0.0000044011354,0.000026728121],"genre_scores_gemma":[0.9886172,0.00008819887,0.011207333,0.000018158536,0.000031927244,0.0000059140925,0.000022784245,0.000004642761,0.000003852137],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99953747,0.000008224667,0.0001949191,0.000102703234,0.000057318543,0.0000993844],"domain_scores_gemma":[0.9996859,0.000013819085,0.00012682183,0.000091793874,0.00004111748,0.000040566112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000091265014,0.00008046238,0.00009840495,0.000044556797,0.000038842863,0.000008686064,0.00004839472,0.00014231952,0.0000010143615],"category_scores_gemma":[0.00005700971,0.00007285601,0.000013666625,0.000045005076,0.00006733488,0.0000064411906,0.00004181552,0.0000620298,6.1705964e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006160859,0.000009571728,0.00021422676,0.00009064709,0.0000038514986,2.597198e-7,0.000074610405,0.000013624503,0.9989458,0.000049380003,5.4610956e-7,0.0005358997],"study_design_scores_gemma":[0.00044664307,0.000092424365,0.00011475403,0.000011181283,0.000010074842,0.00013375771,0.00019357428,0.08166923,0.91705734,0.000040374987,0.000147732,0.00008290848],"about_ca_topic_score_codex":0.00003493826,"about_ca_topic_score_gemma":0.00017061323,"teacher_disagreement_score":0.08188843,"about_ca_system_score_codex":0.0000040879445,"about_ca_system_score_gemma":0.000055956567,"threshold_uncertainty_score":0.2970982},"labels":[],"label_agreement":null},{"id":"W2155233998","doi":"10.1186/1471-2105-11-354","title":"Nonparametric methods for the analysis of single-color pathogen microarrays","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Eye Institute; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Nonparametric statistics; DNA microarray; Normality; Pearson product-moment correlation coefficient; Computational biology; Exact test; Statistics; Computer science; Biology; Pattern recognition (psychology); Bioinformatics; Mathematics; Artificial intelligence; Genetics","score_opus":0.03156090557645123,"score_gpt":0.3328618730589619,"score_spread":0.3013009674825107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155233998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051776946,0.0002340702,0.94659835,0.000055145552,0.0002801972,0.00031704493,0.000075238124,0.000007639526,0.00065537274],"genre_scores_gemma":[0.13958633,0.00005478741,0.85947704,0.00021403788,0.00008428642,0.000084327134,0.00021313217,0.000012303626,0.00027373806],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999318,0.000028686305,0.00032856187,0.00011211402,0.00008012727,0.00013251333],"domain_scores_gemma":[0.9989199,0.0001236334,0.00024935525,0.0005157267,0.00014886462,0.00004253705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004995612,0.00009487501,0.00015113386,0.0001638517,0.00007279333,0.00002373188,0.00027064056,0.00014011738,0.000019048539],"category_scores_gemma":[0.00039030603,0.00006360599,0.00022138972,0.0006049077,0.00007285752,0.0000039783476,0.000052970576,0.00005930893,0.0000017388041],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031493302,0.000034598932,0.0004752289,0.000028574985,0.00015945685,4.9883493e-9,0.00008339209,0.00036454046,0.96012324,0.00012083534,0.00087156915,0.037707094],"study_design_scores_gemma":[0.0004061086,0.00012594892,0.0049411906,0.0000030939625,0.0006498748,0.0000017210897,0.00034914428,0.17260924,0.6682136,0.000047477188,0.15247989,0.00017268576],"about_ca_topic_score_codex":0.000002345506,"about_ca_topic_score_gemma":0.00002289355,"teacher_disagreement_score":0.29190958,"about_ca_system_score_codex":0.0000053872536,"about_ca_system_score_gemma":0.00006610571,"threshold_uncertainty_score":0.25937772},"labels":[],"label_agreement":null},{"id":"W2155875572","doi":"10.1186/1471-2105-13-s5-s5","title":"Parametric modeling of cellular state transitions as measured with flow cytometry","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Science Council","keywords":"Outlier; Parametric statistics; Computer science; Skew; Gaussian; Biological system; Principle of maximum entropy; Nonparametric statistics; Robustness (evolution); Algorithm; Greedy algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence; Biology; Statistics; Physics","score_opus":0.02444447794471104,"score_gpt":0.2245223470422727,"score_spread":0.20007786909756164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155875572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36571854,0.0003359614,0.63276505,0.0000051275188,0.00007578162,0.00012968716,0.000038143837,0.00001316789,0.0009184945],"genre_scores_gemma":[0.8997829,0.000058458285,0.09982849,0.00006456737,0.000057014917,0.000006376118,0.00013043468,0.000020431182,0.000051316663],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897045,0.000025710142,0.00036566227,0.00009749241,0.00023458854,0.00030607713],"domain_scores_gemma":[0.9993386,0.000011494422,0.00009710883,0.00029203668,0.00012678442,0.00013396367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002351103,0.00016547843,0.00018924732,0.00013647147,0.00006609918,0.000018781006,0.00013871778,0.00012556756,0.000009908854],"category_scores_gemma":[0.000042099942,0.00013857808,0.000103442704,0.0003227112,0.00006024913,0.000020142039,0.000018156312,0.00009392654,0.000014697878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014229002,0.0015790629,0.030347114,0.0019949465,0.0006504561,0.0000030902124,0.0060716216,0.4422296,0.50495,0.0002916113,0.0003390554,0.010120588],"study_design_scores_gemma":[0.0013740188,0.00047236163,0.00021768046,0.00005222228,0.000115571565,0.000027149812,0.00062888983,0.8085674,0.18737899,0.000038185386,0.00068622833,0.00044129402],"about_ca_topic_score_codex":0.000016421267,"about_ca_topic_score_gemma":0.000012954989,"teacher_disagreement_score":0.53406435,"about_ca_system_score_codex":0.0000123243235,"about_ca_system_score_gemma":0.00009889803,"threshold_uncertainty_score":0.56510496},"labels":[],"label_agreement":null},{"id":"W2156995746","doi":"10.1186/1471-2105-10-316","title":"Unsupervised statistical clustering of environmental shotgun sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Burroughs Wellcome Fund","keywords":"Cluster analysis; Computer science; Shotgun sequencing; Dimensionality reduction; Unsupervised learning; Pairwise comparison; Statistical model; Pattern recognition (psychology); Artificial intelligence; Computational biology; Data mining; Genome; Biology; Genetics","score_opus":0.013628305682145651,"score_gpt":0.22951481145326502,"score_spread":0.21588650577111937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156995746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91971767,0.0006163467,0.075548366,0.000034221608,0.00010547399,0.00019946534,0.00023788658,0.000004798731,0.00353579],"genre_scores_gemma":[0.89196193,0.00021897114,0.1075342,0.00014215882,0.0000422017,0.000001998809,0.00005093668,0.00000484677,0.000042763833],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99937034,0.000011531485,0.000273054,0.00009282796,0.00009815818,0.00015409716],"domain_scores_gemma":[0.99967706,0.000011096065,0.000070972295,0.00018212608,0.000011240833,0.000047488847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007784682,0.00010663289,0.00012391008,0.000021238433,0.00004355293,0.000010077153,0.0001245296,0.00006232572,0.00001891873],"category_scores_gemma":[0.000018091074,0.000094753384,0.000047015554,0.000025266676,0.000082713006,0.0000012202726,0.00006349886,0.000031735606,0.0000068259574],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020836414,0.0002523105,0.02340457,0.00023382241,0.00014930662,0.0000023785462,0.0014615492,0.005043972,0.90614337,0.0009357831,0.0010717383,0.06109283],"study_design_scores_gemma":[0.0042301556,0.0049512344,0.55255246,0.00009124674,0.00020072686,0.00011908177,0.0057293763,0.22449964,0.18136543,0.001989639,0.022361914,0.0019090872],"about_ca_topic_score_codex":0.0000021140481,"about_ca_topic_score_gemma":0.0000062507465,"teacher_disagreement_score":0.72477794,"about_ca_system_score_codex":0.0000067700093,"about_ca_system_score_gemma":0.000028077668,"threshold_uncertainty_score":0.38639307},"labels":[],"label_agreement":null},{"id":"W2157031164","doi":"10.1186/1471-2105-11-60","title":"Testing for mean and correlation changes in microarray experiments: an application for pathway analysis","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Health Canada","funders":"","keywords":"DNA microarray; Rank (graph theory); Microarray analysis techniques; Correlation; Microarray; Computational biology; Gene; Rank correlation; Function (biology); Representation (politics); Computer science; Set (abstract data type); Biological pathway; Biology; Genetics; Mathematics; Gene expression; Machine learning","score_opus":0.0178437617757931,"score_gpt":0.260471605891446,"score_spread":0.2426278441156529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157031164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2654561,0.00006338693,0.73326415,0.000021097489,0.00009903656,0.0008590061,0.00007448032,0.000012957111,0.00014975946],"genre_scores_gemma":[0.5684691,0.0000066344674,0.42956218,0.000189146,0.00017474835,0.0002774201,0.0012647687,0.000017273243,0.000038718623],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999258,0.0000073016954,0.0003285682,0.00014998327,0.00005394604,0.00020222156],"domain_scores_gemma":[0.9993282,0.000041355102,0.0001980292,0.00027220437,0.000093124814,0.00006711302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003859834,0.0001310855,0.00015078869,0.000105328014,0.0000952815,0.000047347945,0.000113314505,0.00019370594,0.0000012979799],"category_scores_gemma":[0.000065083565,0.00012548263,0.00005165024,0.00014879661,0.000039516253,0.000017167666,0.000037828064,0.00006438798,8.1429613e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003402028,0.00024640298,0.049404148,0.0006880103,0.00031761118,8.738674e-8,0.005274317,0.00822438,0.6934173,0.0026775515,0.00043003264,0.23897997],"study_design_scores_gemma":[0.000897631,0.00027902523,0.0029857166,0.00000712555,0.00007059412,0.0000027944,0.00072788016,0.97749984,0.0123578375,0.0002637974,0.004656579,0.00025119018],"about_ca_topic_score_codex":0.0000088627685,"about_ca_topic_score_gemma":0.0012691338,"teacher_disagreement_score":0.9692755,"about_ca_system_score_codex":0.000008662453,"about_ca_system_score_gemma":0.00003991285,"threshold_uncertainty_score":0.5117033},"labels":[],"label_agreement":null},{"id":"W2157075067","doi":"10.1186/1471-2105-9-s10-o6","title":"Ranking single nucleotide polymorphisms by potential deleterious effects","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Single-nucleotide polymorphism; SNP genotyping; Genotyping; Biology; Computational biology; Human genome; Genetics; Mendelian inheritance; Genome-wide association study; DNA microarray; Genetic association; Bioinformatics; Genome; Gene; Genotype","score_opus":0.010665789022997446,"score_gpt":0.2159110418210307,"score_spread":0.20524525279803327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157075067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81524795,0.0004940347,0.18222062,0.00006208748,0.00035180702,0.00018589167,0.000022669703,0.0000309102,0.0013840105],"genre_scores_gemma":[0.9262876,0.00018997471,0.07136379,0.0010171958,0.00022758168,0.000014531691,0.00027589846,0.000025250662,0.00059815345],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988948,0.000061905565,0.00038626455,0.00016123928,0.00012881833,0.0003669566],"domain_scores_gemma":[0.99933994,0.000030175877,0.00019227271,0.00028995084,0.00005198377,0.00009565498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015878664,0.00017488019,0.00020769179,0.000040293093,0.00020547745,0.0000174115,0.00018213116,0.00021117616,0.000013614331],"category_scores_gemma":[0.00014956742,0.0001668294,0.00012742818,0.00007303158,0.000101887235,0.000006868185,0.00010456426,0.00007779197,0.000069539215],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018041432,0.00049981603,0.08372514,0.0002593559,0.0003543818,0.000024837587,0.0009418411,0.002500592,0.643239,0.000058761383,0.24465965,0.023556173],"study_design_scores_gemma":[0.015542122,0.0062114536,0.19091415,0.00018857383,0.0004944092,0.0024413913,0.0010131957,0.19574131,0.2965777,0.00065950106,0.2847991,0.005417105],"about_ca_topic_score_codex":0.000019037894,"about_ca_topic_score_gemma":0.0000075815724,"teacher_disagreement_score":0.34666136,"about_ca_system_score_codex":0.000023014796,"about_ca_system_score_gemma":0.000058934882,"threshold_uncertainty_score":0.68031055},"labels":[],"label_agreement":null},{"id":"W2158055157","doi":"10.1186/1471-2105-14-s15-s7","title":"Phase change for the accuracy of the median value in estimating divergence time","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Divergence (linguistics); Statistics; Phase (matter); Value (mathematics); Mathematics; Computer science; Physics","score_opus":0.03238774637538646,"score_gpt":0.27991624986510255,"score_spread":0.24752850348971608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158055157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.806235,0.00080742076,0.18315029,0.0016060837,0.0009876788,0.0062902216,0.00018155108,0.000024998084,0.0007167397],"genre_scores_gemma":[0.5738331,0.0001537824,0.42330483,0.0007126885,0.0005629764,0.00079680374,0.00015272718,0.00004195576,0.00044114457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993114,0.000019363059,0.00028313388,0.00007413602,0.00012486047,0.00018713051],"domain_scores_gemma":[0.99929076,0.00008552521,0.00018418043,0.00034493537,0.00006470702,0.000029868635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023937554,0.00009768807,0.00009370494,0.00002383678,0.000070803944,0.000019713543,0.00038170695,0.000062789775,0.000028125514],"category_scores_gemma":[0.00036311778,0.00005676977,0.000074645766,0.00010231369,0.000068932066,0.000014484503,0.0001725865,0.000048733316,0.000029510655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020539157,0.001512335,0.020518148,0.0034616927,0.0005368419,7.6911294e-7,0.025309894,0.019906553,0.22204022,0.0006681363,0.03045185,0.67538816],"study_design_scores_gemma":[0.0009666038,0.00012586718,0.0015058473,0.000033110457,0.000019358276,0.0000019529634,0.00038895314,0.98633367,0.008732813,0.00013468864,0.0016435086,0.00011361739],"about_ca_topic_score_codex":0.00004862668,"about_ca_topic_score_gemma":0.000012755953,"teacher_disagreement_score":0.96642715,"about_ca_system_score_codex":0.000009293272,"about_ca_system_score_gemma":0.00004302735,"threshold_uncertainty_score":0.23150042},"labels":[],"label_agreement":null},{"id":"W2158386569","doi":"10.1186/1471-2105-6-305","title":"The Gene Set Builder: collation, curation, and distribution of sets of genes","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Child and Family Research Institute","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Ensembl; Computer science; Identifier; Set (abstract data type); Gene nomenclature; Unique identifier; Database; Table (database); World Wide Web; Gene; Genome; Genomics; Biology; Genetics; Programming language","score_opus":0.009980879081941396,"score_gpt":0.23682597894491675,"score_spread":0.22684509986297535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158386569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64597374,0.003850171,0.34805253,0.00027534206,0.00016821598,0.00054364005,0.00041445854,0.000012621093,0.00070926314],"genre_scores_gemma":[0.95709354,0.0019521646,0.039875034,0.00007147003,0.00011773426,0.000007980908,0.00077567296,0.000009248936,0.00009716549],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991156,0.000016651924,0.00055414793,0.0000624592,0.00011547958,0.00013568453],"domain_scores_gemma":[0.99916416,0.000028542363,0.000336166,0.0002590869,0.000170395,0.000041663472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028340833,0.000100977115,0.00012106052,0.000017044818,0.00011601964,0.000022941786,0.00012182862,0.00011078314,0.0000020786958],"category_scores_gemma":[0.00004395606,0.000074821495,0.000047735164,0.000078520985,0.00013764862,0.00001684654,0.00008142717,0.000038048063,0.0000021351111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009812263,0.0003504328,0.056878883,0.002276083,0.0009399944,3.7577345e-7,0.005444043,0.08209944,0.06310171,0.036736418,0.12774356,0.62344784],"study_design_scores_gemma":[0.0018122343,0.0004174465,0.012105377,0.000052517917,0.000095736505,0.000053263437,0.0011624795,0.682265,0.104605734,0.00080927525,0.196115,0.00050596043],"about_ca_topic_score_codex":0.000003374461,"about_ca_topic_score_gemma":0.00004219514,"teacher_disagreement_score":0.6229419,"about_ca_system_score_codex":0.000008462821,"about_ca_system_score_gemma":0.00007696337,"threshold_uncertainty_score":0.3051132},"labels":[],"label_agreement":null},{"id":"W2158564991","doi":"10.1186/1471-2105-8-239","title":"Probabilistic prediction and ranking of human protein-protein interactions","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Ranking (information retrieval); Computer science; Probabilistic logic; Bayes' theorem; Naive Bayes classifier; False positive rate; Set (abstract data type); False discovery rate; Bayesian probability; Data mining; Machine learning; Protein–protein interaction; Protein function prediction; Human proteome project; Bayesian network; Interaction network; Function (biology); Computational biology; Artificial intelligence; Protein function; Proteomics; Biology; Support vector machine; Genetics","score_opus":0.013808769752298883,"score_gpt":0.2508298393515291,"score_spread":0.2370210695992302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158564991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7534229,0.00009564882,0.23981957,0.000012779088,0.00009946089,0.0007004489,0.00002874864,0.00002171753,0.0057986793],"genre_scores_gemma":[0.9621929,0.000006576184,0.037119593,0.000036731337,0.0001327875,0.000018390143,0.00011642311,0.000013730564,0.0003628819],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989243,0.000012869325,0.0006121103,0.00010563756,0.00012457612,0.00022047327],"domain_scores_gemma":[0.9992776,0.000012068563,0.00027090777,0.00027184826,0.00009077518,0.00007681729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004906371,0.00014033003,0.0001440169,0.000077212775,0.00011926704,0.000028701528,0.00011428532,0.00013019971,0.000009236079],"category_scores_gemma":[0.000058182883,0.00012954893,0.00006108091,0.00008872849,0.0001163967,0.000017045637,0.000108418215,0.00011649255,0.0000038919798],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061997253,0.00043483844,0.007559059,0.0041199387,0.0003495238,0.0000020564664,0.003481947,0.0014411772,0.8809838,0.027025245,0.0019334476,0.07204894],"study_design_scores_gemma":[0.011024559,0.005545228,0.031775102,0.0022549655,0.0004111602,0.00037131715,0.0069766156,0.32069957,0.5489891,0.020596685,0.048086993,0.0032687117],"about_ca_topic_score_codex":0.0000075888397,"about_ca_topic_score_gemma":0.00006166704,"teacher_disagreement_score":0.33199474,"about_ca_system_score_codex":0.000016333608,"about_ca_system_score_gemma":0.0000418473,"threshold_uncertainty_score":0.5282852},"labels":[],"label_agreement":null},{"id":"W2159070430","doi":"10.1186/1471-2105-12-s9-s2","title":"Evolution of orthologous tandemly arrayed gene clusters","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bombardier (Canada); Université de Montréal","funders":"","keywords":"DNA microarray; Genetics; Biology; Computational biology; Gene; Evolutionary biology; Gene expression","score_opus":0.021895325964833415,"score_gpt":0.21869581851453831,"score_spread":0.1968004925497049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159070430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5280354,0.00026192854,0.46049184,0.0000047880985,0.00023647708,0.00033932805,0.00003153991,0.000026887185,0.010571834],"genre_scores_gemma":[0.7077473,0.00007155851,0.29163226,0.000049855007,0.00006975533,0.000011556952,0.00009501062,0.000017262997,0.00030547776],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991936,0.00002100035,0.0003448132,0.00010810595,0.0001304542,0.00020199872],"domain_scores_gemma":[0.9993235,0.000003829415,0.00018707836,0.00033988777,0.00008731524,0.000058405978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018297341,0.00012385074,0.00013204078,0.000066291635,0.000036234094,0.0000058246924,0.00018351906,0.00013493614,0.00003757906],"category_scores_gemma":[0.00003696432,0.00011401045,0.00008716347,0.000095675736,0.00008742521,0.000007186913,0.00009290682,0.000047020687,0.000048875878],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013541286,0.0012758162,0.31035468,0.0020360542,0.0010520421,0.000013401063,0.011064961,0.0033526558,0.62943727,0.0020524696,0.009634345,0.028372178],"study_design_scores_gemma":[0.008552311,0.0043479856,0.20031159,0.0001151582,0.00043620975,0.0003084943,0.007542001,0.082448006,0.67337686,0.0011833096,0.018923141,0.0024549202],"about_ca_topic_score_codex":0.000011723481,"about_ca_topic_score_gemma":0.000017363078,"teacher_disagreement_score":0.17971186,"about_ca_system_score_codex":0.000021173048,"about_ca_system_score_gemma":0.00007858512,"threshold_uncertainty_score":0.46492112},"labels":[],"label_agreement":null},{"id":"W2159184793","doi":"10.1186/1471-2105-11-420","title":"An improved classification of G-protein-coupled receptors using sequence-derived features","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Ministry of Education, India","keywords":"G protein-coupled receptor; Jackknife resampling; Computational biology; Identification (biology); Artificial intelligence; Subfamily; Computer science; Principal component analysis; Feature (linguistics); Sequence (biology); Biology; Pattern recognition (psychology); Machine learning; Bioinformatics; Receptor; Genetics; Mathematics; Estimator; Statistics; Gene","score_opus":0.02074571848625936,"score_gpt":0.29216161463697266,"score_spread":0.2714158961507133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159184793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9305156,0.000018272147,0.0677783,0.000019631334,0.000327874,0.00043227896,0.000024970486,0.00004819867,0.0008349054],"genre_scores_gemma":[0.59603405,0.000007370454,0.4033758,0.000056089684,0.00011861817,0.000010200438,0.00029466467,0.000023927623,0.00007926278],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862874,0.000041141422,0.0006489131,0.00016967246,0.00022224445,0.00028926833],"domain_scores_gemma":[0.99820244,0.000016041042,0.0006013405,0.00081973337,0.00023074205,0.00012968181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004093919,0.00023953653,0.00021900515,0.000103733975,0.00012586857,0.00006238012,0.0004483107,0.0003828354,0.00003901793],"category_scores_gemma":[0.00037176904,0.00021608567,0.00010587261,0.00016096327,0.00020524982,0.00004117177,0.000094337825,0.00032389112,0.000009789837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005258039,0.00003893918,0.0019315925,0.00016288346,0.000020478425,6.6176064e-8,0.0003250239,0.00043513352,0.9945389,0.00022850191,0.00005395887,0.0022119114],"study_design_scores_gemma":[0.0005299648,0.00028907097,0.0034170276,0.000023360388,0.000025550378,0.000023928267,0.0005779849,0.80434895,0.18931766,0.000035799156,0.0010781974,0.00033251644],"about_ca_topic_score_codex":0.000043359792,"about_ca_topic_score_gemma":0.00010534717,"teacher_disagreement_score":0.80522126,"about_ca_system_score_codex":0.00001683031,"about_ca_system_score_gemma":0.00022633163,"threshold_uncertainty_score":0.88117176},"labels":[],"label_agreement":null},{"id":"W2159230276","doi":"10.1186/1471-2105-9-s11-s10","title":"Recognizing speculative language in biomedical research articles: a linguistically motivated perspective","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Collège de Maisonneuve; Concordia University","funders":"","keywords":"Weighting; Computer science; Perspective (graphical); Sentence; Artificial intelligence; Natural language processing; Point (geometry); Scheme (mathematics); Machine learning; Mathematics","score_opus":0.09097231171662291,"score_gpt":0.36817676912295266,"score_spread":0.27720445740632976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159230276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638024,0.00051159004,0.02549662,0.00022513185,0.00014524952,0.00031291385,0.00002378615,0.0000673419,0.009414971],"genre_scores_gemma":[0.87785035,0.00008947759,0.12121637,0.00014576838,0.00023780711,0.000017784114,0.00006280685,0.000018218796,0.00036139734],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99830884,0.0001362413,0.0004150276,0.00024876164,0.00039026394,0.0005008629],"domain_scores_gemma":[0.999058,0.00016331043,0.00006855149,0.00029319327,0.0002520819,0.00016482579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007269331,0.00015213818,0.00020121099,0.00022116685,0.00013671146,0.000021393316,0.0002476088,0.00028154804,0.000029322979],"category_scores_gemma":[0.0046038465,0.00012750976,0.000068107875,0.00055840646,0.00080030784,0.0000054506468,0.00020048989,0.00035842927,0.00008606615],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004128301,0.006335628,0.15349679,0.0015394032,0.0009980609,0.0020429438,0.38545248,0.000458522,0.20822357,0.01148178,0.06471242,0.16113012],"study_design_scores_gemma":[0.01720861,0.008217485,0.13294274,0.0013517105,0.00009574682,0.0013048425,0.45424494,0.20355178,0.10501243,0.0063564107,0.06569085,0.0040224646],"about_ca_topic_score_codex":0.00011287235,"about_ca_topic_score_gemma":0.00009190595,"teacher_disagreement_score":0.20309326,"about_ca_system_score_codex":0.0000734441,"about_ca_system_score_gemma":0.00026237508,"threshold_uncertainty_score":0.5511567},"labels":[],"label_agreement":null},{"id":"W2159348493","doi":"10.1186/1471-2105-9-327","title":"Gene Ontology term overlap as a measure of gene functional similarity","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Michael Smith Health Research BC","funders":"National Institute of General Medical Sciences; National Institutes of Health; Michael Smith Health Research BC","keywords":"Semantic similarity; Computer science; Similarity (geometry); Term (time); Measure (data warehouse); Data mining; Similarity measure; Ontology; Gene ontology; Information retrieval; Artificial intelligence; Machine learning; Gene; Biology; Genetics","score_opus":0.024040132471224746,"score_gpt":0.2268267298727449,"score_spread":0.20278659740152016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159348493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6587373,0.0012389185,0.31819248,0.000089102294,0.0007959438,0.00061477633,0.00019125493,0.000050458777,0.020089736],"genre_scores_gemma":[0.8377615,0.0004806663,0.1581208,0.0012466322,0.0005056117,0.00002580526,0.00088277855,0.00003965061,0.0009365445],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984857,0.000028576815,0.0006874105,0.00016786862,0.00028067056,0.00034976256],"domain_scores_gemma":[0.99877936,0.00002063826,0.00033130255,0.0005398721,0.00019109208,0.00013773057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024633954,0.00024110421,0.00029729996,0.000071394374,0.00015292154,0.000013923588,0.0002670144,0.0003790996,0.000052999556],"category_scores_gemma":[0.00007476971,0.00022250757,0.00020185587,0.00011267869,0.00022462188,0.000015748463,0.00013642028,0.00016138659,0.000056356737],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059491596,0.0028406058,0.28806818,0.0035893645,0.0036396577,0.00008147624,0.009840687,0.027708156,0.40923333,0.009667242,0.17784584,0.06153632],"study_design_scores_gemma":[0.017840436,0.004877083,0.18199413,0.00021259976,0.000579038,0.0071304096,0.0021692645,0.18000296,0.48878697,0.002626761,0.10871859,0.0050617857],"about_ca_topic_score_codex":0.000013032186,"about_ca_topic_score_gemma":0.000033191245,"teacher_disagreement_score":0.1790242,"about_ca_system_score_codex":0.000023922381,"about_ca_system_score_gemma":0.00035708628,"threshold_uncertainty_score":0.90735954},"labels":[],"label_agreement":null},{"id":"W2159835316","doi":"10.1186/1471-2105-8-242","title":"Improving gene set analysis of microarray data by SAM-GS","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":263,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Astellas Pharma; Genome Alberta; Canada Research Chairs; Muttart Foundation; University of Alberta; Fondation pour la Recherche Médicale; Roche Organ Transplant Research Foundation; Kidney Foundation of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Gene; Microarray analysis techniques; DNA microarray; Biology; Computational biology; Microarray; Genetics; Gene expression; Gene expression profiling; Significance analysis of microarrays; Phenotype; Microarray databases; Biological pathway","score_opus":0.018778310927165674,"score_gpt":0.25856707239389176,"score_spread":0.2397887614667261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159835316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09986679,0.0008175154,0.8964236,0.000013286667,0.00012923885,0.00021540417,0.0012671598,0.000016911736,0.0012501382],"genre_scores_gemma":[0.41648087,0.00042449302,0.5523283,0.0009862244,0.00031306827,0.000005507182,0.028611138,0.000056083667,0.0007942995],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982576,0.000014508875,0.0009066202,0.00021286157,0.0002025095,0.00040590807],"domain_scores_gemma":[0.99790025,0.000033960718,0.00049589615,0.0013373585,0.00009781831,0.0001347167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010340157,0.00021519767,0.0003270638,0.000169451,0.00007709195,0.000041757434,0.0007520979,0.0002593282,0.000018282934],"category_scores_gemma":[0.000068523754,0.0001977847,0.00015898941,0.00044005987,0.00010621755,0.000021945438,0.000505063,0.000113684495,0.000014690098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050775637,0.0004216986,0.043673877,0.0013227938,0.0065583596,0.0000033925667,0.0023333703,0.006668683,0.57734257,0.00036753644,0.2531366,0.10766336],"study_design_scores_gemma":[0.0016024535,0.00029251288,0.0032462596,0.000027484562,0.0015931157,0.00002523556,0.0017540678,0.7898915,0.105509356,0.000025337584,0.09492117,0.0011115366],"about_ca_topic_score_codex":0.000043705244,"about_ca_topic_score_gemma":0.00015728742,"teacher_disagreement_score":0.7832228,"about_ca_system_score_codex":0.000016751477,"about_ca_system_score_gemma":0.00009302506,"threshold_uncertainty_score":0.80654263},"labels":[],"label_agreement":null},{"id":"W2160824383","doi":"10.1186/1471-2105-14-s6-s1","title":"Reconstruction of regulatory networks through temporal enrichment profiling and its application to H1N1 influenza viral infection","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"interferon and immune responses","field":"Immunology and Microbiology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Center for Advancing Translational Sciences; National Institute of Allergy and Infectious Diseases; NIH Clinical Center; National Institutes of Health","keywords":"Biology; Gene regulatory network; Computational biology; Influenza A virus; Gene expression profiling; Transcription factor; Genome; Gene; Virology; Virus; Gene expression; Genetics","score_opus":0.014866996160236071,"score_gpt":0.25093402042136187,"score_spread":0.2360670242611258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160824383","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9383508,0.0005317041,0.059169453,0.000019738713,0.00037992137,0.0007861527,0.0000038300122,0.000057225127,0.0007011545],"genre_scores_gemma":[0.992749,0.000050162977,0.006686871,0.00017274017,0.000021279047,0.00008140316,0.000031815107,0.000008277862,0.00019846579],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914646,0.000057902296,0.0004905639,0.0000976074,0.000030046087,0.00017743174],"domain_scores_gemma":[0.99943256,0.00003976615,0.00022778808,0.00017107374,0.00011173666,0.000017068887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016449713,0.00012227114,0.00017696287,0.00009591882,0.000094246534,0.000015825095,0.00006413299,0.00019192325,0.000051842224],"category_scores_gemma":[0.00004516843,0.00010713279,0.000040898736,0.00010288609,0.000069169364,0.00040550734,0.000066020206,0.00013115094,0.00019415758],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016218872,0.0003614174,0.12778099,0.001432043,0.00050415925,1.7718176e-7,0.007874367,0.005106951,0.5428519,0.022228971,0.004357983,0.28587914],"study_design_scores_gemma":[0.0035430142,0.0016908529,0.14198373,0.00034183587,0.00012240298,0.00027465224,0.002788123,0.09401581,0.7356452,0.00068014034,0.017912526,0.0010017294],"about_ca_topic_score_codex":0.00008156319,"about_ca_topic_score_gemma":0.000005460705,"teacher_disagreement_score":0.28487742,"about_ca_system_score_codex":0.00004051458,"about_ca_system_score_gemma":0.000034289413,"threshold_uncertainty_score":0.43687487},"labels":[],"label_agreement":null},{"id":"W2160853918","doi":"10.1186/1471-2105-10-s1-s49","title":"Quality assessment of tandem mass spectra using support vector machine (SVM)","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Université Laval; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Tandem; Computer science; Data mining; Quality (philosophy); Pattern recognition (psychology); Quality assurance; DNA microarray; Artificial intelligence; Machine learning; Computational biology; Biology; Materials science; Engineering; Physics; Genetics; Gene expression; External quality assessment; Operations management","score_opus":0.04707407499927428,"score_gpt":0.3609859428142803,"score_spread":0.313911867815006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160853918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018969841,0.000013485511,0.93843144,0.000051137675,0.000014907235,0.00017495875,0.00011517668,0.00013069033,0.04209838],"genre_scores_gemma":[0.22112902,0.000020854688,0.77855855,0.000061010058,0.00003240561,0.0000076010865,0.00006544572,0.000008709201,0.000116383635],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988154,0.0000061102382,0.0006572578,0.00010314277,0.000217578,0.00020050105],"domain_scores_gemma":[0.9989675,0.000035573048,0.0004153563,0.00045303264,0.000060017523,0.00006850134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020304655,0.00014559802,0.00024198441,0.000035291218,0.000073313066,0.00002185693,0.00021066792,0.000103984,0.00024472972],"category_scores_gemma":[0.000021500031,0.00013741624,0.00009705607,0.00011772081,0.000039801966,0.0001414804,0.000032269334,0.00017511379,0.0000042562706],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006596859,0.00082190905,0.05340512,0.0019834796,0.00010440668,0.0000037575949,0.0006784398,0.0040690396,0.7351836,0.18314514,0.0007314056,0.019807735],"study_design_scores_gemma":[0.0010194089,0.00012867976,0.0057252743,0.00010409073,0.00006197871,0.00002570217,0.00028916076,0.6037364,0.36010024,0.025084162,0.0030035316,0.0007213429],"about_ca_topic_score_codex":0.000008051784,"about_ca_topic_score_gemma":0.000002319994,"teacher_disagreement_score":0.5996674,"about_ca_system_score_codex":0.00011750639,"about_ca_system_score_gemma":0.00011530783,"threshold_uncertainty_score":0.56036717},"labels":[],"label_agreement":null},{"id":"W2161701113","doi":"10.1186/1471-2105-7-365","title":"PIPE: a protein-protein interaction prediction engine based on the re-occurring short polypeptide sequences between known interacting protein pairs","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":219,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem affinity purification; Saccharomyces cerevisiae; Protein–protein interaction; Yeast; Computational biology; Interaction network; Biology; Gene; Genetics; Bioinformatics; Biochemistry","score_opus":0.017602154927653123,"score_gpt":0.2389834037510581,"score_spread":0.22138124882340496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161701113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7094641,0.00007622402,0.27640063,0.00034476933,0.00031133927,0.0027112782,0.00013831045,0.00014291599,0.010410449],"genre_scores_gemma":[0.9700279,0.0000022868974,0.02803907,0.0001873544,0.0007360983,0.00023340185,0.00041057466,0.00003604841,0.00032723707],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791014,0.00008748876,0.0009341653,0.0002558326,0.0003406329,0.00047176794],"domain_scores_gemma":[0.9987123,0.000066976485,0.00040814467,0.0006060833,0.00011246598,0.000094002964],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008058713,0.00036765265,0.00024629052,0.00012648874,0.00031131087,0.00020353885,0.00037085856,0.00026630238,0.000031200565],"category_scores_gemma":[0.00017533237,0.00027627332,0.00018128661,0.00021308221,0.00009738868,0.000059798527,0.000139623,0.0004568099,0.00003740944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024133348,0.0011798595,0.028662251,0.004995169,0.00096505595,0.000015596093,0.0026595306,0.17585178,0.56752336,0.00365718,0.027900081,0.18417677],"study_design_scores_gemma":[0.0007783776,0.00083894876,0.0006610623,0.0012171398,0.000059086145,0.000013414245,0.0014300685,0.74447894,0.227973,0.00025657433,0.02152647,0.000766941],"about_ca_topic_score_codex":0.000060775594,"about_ca_topic_score_gemma":0.00008204162,"teacher_disagreement_score":0.5686271,"about_ca_system_score_codex":0.00009290737,"about_ca_system_score_gemma":0.00013292323,"threshold_uncertainty_score":0.99996895},"labels":[],"label_agreement":null},{"id":"W2161758034","doi":"10.1186/1471-2105-8-177","title":"Requirements and ontology for a G protein-coupled receptor oligomerization knowledge base","year":2007,"lang":"en","type":"editorial","venue":"BMC Bioinformatics","topic":"Receptor Mechanisms and Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institute on Drug Abuse; National Institutes of Health","keywords":"G protein-coupled receptor; Ontology; Context (archaeology); Computer science; Computational biology; Knowledge base; Data science; Knowledge management; Biology; Receptor; World Wide Web; Biochemistry","score_opus":0.020055085445667805,"score_gpt":0.28881668647521375,"score_spread":0.26876160102954594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161758034","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037299448,0.0009680607,0.644574,0.000010996566,0.34703586,0.0024772072,0.00045662592,0.000052086918,0.0006952622],"genre_scores_gemma":[0.00042484156,0.0007306736,0.40854517,0.00010840745,0.57003504,0.00057307864,0.014903354,0.00020070374,0.004478742],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981027,0.000037169117,0.00072152086,0.00035736526,0.00029403766,0.0004871977],"domain_scores_gemma":[0.99847174,0.000074532036,0.00047091432,0.00036660171,0.00046020487,0.00015598981],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008634322,0.0003893609,0.0004152591,0.00013987906,0.00015522864,0.00007630582,0.00024148251,0.0013367457,0.000035935333],"category_scores_gemma":[0.0010222107,0.00037146805,0.00014579805,0.00009178762,0.0000728595,0.0000131754805,0.0001468303,0.00022545396,0.00001728566],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006678544,0.00013404676,0.000009999502,0.0030694131,0.00020788051,5.1873457e-7,0.00044113598,0.000019439221,0.2072692,0.00019121186,0.78170156,0.0062877387],"study_design_scores_gemma":[0.001858784,0.0009101103,0.0000011505523,0.00021045115,0.00008380403,0.0000021067565,0.00019656173,0.012059108,0.05309153,0.000056262266,0.9308879,0.00064226333],"about_ca_topic_score_codex":0.000008652631,"about_ca_topic_score_gemma":0.000055883465,"teacher_disagreement_score":0.23602879,"about_ca_system_score_codex":0.000054092267,"about_ca_system_score_gemma":0.00048795543,"threshold_uncertainty_score":0.9999597},"labels":[],"label_agreement":null},{"id":"W2162224067","doi":"10.1186/1471-2105-9-340","title":"RNA STRAND: The RNA Secondary Structure and Statistical Analysis Database","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":287,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"RNA; Nucleic acid secondary structure; Database; Protein secondary structure; Computer science; Nucleic acid structure; Computational biology; Biology; Genetics; Gene","score_opus":0.013741878627289974,"score_gpt":0.2343050137810196,"score_spread":0.2205631351537296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162224067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4763693,0.0007796486,0.5178553,0.00006892575,0.000128835,0.00036027268,0.0016486361,0.00002170896,0.0027674085],"genre_scores_gemma":[0.8419263,0.00045194267,0.15559961,0.00051586796,0.00013529409,0.000010666883,0.0007658645,0.000017517314,0.00057697267],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991556,0.000051778243,0.00027223025,0.00014935761,0.00017145729,0.00019959723],"domain_scores_gemma":[0.9992825,0.00004611557,0.0000976173,0.00043900096,0.00003664665,0.00009816491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001694404,0.00015449805,0.00017352204,0.000049367445,0.0002047841,0.00003809218,0.00018912564,0.00011734879,0.0002474762],"category_scores_gemma":[0.000079509984,0.00010226795,0.0000725412,0.00012722368,0.00015071113,0.0000112946545,0.00009932838,0.00010974899,0.000012647565],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013281904,0.00029787832,0.014886898,0.0015132176,0.0053799907,0.00008207325,0.005142096,0.0018420833,0.75107634,0.011617766,0.069103524,0.13772997],"study_design_scores_gemma":[0.003971832,0.00097326905,0.034656875,0.000052492986,0.0020934767,0.0006207191,0.002235142,0.06455161,0.81208736,0.0015855237,0.07499057,0.0021811398],"about_ca_topic_score_codex":0.000012457309,"about_ca_topic_score_gemma":0.000043632124,"teacher_disagreement_score":0.365557,"about_ca_system_score_codex":0.0000043182813,"about_ca_system_score_gemma":0.00009055339,"threshold_uncertainty_score":0.4170366},"labels":[],"label_agreement":null},{"id":"W2164147743","doi":"10.1186/1471-2105-9-422","title":"SIGMA2: A system for the integrative genomic multi-dimensional analysis of cancer genomes, epigenomes, and transcriptomes","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Dental and Craniofacial Research; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC; Genome Canada","keywords":"Computational biology; Genome; Biology; DNA microarray; Transcriptome; DNA methylation; Epigenomics; Genomics; Tiling array; Identification (biology); Genetics; Gene; Bioinformatics; Gene expression","score_opus":0.027245981636458732,"score_gpt":0.27723991678293497,"score_spread":0.24999393514647625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164147743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69873124,0.03252394,0.2674144,0.000030983676,0.00016004084,0.0006059626,0.00046006657,0.000010074439,0.00006328353],"genre_scores_gemma":[0.935523,0.003554446,0.060248975,0.000052063147,0.00006944933,0.00008295192,0.00024502608,0.000017010718,0.00020710085],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991276,0.000028022127,0.00041782754,0.0001462146,0.00011496605,0.00016535347],"domain_scores_gemma":[0.9992459,0.000080485646,0.00021124203,0.00024528807,0.00016232356,0.000054755146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022561166,0.00015440947,0.00026717008,0.00011632185,0.00016997308,0.0000122106885,0.00013653554,0.00010491987,0.0000049546766],"category_scores_gemma":[0.00002933837,0.000102518585,0.0001928619,0.0002015029,0.00014091586,0.0000056567155,0.000041696396,0.000046935213,6.5536466e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086638663,0.00031680526,0.24951024,0.0016122027,0.011046418,0.0000017076471,0.015170472,0.1807767,0.51006126,0.0010691793,0.00056285533,0.029005768],"study_design_scores_gemma":[0.0017710463,0.0003135923,0.11758874,0.00003514185,0.0016450369,0.000005243577,0.0021700365,0.8079859,0.056721866,0.000011273768,0.011301631,0.00045048195],"about_ca_topic_score_codex":0.00007198891,"about_ca_topic_score_gemma":0.00035009475,"teacher_disagreement_score":0.6272092,"about_ca_system_score_codex":0.000025481258,"about_ca_system_score_gemma":0.00013109746,"threshold_uncertainty_score":0.41805863},"labels":[],"label_agreement":null},{"id":"W2164314657","doi":"10.1186/1471-2105-7-s2-s18","title":"Differential gene expression in mouse primary hepatocytes exposed to the peroxisome proliferator-activated receptor α agonists","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Peroxisome Proliferator-Activated Receptors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta","keywords":"Bezafibrate; Peroxisome proliferator-activated receptor; Fenofibrate; Peroxisome proliferator-activated receptor alpha; Transactivation; Endocrinology; Internal medicine; Peroxisome proliferator-activated receptor gamma; Peroxisome; Clofibric acid; Biology; Agonist; Receptor; Pharmacology; Chemistry; Nuclear receptor; Gene expression; Medicine; Gene; Biochemistry; Transcription factor","score_opus":0.01067915524515267,"score_gpt":0.21851386693985134,"score_spread":0.20783471169469867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164314657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898364,0.00013502833,0.008023724,0.00010094407,0.0003031151,0.0011163601,0.00012083223,0.00008283992,0.00028076206],"genre_scores_gemma":[0.9651324,0.00008266799,0.03142986,0.0005197807,0.0006247613,0.00033522132,0.0011278486,0.00008844035,0.0006590216],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976152,0.00014413949,0.00078453356,0.0004039356,0.00041505322,0.000637133],"domain_scores_gemma":[0.9986761,0.00003057646,0.00024382827,0.0007449446,0.00012540563,0.00017910665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020914892,0.00044987362,0.00036255593,0.00016658712,0.00022650162,0.00015493849,0.00056195224,0.0003836682,0.000060590803],"category_scores_gemma":[0.000110972425,0.00033044838,0.00014287414,0.0003148585,0.000098170865,0.000042974276,0.00035310353,0.00028829323,0.00010797477],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037347287,0.00020042348,0.008624971,0.00007550017,0.000021178872,7.0217203e-7,0.00021425632,0.00047164076,0.98579293,0.000007560528,0.0038733839,0.00034395084],"study_design_scores_gemma":[0.0011403321,0.00020791178,0.0013010255,0.000040059633,0.000007626595,0.000008978349,0.00013785131,0.000953088,0.98750913,0.0000054810534,0.008224202,0.00046431916],"about_ca_topic_score_codex":0.000018317662,"about_ca_topic_score_gemma":0.000043492237,"teacher_disagreement_score":0.024703996,"about_ca_system_score_codex":0.0001468619,"about_ca_system_score_gemma":0.00023486445,"threshold_uncertainty_score":0.99991477},"labels":[],"label_agreement":null},{"id":"W2165057277","doi":"10.1186/s12859-015-0488-1","title":"OTO: Ontology Term Organizer","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"National Science Foundation","keywords":"Term (time); Ontology; Computer science; Computational biology; Information retrieval; DNA microarray; Gene ontology; Biology; Data science; Bioinformatics; World Wide Web; Genetics; Gene; Physics","score_opus":0.04411125647240074,"score_gpt":0.2846898439338195,"score_spread":0.24057858746141877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165057277","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60371655,0.00188615,0.3311269,0.00095005543,0.002467231,0.0006914084,0.000091671434,0.00038411608,0.0586859],"genre_scores_gemma":[0.35235038,0.00012275328,0.6376148,0.0032781365,0.0009038695,0.00004216888,0.0006154916,0.00006277523,0.0050095986],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916065,0.000027317941,0.00026972007,0.00012934503,0.00014532915,0.0002676663],"domain_scores_gemma":[0.9992899,0.000019101219,0.00008794232,0.0003391682,0.0000873482,0.00017659093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021666136,0.00013632604,0.00015200046,0.000037173915,0.000043239856,0.00002423585,0.0002493888,0.00026496395,0.00003211333],"category_scores_gemma":[0.00061350403,0.000108286455,0.000053099822,0.00008705294,0.00013006644,0.00000399386,0.00015710291,0.00008647442,0.0002977077],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005621283,0.0004572286,0.14359288,0.000445623,0.00029654408,0.00002421772,0.00400643,0.00011968232,0.01721914,0.0016425373,0.6750855,0.15654808],"study_design_scores_gemma":[0.0031794729,0.0015505238,0.008660511,0.000042705768,0.000060680766,0.00033549912,0.0033009488,0.006675228,0.023850068,0.00046493983,0.9509542,0.0009252446],"about_ca_topic_score_codex":0.000006005945,"about_ca_topic_score_gemma":0.000028708968,"teacher_disagreement_score":0.30648792,"about_ca_system_score_codex":0.00001493363,"about_ca_system_score_gemma":0.0001859728,"threshold_uncertainty_score":0.44157934},"labels":[],"label_agreement":null},{"id":"W2165145683","doi":"10.1186/1471-2105-14-69","title":"BOND: Basic OligoNucleotide Design","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Oligonucleotide; DNA microarray; Computer science; Software; Computational biology; DNA; Gene; Biology; Genetics; Programming language","score_opus":0.02351071718670648,"score_gpt":0.23917089378504766,"score_spread":0.2156601765983412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165145683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049352802,0.00028499772,0.9192699,0.0002773794,0.00035989896,0.00073662365,0.0000073395763,0.00007197744,0.02963908],"genre_scores_gemma":[0.49629962,0.00022887133,0.4953559,0.0025074966,0.00033445837,0.00022327398,0.00015725258,0.000047885278,0.0048452294],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931586,0.000022378601,0.0002398869,0.00011851885,0.00011523277,0.00018811758],"domain_scores_gemma":[0.99934524,0.000008790629,0.00009952583,0.00037966357,0.00007223581,0.000094570445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001075218,0.00011445809,0.000080662096,0.000045383105,0.000064877575,0.00005633123,0.00018138571,0.00010222291,0.00010938674],"category_scores_gemma":[0.000050194994,0.00009730488,0.00005543316,0.00008516517,0.000037675643,0.000012192498,0.00006120651,0.000049870836,0.00056531816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004771104,0.00008274312,0.0018722131,0.00011670386,0.000035052573,2.3367913e-7,0.00026689487,0.0011006963,0.3420464,0.0006955284,0.6215324,0.032203447],"study_design_scores_gemma":[0.0017178847,0.00044574245,0.017603578,0.000053598993,0.0000359905,0.000031117106,0.0013217397,0.10127856,0.5631087,0.000998496,0.31248045,0.0009241508],"about_ca_topic_score_codex":0.0000052662726,"about_ca_topic_score_gemma":0.0000020182736,"teacher_disagreement_score":0.44694683,"about_ca_system_score_codex":0.000010598374,"about_ca_system_score_gemma":0.00007935256,"threshold_uncertainty_score":0.726621},"labels":[],"label_agreement":null},{"id":"W2165336044","doi":"10.1186/1471-2105-11-304","title":"Scaffold filling, contig fusion and comparative gene order inference","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Contig; Synteny; Biology; Computational biology; Phylogenetic tree; Comparative genomics; Hybrid genome assembly; DNA microarray; Gene; Genetics; Genomics","score_opus":0.027260786510222387,"score_gpt":0.26934092065029847,"score_spread":0.24208013414007606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165336044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93880624,0.00019980261,0.05572917,0.00003260403,0.00024132662,0.00031849768,0.0000318365,0.000022579394,0.004617953],"genre_scores_gemma":[0.6563189,0.00023499806,0.34188962,0.00018340291,0.00016998748,0.000018594359,0.00026257755,0.000013362681,0.0009085601],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993038,0.0000123293175,0.00023203256,0.00013520055,0.00012066316,0.0001959362],"domain_scores_gemma":[0.99938136,0.000015588763,0.000106255175,0.00027484485,0.0001305742,0.00009135938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013671655,0.00014826618,0.00013943324,0.000042480155,0.00008668814,0.000053100914,0.0001396681,0.0001434268,0.000045364835],"category_scores_gemma":[0.000059745435,0.0001289141,0.00003255368,0.00007905237,0.00010273866,0.000009812163,0.00015260499,0.00010204101,0.00004810653],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102208156,0.00019717,0.044775236,0.0003001366,0.00017585747,0.0000019975835,0.0028710996,0.0005427844,0.92808294,0.0013628901,0.0063463314,0.015241319],"study_design_scores_gemma":[0.0051786355,0.0010947179,0.044830725,0.000069959686,0.0001275168,0.00010204049,0.002057209,0.3017126,0.38399926,0.0002887277,0.25862598,0.0019126111],"about_ca_topic_score_codex":0.0000065476015,"about_ca_topic_score_gemma":0.000093902825,"teacher_disagreement_score":0.5440837,"about_ca_system_score_codex":0.000003487766,"about_ca_system_score_gemma":0.0000589538,"threshold_uncertainty_score":0.5256964},"labels":[],"label_agreement":null},{"id":"W2167155214","doi":"10.1186/1471-2105-10-192","title":"OrthoClusterDB: an online platform for synteny blocks","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Universities Space Research Association","keywords":"Synteny; Genome; Comparative genomics; Identification (biology); Biology; Block (permutation group theory); Visualization; Computational biology; Genomics; Computer science; Gene; Genetics; Data mining; Mathematics","score_opus":0.03838297489699107,"score_gpt":0.276687611470927,"score_spread":0.23830463657393594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167155214","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54859394,0.00030739728,0.4451663,0.00019961142,0.0003428044,0.0014373637,0.0003410707,0.000111934496,0.0034996197],"genre_scores_gemma":[0.15437809,0.00012063593,0.83738196,0.001762828,0.0007863014,0.00003874164,0.003283192,0.00004652319,0.0022017492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998984,0.0000067128194,0.00036188168,0.00016629077,0.00014328385,0.0003378476],"domain_scores_gemma":[0.99918365,0.000009342451,0.00012394154,0.0004452663,0.000109276305,0.00012854609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017216842,0.00018932302,0.00015953694,0.00006232822,0.000078601945,0.000046245994,0.00026565403,0.00016976394,0.000013204384],"category_scores_gemma":[0.000056969002,0.00017007231,0.000113459435,0.000074442345,0.000030475047,0.00001694965,0.000055377786,0.00006379824,0.000013091721],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016634107,0.0031831313,0.0072432472,0.0013611228,0.0005973144,0.0000090243675,0.003351867,0.007896173,0.10782463,0.001812196,0.042476095,0.82258177],"study_design_scores_gemma":[0.0075394074,0.007953158,0.010550933,0.00009542498,0.00021986953,0.00016128735,0.0032504238,0.6653719,0.027445,0.001129997,0.27417025,0.0021123914],"about_ca_topic_score_codex":0.0000014887412,"about_ca_topic_score_gemma":0.000038673817,"teacher_disagreement_score":0.8204694,"about_ca_system_score_codex":0.000016205646,"about_ca_system_score_gemma":0.00007244393,"threshold_uncertainty_score":0.69353473},"labels":[],"label_agreement":null},{"id":"W2167432612","doi":"10.1186/1471-2105-16-s11-s2","title":"VisRseq: R-based visual framework for analysis of sequencing data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Computer science; Workflow; Usability; Interactivity; Bioconductor; Set (abstract data type); Data science; Visualization; Graphical user interface; Software engineering; World Wide Web; Data mining; Human–computer interaction; Programming language; Database","score_opus":0.12628157001908993,"score_gpt":0.352157416540137,"score_spread":0.22587584652104706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167432612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24489677,0.00032378218,0.7537481,0.00001996011,0.00011734738,0.00019101785,0.00043922052,0.000003855228,0.00025992637],"genre_scores_gemma":[0.45449635,0.000021185455,0.5443218,0.00018500861,0.0000809726,0.000010570723,0.0008477215,0.000011230253,0.000025202242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991837,0.0000145662825,0.00035246744,0.00015250414,0.00012359882,0.00017316587],"domain_scores_gemma":[0.9988641,0.000055557415,0.00019364797,0.0006409821,0.00016985346,0.00007586555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003594172,0.00011853415,0.00023299869,0.000090784175,0.00004050841,0.000016966274,0.0003305839,0.000114823015,0.00000223885],"category_scores_gemma":[0.00040699137,0.000106910455,0.00011279566,0.00022413829,0.000060363964,0.0000017803883,0.00020330424,0.000034018776,0.0000019010859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021842592,0.00092885294,0.27556095,0.0026673512,0.01714069,0.0000023219172,0.0056427303,0.48779607,0.14387192,0.011027148,0.02491269,0.028265042],"study_design_scores_gemma":[0.00069907453,0.00042238203,0.0016826433,0.000016116934,0.0008353319,8.5979656e-7,0.0013973134,0.9709133,0.015153767,0.00031934824,0.008274679,0.0002852221],"about_ca_topic_score_codex":0.000010954939,"about_ca_topic_score_gemma":0.000045204706,"teacher_disagreement_score":0.4831172,"about_ca_system_score_codex":0.000014310673,"about_ca_system_score_gemma":0.00026383603,"threshold_uncertainty_score":0.4359682},"labels":[],"label_agreement":null},{"id":"W2167516501","doi":"10.1186/1471-2105-15-147","title":"A fast and robust iterative algorithm for prediction of RNA pseudoknotted secondary structures","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudoknot; Algorithm; Computer science; Robustness (evolution); Iterative method; Iterative and incremental development; Nucleic acid secondary structure; Iterative refinement; Data mining; RNA; Biology","score_opus":0.012078838786371534,"score_gpt":0.21726912304457013,"score_spread":0.2051902842581986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167516501","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027796261,0.00009952276,0.97053874,0.000011043318,0.00011005082,0.00032430724,0.0003780548,0.000010284024,0.00073175086],"genre_scores_gemma":[0.053183775,0.000043925374,0.94583565,0.00013797301,0.00019659029,0.00004324771,0.0003550826,0.00001813817,0.00018560742],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993977,0.000026885638,0.00026499707,0.00010688993,0.000078791,0.00012472575],"domain_scores_gemma":[0.99951935,0.000027287488,0.00015169894,0.00017100829,0.00008410106,0.000046570083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017520922,0.00011662289,0.00013996425,0.000038907052,0.00006486948,0.000023463464,0.00008171814,0.0001372316,0.0000093485005],"category_scores_gemma":[0.000071964416,0.00009847124,0.000053973894,0.000032935113,0.000052647865,0.0000105399295,0.000042595493,0.000038222566,7.861877e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014203992,0.000041504045,0.00026144617,0.0006891976,0.00013738163,1.0670748e-7,0.00085312215,0.00065920677,0.263056,0.0016185998,0.0018822137,0.7306592],"study_design_scores_gemma":[0.0012268029,0.0008210326,0.0009652899,0.00003935373,0.000040754196,0.000017735749,0.00038582017,0.32875633,0.6627468,0.0011249078,0.0036687925,0.00020640873],"about_ca_topic_score_codex":0.000001509235,"about_ca_topic_score_gemma":0.0000028445156,"teacher_disagreement_score":0.7304528,"about_ca_system_score_codex":0.0000036901224,"about_ca_system_score_gemma":0.00003619794,"threshold_uncertainty_score":0.40155405},"labels":[],"label_agreement":null},{"id":"W2170551185","doi":"10.1186/1471-2105-12-237","title":"Semi-Automatic segmentation of multiple mouse embryos in MR images","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Centre for Phenogenomics; Hospital for Sick Children","funders":"Genome Canada; Ontario Genomics; Institut national de recherche en informatique et en automatique (INRIA); British Heart Foundation; Wellcome Trust; Ontario Genomics Institute","keywords":"Initialization; Segmentation; Artificial intelligence; Computer science; Computer vision; Intersection (aeronautics); Image segmentation; Magnetic resonance imaging; Pattern recognition (psychology); Collision; Boundary (topology); Collision detection; Algorithm; Mathematics","score_opus":0.02431074920467926,"score_gpt":0.2803238978378402,"score_spread":0.25601314863316094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170551185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8995814,0.00007188694,0.09652439,0.000021741402,0.000030012809,0.0006373605,0.00009272946,0.000026513053,0.0030139918],"genre_scores_gemma":[0.8121724,0.000097693235,0.1868739,0.00009936041,0.000025364037,0.00011139978,0.00029522172,0.000017225293,0.00030743988],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902666,0.000029607887,0.00042505327,0.00010612338,0.00020122585,0.00021132348],"domain_scores_gemma":[0.9993326,0.000033100016,0.00013622819,0.00033261723,0.00007173145,0.0000937124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002411638,0.00009926855,0.000118772216,0.00010283178,0.000025213507,0.0000098790215,0.00023311067,0.00010655929,0.000052510703],"category_scores_gemma":[0.00036918235,0.00009041384,0.000049806953,0.00018054484,0.00013229334,0.00001383296,0.00011406867,0.000071205955,0.000044406515],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109330176,0.0006815452,0.047209967,0.0010375978,0.00007243609,0.0000014206993,0.0018638747,0.00008004595,0.9218373,0.00016724298,0.007377417,0.019561838],"study_design_scores_gemma":[0.0011917826,0.00020690387,0.017293723,0.000034465105,0.00000996668,0.0000046859955,0.0010926484,0.054562252,0.9248039,0.000119048105,0.0004851139,0.0001955199],"about_ca_topic_score_codex":0.0000495256,"about_ca_topic_score_gemma":0.00008211631,"teacher_disagreement_score":0.09034951,"about_ca_system_score_codex":0.00001808494,"about_ca_system_score_gemma":0.00010276994,"threshold_uncertainty_score":0.36869696},"labels":[],"label_agreement":null},{"id":"W2170998535","doi":"10.1186/1471-2105-13-s9-s8","title":"Generalized adjacency and the conservation of gene clusters in genetic networks defined by synthetic lethals","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Adjacency list; Biology; Schizosaccharomyces pombe; Computational biology; Genetics; Adjacency matrix; Gene; Vertex (graph theory); Saccharomyces cerevisiae; Computer science; Theoretical computer science; Graph; Algorithm","score_opus":0.01116216227566326,"score_gpt":0.21711234933954202,"score_spread":0.20595018706387874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170998535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89926535,0.0076760394,0.091858394,0.00012849265,0.00013509003,0.0005787258,0.00001703291,0.0000075742582,0.00033330644],"genre_scores_gemma":[0.8463642,0.0021733542,0.15035154,0.0005728571,0.00010803793,0.00006765903,0.00018887923,0.000028346489,0.0001451173],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897844,0.00009011167,0.00045198103,0.0000916748,0.00012172839,0.000266093],"domain_scores_gemma":[0.9993813,0.00004298632,0.00020093871,0.0002790916,0.000038269114,0.000057385263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005014861,0.00013937448,0.00019100348,0.00004165866,0.00003853546,0.000012456468,0.00013903543,0.00012218695,0.000007076706],"category_scores_gemma":[0.00008279203,0.000103809776,0.000054250006,0.00010446806,0.00016013854,0.000009794939,0.00008119079,0.00005831456,0.0000030210242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002456252,0.0011652509,0.7183301,0.0022837091,0.00090011925,0.0000018570906,0.009289633,0.03411695,0.16501684,0.0028548804,0.022842877,0.040741514],"study_design_scores_gemma":[0.017862478,0.0004111583,0.07246462,0.00011707291,0.00030034632,0.00010291935,0.0015175701,0.8607949,0.033056576,0.00014938149,0.012006498,0.0012164874],"about_ca_topic_score_codex":0.00003158502,"about_ca_topic_score_gemma":0.000019528243,"teacher_disagreement_score":0.8266779,"about_ca_system_score_codex":0.00001108487,"about_ca_system_score_gemma":0.000026034004,"threshold_uncertainty_score":0.42332396},"labels":[],"label_agreement":null},{"id":"W2171179395","doi":"10.1186/1471-2105-11-252","title":"Antisense DNA parameters derived from next-nearest-neighbor analysis of experimental data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"University of Texas at Dallas; Welch Foundation","keywords":"k-nearest neighbors algorithm; DNA; Computational biology; DNA microarray; Sense (electronics); Nucleotide; Gene; Biology; Sequence (biology); DNA sequencing; Gene expression; Genetics; Molecular biology; Chemistry; Computer science; Artificial intelligence","score_opus":0.029404808140034006,"score_gpt":0.27252597040517273,"score_spread":0.24312116226513872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171179395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99556124,0.00011108766,0.0027630737,0.000009797241,0.00014855739,0.000087333865,0.0005945494,0.000015917496,0.00070843135],"genre_scores_gemma":[0.89730924,0.00003382713,0.09998321,0.000096651216,0.000061357496,0.0000031194052,0.0024630683,0.000014168276,0.00003535443],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998949,0.000013750752,0.0004131786,0.00024079368,0.00017759325,0.00020566829],"domain_scores_gemma":[0.99820834,0.00003335501,0.00022134032,0.001376428,0.0000471418,0.00011336732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103520346,0.00017677857,0.00026348568,0.000060888247,0.000049195336,0.00004517443,0.00061170175,0.0002114483,0.00010781029],"category_scores_gemma":[0.00013521568,0.0001641217,0.00014381402,0.00017896704,0.00017694822,0.000022287686,0.00041333228,0.00010874409,0.000013449819],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000492039,0.00007075041,0.004988967,0.000018472725,0.00040576342,0.0000010034602,0.00012612015,0.000037296963,0.99297726,0.0000041721455,0.0007234623,0.00059752946],"study_design_scores_gemma":[0.00042424395,0.000047430385,0.0038187187,0.000006092138,0.00032348814,0.0000034445331,0.0006459262,0.0659489,0.9271815,0.0000033282372,0.0013754404,0.00022149378],"about_ca_topic_score_codex":0.000043528275,"about_ca_topic_score_gemma":0.00006475359,"teacher_disagreement_score":0.098252006,"about_ca_system_score_codex":0.0000049243195,"about_ca_system_score_gemma":0.00006654103,"threshold_uncertainty_score":0.6692689},"labels":[],"label_agreement":null},{"id":"W2171283513","doi":"10.1186/1471-2105-8-342","title":"A replica exchange Monte Carlo algorithm for protein folding in the HP model","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research; Mitacs; Michael Smith Health Research BC","keywords":"Protein structure prediction; Replica; Lattice protein; Protein folding; Ab initio; Monte Carlo method; Algorithm; Computer science; Statistical potential; Protein design; Ground state; Protein structure; Statistical physics; Physics; Mathematics","score_opus":0.016653440858015716,"score_gpt":0.2644799402148487,"score_spread":0.247826499356833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171283513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046484374,0.00027080468,0.9506157,0.00004535154,0.000046034358,0.0012096234,0.000056238474,0.000014877733,0.0012569916],"genre_scores_gemma":[0.14468761,0.00003462501,0.85349107,0.00079471344,0.00022753314,0.00023457824,0.000092430004,0.000026450864,0.000410974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990063,0.000013160312,0.00034702342,0.00014911842,0.00014421342,0.0003402181],"domain_scores_gemma":[0.9993145,0.000015950458,0.00011955927,0.00044570092,0.000057252575,0.00004705243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007123401,0.00015335092,0.00012658948,0.000054860273,0.000084672094,0.00003541932,0.00029030183,0.00018657075,7.183652e-7],"category_scores_gemma":[0.00008106795,0.00011225798,0.00009705406,0.00010692505,0.000038847353,0.000010471588,0.000084068786,0.000099517616,0.0000014132405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008328174,0.000342787,0.000940188,0.0019914517,0.00018671807,0.000015327747,0.009847897,0.01709675,0.057061646,0.0064602084,0.008498117,0.8967261],"study_design_scores_gemma":[0.0007360906,0.00019082872,0.0000783874,0.000023090559,0.000012314575,0.000019208617,0.00053077,0.98419064,0.006885674,0.0006506596,0.006454814,0.00022753263],"about_ca_topic_score_codex":0.000013737573,"about_ca_topic_score_gemma":0.00019010005,"teacher_disagreement_score":0.9670939,"about_ca_system_score_codex":0.000020692674,"about_ca_system_score_gemma":0.00006415741,"threshold_uncertainty_score":0.45777473},"labels":[],"label_agreement":null},{"id":"W2171898201","doi":"10.1186/1471-2105-15-s6-s6","title":"Functional and genetic analysis of the colon cancer network","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Queen's University; Queen's University Belfast","keywords":"Gene; DNA microarray; Computational biology; Biology; Gene regulatory network; Interaction network; Genome; Complex disease; Cancer; Genetics; Network analysis; Set (abstract data type); Biological network; Functional analysis; Computer science; Gene expression","score_opus":0.009058436959456604,"score_gpt":0.21324121794806064,"score_spread":0.20418278098860404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171898201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6300986,0.0009778513,0.36428544,0.0001350665,0.000590469,0.00033954153,0.00006380456,0.000012445649,0.00349681],"genre_scores_gemma":[0.973004,0.00024382146,0.025151975,0.00086835196,0.00028617174,0.000016701959,0.00007752802,0.00001157884,0.0003398917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924415,0.000025828307,0.0003465042,0.00008599757,0.00012119644,0.00017630968],"domain_scores_gemma":[0.99931943,0.000024092062,0.00022335174,0.00032379405,0.000059150727,0.00005017119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017052657,0.00010990241,0.0001714658,0.000038440976,0.000098992445,0.000020212847,0.00014779627,0.00011820167,0.000020465715],"category_scores_gemma":[0.000025472418,0.00007729602,0.0001258217,0.00027418483,0.00011254213,0.0000038473718,0.00015254585,0.00006255988,0.0000021733774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014624107,0.000057537014,0.28010744,0.00033986836,0.0019638813,8.910022e-8,0.0004449823,0.644409,0.0022234607,0.0055699856,0.030491214,0.03424633],"study_design_scores_gemma":[0.0003940568,0.000078001314,0.23213558,0.000017758886,0.0005310015,0.0000045188217,0.0000647154,0.75205624,0.0003980813,0.0002860764,0.013847557,0.00018642057],"about_ca_topic_score_codex":0.000011153482,"about_ca_topic_score_gemma":0.00022335892,"teacher_disagreement_score":0.3429054,"about_ca_system_score_codex":0.0000069815164,"about_ca_system_score_gemma":0.00005274135,"threshold_uncertainty_score":0.31520402},"labels":[],"label_agreement":null},{"id":"W2174601642","doi":"10.1186/s12859-015-0826-3","title":"MSAIndelFR: a scheme for multiple protein sequence alignment using information on indel flanking regions","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indel; INDEL Mutation; Sequence (biology); Genetics; Computational biology; Flanking maneuver; DNA microarray; Multiple sequence alignment; Alignment-free sequence analysis; Biology; Sequence analysis; Sequence alignment; 5' flanking region; Computer science; Gene; Peptide sequence; Single-nucleotide polymorphism; Engineering; Promoter; Genotype","score_opus":0.10191809340865522,"score_gpt":0.291020284811656,"score_spread":0.18910219140300077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174601642","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70591277,0.00008967661,0.29140064,0.00007683499,0.0001810487,0.0012304152,0.00012701839,0.000014140893,0.00096746127],"genre_scores_gemma":[0.63333344,0.000014656055,0.36564866,0.00046545078,0.00013608421,0.00012446223,0.00019426546,0.00001639336,0.00006661062],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905765,0.000015363901,0.00037367333,0.00011380915,0.00017486031,0.0002646137],"domain_scores_gemma":[0.99919605,0.000015349002,0.00020937237,0.00029913252,0.00018100344,0.000099075456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002745701,0.00017146904,0.00013490423,0.00006155612,0.00013903111,0.00005217724,0.00016233139,0.00012740828,5.4201905e-7],"category_scores_gemma":[0.00023176793,0.00015711345,0.000076263386,0.00006885942,0.00004807006,0.000009006197,0.00011739578,0.000054356533,0.000011582083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031225134,0.00079351256,0.04023405,0.0026680669,0.0012225629,0.0000032937087,0.02090184,0.1869128,0.6629802,0.025990123,0.028757421,0.02641359],"study_design_scores_gemma":[0.0044583254,0.0012443002,0.0004209906,0.00014815731,0.00005248776,0.000030208173,0.00409891,0.8024953,0.06840478,0.00132138,0.11638288,0.0009422681],"about_ca_topic_score_codex":0.000015297639,"about_ca_topic_score_gemma":0.000017909408,"teacher_disagreement_score":0.6155825,"about_ca_system_score_codex":0.000061347346,"about_ca_system_score_gemma":0.00020402487,"threshold_uncertainty_score":0.64069},"labels":[],"label_agreement":null},{"id":"W2180283910","doi":"10.1186/1471-2105-9-s6-s13","title":"Quality assessment of peptide tandem mass spectra","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mass spectrum; Tandem; Computer science; Tandem mass spectrometry; Quality (philosophy); Spectral line; Classifier (UML); Pattern recognition (psychology); Linear discriminant analysis; Artificial intelligence; Data mining; Mass spectrometry; Biological system; Chemistry; Biology; Chromatography; Materials science; Physics","score_opus":0.04926022827379116,"score_gpt":0.3350040443686998,"score_spread":0.2857438160949086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180283910","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03891439,0.000010940093,0.8289358,0.000025501498,0.000009549181,0.000118233715,0.000048354694,0.0001238362,0.13181338],"genre_scores_gemma":[0.12044617,0.00009019766,0.87869996,0.000029571509,0.00002882947,0.000035233457,0.0000347382,0.000009576936,0.000625731],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990202,0.000004742456,0.0005395696,0.00008161587,0.00019878516,0.00015506208],"domain_scores_gemma":[0.999077,0.000058394664,0.0003182074,0.00043098108,0.000060652426,0.00005471695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012506853,0.00010872623,0.00018729526,0.00002535725,0.0000908981,0.0000074244836,0.00019600274,0.00008381778,0.00016444759],"category_scores_gemma":[0.00002558506,0.000102182144,0.00008650542,0.0000920262,0.0000865006,0.0001110089,0.00004382643,0.00014657919,0.000011319037],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053711607,0.00087127247,0.44334838,0.0039175977,0.00017410784,0.0000066282937,0.0022379134,0.0035519432,0.22197309,0.30828997,0.007895811,0.0076795616],"study_design_scores_gemma":[0.0021086177,0.00011180153,0.026644936,0.00019920687,0.000057128836,0.00009714478,0.0019183642,0.25863773,0.6391822,0.037244946,0.032368083,0.0014298583],"about_ca_topic_score_codex":0.0000075052635,"about_ca_topic_score_gemma":0.0000025957142,"teacher_disagreement_score":0.41720912,"about_ca_system_score_codex":0.000067168025,"about_ca_system_score_gemma":0.00010053961,"threshold_uncertainty_score":0.4166867},"labels":[],"label_agreement":null},{"id":"W2209020362","doi":"10.1186/s12859-015-0840-5","title":"Pathosphere.org: pathogen detection and characterization through a web-based, open source informatics platform","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Edgewood Chemical Biological Center; Defense Threat Reduction Agency","keywords":"Metagenomics; Computational biology; Computer science; Workflow; Biodefense; Traceability; Upload; Biology; World Wide Web; Database; Genetics; Software engineering; Microbiology","score_opus":0.07801965046886242,"score_gpt":0.2946562580478169,"score_spread":0.2166366075789545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2209020362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68643594,0.000017112416,0.30664504,0.000033233988,0.00014161534,0.00053912983,0.000008890894,0.00021741427,0.005961646],"genre_scores_gemma":[0.8422889,0.000006924218,0.15420468,0.003190514,0.00009862962,0.00003755638,0.000054406926,0.000032536296,0.00008582683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987298,0.000016557566,0.0006241037,0.00009201009,0.00029041804,0.00024708768],"domain_scores_gemma":[0.9990314,0.000050347866,0.0003201484,0.00028135494,0.00018348134,0.00013321408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045655426,0.00018361161,0.00024025052,0.00008890725,0.00015437134,0.00018067278,0.00012012199,0.00013505244,0.000009937437],"category_scores_gemma":[0.00034455545,0.00015956817,0.00004571787,0.00038142258,0.000058016918,0.0013368195,0.00012433254,0.0001679185,0.000110012916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019583965,0.00060151063,0.19670285,0.0029859347,0.00016972632,0.000022154169,0.046043012,0.00033573905,0.20364104,0.0008866275,0.00033514496,0.5463179],"study_design_scores_gemma":[0.0053215534,0.0005381301,0.0050447104,0.00015952387,0.000077074284,0.00036834227,0.005155303,0.89785355,0.053774368,0.00007908978,0.03130594,0.0003224276],"about_ca_topic_score_codex":0.000026394217,"about_ca_topic_score_gemma":0.00002201395,"teacher_disagreement_score":0.8975178,"about_ca_system_score_codex":0.000091234826,"about_ca_system_score_gemma":0.00022762721,"threshold_uncertainty_score":0.65070015},"labels":[],"label_agreement":null},{"id":"W222181838","doi":"10.1186/s12859-015-0453-z","title":"MeSH ORA framework: R/Bioconductor packages to support MeSH over-representation analysis","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; RIKEN; Research Organization of Information and Systems","keywords":"Computer science","score_opus":0.0652034063736068,"score_gpt":0.3488638436000229,"score_spread":0.2836604372264161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W222181838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5098692,0.00016951578,0.4854861,0.00045338992,0.0005770361,0.00040715854,0.00013949408,0.000127095,0.0027710292],"genre_scores_gemma":[0.51757425,0.00006647951,0.47657558,0.0020352805,0.00042098577,0.000054629745,0.0009763092,0.00003235834,0.0022641127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985795,0.00004813198,0.00044034823,0.00024220014,0.00034602094,0.000343816],"domain_scores_gemma":[0.9987215,0.00004442158,0.00015488295,0.00058880507,0.00014917464,0.00034121037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003689181,0.00020039576,0.00029119747,0.0001720223,0.00006080315,0.000081106875,0.0003228127,0.00033316208,0.00008725229],"category_scores_gemma":[0.001032902,0.00016701434,0.00017733764,0.00059556565,0.000114222894,0.000013078926,0.00022443247,0.00011797687,0.00014040031],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006913573,0.00054914533,0.24021107,0.00040675388,0.0031818973,0.000022679405,0.010541229,0.0017901962,0.010714409,0.002252023,0.62033135,0.10930791],"study_design_scores_gemma":[0.0052630757,0.005797328,0.0677407,0.00013391575,0.0023432435,0.000076997356,0.025748152,0.04631093,0.10012072,0.002250162,0.7403915,0.003823283],"about_ca_topic_score_codex":0.000021004,"about_ca_topic_score_gemma":0.000046006517,"teacher_disagreement_score":0.17247038,"about_ca_system_score_codex":0.000025420035,"about_ca_system_score_gemma":0.00016905688,"threshold_uncertainty_score":0.6810647},"labels":[],"label_agreement":null},{"id":"W2235905640","doi":"10.1186/s12859-015-0869-5","title":"Aligning the unalignable: bacteriophage whole genome alignments","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"European Research Council; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Genome; Computational biology; Similarity (geometry); Bacteriophage; Bacterial genome size; Function (biology); Biology; Computer science; Genetics; Artificial intelligence; Image (mathematics); Gene","score_opus":0.013088884900744172,"score_gpt":0.21883196323003912,"score_spread":0.20574307832929495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235905640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93714213,0.0015139047,0.05191674,0.00073613523,0.0005224472,0.00060461974,0.0003332886,0.000020059613,0.007210682],"genre_scores_gemma":[0.9747939,0.0005057759,0.02008755,0.0009711371,0.00034637915,0.000047398004,0.00006292268,0.000034538338,0.0031504126],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906266,0.000028768252,0.00030775755,0.00015066296,0.000137068,0.00031307052],"domain_scores_gemma":[0.99926144,0.000025672352,0.00013195458,0.00045892881,0.000055150333,0.00006686461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023142638,0.00017303631,0.00012714494,0.00002397972,0.00016417188,0.000044567343,0.00031890077,0.00008352412,0.00002030103],"category_scores_gemma":[0.000045559882,0.000093975235,0.000085648666,0.00006234917,0.00010940652,0.0000027258768,0.00025227098,0.000030983483,0.0001243336],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026654521,0.000023677476,0.005058358,0.000038837854,0.00012189764,7.550997e-7,0.00045187093,0.00007101109,0.9875357,0.00015141365,0.0028300867,0.003689696],"study_design_scores_gemma":[0.002070318,0.00046249508,0.045232557,0.00006273347,0.00009419742,0.00005402383,0.0015546731,0.0006564963,0.11572038,0.00045127328,0.83276975,0.00087112805],"about_ca_topic_score_codex":0.0000032503717,"about_ca_topic_score_gemma":0.0000079891215,"teacher_disagreement_score":0.8718154,"about_ca_system_score_codex":0.000016289223,"about_ca_system_score_gemma":0.00005672307,"threshold_uncertainty_score":0.38321987},"labels":[],"label_agreement":null},{"id":"W2290848280","doi":"10.1186/s12859-016-0970-4","title":"MetICA: independent component analysis for high-resolution mass-spectrometry based non-targeted metabolomics","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Lallemand","keywords":"Independent component analysis; Overfitting; Principal component analysis; Metabolomics; Computer science; Component (thermodynamics); Data mining; Artificial intelligence; Pattern recognition (psychology); Bioinformatics; Biology; Artificial neural network","score_opus":0.01337171532866286,"score_gpt":0.23613748659713293,"score_spread":0.22276577126847008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290848280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09700882,0.00041923538,0.9008165,0.00021633145,0.0002907035,0.000495412,0.00044622913,0.000031083833,0.00027571223],"genre_scores_gemma":[0.56460524,0.00029636928,0.43405676,0.00017799767,0.00013420802,0.00007917466,0.00039490152,0.00002500239,0.00023032264],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99798024,0.000048868293,0.0007058904,0.00037849948,0.00032238045,0.00056413753],"domain_scores_gemma":[0.9984663,0.00009977979,0.00037394572,0.0006768633,0.00022859861,0.00015449787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061813474,0.00034375017,0.00058767345,0.0004909698,0.00017827304,0.000051902905,0.00035005863,0.00024072718,0.00005596553],"category_scores_gemma":[0.00027675516,0.0002441735,0.00046235905,0.0005889243,0.00011599567,0.000016521868,0.00014208308,0.00008229321,0.000023653753],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066383986,0.00029883345,0.016111422,0.00020989563,0.004099216,0.0000010359178,0.000049959453,0.0023122646,0.9640155,0.00758637,0.0034555937,0.0011960942],"study_design_scores_gemma":[0.009858129,0.001444363,0.0897098,0.000035291298,0.003734048,0.0000065231225,0.0003655354,0.13504186,0.73323107,0.0014626818,0.023187853,0.0019228271],"about_ca_topic_score_codex":0.000010781568,"about_ca_topic_score_gemma":0.00004777571,"teacher_disagreement_score":0.46759644,"about_ca_system_score_codex":0.00007455559,"about_ca_system_score_gemma":0.00011493609,"threshold_uncertainty_score":0.99571073},"labels":[],"label_agreement":null},{"id":"W2295126179","doi":"10.1186/s12859-016-0943-7","title":"Improving cell mixture deconvolution by identifying optimal DNA methylation libraries (IDOL)","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institutes of Health; National Cancer Institute; University of California, San Francisco; National Institute of General Medical Sciences; Kansas IDeA Network of Biomedical Research Excellence; Child and Family Research Institute","keywords":"DNA methylation; Deconvolution; Methylation; Flow cytometry; Computational biology; Biology; DNA; Computer science; Molecular biology; Algorithm; Genetics; Gene; Gene expression","score_opus":0.012194397400628061,"score_gpt":0.23053550395858227,"score_spread":0.21834110655795422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295126179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25119534,0.0015853175,0.7459984,0.00003801598,0.00020678317,0.00016539202,0.000042929027,0.0000291843,0.0007386354],"genre_scores_gemma":[0.7637051,0.000583822,0.23296797,0.00011015342,0.00031629484,0.000024089095,0.0005050855,0.000047385132,0.0017401053],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988821,0.000045542565,0.0004213637,0.00019851822,0.00017924429,0.00027321564],"domain_scores_gemma":[0.99918693,0.000039590614,0.00027591226,0.0003159661,0.00008903127,0.00009257542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028420135,0.00018341927,0.00012957245,0.00006455142,0.00013886628,0.00010529133,0.00017356542,0.00025413,0.00002293537],"category_scores_gemma":[0.00014518399,0.00014165168,0.00009365648,0.00009001625,0.00006352113,0.00006091576,0.00012371072,0.00006134227,0.00004063577],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031422438,0.000022724016,0.0015493672,0.00010423219,0.000013582187,1.1998665e-7,0.00012687697,0.000112304646,0.97600704,0.000083505984,0.0014715935,0.020477248],"study_design_scores_gemma":[0.00062516495,0.00012797734,0.0006648696,0.000021562835,0.000024327395,0.000001353519,0.00013796223,0.009458516,0.9765813,0.0001858699,0.011894822,0.0002763097],"about_ca_topic_score_codex":0.000005331465,"about_ca_topic_score_gemma":0.000008360859,"teacher_disagreement_score":0.5130304,"about_ca_system_score_codex":0.000026026333,"about_ca_system_score_gemma":0.00009108202,"threshold_uncertainty_score":0.57763875},"labels":[],"label_agreement":null},{"id":"W2319368514","doi":"10.1186/s12859-016-0997-6","title":"Unaccounted uncertainty from qPCR efficiency estimates entails uncontrolled false positive rates","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Danish Agency for Science and Higher Education; Forsknings- og Innovationsstyrelsen; Stem Cell Network","keywords":"Statistics; DNA microarray; Computational biology; Biology; Computer science; Econometrics; Genetics; Mathematics; Gene","score_opus":0.00815022176829765,"score_gpt":0.2639605235602022,"score_spread":0.25581030179190456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319368514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25090012,0.00029775716,0.74572086,0.00029607335,0.00007692121,0.0006038511,0.00047687042,0.00008950813,0.0015380337],"genre_scores_gemma":[0.8963961,0.00023932852,0.100498736,0.0009581166,0.00013487731,0.00018381688,0.0011121668,0.00003332492,0.00044352488],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988435,0.000037694477,0.00041673126,0.00026519736,0.00012178718,0.00031512146],"domain_scores_gemma":[0.998944,0.000095821684,0.0002006106,0.0005114721,0.00015167735,0.00009643301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017143469,0.00024073842,0.00022467312,0.0000493578,0.00012689678,0.00003801458,0.0003195986,0.00023972198,0.000062219595],"category_scores_gemma":[0.0002039375,0.00015669886,0.00013778768,0.00010624587,0.0001779671,0.000010373376,0.00014283917,0.00006285859,0.00007090391],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002841238,0.00018590727,0.00862232,0.000020407411,0.00018615364,0.000002033155,0.00010452567,0.00018231985,0.9712088,0.0023720732,0.0055492567,0.011282074],"study_design_scores_gemma":[0.004457746,0.000812862,0.003910902,0.00016615461,0.00015001216,0.000025744219,0.00031147883,0.028533468,0.93503886,0.0029645031,0.022483813,0.0011444566],"about_ca_topic_score_codex":0.000054779055,"about_ca_topic_score_gemma":0.00005368569,"teacher_disagreement_score":0.645496,"about_ca_system_score_codex":0.000030375812,"about_ca_system_score_gemma":0.000099187724,"threshold_uncertainty_score":0.6389994},"labels":[],"label_agreement":null},{"id":"W2333744840","doi":"10.1186/s12859-016-1001-1","title":"PAT: predictor for structured units and its application for the optimization of target molecules for the generation of synthetic antibodies","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education, Science and Technology; National Research Foundation of Korea; Canadian Institutes of Health Research; National Research Foundation","keywords":"Identification (biology); Computer science; Computational biology; Domain (mathematical analysis); Sequence (biology); Folding (DSP implementation); Biology; Mathematics; Genetics; Engineering","score_opus":0.051578017763264324,"score_gpt":0.29771693629819546,"score_spread":0.24613891853493114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333744840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018462531,0.00085248676,0.97560376,0.0011267324,0.00006065166,0.0029257834,0.0009396171,0.0000086542,0.000019783627],"genre_scores_gemma":[0.7039223,0.0016279325,0.29217258,0.00013230238,0.00034005084,0.00080441183,0.00043248697,0.000032925684,0.0005350419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992806,0.000010849026,0.0003431494,0.000071712246,0.00016533396,0.0001283839],"domain_scores_gemma":[0.99815667,0.0009014749,0.00020044355,0.00015498711,0.0005549966,0.000031406737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025874758,0.00009027626,0.00016423735,0.00004506671,0.00013587491,0.000008488891,0.00009500562,0.00005811094,0.00000504726],"category_scores_gemma":[0.00051511714,0.00003873982,0.000061502906,0.000076679324,0.00011265788,0.00007157652,0.000026345973,0.000024542602,2.5173307e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012378309,0.0004794432,0.015232046,0.03776946,0.0023340096,2.1460542e-7,0.010158504,0.10156099,0.27302393,0.18734959,0.01424245,0.34547105],"study_design_scores_gemma":[0.00091282855,0.000262695,0.0009521648,0.00006614474,0.00011264208,0.0000028167988,0.00017681917,0.9500042,0.044614162,0.00029578074,0.0025470743,0.00005263885],"about_ca_topic_score_codex":0.0000031414838,"about_ca_topic_score_gemma":0.0000059013128,"teacher_disagreement_score":0.84844327,"about_ca_system_score_codex":0.000009131868,"about_ca_system_score_gemma":0.00008770679,"threshold_uncertainty_score":0.1579764},"labels":[],"label_agreement":null},{"id":"W2338215681","doi":"10.1186/s12859-016-1015-8","title":"BAGEL: a computational framework for identifying essential genes from pooled library screens","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Computational biology; DNA microarray; Gene; Computer science; Biology; Genetics; Bioinformatics; Gene expression","score_opus":0.01657515414873308,"score_gpt":0.3018650987314888,"score_spread":0.28528994458275575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338215681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04372719,0.00045659192,0.95486563,0.000106853455,0.00024230896,0.00018907353,0.00025121297,0.00004245027,0.00011866473],"genre_scores_gemma":[0.15270394,0.000078632744,0.84587044,0.00018607332,0.0005023561,0.000022044676,0.00043078294,0.00003014713,0.00017557794],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922645,0.000010111095,0.0002883198,0.00014883051,0.000116172545,0.00021013842],"domain_scores_gemma":[0.9994808,0.000093422575,0.00008110437,0.0002290969,0.000037931797,0.000077652236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058607257,0.00014011517,0.00011908083,0.000042307136,0.00007101714,0.00006150793,0.00017666965,0.00014955628,0.00005127993],"category_scores_gemma":[0.00008013672,0.00011087246,0.00011583884,0.000051065803,0.00003850888,0.000018067323,0.00011682172,0.000037837963,0.000026390471],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015084564,0.00046232276,0.040787894,0.001993165,0.00215821,0.000009460006,0.0020464736,0.08496304,0.5888955,0.0295989,0.057851773,0.1897248],"study_design_scores_gemma":[0.0053269877,0.00043052185,0.015792567,0.0005670581,0.00029264085,0.000029288316,0.000854621,0.2711196,0.6229974,0.02620051,0.054605886,0.0017829146],"about_ca_topic_score_codex":0.0000015070239,"about_ca_topic_score_gemma":0.0000038261896,"teacher_disagreement_score":0.18794188,"about_ca_system_score_codex":0.000004843677,"about_ca_system_score_gemma":0.00006150624,"threshold_uncertainty_score":0.45212477},"labels":[],"label_agreement":null},{"id":"W2342801191","doi":"10.1186/s12859-016-1057-y","title":"ImiRP: a computational approach to microRNA target site mutation","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Canadian Institutes of Health Research; Alexander and Margaret Stewart Trust","keywords":"MiRBase; Biology; microRNA; Computational biology; Genetics; Mutation; Protein-fragment complementation assay; Mutant; Complementation; Gene","score_opus":0.011113234247392027,"score_gpt":0.23200430746932216,"score_spread":0.22089107322193013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342801191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18117213,0.000048204263,0.81684566,0.00010202088,0.0000550335,0.00030743793,0.000116581985,0.000026128486,0.0013268328],"genre_scores_gemma":[0.3177056,0.0000035388748,0.6803484,0.00037276433,0.00013906548,0.000033853587,0.0008706716,0.000022580063,0.00050351775],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919456,0.000024268076,0.00026416843,0.00016593869,0.0001542168,0.0001968417],"domain_scores_gemma":[0.99936444,0.0000144089745,0.00012037114,0.00024931916,0.00013060437,0.000120837234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012071402,0.00013867614,0.00009684421,0.00007248022,0.000061930536,0.000033028362,0.00013271677,0.00010127555,0.000015342779],"category_scores_gemma":[0.00008376085,0.00010546231,0.00009219122,0.00010092887,0.000041906605,0.000014922765,0.000083262734,0.000025158597,0.00023971281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064471556,0.00057591306,0.019137759,0.00062967645,0.00032402645,0.0000024549795,0.0015850366,0.12203615,0.6358226,0.0015070583,0.19752152,0.02021309],"study_design_scores_gemma":[0.006687617,0.0007987191,0.10474552,0.00018605668,0.00011021922,0.00024620775,0.00034344677,0.70471317,0.08849745,0.0013799723,0.09012085,0.0021707963],"about_ca_topic_score_codex":0.0000021020844,"about_ca_topic_score_gemma":0.0000019188253,"teacher_disagreement_score":0.582677,"about_ca_system_score_codex":0.000043924156,"about_ca_system_score_gemma":0.00012114413,"threshold_uncertainty_score":0.43006283},"labels":[],"label_agreement":null},{"id":"W2395761288","doi":"10.1186/s12859-016-1074-x","title":"RNA motif search with data-driven element ordering","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Division of Molecular and Cellular Biosciences; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Eurostars; Agentúra na Podporu Výskumu a Vývoja; Pew Charitable Trusts; National Institutes of Health; National Science Foundation","keywords":"Speedup; RNA; Motif (music); Computer science; Computational biology; Backtracking; Search algorithm; Structural motif; Nucleic acid structure; Algorithm; Biology; Genetics; Gene; Physics","score_opus":0.03514694564220968,"score_gpt":0.2618498593336783,"score_spread":0.22670291369146864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395761288","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1112504,0.00007551268,0.8851525,0.00015850701,0.000081516264,0.00035785744,0.00009627533,0.000031408174,0.0027959992],"genre_scores_gemma":[0.45265043,0.00029586162,0.5446411,0.00024091803,0.00026032247,0.00003687818,0.00022979893,0.000048895672,0.001595808],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990733,0.000026524367,0.00023007746,0.00018346103,0.0002098976,0.00027671817],"domain_scores_gemma":[0.9989165,0.000017163627,0.00007615634,0.0008483826,0.000056048062,0.000085759355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000256158,0.00013906001,0.00011171411,0.000033374246,0.0000732869,0.000035863224,0.0004636166,0.00008245303,0.00006643777],"category_scores_gemma":[0.00004711256,0.000082232364,0.000028518461,0.000054093332,0.000048905484,0.00001773738,0.00033149772,0.0000353826,0.00009978993],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034390276,0.00012259398,0.0032781598,0.00039488677,0.00025781762,0.000010847164,0.0002958131,0.00072755106,0.747579,0.0010386253,0.0043738787,0.24157694],"study_design_scores_gemma":[0.001916488,0.0008805239,0.0005043388,0.00020594127,0.00004866447,0.00009194534,0.00051023246,0.02031637,0.89624614,0.00007348804,0.07848937,0.0007165032],"about_ca_topic_score_codex":0.000004163642,"about_ca_topic_score_gemma":0.000028850727,"teacher_disagreement_score":0.34140003,"about_ca_system_score_codex":0.000011909347,"about_ca_system_score_gemma":0.00010295957,"threshold_uncertainty_score":0.33533385},"labels":[],"label_agreement":null},{"id":"W2467978015","doi":"10.1186/s12859-016-1125-3","title":"Reusable, extensible, and modifiable R scripts and Kepler workflows for comprehensive single set ChIP-seq analysis","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Stellar, planetary, and galactic studies","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Computer science; Pipeline (software); Workflow; Pipeline transport; Turnkey; Software; Scripting language; XML; Set (abstract data type); Modular design; Software engineering; Database; Operating system; Programming language; Engineering","score_opus":0.05041953886822691,"score_gpt":0.25351163983451525,"score_spread":0.20309210096628832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467978015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42742994,0.0026226062,0.49118727,0.00060614536,0.0009776014,0.0023240612,0.0009648913,0.0002496644,0.07363782],"genre_scores_gemma":[0.8593936,0.00019131915,0.1369889,0.0003461338,0.00034331201,0.00005695334,0.0002563214,0.000036767946,0.002386717],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989214,0.00001849418,0.00037571602,0.00019657177,0.00013869254,0.00034912865],"domain_scores_gemma":[0.9988455,0.00044355937,0.00017562874,0.00028749736,0.00013230731,0.0001154875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011049771,0.00023520665,0.00043344512,0.00013636444,0.0002230213,0.00010194028,0.000088026776,0.000057015077,0.000055231383],"category_scores_gemma":[0.00002645816,0.00016090224,0.00010132793,0.00022080535,0.00012350056,0.0002600856,0.000090331305,0.0000552523,0.000019242803],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077913704,0.000049331997,0.9725584,0.00017821621,0.0010213905,4.0260787e-7,0.0009423606,0.00035315254,0.00003223825,0.0009744471,0.013143831,0.010668361],"study_design_scores_gemma":[0.006723101,0.00050436147,0.544224,0.0002960903,0.0035055256,0.000014765057,0.004780919,0.3837297,0.0005222763,0.0071277493,0.04680583,0.0017656718],"about_ca_topic_score_codex":0.000080283986,"about_ca_topic_score_gemma":0.000022069127,"teacher_disagreement_score":0.43196365,"about_ca_system_score_codex":0.000012434876,"about_ca_system_score_gemma":0.000023308969,"threshold_uncertainty_score":0.65614027},"labels":[],"label_agreement":null},{"id":"W2474345237","doi":"10.1186/s12859-016-1142-2","title":"A De-Novo Genome Analysis Pipeline (DeNoGAP) for large-scale comparative prokaryotic genomics studies","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Genomics; Genome; DNA microarray; Comparative genomics; Biology; Pipeline (software); Genetics; Computer science; Gene; Gene expression","score_opus":0.03974294721149125,"score_gpt":0.30524999874263525,"score_spread":0.265507051531144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474345237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19661567,0.001034703,0.8005386,0.00010060218,0.0000951801,0.0007834665,0.0003922236,0.000029613686,0.0004099541],"genre_scores_gemma":[0.30778104,0.0009870029,0.68204284,0.0005227225,0.00066096924,0.00035344355,0.0008378835,0.00007116284,0.0067428956],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985268,0.00003496538,0.0005189517,0.00025086667,0.00015476298,0.00051364664],"domain_scores_gemma":[0.99882025,0.000053314954,0.00023620269,0.0004793057,0.00028954993,0.00012140176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047252927,0.00025433133,0.0004191554,0.00016057295,0.00013660571,0.00003981081,0.00029198077,0.00013464304,0.000022385055],"category_scores_gemma":[0.00009307109,0.00018203106,0.00027375066,0.00024706457,0.00009142423,0.000014601451,0.0001951909,0.000046488236,0.00005597892],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035669787,0.0032963527,0.108848214,0.006518138,0.04175349,0.000018522538,0.08640235,0.031178715,0.6588272,0.00223563,0.034622688,0.022731757],"study_design_scores_gemma":[0.019150965,0.0030119577,0.017245438,0.00016000065,0.006620999,0.000095550524,0.03599751,0.42413425,0.07831462,0.0012577787,0.40985957,0.004151358],"about_ca_topic_score_codex":8.629342e-7,"about_ca_topic_score_gemma":0.000109715416,"teacher_disagreement_score":0.5805125,"about_ca_system_score_codex":0.00010175983,"about_ca_system_score_gemma":0.00013023663,"threshold_uncertainty_score":0.7423011},"labels":[],"label_agreement":null},{"id":"W2482431271","doi":"10.1186/s12859-016-1098-2","title":"Sensorimotor control: computing the immediate future from the delayed present","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Vestibular and auditory disorders","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Model predictive control; Sensory system; Control (management); Artificial intelligence; Control theory (sociology); Neuroscience; Psychology","score_opus":0.017707616601213155,"score_gpt":0.23337582189107875,"score_spread":0.2156682052898656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482431271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1577441,0.00035511274,0.799879,0.026227927,0.008030247,0.0020755916,0.000873278,0.00046528474,0.0043494534],"genre_scores_gemma":[0.9812012,0.00014587806,0.005397784,0.008528515,0.004193751,0.000018879027,0.000009256358,0.000038506136,0.00046626647],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986944,0.00014903475,0.0003477096,0.00013590357,0.0003572813,0.00031563287],"domain_scores_gemma":[0.9975543,0.0016502792,0.00021451144,0.0004816794,0.000031643307,0.000067608074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023782943,0.0001598077,0.0001331077,0.00001634878,0.00038702643,0.00010504433,0.0005675601,0.000066616165,0.00003690973],"category_scores_gemma":[0.0004580999,0.00006174378,0.00009228968,0.00011600096,0.00021116695,0.00019347828,0.00010299663,0.0001521914,0.00041750414],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007515009,0.0003901124,0.026090488,0.00017897408,0.00027132413,0.000030656967,0.023464482,0.02406533,0.03554243,0.0078032743,0.6330314,0.24838],"study_design_scores_gemma":[0.003950278,0.00013040846,0.008811858,0.000083970524,0.00009324657,0.000026498781,0.0030817227,0.64416194,0.0067274817,0.0006811494,0.33169624,0.00055522105],"about_ca_topic_score_codex":0.000017874909,"about_ca_topic_score_gemma":0.000015473084,"teacher_disagreement_score":0.82345706,"about_ca_system_score_codex":0.000020813604,"about_ca_system_score_gemma":0.000066393746,"threshold_uncertainty_score":0.53663105},"labels":[],"label_agreement":null},{"id":"W2501117253","doi":"10.1186/s12859-016-1097-3","title":"Evaluating the necessity of PCR duplicate removal from next-generation sequencing data and a comparison of approaches","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":178,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Servier; Brigham Young University; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Transversion; Computational biology; Reference genome; Biology; DNA sequencing; Concordance; Genetics; Exome; Population; Data mining; Computer science; Bioinformatics; Exome sequencing; Gene; Mutation; Medicine","score_opus":0.3861978566480501,"score_gpt":0.34933855266425884,"score_spread":0.03685930398379128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501117253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9640781,0.0012690698,0.034132395,0.00005994014,0.000040248768,0.00013866225,0.00014199552,0.0000013895242,0.00013818861],"genre_scores_gemma":[0.915427,0.0001230579,0.08426057,0.000017638953,0.00007085047,0.0000032493854,0.00008054919,0.000005009175,0.0000120232835],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992499,0.00004136324,0.00037239454,0.00013364317,0.00010861577,0.00009410609],"domain_scores_gemma":[0.9990092,0.00006109033,0.00030066117,0.0005532337,0.000054330885,0.00002146706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004260937,0.00008850403,0.0001543835,0.000012943693,0.000070300266,0.000013836847,0.00025827222,0.000059241615,0.0000014162848],"category_scores_gemma":[0.0001641679,0.00005118764,0.000026317924,0.00003446421,0.00012775055,0.0000044178814,0.00038800098,0.00002673988,6.200606e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027185055,0.000013313669,0.013552845,0.000051464536,0.000055424993,1.8679396e-8,0.0006853486,0.00022919058,0.9443132,0.00005712328,0.0001096054,0.04090528],"study_design_scores_gemma":[0.00062998134,0.0002476798,0.008155677,0.000042903073,0.00009466381,0.000004722788,0.001770003,0.6646588,0.32355157,0.00019025804,0.00047697063,0.00017678294],"about_ca_topic_score_codex":0.000034844878,"about_ca_topic_score_gemma":0.00008682989,"teacher_disagreement_score":0.6644296,"about_ca_system_score_codex":0.0000056078593,"about_ca_system_score_gemma":0.000067882684,"threshold_uncertainty_score":0.20873713},"labels":[],"label_agreement":null},{"id":"W2507335589","doi":"10.1186/s12859-016-1157-8","title":"Additive methods for genomic signatures","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computational biology; DNA microarray; Genomics; Biology; Computer science; Genetics; Data science; Genome; Gene; Gene expression","score_opus":0.016123286081176188,"score_gpt":0.31055983991457325,"score_spread":0.29443655383339706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507335589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010584391,0.00034127638,0.9868138,0.000092567156,0.000092810136,0.00018430536,0.00012706054,0.000015535536,0.0017482776],"genre_scores_gemma":[0.0478002,0.00025297754,0.9484115,0.000740384,0.0002664996,0.000066728106,0.00021675433,0.000020020198,0.002224909],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994003,0.000023746028,0.00021120178,0.00012024486,0.000051340856,0.00019317752],"domain_scores_gemma":[0.9994525,0.00007524713,0.00010206581,0.00022881795,0.000081024016,0.00006038003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019513772,0.00011298487,0.00011844366,0.00004021988,0.000059167265,0.000017317092,0.00015893293,0.0001266795,0.00003671701],"category_scores_gemma":[0.00025430616,0.00006939642,0.00015372178,0.00005073982,0.00006882967,0.000009520344,0.00006141314,0.000026474258,0.000040148596],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011912929,0.000027631693,0.0002114642,0.000056179044,0.00012863193,2.0651854e-7,0.000080043435,0.00006128422,0.70970684,0.0007482365,0.010708787,0.27815157],"study_design_scores_gemma":[0.0011701887,0.0004817524,0.0009606108,0.000033311513,0.00010542285,0.0000067237397,0.00031299505,0.01338206,0.519355,0.001976334,0.4616783,0.00053731416],"about_ca_topic_score_codex":0.0000021754765,"about_ca_topic_score_gemma":0.000008627281,"teacher_disagreement_score":0.45096952,"about_ca_system_score_codex":0.000013583875,"about_ca_system_score_gemma":0.000063928586,"threshold_uncertainty_score":0.28299037},"labels":[],"label_agreement":null},{"id":"W2511892808","doi":"10.1186/s12859-016-1228-x","title":"The parameter sensitivity of random forests","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Canadian Institutes of Health Research; Government of Ontario; Movember Foundation","keywords":"Sensitivity (control systems); Random forest; DNA microarray; Computational biology; Computer science; Biology; Artificial intelligence; Genetics; Engineering; Gene","score_opus":0.015477327724937201,"score_gpt":0.2505137324377511,"score_spread":0.2350364047128139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511892808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18738808,0.00016283059,0.8097229,0.00028788263,0.00022494905,0.00022816598,0.000018682958,0.00001129535,0.0019551883],"genre_scores_gemma":[0.99434817,0.00015303763,0.0046579316,0.00006793193,0.00004914456,0.00001229797,0.0000079196325,0.0000055162013,0.0006980692],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999483,0.000049359332,0.00020103714,0.00006240786,0.00009658298,0.00010759554],"domain_scores_gemma":[0.9993484,0.00010547187,0.00012766776,0.0003226717,0.00006362005,0.000032186774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003253935,0.00006256019,0.00006593732,0.000014496166,0.000055008357,0.000010749412,0.00008545123,0.00006074132,0.000003744141],"category_scores_gemma":[0.00030109775,0.000029754616,0.00006311337,0.00003762004,0.0000914127,0.0000041477397,0.00004676171,0.000018641644,0.00001168087],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007704525,0.0000574601,0.030262053,0.000094551986,0.000068474066,2.5471195e-7,0.00016293484,0.000105859806,0.7120086,0.0011689481,0.03315802,0.22214241],"study_design_scores_gemma":[0.0030219182,0.00017749133,0.036291547,0.00006550974,0.000023699515,0.0000147617375,0.00020575845,0.01289565,0.7937935,0.0006479201,0.15259075,0.00027150963],"about_ca_topic_score_codex":0.0000011641582,"about_ca_topic_score_gemma":0.000040762163,"teacher_disagreement_score":0.80696005,"about_ca_system_score_codex":0.0000048622683,"about_ca_system_score_gemma":0.000048667396,"threshold_uncertainty_score":0.121335804},"labels":[],"label_agreement":null},{"id":"W2512143001","doi":"10.1186/s12859-016-1115-5","title":"Predicting essential proteins based on subcellular localization, orthology and PPI networks","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Subcellular localization; Computational biology; DNA microarray; Protein subcellular localization prediction; Biology; Computer science; Genetics; Gene; Gene expression","score_opus":0.00529630127268006,"score_gpt":0.21752425144842968,"score_spread":0.21222795017574964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512143001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050674282,0.0000464123,0.9469353,0.000115054325,0.0001586326,0.00037532326,0.000016000335,0.00006110574,0.001617911],"genre_scores_gemma":[0.9158099,0.00007903006,0.08202196,0.0010235053,0.0003380537,0.000039967534,0.0002623712,0.000048622296,0.00037655563],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869984,0.00006910775,0.0005035982,0.00018628001,0.00020233035,0.00033884463],"domain_scores_gemma":[0.99900866,0.000056666973,0.00026404014,0.0004576122,0.0000963192,0.00011668679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003719677,0.00022859918,0.00017290025,0.000085425665,0.00016734496,0.000049577877,0.00018868153,0.00027831484,0.000029938845],"category_scores_gemma":[0.00036073243,0.00016310145,0.000064177206,0.00010896439,0.00017438491,0.000016680511,0.00013552117,0.000122009566,0.000023935328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061943906,0.00023439193,0.7254546,0.0010700808,0.00013244881,0.0000071004715,0.0006096036,0.23927735,0.0050081387,0.0020315617,0.005160405,0.020394852],"study_design_scores_gemma":[0.0010987403,0.00042744356,0.0023595188,0.000085471234,0.00002140044,0.00002325041,0.00005289388,0.9863968,0.002826711,0.000018826988,0.006413172,0.00027577812],"about_ca_topic_score_codex":0.0000037313139,"about_ca_topic_score_gemma":0.000019773213,"teacher_disagreement_score":0.86513567,"about_ca_system_score_codex":0.00001677702,"about_ca_system_score_gemma":0.000084625055,"threshold_uncertainty_score":0.6651084},"labels":[],"label_agreement":null},{"id":"W2515914883","doi":"10.1186/s12859-016-1174-7","title":"CloneCNA: detecting subclonal somatic copy number alterations in heterogeneous tumor samples from whole-exome sequencing data","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; National Natural Science Foundation of China","keywords":"Biology; Exome sequencing; Somatic cell; Computational biology; Copy-number variation; Copy number analysis; DNA microarray; Genetics; Exome; Genome; Mutation; Gene","score_opus":0.04086990124518253,"score_gpt":0.2729770383497744,"score_spread":0.23210713710459185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515914883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8938334,0.0001940688,0.10359606,0.00007743723,0.00024393623,0.00023731889,0.0015727152,0.00002242155,0.00022266891],"genre_scores_gemma":[0.9005565,0.000114648996,0.097427525,0.00040199357,0.00031812536,0.000024727786,0.0010773254,0.000032341315,0.000046799523],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99853593,0.000034715966,0.00061300525,0.00029623305,0.00016482409,0.00035529496],"domain_scores_gemma":[0.9985152,0.00020409367,0.00021060208,0.00090011983,0.00006043499,0.000109584216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022296992,0.00021405291,0.00021756088,0.00005190211,0.00010871336,0.0000995318,0.00045708934,0.000113226364,0.000049323735],"category_scores_gemma":[0.00052440376,0.00017584494,0.00006413543,0.00009163875,0.00006890422,0.000033247034,0.000425415,0.000081333565,0.00011563226],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005188729,0.00036299304,0.4313036,0.0006460361,0.00043888373,0.000078967605,0.002152699,0.009444169,0.51544774,0.00052346766,0.007600797,0.0314818],"study_design_scores_gemma":[0.01223486,0.0008187986,0.026472438,0.0014510007,0.00033618102,0.0008284847,0.0030107286,0.38166794,0.50806916,0.004369937,0.05635428,0.004386201],"about_ca_topic_score_codex":0.00021831896,"about_ca_topic_score_gemma":0.0023562626,"teacher_disagreement_score":0.40483117,"about_ca_system_score_codex":0.00009710445,"about_ca_system_score_gemma":0.00032698363,"threshold_uncertainty_score":0.7170748},"labels":[],"label_agreement":null},{"id":"W2516950472","doi":"10.1186/s12859-016-1162-y","title":"BAMQL: a query language for extracting reads from BAM files","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; Ontario Institute for Cancer Research; Terry Fox Research Institute; Movember Foundation; Johns Hopkins University","keywords":"Computer science; Web search query; Information retrieval; Database; Programming language; Search engine","score_opus":0.017234525637118803,"score_gpt":0.252842834337511,"score_spread":0.23560830870039218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516950472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85492796,0.0011759157,0.14017291,0.00012347434,0.00031808374,0.00034945318,0.0007547995,0.000015862033,0.002161539],"genre_scores_gemma":[0.72717327,0.00038448875,0.2695611,0.0003812273,0.00071652426,0.00008114727,0.0002595641,0.000040164963,0.0014024915],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992707,0.0000122685215,0.00027058215,0.00014567215,0.00007169438,0.00022913255],"domain_scores_gemma":[0.9993422,0.00011427625,0.00012726722,0.00030562092,0.00005501951,0.000055604014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013086751,0.00014168119,0.00013626441,0.00002394491,0.0000820705,0.000023492346,0.00015213512,0.0001124224,0.00001675609],"category_scores_gemma":[0.00022367499,0.000098351906,0.00010320095,0.000026449092,0.000045943252,0.0000024593176,0.00010185521,0.000027078973,0.000029602792],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016023531,0.00005574159,0.008940055,0.00012563363,0.00018300321,8.595244e-7,0.0012442605,0.000040323324,0.90027547,0.00022087566,0.014360219,0.0743933],"study_design_scores_gemma":[0.005719613,0.0010108772,0.03905346,0.00027148545,0.00021435108,0.000031686475,0.0072946283,0.006359916,0.5762025,0.0016078183,0.36028633,0.0019473113],"about_ca_topic_score_codex":0.000015282903,"about_ca_topic_score_gemma":0.000066188164,"teacher_disagreement_score":0.3459261,"about_ca_system_score_codex":0.000010000339,"about_ca_system_score_gemma":0.00005219066,"threshold_uncertainty_score":0.40106744},"labels":[],"label_agreement":null},{"id":"W2520927888","doi":"10.1186/s12859-016-1238-8","title":"A haplotype-based normalization technique for the analysis and detection of allele specific expression","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Syndromes and Imprinting","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research; University of Toronto; Ontario Institute for Cancer Research; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Medical Research Council; Partenariat Canadien Contre Le Cancer; Fonds Québécois de la Recherche sur la Nature et les Technologies; Ontario Institute for Cancer Research","keywords":"Haplotype; DNA microarray; Normalization (sociology); Allele; Genetics; Computational biology; Biology; Haplotype estimation; Gene expression; Gene","score_opus":0.011896984848092967,"score_gpt":0.22670366014951726,"score_spread":0.2148066753014243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520927888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08400572,0.00011189303,0.9155435,0.000017285327,0.000021320711,0.00025811122,0.000009065185,0.0000048267657,0.000028307742],"genre_scores_gemma":[0.91166157,0.00011409342,0.08807881,0.000017321805,0.000023532884,0.000042593303,0.000017945806,0.000006615208,0.000037500406],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995582,0.000011857949,0.00020316598,0.00007531186,0.000062649815,0.00008880679],"domain_scores_gemma":[0.9995365,0.000034232726,0.00013326302,0.00020768307,0.00006803511,0.000020242605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001798138,0.00006577624,0.000079850695,0.000055831348,0.000058791866,0.000010775249,0.00007246593,0.0000708359,0.000004763287],"category_scores_gemma":[0.000056238227,0.000036996436,0.000071626426,0.00010354157,0.00004008318,0.0000044184517,0.000037739122,0.000013058408,6.2911784e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019545218,0.000009340624,0.004288824,0.000055413635,0.000035107827,5.9658256e-9,0.000026200745,0.00026750425,0.9809696,0.000009686512,0.00004669762,0.014272054],"study_design_scores_gemma":[0.00034281358,0.00011666528,0.01400849,0.000015136926,0.000058669008,0.0000022368827,0.000065621614,0.018942334,0.9626242,0.000014572081,0.0037347118,0.00007456444],"about_ca_topic_score_codex":0.0000027714173,"about_ca_topic_score_gemma":0.000013145659,"teacher_disagreement_score":0.82765585,"about_ca_system_score_codex":0.0000040444465,"about_ca_system_score_gemma":0.000016176422,"threshold_uncertainty_score":0.15086709},"labels":[],"label_agreement":null},{"id":"W2527996525","doi":"10.1186/s12859-016-1214-3","title":"VDJML: a file format with tools for capturing the results of inferring immune receptor rearrangements","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"T-cell and B-cell Immunology","field":"Immunology and Microbiology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Institutes of Health; Pharmaceutical Research and Manufacturers of America Foundation","keywords":"DNA microarray; File format; Computational biology; Computer science; Immune receptor; Immune system; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.0258210095417527,"score_gpt":0.22303082367523128,"score_spread":0.19720981413347857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527996525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8059241,0.00413571,0.11735603,0.002691039,0.0050375694,0.008528442,0.012278669,0.00090920855,0.043139186],"genre_scores_gemma":[0.92672014,0.00040610656,0.04730473,0.00028414768,0.00010959706,0.00046982573,0.0015350761,0.000083428786,0.023086961],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985621,0.00005214021,0.0007554801,0.0001302382,0.000053719596,0.00044635122],"domain_scores_gemma":[0.9980039,0.00083436706,0.00048856315,0.00053139706,0.00012469766,0.00001704955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003843206,0.00020672417,0.00031691758,0.0000881487,0.00022099957,0.000026636917,0.00040436414,0.00020299488,0.00035929508],"category_scores_gemma":[0.00033868803,0.00010011894,0.00011927201,0.000105009414,0.00029733145,0.0004295469,0.0001556051,0.0001410443,0.0002793161],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033168984,0.00018664994,0.00030814536,0.00046930878,0.000615495,5.1771303e-7,0.006232788,0.00004561541,0.87083554,0.00086844224,0.06292501,0.054195557],"study_design_scores_gemma":[0.012985322,0.0011333382,0.00069698045,0.0006771938,0.000120488534,0.000068983,0.0040727905,0.00028800016,0.5364881,0.00007317565,0.44286928,0.00052633317],"about_ca_topic_score_codex":0.000044242042,"about_ca_topic_score_gemma":0.00004766479,"teacher_disagreement_score":0.37994426,"about_ca_system_score_codex":0.000037128724,"about_ca_system_score_gemma":0.00007640224,"threshold_uncertainty_score":0.40827316},"labels":[],"label_agreement":null},{"id":"W2528057066","doi":"10.1186/s12859-016-1281-5","title":"VennDiagramWeb: a web application for the generation of highly customizable Venn and Euler diagrams","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Department of Medical Biophysics, University of Toronto; Canadian Institutes of Health Research; Prostate Cancer Canada; Government of Ontario; Movember Foundation; Terry Fox Research Institute; University of Toronto","keywords":"Venn diagram; Computer science; Visualization; Web application; Upload; Wizard; Documentation; Graphics; Pipeline (software); Data visualization; Interface (matter); Programming language; Data mining; World Wide Web; Computer graphics (images); Operating system","score_opus":0.013876133246091655,"score_gpt":0.24759717050703609,"score_spread":0.23372103726094443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528057066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054034498,0.00037848862,0.94468254,0.00011889471,0.000021061323,0.00048899784,0.00002029762,0.000018214489,0.0002370067],"genre_scores_gemma":[0.9517791,0.00082330784,0.046464182,0.00012289135,0.0001714216,0.00021112536,0.00012998834,0.000016269874,0.00028171105],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946785,0.00001256331,0.00024301841,0.00009895176,0.00007251143,0.00010510152],"domain_scores_gemma":[0.9993173,0.000054907454,0.00015812786,0.00034544122,0.000097889264,0.00002637496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024151389,0.00008474634,0.00009766818,0.00003109445,0.00005686712,0.000017946615,0.00012125975,0.0000843822,0.0000019122608],"category_scores_gemma":[0.00011252804,0.000049247894,0.00006735735,0.000059905804,0.000080008125,0.000010594681,0.00005430856,0.00001914934,0.000003998453],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004422918,0.000043728323,0.0018800624,0.00010499973,0.00007007276,3.3595065e-8,0.00005843278,0.00005147302,0.8979584,0.00070958666,0.014371378,0.08470761],"study_design_scores_gemma":[0.000744902,0.00017377715,0.00039075164,0.000015455413,0.000106009786,0.0000036858105,0.000051618943,0.11705884,0.7783436,0.00015116732,0.10277883,0.00018133591],"about_ca_topic_score_codex":0.000005736762,"about_ca_topic_score_gemma":0.00005424959,"teacher_disagreement_score":0.89821833,"about_ca_system_score_codex":0.00000862652,"about_ca_system_score_gemma":0.000039937306,"threshold_uncertainty_score":0.20082708},"labels":[],"label_agreement":null},{"id":"W2529628971","doi":"10.1186/s12859-016-1265-5","title":"A continuous analog of run length distributions reflecting accumulated fractionation events","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fractionation; Inference; Biological system; Computer science; Algorithm; Series (stratigraphy); Distribution (mathematics); Line (geometry); DNA microarray; Computational biology; Biology; Artificial intelligence; Mathematics; Gene; Chemistry; Chromatography; Geometry; Genetics","score_opus":0.04314688451154655,"score_gpt":0.27792341373562685,"score_spread":0.2347765292240803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529628971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865199,0.000014794154,0.011028933,0.0005380441,0.00012227042,0.0001810646,0.0003007267,0.00006189393,0.0012323876],"genre_scores_gemma":[0.99465317,0.000015196552,0.0049566454,0.000022976024,0.00006121203,0.000006245394,0.0001334185,4.442562e-7,0.00015067558],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992875,0.000023541566,0.000329959,0.0000720877,0.00015017844,0.00013675862],"domain_scores_gemma":[0.99932116,0.00023891198,0.00021252729,0.00004776455,0.00013433954,0.00004530659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012215768,0.00007334061,0.00010362535,0.000013444481,0.00015003703,0.000012998195,0.0001025171,0.00006983398,0.00022975891],"category_scores_gemma":[0.00022905403,0.000024882414,0.000065491324,0.0002701052,0.000023269202,0.00017440005,0.0000354401,0.000036680693,0.000048139977],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007917933,0.0005367535,0.20933226,0.000066887755,0.00012243941,5.227539e-7,0.0006190305,0.0001348276,0.37910318,0.0089303255,0.0007613508,0.40031326],"study_design_scores_gemma":[0.000726616,0.0003263881,0.95736504,0.00012082602,0.000051605475,0.000017130807,0.000518043,0.012495523,0.0083735185,0.0049123736,0.01476568,0.00032723023],"about_ca_topic_score_codex":0.00003171097,"about_ca_topic_score_gemma":0.0001889581,"teacher_disagreement_score":0.7480328,"about_ca_system_score_codex":0.000030632775,"about_ca_system_score_gemma":0.000015718737,"threshold_uncertainty_score":0.2515699},"labels":[],"label_agreement":null},{"id":"W2550915265","doi":"10.1186/s12859-016-1352-7","title":"Introducing Explorer of Taxon Concepts with a case study on spider measurement matrix building","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Consejo Nacional de Investigaciones Científicas y Técnicas; University of Florida; Stony Brook University; National Science Foundation","keywords":"Spider; Taxon; Data science; Biology; Evolutionary biology; Computer science; Matrix (chemical analysis); Computational biology; Geography; Ecology; Chemistry","score_opus":0.051289187817629374,"score_gpt":0.3172159791570347,"score_spread":0.26592679133940533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550915265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85079205,0.00009206303,0.14851874,0.000070101814,0.00009305891,0.00028265035,0.0000077688765,0.000021608676,0.00012195598],"genre_scores_gemma":[0.92717534,0.000007843946,0.07260523,0.000050525774,0.00008896871,0.000023742543,0.0000018994994,0.000011441253,0.000035009452],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988821,0.00004501865,0.0003610154,0.00017650728,0.00031925034,0.00021609069],"domain_scores_gemma":[0.9991663,0.000036134596,0.00018731016,0.0004063226,0.00013275367,0.00007114934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004934359,0.00015764526,0.00019545008,0.000055819506,0.000054464243,0.000015222358,0.00013368024,0.00009515342,0.0000084469075],"category_scores_gemma":[0.00035075055,0.00008602102,0.000049329123,0.000078485245,0.00014126372,0.0000061736782,0.00008271416,0.00005655994,0.000007553261],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029801482,0.0039000944,0.12541707,0.0015326418,0.0017188622,0.0005666808,0.018512815,0.0012254677,0.3036752,0.0005821362,0.017227044,0.52266186],"study_design_scores_gemma":[0.029275136,0.047323633,0.0092402855,0.0025232628,0.0006506082,0.0035384395,0.17586948,0.005025258,0.6696995,0.000105558414,0.053369343,0.0033795333],"about_ca_topic_score_codex":0.000015220916,"about_ca_topic_score_gemma":0.000032057982,"teacher_disagreement_score":0.51928234,"about_ca_system_score_codex":0.000026997113,"about_ca_system_score_gemma":0.000079697566,"threshold_uncertainty_score":0.35078356},"labels":[],"label_agreement":null},{"id":"W2555781494","doi":"10.1186/s12859-016-1319-8","title":"SABRE: a method for assessing the stability of gene modules in complex tissues and subject populations","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; BC Centre for Disease Control; Prevention of Organ Failure","funders":"Canadian Institutes of Health Research; Genome British Columbia; Providence Health Care; St. Paul's Foundation; Genome Canada","keywords":"Computational biology; Subject (documents); DNA microarray; Biology; Gene; Stability (learning theory); Computer science; Genetics; Bioinformatics; Gene expression; World Wide Web","score_opus":0.058376568827618255,"score_gpt":0.33337908630893925,"score_spread":0.275002517481321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555781494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15894334,0.00020141997,0.8399125,0.00014833699,0.000045767505,0.00038084024,0.000098173005,0.000005560439,0.00026407914],"genre_scores_gemma":[0.4418441,0.000042274525,0.55788434,0.000072092924,0.00004230797,0.000018455616,0.00006967635,0.000007988205,0.000018779401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910945,0.000043903314,0.00048672856,0.000097616816,0.00007794645,0.00018435386],"domain_scores_gemma":[0.99927723,0.00010713529,0.00019738649,0.00031268783,0.000068765214,0.000036789294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067975523,0.00011567667,0.0001716359,0.000028234877,0.000078327095,0.000031631014,0.00014085248,0.000104186736,0.000005155827],"category_scores_gemma":[0.0001231201,0.000067948786,0.000060930302,0.000067897054,0.000110231886,0.00001712907,0.000080312624,0.00003746807,6.833022e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003857494,0.0003125978,0.1780358,0.002014425,0.0002380325,3.796796e-7,0.0050928784,0.002146704,0.25080186,0.015805466,0.0056719333,0.53949416],"study_design_scores_gemma":[0.0034013637,0.00037526805,0.14354488,0.00013754588,0.00009034588,0.000036948124,0.002795044,0.7709193,0.056723755,0.008261358,0.012987213,0.00072692],"about_ca_topic_score_codex":0.00001856292,"about_ca_topic_score_gemma":0.00018764395,"teacher_disagreement_score":0.76877266,"about_ca_system_score_codex":0.000012980684,"about_ca_system_score_gemma":0.00004763236,"threshold_uncertainty_score":0.27708712},"labels":[],"label_agreement":null},{"id":"W2561707810","doi":"10.1186/s12859-016-1431-9","title":"Fast-GBS: a new pipeline for the efficient and highly accurate calling of SNPs from genotyping-by-sequencing data","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":142,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Canadian Field Crop Research Alliance; Université Laval","keywords":"Genotyping; Indel; Genome; Biology; Reference genome; DNA sequencing; Computational biology; Whole genome sequencing; Genetics; Single-nucleotide polymorphism; Deep sequencing; SNP genotyping; Genotype; Gene","score_opus":0.06061099289774968,"score_gpt":0.2842035901364003,"score_spread":0.2235925972386506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561707810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15902144,0.0008213016,0.8383414,0.00016640163,0.00020937134,0.00027774493,0.0010055933,0.000005765092,0.00015095779],"genre_scores_gemma":[0.8738264,0.00018714402,0.123957485,0.0002338238,0.00024384487,0.0000021797596,0.0011990456,0.000011657395,0.00033842155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993882,0.000008295021,0.00023990445,0.00013588309,0.00009966926,0.00012804569],"domain_scores_gemma":[0.99874264,0.000037440142,0.00029087104,0.00080946233,0.00006364179,0.000055922308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015843078,0.00010256792,0.00011380461,0.000012845266,0.00028024954,0.00009093047,0.0005776738,0.00010086769,0.000005591174],"category_scores_gemma":[0.0002118151,0.000076048746,0.000035351142,0.000016001308,0.00008017817,0.0000112159505,0.00041299168,0.000047253205,0.0000018330968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018049555,0.0001525404,0.030634915,0.0019003826,0.0012852864,0.0000020743848,0.012830421,0.22830825,0.25609255,0.0017543676,0.17859901,0.28663525],"study_design_scores_gemma":[0.0014370627,0.00006548187,0.0037831706,0.000046008205,0.00015114571,0.0000038444246,0.0009753547,0.9277169,0.022979865,0.00012901692,0.042451754,0.00026038173],"about_ca_topic_score_codex":0.00018545882,"about_ca_topic_score_gemma":0.00009454849,"teacher_disagreement_score":0.71480495,"about_ca_system_score_codex":0.000004895231,"about_ca_system_score_gemma":0.00009433851,"threshold_uncertainty_score":0.31011778},"labels":[],"label_agreement":null},{"id":"W2562192001","doi":"10.1186/s12859-016-1387-9","title":"Prior knowledge guided eQTL mapping for identifying candidate genes","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Computational biology; DNA microarray; Expression quantitative trait loci; Gene; Biology; Genetics; Candidate gene; Gene expression; Single-nucleotide polymorphism; Genotype","score_opus":0.08867604310489179,"score_gpt":0.2864843301914792,"score_spread":0.19780828708658738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562192001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96381205,0.00071970397,0.030247942,0.0004841027,0.0009021266,0.00060254376,0.00019771031,0.00011362943,0.0029202036],"genre_scores_gemma":[0.84187615,0.0009756632,0.14555585,0.0005703286,0.002632488,0.00017983379,0.00021419639,0.000007730296,0.007987729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911696,0.000018833263,0.00034263445,0.00012449626,0.00008042928,0.00031662278],"domain_scores_gemma":[0.99944067,0.00020213859,0.000105615065,0.00006759031,0.00010285057,0.000081126294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000268681,0.00012548921,0.0001613475,0.000019131108,0.00022725912,0.000061916166,0.00021161551,0.0000988933,0.00009148832],"category_scores_gemma":[0.00006243323,0.000038414462,0.00010548039,0.00012364222,0.000043651115,0.00011339998,0.000081578815,0.000027206803,0.00011894541],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002204103,0.000042643544,0.003956678,0.00014749377,0.000018473902,7.756386e-7,0.000604422,0.0000028960667,0.20394127,0.000758319,0.008267324,0.78223765],"study_design_scores_gemma":[0.0029677418,0.0009355717,0.067139216,0.0007453473,0.00012749783,0.00016087445,0.0031928401,0.023348587,0.10228734,0.0061163376,0.7907736,0.0022050731],"about_ca_topic_score_codex":0.0000104159235,"about_ca_topic_score_gemma":0.00027679853,"teacher_disagreement_score":0.7825063,"about_ca_system_score_codex":0.00001544676,"about_ca_system_score_gemma":0.000018024108,"threshold_uncertainty_score":0.17479163},"labels":[],"label_agreement":null},{"id":"W2562995081","doi":"10.1186/s12859-016-1340-y","title":"Compromise or optimize? The breakpoint anti-median","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Compromise; Phylogenetic tree; Generality; Biology; Adjacency list; Computational biology; Computer science; Data mining; Mathematics; Algorithm; Genetics; Gene","score_opus":0.020010118488466774,"score_gpt":0.2385707755167301,"score_spread":0.21856065702826333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562995081","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31226182,0.00047374563,0.66673064,0.0043417863,0.0012922849,0.0022444152,0.0002612306,0.00015992003,0.012234133],"genre_scores_gemma":[0.3700041,0.0016774379,0.6083492,0.0021105723,0.001363159,0.00017203591,0.00026539588,0.00012999156,0.015928118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990479,0.000029013092,0.00031411773,0.0001367841,0.00017400684,0.00029820387],"domain_scores_gemma":[0.9991205,0.00003517389,0.00012427448,0.0005643858,0.000059573504,0.00009610613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024859075,0.00016536089,0.00013737618,0.000033876808,0.00009671807,0.000041741194,0.00036650532,0.000106545696,0.00011947897],"category_scores_gemma":[0.00009932909,0.000075562886,0.000093933355,0.000079089,0.00014255126,0.0000088042125,0.00018552384,0.000050742427,0.0002739503],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015981308,0.00094867987,0.032868575,0.0013309099,0.0013851383,0.000033542594,0.003912799,0.0025287275,0.30948022,0.00077796925,0.2482603,0.396875],"study_design_scores_gemma":[0.015927602,0.001921635,0.024217958,0.0003142274,0.00026115243,0.00050205336,0.0030769203,0.09601589,0.13554332,0.0003193346,0.719231,0.0026689102],"about_ca_topic_score_codex":0.0000032988569,"about_ca_topic_score_gemma":0.000017535016,"teacher_disagreement_score":0.4709707,"about_ca_system_score_codex":0.000016022823,"about_ca_system_score_gemma":0.00009010013,"threshold_uncertainty_score":0.35211685},"labels":[],"label_agreement":null},{"id":"W2565874974","doi":"10.1186/s12859-016-1330-0","title":"Spectra library assisted de novo peptide sequencing for HCD and ETD spectra pairs","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Biology","score_opus":0.025093549680734226,"score_gpt":0.25720118263225245,"score_spread":0.2321076329515182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565874974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034841117,0.000040488598,0.9319968,0.00036826008,0.000013128298,0.00032628508,0.00019862349,0.00046722704,0.03174807],"genre_scores_gemma":[0.02360672,0.00013522667,0.9740965,0.00015693015,0.000111421505,0.00014034627,0.000034524837,0.000035326284,0.0016830512],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910396,0.0000035975395,0.0003562089,0.00014024961,0.00008498811,0.0003110048],"domain_scores_gemma":[0.99917877,0.00017536843,0.00017025277,0.00033684808,0.000023256176,0.00011553552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000092113936,0.00016264038,0.00015641049,0.00004178642,0.00012433562,0.00006182562,0.00018825942,0.00013111463,0.00011764396],"category_scores_gemma":[0.000059855356,0.00012439628,0.00007505693,0.00007597425,0.00007578068,0.0004056716,0.0000697631,0.000104691935,0.000013800275],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028427358,0.00019758755,0.013699901,0.0045454917,0.00016097688,0.000014396162,0.0021768538,0.0000840111,0.7111994,0.15078643,0.0102953855,0.10655529],"study_design_scores_gemma":[0.0015063966,0.00007869425,0.0003313423,0.00043961275,0.000059151214,0.00026085653,0.00085950794,0.03523524,0.87535024,0.050845757,0.034256518,0.00077670714],"about_ca_topic_score_codex":0.0000018191349,"about_ca_topic_score_gemma":0.000004445821,"teacher_disagreement_score":0.16415082,"about_ca_system_score_codex":0.00011284615,"about_ca_system_score_gemma":0.00014431821,"threshold_uncertainty_score":0.5072733},"labels":[],"label_agreement":null},{"id":"W2567538927","doi":"10.1186/s12859-016-1370-5","title":"Ceph-X: development and evaluation of 2D cephalometric system","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Malaya; Ryerson University","keywords":"Cephalometric analysis; Usability; Reliability (semiconductor); Computer science; Orthodontics; Metric (unit); Artificial intelligence; Medicine; Engineering","score_opus":0.03751919568225653,"score_gpt":0.27639536932325015,"score_spread":0.23887617364099362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567538927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93570864,0.00040640804,0.048650887,0.0000055351948,0.00042802223,0.00028405804,0.000020535383,0.00006311333,0.014432824],"genre_scores_gemma":[0.96543014,0.000005082182,0.034398872,0.00000806831,0.000016726333,0.000008318119,0.000005571084,0.000006643141,0.00012055043],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987124,0.000034362296,0.00046761535,0.00007731809,0.0005604926,0.00014780907],"domain_scores_gemma":[0.9993211,0.00008376958,0.00021647789,0.00017887168,0.0001414284,0.00005837274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008096387,0.000096708696,0.0001409126,0.00038349273,0.000056817637,0.00003256355,0.00010253222,0.000047102407,0.000037129106],"category_scores_gemma":[0.000101722224,0.00006583332,0.000046951707,0.00043578164,0.00005006125,0.000370913,0.000051059735,0.000030220644,0.000125623],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000402001,0.000095048315,0.26784733,0.0025876483,0.00013593589,0.0000033786691,0.0021911648,0.000025555722,0.0006943304,0.006069639,0.0014508928,0.7188589],"study_design_scores_gemma":[0.0049588615,0.00007445656,0.87307775,0.00074708235,0.00029338963,0.00030444778,0.0067349267,0.08925039,0.018708885,0.0001210418,0.005147387,0.00058134686],"about_ca_topic_score_codex":0.0000028142088,"about_ca_topic_score_gemma":0.0000070971755,"teacher_disagreement_score":0.7182775,"about_ca_system_score_codex":0.00008773028,"about_ca_system_score_gemma":0.000086960856,"threshold_uncertainty_score":0.2684605},"labels":[],"label_agreement":null},{"id":"W2592654158","doi":"10.1186/s12859-017-1558-3","title":"Drug voyager: a computational platform for exploring unintended drug action","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Pharmacogenomics; Drug; Computer science; Adverse effect; Systems pharmacology; Drug action; Drug discovery; Exploit; Mechanism (biology); Computational biology; Bioinformatics; Medicine; Risk analysis (engineering); Pharmacology; Biology; Computer security","score_opus":0.17984133807801395,"score_gpt":0.35653701162446017,"score_spread":0.17669567354644622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592654158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012762071,0.000012798848,0.98252046,0.00067309936,0.0012981127,0.00042958604,0.00002328326,0.00020706323,0.0020735029],"genre_scores_gemma":[0.074898764,0.000006374815,0.9242809,0.00017850865,0.00014329368,0.00009362668,0.00004108634,0.000015291424,0.00034216227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983598,0.00003148157,0.0005356411,0.00024127371,0.00048274413,0.0003490529],"domain_scores_gemma":[0.9976511,0.0006571059,0.0005187384,0.0007840334,0.00026114815,0.0001278603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008664649,0.00021565291,0.00023072147,0.00018872999,0.0008893375,0.0010024535,0.0013956188,0.000044356555,0.0000054655466],"category_scores_gemma":[0.00039584935,0.00020912354,0.00016948019,0.00012652235,0.00011678853,0.005101806,0.00051325554,0.00015380153,0.000071486094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006699508,0.00010525659,0.0005190348,0.00046229304,0.00007188189,0.0000023967164,0.006803453,0.37694854,0.000007781853,0.43376818,0.0069684237,0.17427577],"study_design_scores_gemma":[0.0007013329,0.000021180133,0.0037947258,0.000045979927,0.000009237513,0.000014466303,0.00039940508,0.9335919,0.0002757912,0.0575355,0.0033591872,0.00025132086],"about_ca_topic_score_codex":0.000020440508,"about_ca_topic_score_gemma":0.000035193614,"teacher_disagreement_score":0.55664337,"about_ca_system_score_codex":0.00013004671,"about_ca_system_score_gemma":0.0002821958,"threshold_uncertainty_score":0.96666825},"labels":[],"label_agreement":null},{"id":"W2594310188","doi":"10.1186/s12859-017-1564-5","title":"Two-way learning with one-way supervision for gene expression data","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; McMaster University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Biclustering; Mixture model; Computer science; Data set; Covariance matrix; Data mining; Bayesian probability; Expectation–maximization algorithm; Pattern recognition (psychology); Microarray analysis techniques; Artificial intelligence; Algorithm; Cluster analysis; Mathematics; Gene expression; Gene; Statistics; Biology; Genetics","score_opus":0.0696000141553618,"score_gpt":0.31492623011808707,"score_spread":0.24532621596272527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594310188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12383456,0.00032512224,0.86808115,0.0002120588,0.00033239927,0.00075415435,0.00012349439,0.000052871263,0.0062842006],"genre_scores_gemma":[0.6079379,0.00025489143,0.38748282,0.0001524269,0.0004068728,0.00006719906,0.0021640155,0.000041447864,0.001492441],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990078,0.000024062689,0.0002628847,0.0002829963,0.00019557828,0.00022665935],"domain_scores_gemma":[0.99772197,0.00001390702,0.00031125106,0.001739608,0.00011650377,0.00009676996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029513304,0.00015750533,0.00013856938,0.00003808875,0.00055210956,0.00017419049,0.00080811343,0.00012715092,0.000014460309],"category_scores_gemma":[0.00019309603,0.00012224338,0.00004494153,0.000028261466,0.00007063476,0.000047295052,0.00045919683,0.00009056812,0.000015300186],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055003987,0.00010743293,0.007262476,0.00027756777,0.00004494447,3.8048833e-7,0.00026172018,0.0009870538,0.94375986,0.00014438227,0.010956732,0.03564741],"study_design_scores_gemma":[0.0035167725,0.0005264812,0.0050300607,0.00019028709,0.000054895176,0.000011763328,0.00071911904,0.08406047,0.7630141,0.00005375664,0.14226715,0.0005551493],"about_ca_topic_score_codex":0.0000060669176,"about_ca_topic_score_gemma":0.000023453284,"teacher_disagreement_score":0.48410332,"about_ca_system_score_codex":0.000010278183,"about_ca_system_score_gemma":0.00009023507,"threshold_uncertainty_score":0.49849406},"labels":[],"label_agreement":null},{"id":"W2594844287","doi":"10.1186/s12859-017-1559-2","title":"Reactome pathway analysis: a high-performance in-memory approach","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":927,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; European Bioinformatics Institute","keywords":"Computer science; DNA microarray; Computational biology; Biology; Genetics; Gene; Gene expression","score_opus":0.014243692549370851,"score_gpt":0.22662885348526707,"score_spread":0.2123851609358962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594844287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83733106,0.00026679816,0.09567266,0.00004926585,0.0003745451,0.0005661005,0.00006353035,0.000040282725,0.06563574],"genre_scores_gemma":[0.93956393,0.00012395592,0.05889128,0.00020457986,0.00016813583,0.000030370498,0.00031765422,0.000018882622,0.00068120105],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847406,0.00001918148,0.00063613435,0.00021628721,0.000204233,0.00045009446],"domain_scores_gemma":[0.9978706,0.000009908904,0.0004751769,0.0014613847,0.00006250152,0.00012037887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005338714,0.00025802798,0.00034553988,0.0001817562,0.00026985488,0.00019826357,0.00076819723,0.0002924935,0.000008564676],"category_scores_gemma":[0.000058817644,0.00022877447,0.00016133618,0.00017597219,0.00014413122,0.0000355265,0.00034770265,0.00020151753,0.000045943278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011820752,0.0013964069,0.5115099,0.0034343642,0.0037369414,0.00001839541,0.0059629516,0.21593954,0.0047983225,0.005198833,0.0046599247,0.24216235],"study_design_scores_gemma":[0.002366341,0.00025640507,0.26593176,0.000054516648,0.00020232139,0.000025720778,0.0007231585,0.719676,0.0027676472,0.00012039309,0.006887678,0.0009880355],"about_ca_topic_score_codex":0.000037992406,"about_ca_topic_score_gemma":0.0001304698,"teacher_disagreement_score":0.5037365,"about_ca_system_score_codex":0.00002721529,"about_ca_system_score_gemma":0.00012485702,"threshold_uncertainty_score":0.9329152},"labels":[],"label_agreement":null},{"id":"W2595675726","doi":"10.1186/s12859-017-1596-x","title":"Bioinformatics identification of new targets for improving low temperature stress tolerance in spring and winter wheat","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Plant Stress Responses and Tolerance","field":"Agricultural and Biological Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Biology; Gene; Cultivar; Cold stress; Genetics; Gene expression; Phenotype; DNA microarray; Adaptation (eye); Botany","score_opus":0.017537560967064183,"score_gpt":0.23500215439806982,"score_spread":0.21746459343100563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2595675726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978416,0.0001815676,0.0008873776,0.00017774825,0.0001723099,0.0003644496,0.00024289369,0.000017140494,0.00011494184],"genre_scores_gemma":[0.98777264,0.000093846145,0.011676962,0.000051040315,0.000096246375,0.000011037344,0.000042965374,0.0000012778684,0.00025397402],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990428,0.000007724724,0.00049974356,0.00010488445,0.00012923985,0.0002155943],"domain_scores_gemma":[0.9992379,0.000092280345,0.0004173687,0.00013176735,0.00005207448,0.000068643014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016028843,0.00013113173,0.00020498555,0.000021661435,0.00021749167,0.00023826574,0.00030204572,0.000103669336,0.0000062483246],"category_scores_gemma":[0.000114599134,0.000060632457,0.000055618137,0.000052143652,0.00005466698,0.00066929316,0.00008505092,0.00008368746,0.0000026170137],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000850637,0.00020039093,0.17437343,0.004504571,0.00003843788,0.0000034618436,0.00325356,0.0014521407,0.2281301,0.00074121426,0.00073798967,0.58571404],"study_design_scores_gemma":[0.000751651,0.000102181024,0.67336917,0.000436507,0.000012019817,0.000004710015,0.0005056392,0.29256496,0.030920783,0.000097160184,0.0009328799,0.0003023109],"about_ca_topic_score_codex":0.0001354246,"about_ca_topic_score_gemma":0.0007601582,"teacher_disagreement_score":0.5854117,"about_ca_system_score_codex":0.000012105114,"about_ca_system_score_gemma":0.00001664052,"threshold_uncertainty_score":0.24725199},"labels":[],"label_agreement":null},{"id":"W2605595174","doi":"10.1186/s12859-017-1602-3","title":"A machine learning approach for viral genome classification","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Subtyping; Computational biology; In silico; Genetics; Artificial intelligence; Computer science; Gene","score_opus":0.029051288775398105,"score_gpt":0.28135736090967217,"score_spread":0.2523060721342741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605595174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010625185,0.00011206914,0.9508111,0.00006904471,0.00014734638,0.00068823533,0.00007068175,0.00006593917,0.03741042],"genre_scores_gemma":[0.25324067,0.00009091047,0.7404467,0.00021031729,0.00035215993,0.0001052137,0.0024073026,0.00005073725,0.0030959737],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876714,0.000028876588,0.00047964495,0.00018744833,0.00018638969,0.0003504775],"domain_scores_gemma":[0.99822307,0.000018586477,0.0006318124,0.0009070194,0.0001173707,0.00010212579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053152104,0.00023218442,0.00020101233,0.0000641783,0.00077608717,0.00027083457,0.0006797421,0.00022618347,0.000009046016],"category_scores_gemma":[0.0007537461,0.00021221723,0.00015500309,0.000029923216,0.00013743712,0.000034927434,0.0002562544,0.00020717639,0.00003375246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035537528,0.0017322487,0.38629824,0.015000826,0.0017025708,0.0000031873165,0.009468461,0.22210386,0.1229196,0.054703627,0.017884057,0.16462956],"study_design_scores_gemma":[0.00091839535,0.00024981756,0.0063202344,0.000007725442,0.000027615226,0.000015242051,0.00015719814,0.9137168,0.00049398956,0.000043525124,0.07773948,0.000309975],"about_ca_topic_score_codex":0.000007701352,"about_ca_topic_score_gemma":0.000006323701,"teacher_disagreement_score":0.69161296,"about_ca_system_score_codex":0.000023311268,"about_ca_system_score_gemma":0.00007993015,"threshold_uncertainty_score":0.8653968},"labels":[],"label_agreement":null},{"id":"W2610063871","doi":"10.1186/1471-2105-13-180","title":"Erratum to: A linear classifier based on entity recognition tools and a statistical approach to method extraction in the protein-protein interaction literature","year":2012,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Classifier (UML); Computer science; Pattern recognition (psychology); Artificial intelligence; Computational biology; Biology","score_opus":0.05961479667506053,"score_gpt":0.33777227297490175,"score_spread":0.2781574762998412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610063871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011251076,0.00021295932,0.9760541,0.00045266582,0.0024103005,0.0023887267,0.0007728917,0.00004395484,0.016539335],"genre_scores_gemma":[0.0023555858,0.000032912783,0.98031086,0.0017182825,0.0012166309,0.0007774361,0.007838484,0.00004576479,0.005704065],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980047,0.00034453036,0.0005201629,0.00036872402,0.00037803108,0.0003838818],"domain_scores_gemma":[0.9989371,0.00010168623,0.00022179981,0.0004578946,0.000111877016,0.00016969933],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001057176,0.00036171934,0.00032370078,0.00022756611,0.00010182503,0.00023602578,0.00024938144,0.0010722838,0.000010071914],"category_scores_gemma":[0.0015481386,0.00025632075,0.0000895636,0.0002992178,0.00006404093,0.000025144653,0.00009752934,0.0011298052,0.00003528109],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016186561,0.0010219557,0.000042304382,0.0033432078,0.00009165361,0.000008663424,0.0024763062,0.00009171775,0.003983353,0.00017618855,0.68816257,0.29898345],"study_design_scores_gemma":[0.0010670427,0.002011521,0.0012796498,0.0019368789,0.00010836198,0.00008271846,0.0017981847,0.0862595,0.0014694287,0.00020234121,0.9026765,0.0011078587],"about_ca_topic_score_codex":0.000013825267,"about_ca_topic_score_gemma":0.0000446331,"teacher_disagreement_score":0.29787558,"about_ca_system_score_codex":0.000055162014,"about_ca_system_score_gemma":0.00015897732,"threshold_uncertainty_score":0.9999889},"labels":[],"label_agreement":null},{"id":"W2612656963","doi":"10.1186/1471-2105-9-s10-i1","title":"Highlights from the Fourth International Society for Computational Biology Student Council Symposium at the Sixteenth Annual International Conference on Intelligent Systems for Molecular Biology","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Oxford; Ontario Genomics; Ontario Genomics Institute; European Bioinformatics Institute","keywords":"Context (archaeology); Library science; Systems biology; Research council; Engineering ethics; Biology; Computational biology; Computer science; Engineering","score_opus":0.058017625929177606,"score_gpt":0.321326207184666,"score_spread":0.2633085812554884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612656963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043766204,0.0006241465,0.93382645,0.0067577795,0.0034688052,0.0024441623,0.006474643,0.000036549183,0.0026012762],"genre_scores_gemma":[0.69844216,0.016789323,0.20024626,0.01573601,0.006832951,0.0023724185,0.04776661,0.00019201508,0.011622245],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782604,0.000055611334,0.0007362122,0.00030438378,0.00065200235,0.00042576567],"domain_scores_gemma":[0.9975325,0.00040474796,0.00032835445,0.0004118858,0.0011979932,0.00012454884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007538803,0.00027958487,0.00023619251,0.000037428974,0.00041145374,0.00009220364,0.0011271633,0.00028231426,0.000025041647],"category_scores_gemma":[0.00030210483,0.00016658551,0.00035563533,0.0000628688,0.00063971954,0.000014196588,0.00046062397,0.00015035017,0.00003765923],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026067814,0.0012223263,0.0059028165,0.00041661886,0.00509886,0.0000031368245,0.012474155,0.046835866,0.018570377,0.07725055,0.8251713,0.0044472497],"study_design_scores_gemma":[0.0023008336,0.0009826974,0.00032248578,0.00003794827,0.000057889312,0.000023651757,0.0027011463,0.39360374,0.0026182616,0.0009733035,0.595975,0.00040305773],"about_ca_topic_score_codex":0.00003719274,"about_ca_topic_score_gemma":0.00005127364,"teacher_disagreement_score":0.7335802,"about_ca_system_score_codex":0.00022754962,"about_ca_system_score_gemma":0.00063420064,"threshold_uncertainty_score":0.679316},"labels":[],"label_agreement":null},{"id":"W2617372835","doi":"10.1186/s12859-017-1682-0","title":"Numerical integration methods and layout improvements in the context of dynamic RNA visualization","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Computer science; Graph drawing; Visualization; Graph; Theoretical computer science; Graph Layout; RNA; Software; Algorithm; Data mining; Programming language","score_opus":0.02155877607544754,"score_gpt":0.3447552094190393,"score_spread":0.32319643334359177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617372835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18326269,0.00011034368,0.8152508,0.00005313231,0.00008577871,0.00032361457,0.000008252266,0.0000032713358,0.0009020893],"genre_scores_gemma":[0.9151215,0.000062082385,0.08459114,0.0001291831,0.000012628776,0.000015109115,0.000029393306,0.0000050128356,0.000033925113],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946225,0.00007294796,0.00023492635,0.00006889406,0.0000789815,0.00008201872],"domain_scores_gemma":[0.9994036,0.000020314257,0.00022392174,0.00030224313,0.000033356835,0.000016595164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005418632,0.00007406749,0.00009505038,0.000023654919,0.000080974205,0.000048764356,0.0001915993,0.00008208185,0.000002525752],"category_scores_gemma":[0.0002715609,0.000050302453,0.00002923199,0.000021542884,0.0000489849,0.00001340427,0.000049558552,0.00003292129,0.0000012577076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007879805,0.000057845882,0.0013558201,0.00014053,0.000022528917,1.9747458e-7,0.0018180191,0.000009052803,0.4327067,0.002500486,0.000059277925,0.56125075],"study_design_scores_gemma":[0.00094214705,0.00046129254,0.008928355,0.00007051067,0.000026959091,0.000006784166,0.0036377518,0.22399768,0.759828,0.0008584541,0.0010096466,0.00023247358],"about_ca_topic_score_codex":0.00002822544,"about_ca_topic_score_gemma":0.000036880247,"teacher_disagreement_score":0.73185885,"about_ca_system_score_codex":0.000005042393,"about_ca_system_score_gemma":0.000021401886,"threshold_uncertainty_score":0.20512746},"labels":[],"label_agreement":null},{"id":"W2618529956","doi":"10.1186/s12859-017-1871-x","title":"SPRINT: ultrafast protein-protein interaction prediction of the entire human interactome","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Interactome; Sprint; Computer science; Sequence (biology); Task (project management); Artificial intelligence; Machine learning; Data mining; Biology; Genetics","score_opus":0.019005543283534595,"score_gpt":0.255963703538983,"score_spread":0.2369581602554484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618529956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9694956,0.000020697124,0.016658684,0.0000794357,0.0005487394,0.0008137961,0.00007918757,0.000018257544,0.0122856265],"genre_scores_gemma":[0.994564,0.000007407961,0.004117936,0.000044718417,0.0001991733,0.000028943079,0.00007587736,0.000015557049,0.00094636093],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988611,0.000023937302,0.000592301,0.00012434642,0.00018225287,0.0002161007],"domain_scores_gemma":[0.9979324,0.000004428045,0.00081522606,0.0010838449,0.00010445099,0.000059654256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024852064,0.00017883972,0.00015976126,0.000039439867,0.0004213055,0.0001351045,0.00065605046,0.00018335934,0.000023368555],"category_scores_gemma":[0.00009797453,0.00013268416,0.00017585854,0.000037707578,0.00018068594,0.000044262302,0.0003821412,0.00019979381,0.000019609168],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002466221,0.00029443274,0.014259516,0.0013787274,0.000300451,6.8941875e-7,0.0014182515,0.0007126192,0.94125956,0.0053097866,0.0026439403,0.03217542],"study_design_scores_gemma":[0.0026295537,0.0007647503,0.060245648,0.0010245099,0.000097201635,0.00005525278,0.0014684179,0.06785964,0.8185847,0.00090891036,0.045593563,0.0007678522],"about_ca_topic_score_codex":0.000027642618,"about_ca_topic_score_gemma":0.00007022632,"teacher_disagreement_score":0.122674845,"about_ca_system_score_codex":0.00002428889,"about_ca_system_score_gemma":0.00007319615,"threshold_uncertainty_score":0.5410703},"labels":[],"label_agreement":null},{"id":"W2620564586","doi":"10.1186/s12859-017-1699-4","title":"Identification of the sequence determinants of protein N-terminal acetylation through a decision tree approach","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Peptidase Inhibition and Analysis","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Acetylation; Context (archaeology); Biochemistry; Protein sequencing; Biology; Sequence (biology); UniProt; Computational biology; Peptide sequence; Consensus sequence; Gene","score_opus":0.06452521856600396,"score_gpt":0.33763603737817166,"score_spread":0.2731108188121677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620564586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9238966,0.0000070601322,0.07350731,0.000044203978,0.000020098027,0.0004363361,0.000023189703,0.0000102399845,0.0020549567],"genre_scores_gemma":[0.9453438,0.0000042686265,0.05428408,0.00002058265,0.000018312317,0.000011769061,0.0000107025235,0.000004828946,0.00030166726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987627,0.000017779785,0.0006769792,0.00007938814,0.00036935465,0.000093771596],"domain_scores_gemma":[0.9979561,0.000020946154,0.0010645433,0.00076417206,0.00016450767,0.000029732799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029312898,0.00008636683,0.00022630561,0.000056303175,0.00015577371,0.000030850435,0.000225886,0.0000756785,0.000009831499],"category_scores_gemma":[0.00043467613,0.00005562224,0.00014914377,0.0001102891,0.00020330184,0.0003902858,0.00007206403,0.00007238735,0.000009691984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010941105,0.0018441643,0.28522605,0.013121284,0.00022190712,0.0000108751465,0.014058414,0.00079473126,0.33415574,0.0038602755,0.00071481796,0.34489763],"study_design_scores_gemma":[0.0013682531,0.00009349694,0.124807484,0.0018694759,0.00015052091,0.00007093621,0.00071865355,0.63907343,0.23107225,0.0005962435,0.000039211052,0.00014003285],"about_ca_topic_score_codex":0.000014186036,"about_ca_topic_score_gemma":0.000018586446,"teacher_disagreement_score":0.6382787,"about_ca_system_score_codex":0.000025692896,"about_ca_system_score_gemma":0.00009380417,"threshold_uncertainty_score":0.2268209},"labels":[],"label_agreement":null},{"id":"W2626203030","doi":"10.1186/s12859-017-1718-5","title":"Biomarker correlation network in colorectal carcinoma by tumor anatomic location","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic factors in colorectal cancer","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; Uehara Memorial Foundation; Gary Bennett Family Fund; Mochida Memorial Foundation for Medical and Pharmaceutical Research; Dana-Farber/Harvard Cancer Center; National Institute of Diabetes and Digestive and Kidney Diseases; Entertainment Industry Foundation","keywords":"Biomarker; DNA microarray; Colorectal cancer; Correlation; Oncology; Carcinoma; Medicine; Computational biology; Biology; Pathology; Internal medicine; Cancer; Gene; Genetics; Gene expression; Mathematics","score_opus":0.02191543732902508,"score_gpt":0.2761201421532842,"score_spread":0.2542047048242591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626203030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9830368,0.00021882507,0.007989206,0.00009862416,0.00076570554,0.0006998347,0.000012452756,0.000044007953,0.007134501],"genre_scores_gemma":[0.98449147,0.000011756866,0.01496859,0.00016494941,0.000078951445,0.000033963788,0.00008212509,0.000018919294,0.00014924856],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988095,0.000021501828,0.0004626837,0.00013900807,0.00026004732,0.00030721974],"domain_scores_gemma":[0.9989605,0.00006568267,0.00032895713,0.0004353921,0.00010337106,0.00010607539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002887812,0.0001647844,0.00024554174,0.00009094742,0.00016928428,0.000070916496,0.00018392468,0.00013801959,0.00006547574],"category_scores_gemma":[0.00031999647,0.00015258304,0.00005222117,0.00016451586,0.00013336833,0.00022671527,0.00008065646,0.00017558555,0.00010964832],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029842393,0.00004327491,0.9811566,0.00019762003,0.000013856208,0.0000037667635,0.00032142503,0.00073548546,0.00022971536,0.00004444541,0.012528845,0.004426571],"study_design_scores_gemma":[0.0010692652,0.00011129543,0.5892251,0.000077879384,0.000022716684,0.000027029439,0.000093373776,0.40810427,0.0005581589,0.000043269214,0.00054722873,0.00012036766],"about_ca_topic_score_codex":0.00009273178,"about_ca_topic_score_gemma":0.00023497491,"teacher_disagreement_score":0.40736878,"about_ca_system_score_codex":0.00028362035,"about_ca_system_score_gemma":0.00027137014,"threshold_uncertainty_score":0.6222156},"labels":[],"label_agreement":null},{"id":"W2649123629","doi":"10.1186/s12859-017-1728-3","title":"Optimal alpha reduces error rates in gene expression studies: a meta-analysis approach","year":2017,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type I and type II errors; Bonferroni correction; False discovery rate; Statistical power; Multiple comparisons problem; Word error rate; Computer science; DNA microarray; Replication (statistics); Meta-analysis; Sample size determination; Nominal level; Throughput; Data mining; Statistics; Computational biology; Biology; Mathematics; Artificial intelligence; Confidence interval; Gene expression; Gene; Genetics; Medicine","score_opus":0.3857963681457757,"score_gpt":0.45388906396090556,"score_spread":0.06809269581512983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2649123629","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014882911,0.9833755,0.0149095645,0.000009011393,0.00012485482,0.00072677585,0.00010221351,0.000015461246,0.0007217733],"genre_scores_gemma":[0.00002657484,0.8942439,0.10244921,0.00002952497,0.00012561996,0.0006366021,0.0013587238,0.000035850535,0.0010940232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736416,0.00018024264,0.0012452934,0.0005594445,0.00030644538,0.00034440518],"domain_scores_gemma":[0.99679154,0.000035880395,0.0014108054,0.0015139179,0.00013315071,0.00011471185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068555877,0.00058428786,0.0026259888,0.00043923492,0.00017030383,0.00012454501,0.00085393654,0.0005742203,0.000024199486],"category_scores_gemma":[0.00020586878,0.00038842135,0.002024249,0.00038735697,0.0001299533,0.00001977206,0.00038323403,0.00023615693,0.000022927941],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027969497,0.0014954148,0.000060613525,0.08328584,0.36693954,0.00001354769,0.0035972786,0.013162457,0.0012839761,0.00008024136,0.09141411,0.43838727],"study_design_scores_gemma":[0.00032971211,0.00007356057,0.0000032479588,0.0004140494,0.07875814,0.000008632166,0.0007292878,0.0030805098,0.0018452469,0.0000042929814,0.913911,0.0008423448],"about_ca_topic_score_codex":0.000003015201,"about_ca_topic_score_gemma":0.000005349928,"teacher_disagreement_score":0.82249683,"about_ca_system_score_codex":0.00005023756,"about_ca_system_score_gemma":0.00036703303,"threshold_uncertainty_score":0.99985677},"labels":[],"label_agreement":null},{"id":"W2737578470","doi":"10.1186/s12859-017-1758-x","title":"Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"European Regional Development Fund; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Fundação para a Ciência e a Tecnologia; Universitat de València","keywords":"Benchmark (surveying); Proteome; Computational biology; Computer science; Protein function prediction; Structural bioinformatics; Protein structure database; Sequence alignment; Similarity (geometry); Structural alignment; Protein methods; Protein sequencing; Annotation; Protein family; Protein function; Function (biology); Structural similarity; Sequence (biology); Protein structure; Multiple sequence alignment; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Sequence database; Genetics; Gene; Biochemistry","score_opus":0.04100894492899753,"score_gpt":0.2774749193984699,"score_spread":0.23646597446947237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737578470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8258196,0.0010070681,0.15998994,0.0009590725,0.0010327848,0.0030986767,0.00012876572,0.00012205041,0.007842014],"genre_scores_gemma":[0.5534595,0.000106328196,0.44065672,0.00044478578,0.0010272925,0.00040982116,0.00019028015,0.00007245178,0.0036328104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986149,0.000031129297,0.000530568,0.00020952077,0.00023025356,0.00038359882],"domain_scores_gemma":[0.99801135,0.000057817113,0.00065774785,0.0010334738,0.00012583926,0.000113757866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072722766,0.00031384843,0.00025399422,0.00005027936,0.0011999452,0.0006652902,0.0007303707,0.0001618574,0.000002233124],"category_scores_gemma":[0.0016578446,0.00021782162,0.00011641572,0.00004089962,0.00025078835,0.000086997854,0.0005213114,0.00024852814,0.0000061733244],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004161162,0.0010009321,0.15303367,0.029459355,0.0029111276,0.000034225028,0.0914553,0.021474821,0.1561883,0.17340736,0.12971,0.23716374],"study_design_scores_gemma":[0.0047624265,0.0012012149,0.03192105,0.0007190706,0.00023642422,0.00018514843,0.0047032456,0.4180893,0.40097055,0.0006073932,0.13426921,0.0023349596],"about_ca_topic_score_codex":0.000035764773,"about_ca_topic_score_gemma":0.00012304551,"teacher_disagreement_score":0.3966145,"about_ca_system_score_codex":0.000014854771,"about_ca_system_score_gemma":0.00008894926,"threshold_uncertainty_score":0.92291296},"labels":[],"label_agreement":null},{"id":"W2761379268","doi":"10.1186/s12859-017-1843-1","title":"Interpretation of microbiota-based diagnostics by explaining individual classifier decisions","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"National Science Council; Vrije Universiteit Amsterdam; ZonMw","keywords":"Classifier (UML); Machine learning; Artificial intelligence; Gut flora; Computer science; Biology; Immunology","score_opus":0.031172426348228102,"score_gpt":0.2971729783402441,"score_spread":0.266000551992016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761379268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6788258,0.00046537933,0.31618392,0.00017042973,0.0004925923,0.00047623453,0.0008971807,0.0000224484,0.0024659943],"genre_scores_gemma":[0.90902174,0.00018624442,0.08888866,0.00048619663,0.000056234265,0.000009613149,0.0011727936,0.00002020178,0.00015829672],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990312,0.000025177831,0.00045719586,0.0001363339,0.000120173456,0.00022993918],"domain_scores_gemma":[0.99864787,0.00007931986,0.0004659201,0.0006122975,0.000106699656,0.000087887405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000252978,0.00014863226,0.00017793175,0.000057037574,0.00025721852,0.00008857968,0.0004369045,0.00020631475,0.00001693898],"category_scores_gemma":[0.00071328843,0.00013770418,0.00009388599,0.00003244481,0.00015768464,0.000014319105,0.00016656154,0.0001014934,0.000031004114],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053680455,0.0006101181,0.09119763,0.0008446142,0.00025240233,0.000002518495,0.0025942817,0.00088896276,0.50111544,0.0004143261,0.35173133,0.04981156],"study_design_scores_gemma":[0.01106589,0.00277153,0.15567486,0.0015410719,0.00044151823,0.000060836705,0.0035759266,0.13983946,0.47787666,0.00017432524,0.20443533,0.002542611],"about_ca_topic_score_codex":0.000008067288,"about_ca_topic_score_gemma":0.00004497749,"teacher_disagreement_score":0.23019594,"about_ca_system_score_codex":0.00001282604,"about_ca_system_score_gemma":0.00020418667,"threshold_uncertainty_score":0.5615413},"labels":[],"label_agreement":null},{"id":"W2765773784","doi":"10.1186/s12859-017-1830-6","title":"DCJ-RNA - double cut and join for RNA secondary structures","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Plan for Science, Technology and Innovation; King Saud University","keywords":"Nucleic acid secondary structure; Protein secondary structure; Genome; Computer science; Join (topology); RNA; Similarity (geometry); Algorithm; Time complexity; Sequence (biology); Data structure; Representation (politics); Theoretical computer science; Computational biology; Mathematics; Biology; Genetics; Combinatorics; Gene; Artificial intelligence","score_opus":0.02485877873433138,"score_gpt":0.2729704115021062,"score_spread":0.24811163276777484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765773784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88868904,0.0013326863,0.0704722,0.00030660167,0.0010820857,0.0017934704,0.00034276184,0.000054641296,0.035926502],"genre_scores_gemma":[0.58870125,0.00049432955,0.40394333,0.0004917872,0.000863009,0.00010125662,0.0006101512,0.00007718085,0.0047176997],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925786,0.000005716287,0.00023839872,0.00014780991,0.00010055966,0.0002496595],"domain_scores_gemma":[0.99907255,0.000008471005,0.00020439636,0.0005625988,0.00006286166,0.000089109315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001563203,0.00016085035,0.00014849867,0.000036764093,0.00031224926,0.00019090975,0.00029155923,0.00014445321,0.000023131981],"category_scores_gemma":[0.00005608081,0.00014211233,0.00007433375,0.000013795118,0.00011019898,0.000020037942,0.00021516868,0.0000682741,0.000009898308],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002206927,0.00030983496,0.02510094,0.007946783,0.0016702098,0.00000999978,0.0040281033,0.00051720906,0.30957752,0.010164375,0.17051409,0.467954],"study_design_scores_gemma":[0.017464308,0.0013895163,0.037350576,0.00009536394,0.0002453551,0.00010220174,0.001496696,0.035593376,0.50572294,0.0043286015,0.3941538,0.0020572974],"about_ca_topic_score_codex":0.00000938094,"about_ca_topic_score_gemma":0.000047151585,"teacher_disagreement_score":0.4658967,"about_ca_system_score_codex":0.000008279227,"about_ca_system_score_gemma":0.000076327866,"threshold_uncertainty_score":0.5795173},"labels":[],"label_agreement":null},{"id":"W2766029068","doi":"10.1186/s12859-017-1827-1","title":"VAliBS: a visual aligner for bisulfite sequences","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Bisulfite; Computer science; Bisulfite sequencing; DNA methylation; Computational biology; Methylation; Visualization; Artificial intelligence; DNA; Genetics; Biology; Gene","score_opus":0.034252719927802516,"score_gpt":0.33410641764742605,"score_spread":0.29985369771962356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766029068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5447486,0.0005897031,0.4452105,0.00015245134,0.0005727497,0.00062321936,0.00008850748,0.000028712699,0.007985536],"genre_scores_gemma":[0.7907553,0.00035050832,0.20587258,0.00023569468,0.0005872902,0.00007353727,0.00032758823,0.0000346592,0.0017628969],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924916,0.0000125567685,0.0002700555,0.00013581474,0.00011885345,0.00021356021],"domain_scores_gemma":[0.9990869,0.000018132112,0.0002515464,0.0004621369,0.0001090398,0.000072225484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028489626,0.00012895117,0.00011639177,0.000032451626,0.00033146626,0.00017341365,0.00028470802,0.00014505135,0.000006026568],"category_scores_gemma":[0.00027972477,0.000111325746,0.00010605882,0.000019762998,0.00009451751,0.000015208345,0.0001070452,0.000031735355,0.000017736542],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071055524,0.00045473216,0.120383784,0.0017079309,0.0004982145,0.000003188094,0.0016313918,0.0034511837,0.65024054,0.0064892815,0.014389159,0.20004006],"study_design_scores_gemma":[0.002340023,0.001201316,0.016409328,0.00006325463,0.00009098287,0.000006652474,0.00039207772,0.122315176,0.6241473,0.002501261,0.22960868,0.00092397514],"about_ca_topic_score_codex":0.000009873847,"about_ca_topic_score_gemma":0.000041257288,"teacher_disagreement_score":0.24600662,"about_ca_system_score_codex":0.0000071386685,"about_ca_system_score_gemma":0.000083672276,"threshold_uncertainty_score":0.4539732},"labels":[],"label_agreement":null},{"id":"W2766787629","doi":"10.1186/s12859-018-2046-0","title":"Germline contamination and leakage in whole genome somatic single nucleotide variant detection","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Ontario Institute for Cancer Research; National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada; Government of Ontario; Google; Canadian Institutes of Health Research; Genome Canada; National Institutes of Health; Terry Fox Research Institute; Movember Foundation","keywords":"Germline; Somatic cell; Biology; Germline mutation; Genetics; Computational biology; Genome; Gene; Mutation","score_opus":0.009098428916075674,"score_gpt":0.21410578895007318,"score_spread":0.2050073600339975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766787629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9647853,0.00015159596,0.033994216,0.00002509429,0.00011464001,0.00018795053,0.00002883128,0.000011712377,0.0007007007],"genre_scores_gemma":[0.99285495,0.000028215969,0.0065445574,0.00013505734,0.0001525054,0.0000071555505,0.00012558703,0.000012181619,0.00013977615],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937654,0.000018576651,0.00026452736,0.00011423366,0.0000666423,0.00015948666],"domain_scores_gemma":[0.99960506,0.000008451044,0.00009827468,0.00017410956,0.000056533863,0.00005754768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013289353,0.00010482767,0.00009838533,0.00006956974,0.00007085049,0.000045778652,0.00007228152,0.000086875436,0.0000065040326],"category_scores_gemma":[0.00005721482,0.00009891015,0.000031424115,0.000068811416,0.000070251146,0.000012582555,0.00006875932,0.00003665867,0.000028990307],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015545098,0.0003033024,0.004464137,0.00044742067,0.000052185038,0.000010545106,0.001845462,0.00017766852,0.9724623,0.00011951831,0.00017484554,0.019787194],"study_design_scores_gemma":[0.007757988,0.0039031727,0.36233845,0.00021593201,0.00018342424,0.0004924259,0.004684673,0.38836634,0.14936948,0.0013560394,0.07926197,0.0020700854],"about_ca_topic_score_codex":0.000009386784,"about_ca_topic_score_gemma":0.0002861879,"teacher_disagreement_score":0.8230928,"about_ca_system_score_codex":0.000020016198,"about_ca_system_score_gemma":0.00003379435,"threshold_uncertainty_score":0.40334392},"labels":[],"label_agreement":null},{"id":"W2767173690","doi":"10.1186/s12859-018-2111-8","title":"ATMAD: robust image analysis for Automatic Tissue MicroArray De-arraying","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Artificial intelligence; Thresholding; Computer science; Computer vision; Pattern recognition (psychology); Bright-field microscopy; Preprocessor; Sample (material); Biomedical engineering; Microscope; Image (mathematics); Engineering; Optics","score_opus":0.027508111410899483,"score_gpt":0.2767364041537164,"score_spread":0.24922829274281694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767173690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023375307,0.000025013725,0.99475735,0.00015948495,0.00042681795,0.00034456028,0.000009604409,0.00037852136,0.0015611234],"genre_scores_gemma":[0.019920427,0.0000040746977,0.9793491,0.00029272202,0.00017183766,0.000047548547,0.0000067503897,0.0000135917535,0.00019394615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856967,0.000031103802,0.0005063094,0.0002118035,0.00024138944,0.0004397079],"domain_scores_gemma":[0.998441,0.00014625749,0.00028892452,0.0008039846,0.00020661428,0.00011326698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006054324,0.00017970073,0.00025398217,0.00031648434,0.00030260408,0.00036155642,0.0008144082,0.000108364664,0.000044109507],"category_scores_gemma":[0.00012331748,0.00017097579,0.00015415555,0.001205403,0.000103969134,0.0010252226,0.00015409994,0.00008911932,0.00020059252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011783693,0.0004446918,0.013043965,0.005683153,0.0030244587,0.000010263407,0.07967668,0.045971718,0.020504545,0.013152972,0.07280579,0.7455639],"study_design_scores_gemma":[0.00025927636,0.0001283072,0.0009762864,0.00002009004,0.0001147738,0.000014707836,0.00017681086,0.983682,0.00990435,0.00042198368,0.004075191,0.0002262279],"about_ca_topic_score_codex":0.000021580805,"about_ca_topic_score_gemma":0.0000913223,"teacher_disagreement_score":0.9377103,"about_ca_system_score_codex":0.00022042432,"about_ca_system_score_gemma":0.0001634534,"threshold_uncertainty_score":0.6972191},"labels":[],"label_agreement":null},{"id":"W2768591110","doi":"10.1186/s12859-017-1912-5","title":"DBNorm: normalizing high-density oligonucleotide microarray data based on distributions","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Technology Sydney","keywords":"Normalization (sociology); Computer science; Data mining; Quantile; Data set; Visualization; Merge (version control); Gaussian; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Information retrieval","score_opus":0.04508076352832052,"score_gpt":0.29599593996764995,"score_spread":0.2509151764393294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768591110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20035446,0.000101268735,0.7772502,0.0013467288,0.0013035011,0.0006152224,0.0013130606,0.0000995377,0.017616054],"genre_scores_gemma":[0.9511441,0.000049083024,0.045121294,0.00050943665,0.00020522795,0.000011242091,0.0026523606,0.000016107151,0.0002911225],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990552,0.00002529919,0.00027542797,0.00024497163,0.00016994588,0.00022916764],"domain_scores_gemma":[0.9968823,0.000010335245,0.0002905635,0.0026254805,0.0000820045,0.00010931141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024388691,0.00015703587,0.00012144225,0.000040533014,0.0006472597,0.00018071361,0.00094581477,0.00013334637,0.000021654572],"category_scores_gemma":[0.0002630524,0.00014139943,0.00005825192,0.000039941762,0.00011886063,0.000028808157,0.00037653174,0.0000988305,0.000080326834],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008378729,0.0007942107,0.047514915,0.00067880785,0.00017548533,0.00000653268,0.00023435938,0.0031668616,0.40210846,0.0040987036,0.48784938,0.052534416],"study_design_scores_gemma":[0.0026105265,0.00026716586,0.14999145,0.00015164501,0.00008842862,0.000014274292,0.00022770162,0.18402006,0.37933016,0.00012925777,0.28222793,0.00094138214],"about_ca_topic_score_codex":0.00004235243,"about_ca_topic_score_gemma":0.00007691277,"teacher_disagreement_score":0.7507897,"about_ca_system_score_codex":0.00002203279,"about_ca_system_score_gemma":0.0001444447,"threshold_uncertainty_score":0.57661015},"labels":[],"label_agreement":null},{"id":"W2769794976","doi":"10.1186/s12859-017-1930-3","title":"GFF3sort: a novel tool to sort GFF3 files for tabix indexing","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Biotechnology Research Institute","funders":"Ministry of Agriculture of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Search engine indexing; sort; Rendering (computer graphics); Sorting; Visualization; Annotation; JSON; Sorting algorithm; Information retrieval; File format; Data mining; Database; Computer graphics (images); Artificial intelligence; Programming language","score_opus":0.032521873715545255,"score_gpt":0.27872664572990075,"score_spread":0.24620477201435548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769794976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73778003,0.00019940989,0.25363195,0.00024320789,0.00064060336,0.0010956535,0.0006111808,0.000012726242,0.005785223],"genre_scores_gemma":[0.54399073,0.00008454658,0.45261043,0.0008779404,0.00058410974,0.00019061161,0.00012438274,0.000042262833,0.001494959],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907595,0.0000032904481,0.0003206145,0.00018173065,0.00010279955,0.00031558925],"domain_scores_gemma":[0.99890274,0.000017084607,0.00018955414,0.0006925994,0.00011399056,0.00008406111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019555262,0.00018162272,0.00018220965,0.00003582879,0.0004420505,0.00013550614,0.00042539567,0.00012300815,0.0000053252156],"category_scores_gemma":[0.00034140146,0.00016703505,0.00012376074,0.000022623339,0.00006485337,0.0000034421118,0.0003670261,0.00004353758,0.000018688363],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095980946,0.0005315651,0.105604924,0.0017272102,0.001059653,0.0000021137764,0.0044657695,0.006971491,0.6844507,0.008983933,0.07763285,0.10761002],"study_design_scores_gemma":[0.0032096987,0.0008814178,0.09606585,0.000084150684,0.00010580179,0.000025268255,0.0009199445,0.024399234,0.06411276,0.00047684737,0.8083245,0.0013944943],"about_ca_topic_score_codex":0.000011082972,"about_ca_topic_score_gemma":0.00008233445,"teacher_disagreement_score":0.7306917,"about_ca_system_score_codex":0.000010633873,"about_ca_system_score_gemma":0.000092651,"threshold_uncertainty_score":0.6811491},"labels":[],"label_agreement":null},{"id":"W2769985287","doi":"10.1186/s12859-017-1936-x","title":"Software for rapid time dependent ChIP-sequencing analysis (TDCA)","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AXYS Technologies (Canada); Burnaby Hospital; Simon Fraser University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Software; DNA microarray; DNA sequencing; ChIP-sequencing; Data mining; Computational biology; Chip; Chromatin; Algorithm; Bioinformatics; Biology; Genetics; DNA; Gene","score_opus":0.014760311125796347,"score_gpt":0.24256794723702324,"score_spread":0.2278076361112269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769985287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3731911,0.0001390564,0.6230445,0.000041968644,0.00018847207,0.00045047287,0.00031406112,0.00003297092,0.0025974282],"genre_scores_gemma":[0.412553,0.00012796173,0.58269954,0.00027571534,0.0002990174,0.000061926556,0.0015021093,0.000052659027,0.0024280467],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900115,0.00001086242,0.0003667879,0.00019014622,0.00013380354,0.00029724557],"domain_scores_gemma":[0.99837875,0.00001860838,0.0003821944,0.000989825,0.00013465415,0.00009595236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002898448,0.00018455298,0.00023641785,0.00007181862,0.00043076338,0.00020347041,0.00055222557,0.00017450858,0.00002622596],"category_scores_gemma":[0.00030072316,0.00017480698,0.0002542387,0.000055216817,0.00006708654,0.0000131398265,0.00022996105,0.000057399142,0.000039353137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013257745,0.00093103066,0.20954753,0.0054084053,0.017049491,0.000020640648,0.004768722,0.20609504,0.30265784,0.0027440512,0.03378262,0.21566886],"study_design_scores_gemma":[0.0016611082,0.000348238,0.008305223,0.000026066109,0.0007649634,0.000020794962,0.0003326412,0.9624805,0.018126382,0.00032484357,0.0067680455,0.0008411836],"about_ca_topic_score_codex":0.000009319543,"about_ca_topic_score_gemma":0.000085542095,"teacher_disagreement_score":0.75638545,"about_ca_system_score_codex":0.00003660387,"about_ca_system_score_gemma":0.00015348778,"threshold_uncertainty_score":0.71284217},"labels":[],"label_agreement":null},{"id":"W2770091706","doi":"10.1186/s12859-017-1906-3","title":"fLPS: Fast discovery of compositional biases for the protein universe","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computational biology; Contig; Asparagine; Biology; Residue (chemistry); Metagenomics; Sequence (biology); Amino acid; Computer science; Genetics; Biochemistry; Genome; Gene","score_opus":0.033725925211328396,"score_gpt":0.26788335994723483,"score_spread":0.23415743473590644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770091706","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20358132,0.0001704373,0.7912169,0.0002469993,0.00020484056,0.0012752973,0.0005257486,0.000010097246,0.002768359],"genre_scores_gemma":[0.89572436,0.00005454696,0.10211085,0.0000906751,0.00018217272,0.00008308074,0.00013690503,0.000015789354,0.0016016057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99951583,0.000013127116,0.00018126126,0.00007156754,0.00010181402,0.000116407515],"domain_scores_gemma":[0.9991389,0.00004497914,0.00024537064,0.00048286535,0.000064594286,0.000023324632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001625627,0.00008936567,0.00009402853,0.000015824628,0.00029245636,0.00007276968,0.00036300323,0.00007008628,0.0000067912033],"category_scores_gemma":[0.00017811269,0.00006097151,0.00010629342,0.000012067171,0.00013370418,0.000020641379,0.0001468333,0.000025519423,0.000004228853],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005949045,0.0001244795,0.00032450724,0.00042942335,0.00018061939,5.418362e-7,0.00019344359,0.00052027917,0.9616267,0.015694108,0.0022080848,0.018102895],"study_design_scores_gemma":[0.00076531374,0.0003182216,0.00078423636,0.00011276639,0.000041804535,0.000005881038,0.0006386644,0.0086922,0.97894543,0.0005416293,0.008959577,0.0001942485],"about_ca_topic_score_codex":0.000008427681,"about_ca_topic_score_gemma":0.000014742616,"teacher_disagreement_score":0.6921431,"about_ca_system_score_codex":0.000004544784,"about_ca_system_score_gemma":0.000075300646,"threshold_uncertainty_score":0.2486346},"labels":[],"label_agreement":null},{"id":"W2770792541","doi":"10.1186/s12859-017-1903-6","title":"Brain medical image diagnosis based on corners with importance-values","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Servier; H. Lundbeck A/S; IXICO; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China; Eisai; Genentech; Northern California Institute for Research and Education; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; F. Hoffmann-La Roche; University of Southern California; Pfizer; Biogen; BioClinica; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Foundation for the National Institutes of Health","keywords":"Artificial intelligence; Computer science; Classifier (UML); Pattern recognition (psychology); Matching (statistics); Similarity (geometry); Image registration; Image (mathematics); Medical imaging; Computer vision; Medicine; Pathology","score_opus":0.023194025837499698,"score_gpt":0.3068828850040999,"score_spread":0.2836888591666002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770792541","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004512963,0.0000048250263,0.98385596,0.0034228845,0.00012623289,0.00027460852,0.0000058286664,0.0003421761,0.011516191],"genre_scores_gemma":[0.005331072,0.000016305596,0.9857203,0.008667736,0.00004815177,0.00008182886,0.000012479265,0.000012139026,0.000109990666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787664,0.000042690255,0.00042250886,0.00020076356,0.0011604652,0.00029693503],"domain_scores_gemma":[0.9974378,0.0003768038,0.0004056587,0.0013752519,0.0000907421,0.00031375175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008169064,0.00018163878,0.00020225852,0.0001046271,0.0003070248,0.0005510976,0.0018091016,0.00010323986,0.0002015777],"category_scores_gemma":[0.0017921209,0.00012960257,0.000060259765,0.000111064684,0.00039348626,0.0012368831,0.00021657693,0.00020724548,0.00011999276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008583112,0.00059397524,0.08997329,0.0007319989,0.000062464176,0.00026631475,0.002221581,0.000075112555,0.000029402001,0.010113723,0.42216858,0.4736777],"study_design_scores_gemma":[0.001113169,0.0003507111,0.0073780655,0.0002576993,0.000008257528,0.0000131229035,0.00008726366,0.984864,0.0042676413,0.0003908352,0.00095042796,0.000318827],"about_ca_topic_score_codex":0.000013002043,"about_ca_topic_score_gemma":0.00002056323,"teacher_disagreement_score":0.9847889,"about_ca_system_score_codex":0.000051618885,"about_ca_system_score_gemma":0.00031276655,"threshold_uncertainty_score":0.5314247},"labels":[],"label_agreement":null},{"id":"W2771761215","doi":"10.1186/s12859-019-2916-0","title":"A multivariate Poisson-log normal mixture model for clustering transcriptome sequencing data","year":2019,"lang":"en","type":"preprint","venue":"BMC Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Cluster analysis; Mixture model; Overdispersion; Markov chain Monte Carlo; Computer science; Multivariate statistics; Expectation–maximization algorithm; Context (archaeology); Poisson distribution; Count data; Data mining; Mathematics; Statistics; Biology; Artificial intelligence; Machine learning; Bayesian probability","score_opus":0.11826977902242625,"score_gpt":0.3252396361446816,"score_spread":0.20696985712225535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771761215","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004650167,0.0002085917,0.99317044,0.00025206746,0.0020066428,0.0017464933,0.0009964986,0.00034110763,0.0012316657],"genre_scores_gemma":[0.002961421,0.00004230287,0.9947747,0.00075554405,0.00020908151,0.00007713256,0.00048659625,0.00005697077,0.0006362276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964255,0.00009627538,0.001185022,0.00090190663,0.0005214958,0.00086976134],"domain_scores_gemma":[0.99438155,0.00021953681,0.00067049277,0.0042767334,0.00021394342,0.000237763],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019004537,0.00068677077,0.0008601139,0.00028436672,0.00019994781,0.00074937165,0.005640457,0.00081115356,0.0000028908282],"category_scores_gemma":[0.00014374327,0.0006177741,0.00032582387,0.00020585729,0.000050844068,0.0017920096,0.004693283,0.0009795094,0.000022042665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012937919,0.00012190324,0.000025747073,0.014960274,0.00035058497,0.000008203289,0.0358384,0.806761,0.0006531903,0.025637345,0.006349297,0.10916464],"study_design_scores_gemma":[0.00078510185,0.000035801746,0.000007149933,0.00039363542,0.00008050828,0.000028093464,0.000045737565,0.98728275,0.00006433005,0.01000346,0.00048577652,0.0007876818],"about_ca_topic_score_codex":0.000043768287,"about_ca_topic_score_gemma":0.00004809812,"teacher_disagreement_score":0.18052168,"about_ca_system_score_codex":0.00019117308,"about_ca_system_score_gemma":0.0012362436,"threshold_uncertainty_score":0.9997395},"labels":[],"label_agreement":null},{"id":"W2776730476","doi":"10.1186/s12859-017-1995-z","title":"fDETECT webserver: fast predictor of propensity for protein production, purification, and crystallization","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council","keywords":"Crystallization; Propensity score matching; Production (economics); Web server; Computational biology; Computer science; Biology; Chemistry; Mathematics; World Wide Web; Statistics; The Internet","score_opus":0.030323302359978817,"score_gpt":0.23701246349019098,"score_spread":0.20668916113021216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776730476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7822201,0.000021354888,0.2151275,0.00011164861,0.00042146622,0.0015321849,0.00006268021,0.00006073583,0.0004422882],"genre_scores_gemma":[0.88081735,0.0000070844126,0.11837558,0.000011585567,0.00016098656,0.00007680294,0.000030085206,0.000010220699,0.0005103205],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992485,0.000014354517,0.0003360353,0.00012745852,0.00015605293,0.00011761118],"domain_scores_gemma":[0.9986927,0.0000073043966,0.00050818076,0.00045143676,0.00030317577,0.00003719222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033965686,0.000093238,0.00013886935,0.000038070048,0.00038476006,0.00013165268,0.00016520132,0.00006863086,0.0000162614],"category_scores_gemma":[0.0005635606,0.00007417146,0.000026331203,0.000036306617,0.00014000732,0.00077516795,0.000050919472,0.00003359687,0.0000056671556],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021131063,0.000045999637,0.007298566,0.0025043474,0.000013607781,6.053117e-8,0.0012612853,0.00021877688,0.9809549,0.0030632564,0.0015418548,0.0028860338],"study_design_scores_gemma":[0.0006266517,0.00021361746,0.039449435,0.00010908725,0.000039496586,0.000007460497,0.00017608168,0.012846021,0.94269705,0.0014794999,0.0021613974,0.00019422664],"about_ca_topic_score_codex":0.00001209677,"about_ca_topic_score_gemma":0.000046316152,"teacher_disagreement_score":0.09859719,"about_ca_system_score_codex":0.0000148884965,"about_ca_system_score_gemma":0.000052480806,"threshold_uncertainty_score":0.30246243},"labels":[],"label_agreement":null},{"id":"W2778042508","doi":"10.1186/s12859-017-1953-9","title":"HISEA: HIerarchical SEed Aligner for PacBio data","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Computational biology; DNA microarray; Biology; Genetics; Gene; Gene expression","score_opus":0.06171987483104954,"score_gpt":0.3073502706344804,"score_spread":0.24563039580343085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778042508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6376045,0.0027708516,0.31219152,0.0023593076,0.002892008,0.0029609064,0.0046512093,0.000047444715,0.03452231],"genre_scores_gemma":[0.61720604,0.0004964167,0.37696218,0.00079092407,0.0010923945,0.000067204965,0.0012630528,0.000051308998,0.002070439],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916124,0.000009618339,0.00025820947,0.00021032477,0.0000938249,0.00026676562],"domain_scores_gemma":[0.99797016,0.00002142799,0.00017110191,0.0016799862,0.00007116538,0.000086160166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024583223,0.00015098725,0.00015665885,0.000019493364,0.0004195944,0.00011448014,0.0009358783,0.000121320925,0.0000031931884],"category_scores_gemma":[0.00030358168,0.00012803335,0.00007792991,0.000012320741,0.00015165326,0.0000039623997,0.0008816831,0.00004601594,0.000015551941],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017294313,0.00073757255,0.23295745,0.0023323824,0.0021690617,0.000006105551,0.0020328823,0.0006463858,0.23944452,0.011917018,0.37821084,0.12781636],"study_design_scores_gemma":[0.002945724,0.00053065416,0.09176927,0.00003003581,0.00014667794,0.000020726995,0.00032555137,0.064317286,0.011765812,0.0012428613,0.82602537,0.00088001735],"about_ca_topic_score_codex":0.000007684977,"about_ca_topic_score_gemma":0.00005820311,"teacher_disagreement_score":0.44781455,"about_ca_system_score_codex":0.0000058412293,"about_ca_system_score_gemma":0.0000960763,"threshold_uncertainty_score":0.52210486},"labels":[],"label_agreement":null},{"id":"W2783873704","doi":"10.1186/s12859-017-1996-y","title":"diceR: an R package for class discovery using an ensemble driven approach","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Foundation","keywords":"Computer science; Dicer; Cluster analysis; Context (archaeology); Data mining; Set (abstract data type); Class (philosophy); Permutation (music); Generalization; Cluster (spacecraft); Machine learning; Artificial intelligence; Data science; Biology; Mathematics","score_opus":0.08579926171176273,"score_gpt":0.34100829396308385,"score_spread":0.25520903225132113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783873704","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00971716,0.000007251685,0.9875722,0.000015776663,0.00023890716,0.00046764358,0.00002297247,0.00019676374,0.0017613602],"genre_scores_gemma":[0.04167516,0.0000025791826,0.95763844,0.00010534914,0.0002821751,0.000025535099,0.000030689425,0.00002479652,0.00021524125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981972,0.000053307,0.00038404373,0.00030804626,0.00044245334,0.0006149227],"domain_scores_gemma":[0.99811447,0.000092479,0.00015912158,0.0012006456,0.00020363799,0.00022965096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042694015,0.0002005488,0.00021343192,0.00015692216,0.00037108263,0.00069007743,0.0013217861,0.00010849365,0.0000013783498],"category_scores_gemma":[0.0000757523,0.00017849273,0.00006904593,0.00036916032,0.00017265373,0.0052900505,0.0005214868,0.0001450506,0.000026332662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046077234,0.0031970954,0.0016746548,0.0041618007,0.0002703121,0.00002035516,0.06685312,0.16525742,0.014700224,0.13561192,0.0018937242,0.6058986],"study_design_scores_gemma":[0.00047380972,0.00042859092,0.00007738776,0.000018714225,0.000005614143,0.000028602602,0.0005543471,0.99468917,0.0016741717,0.0011021408,0.00068316807,0.0002642801],"about_ca_topic_score_codex":0.000015498243,"about_ca_topic_score_gemma":0.000027274946,"teacher_disagreement_score":0.8294318,"about_ca_system_score_codex":0.000119649856,"about_ca_system_score_gemma":0.00020022994,"threshold_uncertainty_score":0.72787225},"labels":[],"label_agreement":null},{"id":"W2785096815","doi":"10.1186/s12859-018-2315-y","title":"bioSyntax: syntax highlighting for computational biology","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of Waterloo; Terry Fox Research Institute; University of British Columbia","funders":"Faculty of Medicine, University of British Columbia","keywords":"Legibility; Parsing; Computer science; Syntax; DECIPHER; Suite; Biological data; Programming language; Data science; Artificial intelligence; Bioinformatics; Biology","score_opus":0.19608345861600962,"score_gpt":0.42366593650439754,"score_spread":0.22758247788838792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785096815","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007876976,0.000009678311,0.9803612,0.0004698676,0.0018872081,0.0002621323,0.00012360948,0.00009850077,0.008910805],"genre_scores_gemma":[0.16879933,6.003492e-7,0.82891566,0.0006540467,0.00037347453,0.000009714493,0.00011098664,0.000008064435,0.0011281066],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978192,0.00004913894,0.0008914616,0.0003408555,0.00057124055,0.00032809537],"domain_scores_gemma":[0.9965271,0.001815645,0.00037928938,0.0006971509,0.0004882654,0.00009256765],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004047479,0.00012638854,0.00019722932,0.00035493897,0.0004506309,0.00048751474,0.00094467873,0.00005964246,0.00017815002],"category_scores_gemma":[0.0031664162,0.00009028717,0.000102754464,0.00066526554,0.00023437662,0.00032604672,0.00040742802,0.000046413614,0.0016836423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072221876,0.00011420445,0.007511819,0.000085182,0.000054895343,5.410643e-7,0.0019335613,0.00558614,0.00004230173,0.2030256,0.4848873,0.29668623],"study_design_scores_gemma":[0.0002525172,0.000080194906,0.0008712977,0.000010555528,0.0000066995854,0.0000033993774,0.00058817264,0.7752853,0.000066526336,0.026960539,0.19575237,0.0001224485],"about_ca_topic_score_codex":0.0000069370826,"about_ca_topic_score_gemma":0.000021024882,"teacher_disagreement_score":0.76969916,"about_ca_system_score_codex":0.00002804016,"about_ca_system_score_gemma":0.00008041543,"threshold_uncertainty_score":0.99909365},"labels":[],"label_agreement":null},{"id":"W2792331414","doi":"10.1186/s12859-018-2391-z","title":"Valection: design optimization for validation and verification studies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; Terry Fox Research Institute; Movember Foundation","keywords":"Computer science; Software; Selection (genetic algorithm); Inference; Data mining; Machine learning; Artificial intelligence; Programming language","score_opus":0.09419023023291122,"score_gpt":0.3327364530797012,"score_spread":0.23854622284678995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792331414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000141903,0.00003657862,0.9986105,0.0001317533,0.00042906697,0.00032314257,5.1963275e-7,0.00014050229,0.00018606156],"genre_scores_gemma":[0.007240308,0.000027034384,0.9924403,0.00006667315,0.00013495013,0.000027034801,0.000006361918,0.0000055499454,0.000051795683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937284,0.00004320659,0.00023004723,0.00011837859,0.00011967977,0.000115874616],"domain_scores_gemma":[0.9991265,0.000207173,0.00017029537,0.00020965099,0.00025940922,0.000027001322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005161094,0.000083636754,0.00009028169,0.00008489872,0.00030961598,0.00012777725,0.00017192251,0.000047614074,0.0000027451679],"category_scores_gemma":[0.0004949022,0.00007784799,0.000017828817,0.00022699288,0.0000647652,0.000985507,0.000076679265,0.00004051116,0.000009928109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029017872,0.000015159127,0.00022791549,0.00018539696,0.00003104833,4.62706e-8,0.0062149866,0.93411946,0.000022521044,0.022922829,0.0011079605,0.035123628],"study_design_scores_gemma":[0.00025772065,0.000121459474,0.00007526656,0.0000146543325,0.00001133775,0.0000043432947,0.00020559822,0.99701923,0.00064798875,0.001220092,0.0003268068,0.00009549813],"about_ca_topic_score_codex":7.007475e-7,"about_ca_topic_score_gemma":4.997149e-7,"teacher_disagreement_score":0.062899746,"about_ca_system_score_codex":0.000041142423,"about_ca_system_score_gemma":0.000041800016,"threshold_uncertainty_score":0.3174549},"labels":[],"label_agreement":null},{"id":"W2794562641","doi":"10.1186/s12859-018-2076-7","title":"NoLogo: a new statistical model highlights the diversity and suggests new classes of Crm1-dependent nuclear export signals","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Representation (politics); Probabilistic logic; Computational biology; Statistical model; Generative model; Perspective (graphical); Nuclear export signal; Computer science; Generative grammar; Biology; Machine learning; Artificial intelligence; Genetics; RNA; Gene","score_opus":0.019934787242034534,"score_gpt":0.2360017211959825,"score_spread":0.21606693395394796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794562641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7815006,0.0001121995,0.21427204,0.00024276871,0.00032896543,0.00028201367,0.000053942225,0.00003090589,0.003176609],"genre_scores_gemma":[0.94262147,0.00011765473,0.055502243,0.00044167848,0.00025087374,3.5824036e-7,0.000029802133,0.000013820951,0.001022112],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993417,0.00001445857,0.00021770611,0.00011847116,0.00015582405,0.00015184232],"domain_scores_gemma":[0.9994452,0.00001619066,0.00011847141,0.00025385883,0.0000654208,0.00010083164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008330773,0.000115493945,0.0001233129,0.000025288462,0.00022123751,0.000022325186,0.00016187149,0.00013946243,0.000048362323],"category_scores_gemma":[0.00005087669,0.000079652156,0.000037827012,0.000041647967,0.00016851751,0.000012788932,0.00043357644,0.00006537353,0.00001736113],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032614572,0.00032541604,0.030692324,0.00074497826,0.0009267589,0.000009577571,0.020284684,0.0018499516,0.1259997,0.065858185,0.70696497,0.04308197],"study_design_scores_gemma":[0.009612462,0.008623283,0.11829021,0.0001742667,0.0010826329,0.00033570072,0.005933955,0.5179207,0.10720383,0.021921618,0.20610978,0.002791598],"about_ca_topic_score_codex":0.000050714643,"about_ca_topic_score_gemma":0.00006031247,"teacher_disagreement_score":0.5160707,"about_ca_system_score_codex":0.0000072920748,"about_ca_system_score_gemma":0.000100104226,"threshold_uncertainty_score":0.32481205},"labels":[],"label_agreement":null},{"id":"W2795167067","doi":"10.1186/s12859-018-2091-8","title":"Inferring RNA sequence preferences for poorly studied RNA-binding proteins based on co-evolution","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"RNA-binding protein; Computational biology; RNA; Sequence (biology); Biology; Computer science; Genetics; Gene","score_opus":0.060630971087458595,"score_gpt":0.3307538457633682,"score_spread":0.2701228746759096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795167067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73198545,0.000020923932,0.2618553,0.000037869828,0.00009109558,0.00082604564,0.000062121995,0.000030115616,0.005091082],"genre_scores_gemma":[0.95089465,0.00000960261,0.048067935,0.00013213164,0.00021691038,0.00010526305,0.00011862904,0.000015019244,0.00043987966],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884653,0.000029637902,0.000292875,0.00017820031,0.00024980144,0.00040297597],"domain_scores_gemma":[0.9992334,0.00003862885,0.00014009658,0.00030252567,0.00017922599,0.00010612404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004202102,0.00016104973,0.00013826105,0.00009886747,0.00028981522,0.00007370792,0.00024316343,0.00012419684,0.000008910075],"category_scores_gemma":[0.00039571943,0.00013526167,0.000074817035,0.00011004827,0.00012592474,0.000019337633,0.00006269773,0.000095009775,0.000039969527],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008137793,0.00014932505,0.010883455,0.00077303714,0.00010015955,9.876021e-7,0.00036197455,0.0011808139,0.9703408,0.0007882227,0.0031347992,0.011472678],"study_design_scores_gemma":[0.0019188587,0.0035369694,0.002438053,0.00023171141,0.000019278294,0.0000035078049,0.0006564005,0.4372979,0.5500507,0.00014471222,0.003204241,0.00049766916],"about_ca_topic_score_codex":0.00001732933,"about_ca_topic_score_gemma":0.00006401007,"teacher_disagreement_score":0.4361171,"about_ca_system_score_codex":0.00006196148,"about_ca_system_score_gemma":0.00025248856,"threshold_uncertainty_score":0.5515811},"labels":[],"label_agreement":null},{"id":"W2797768225","doi":"10.1186/s12859-018-2106-5","title":"A hidden Markov tree model for testing multiple hypotheses corresponding to Gene Ontology gene sets","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Computational biology; Gene; DNA microarray; Tree (set theory); Genetics; Computer science; Gene ontology; Hidden Markov model; Markov chain; Markov model; Biology; Data mining; Artificial intelligence; Machine learning; Mathematics; Gene expression; Combinatorics","score_opus":0.047579954999098395,"score_gpt":0.27225235799392294,"score_spread":0.22467240299482455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797768225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18295303,0.00008478035,0.8135349,0.00005786262,0.000350171,0.00081214064,0.00020978173,0.000047573925,0.0019497472],"genre_scores_gemma":[0.21172936,0.000010867673,0.7855561,0.001193759,0.00042661247,0.00008436848,0.0002023499,0.000042855307,0.00075377844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817586,0.000022528919,0.00070461264,0.00027048113,0.000155796,0.0006707059],"domain_scores_gemma":[0.99848473,0.0001463385,0.00027286616,0.0005972913,0.00026656594,0.00023221178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044936317,0.00032061155,0.00030993985,0.00013418667,0.00027678872,0.000086831584,0.0004583423,0.00030791672,0.0000069595453],"category_scores_gemma":[0.00066770084,0.00030106475,0.00013891526,0.00018062131,0.00011912574,0.000019388886,0.0003142297,0.000097201686,0.00006450467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003777196,0.0003713454,0.01209419,0.0009901291,0.0005871287,0.000004810008,0.007666461,0.025426123,0.29140335,0.0005785943,0.08863597,0.5684647],"study_design_scores_gemma":[0.0010016698,0.0005482125,0.0005059518,0.000028519546,0.000036183297,0.00004854481,0.00019503891,0.9783777,0.014713785,0.00024347997,0.003861689,0.0004392179],"about_ca_topic_score_codex":0.000008892783,"about_ca_topic_score_gemma":0.00027413815,"teacher_disagreement_score":0.9529516,"about_ca_system_score_codex":0.000042409425,"about_ca_system_score_gemma":0.00021478863,"threshold_uncertainty_score":0.99994415},"labels":[],"label_agreement":null},{"id":"W2798055326","doi":"10.1186/s12859-018-2118-1","title":"Encompassing new use cases - level 3.0 of the HUPO-PSI format for molecular interactions","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"FP7 Health; National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; National Institutes of Health; European Commission; Fondation pour la Recherche Médicale; Institut Français de Bioinformatique; EMBL Australia; British Heart Foundation; Wellcome Trust","keywords":"Computer science; Workgroup; XML; Suite; Data exchange; Collaboratory; Data format; Database; Information retrieval; World Wide Web","score_opus":0.09992559651893787,"score_gpt":0.30643933956922,"score_spread":0.2065137430502821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798055326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08230955,0.000089637346,0.9143545,0.00011529676,0.00076639594,0.000581563,0.00020991359,0.000015600934,0.0015575531],"genre_scores_gemma":[0.68121743,0.000024775676,0.31539539,0.00101631,0.0004656353,0.000021707074,0.00015619885,0.000033932323,0.0016686056],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885076,0.00001693678,0.00059112307,0.00010669349,0.00013881458,0.00029567597],"domain_scores_gemma":[0.9987059,0.00007191827,0.00036573457,0.0005732833,0.00018738401,0.00009575503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015842922,0.00018743951,0.00017888016,0.00005109338,0.00020297438,0.000084669526,0.00034964024,0.00013363009,0.000013647764],"category_scores_gemma":[0.00022670781,0.00013876765,0.00022718775,0.0001254971,0.00017364506,0.000040732273,0.00022018295,0.000092112336,0.000011601629],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017105949,0.0005109208,0.0073186494,0.0019443858,0.0011314001,0.0000019548224,0.007704413,0.0069400035,0.113094024,0.018438166,0.7121925,0.129013],"study_design_scores_gemma":[0.0026370105,0.00091029593,0.002696868,0.00029334097,0.00022507309,0.00026550057,0.0016018163,0.2848297,0.21851224,0.0012220358,0.48584145,0.0009646618],"about_ca_topic_score_codex":0.0000339177,"about_ca_topic_score_gemma":0.0002484004,"teacher_disagreement_score":0.5989591,"about_ca_system_score_codex":0.00002057439,"about_ca_system_score_gemma":0.00023201342,"threshold_uncertainty_score":0.56587803},"labels":[],"label_agreement":null},{"id":"W2798884003","doi":"10.1186/s12859-018-2142-1","title":"Realizing drug repositioning by adapting a recommendation system to handle the process","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Drug repositioning; Computer science; Process (computing); Machine learning; Risk analysis (engineering); Collaborative filtering; Data science; Drug discovery; Precision medicine; Drug; Data mining; Recommender system; Artificial intelligence; Bioinformatics; Medicine","score_opus":0.02224553199740555,"score_gpt":0.30394974581836304,"score_spread":0.2817042138209575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798884003","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062252367,0.000009834422,0.9821702,0.0008185531,0.00030610262,0.00029930734,0.000006406365,0.00021479292,0.009949524],"genre_scores_gemma":[0.20434934,5.022532e-7,0.79470026,0.000658747,0.00014242527,0.000038222675,0.000021328062,0.000009712725,0.00007946601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986458,0.00013748219,0.000493465,0.00017507754,0.00031249586,0.0002357112],"domain_scores_gemma":[0.99868715,0.00036247427,0.0002779324,0.0003664059,0.00022951285,0.00007653437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014597067,0.0001229614,0.000119119635,0.000087602595,0.00056854275,0.00054443936,0.0006127856,0.000030012048,0.0000030280203],"category_scores_gemma":[0.00020140912,0.00009449423,0.000039912924,0.0006186601,0.000032523723,0.0010408236,0.00025573716,0.00009333516,0.00008283347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010396438,0.00017385547,0.0010541793,0.0019420136,0.00013409201,0.0000034177804,0.14180754,0.17205507,0.00030474606,0.21872342,0.08120384,0.38249385],"study_design_scores_gemma":[0.00011084755,0.00003673599,0.000082846935,0.00014551877,0.0000052807313,0.000035465415,0.0026964447,0.99319863,0.0010061363,0.00030492808,0.0022411924,0.00013598979],"about_ca_topic_score_codex":0.000028775905,"about_ca_topic_score_gemma":0.00001605983,"teacher_disagreement_score":0.82114357,"about_ca_system_score_codex":0.00012044234,"about_ca_system_score_gemma":0.00011928171,"threshold_uncertainty_score":0.52500415},"labels":[],"label_agreement":null},{"id":"W2800043800","doi":"10.1186/s12859-018-2131-4","title":"On the rank-distance median of 3 permutations","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; Alfred P. Sloan Foundation","keywords":"Combinatorics; Permutation (music); Mathematics; Median; Rank (graph theory); Distance matrix; Matrix (chemical analysis); Heuristic; Discrete mathematics; Algorithm; Mathematical optimization","score_opus":0.015539769042076981,"score_gpt":0.24492022515144965,"score_spread":0.22938045610937266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800043800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4333993,0.00021198849,0.4963158,0.0008597361,0.0005582187,0.0008909753,0.00016335552,0.000033177035,0.067567445],"genre_scores_gemma":[0.96245074,0.000040229883,0.035997443,0.00042488615,0.0001903313,0.000018885316,0.000087383305,0.000013844897,0.0007762774],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945843,0.00001676959,0.00019689476,0.00006531526,0.00013679382,0.00012577031],"domain_scores_gemma":[0.99941885,0.000026634783,0.0000967659,0.00032689783,0.000098669276,0.000032187978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015559328,0.00007825606,0.000067317604,0.000027410942,0.0000739059,0.000011952766,0.00018775385,0.00005225,0.000070255715],"category_scores_gemma":[0.00013190595,0.00005327127,0.00004981539,0.00009041734,0.00017004416,0.0000029404073,0.00004097122,0.000036744044,0.00010436096],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013248045,0.0015233345,0.021365564,0.002317949,0.001652047,0.000004710703,0.037908968,0.0031190317,0.24660836,0.22367105,0.38315398,0.07735021],"study_design_scores_gemma":[0.0054213516,0.0043626614,0.0160832,0.00024780116,0.00021249878,0.00004115915,0.011105017,0.23925364,0.40003127,0.009603036,0.31186208,0.0017762783],"about_ca_topic_score_codex":0.0000017366227,"about_ca_topic_score_gemma":0.000031323714,"teacher_disagreement_score":0.5290514,"about_ca_system_score_codex":0.0000062885883,"about_ca_system_score_gemma":0.000050044444,"threshold_uncertainty_score":0.21723393},"labels":[],"label_agreement":null},{"id":"W2801401057","doi":"10.1186/s12859-018-2066-9","title":"Pathway-based approach using hierarchical components of rare variants to analyze multiple phenotypes","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Korea Health Industry Development Institute; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Computational biology; Phenotype; Univariate; Missing heritability problem; Pathway analysis; Biology; Exome; Biological pathway; Exome sequencing; Bioinformatics; Computer science; Multivariate statistics; Genetics; Genetic variants; Gene; Genotype; Machine learning","score_opus":0.02683591815347687,"score_gpt":0.2506160568930316,"score_spread":0.22378013873955477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801401057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6895681,0.000039994044,0.30919644,0.000008557432,0.000089733934,0.00021049395,0.00031050714,0.000008980622,0.00056721625],"genre_scores_gemma":[0.7770025,0.0000017126473,0.22229825,0.00018699691,0.00010404127,0.000003823856,0.00037348765,0.00001302189,0.000016157746],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910116,0.00003465404,0.00033514274,0.00015684238,0.00014678371,0.00022541654],"domain_scores_gemma":[0.99920183,0.00001602863,0.00012326422,0.00037112358,0.0001388603,0.00014891727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013677719,0.00014596815,0.00017344728,0.00008011036,0.00009085228,0.000025094329,0.00023294796,0.00010671975,0.000010461881],"category_scores_gemma":[0.00011898077,0.00012790122,0.00010146014,0.00012683228,0.00010644298,0.0000053985636,0.00013872825,0.000047469126,0.000011117908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026325486,0.0021521626,0.069024086,0.0018758723,0.00053919153,0.000008045082,0.0021123681,0.05435878,0.85337305,0.0007668873,0.0031284383,0.01002858],"study_design_scores_gemma":[0.0013545502,0.00038095703,0.012285952,0.000049446375,0.000049602582,0.000012013905,0.0002719557,0.9394834,0.04166967,0.000040563526,0.003985946,0.00041596423],"about_ca_topic_score_codex":0.00002407052,"about_ca_topic_score_gemma":0.000014706221,"teacher_disagreement_score":0.8851246,"about_ca_system_score_codex":0.000011029472,"about_ca_system_score_gemma":0.0001874717,"threshold_uncertainty_score":0.5215661},"labels":[],"label_agreement":null},{"id":"W2801476357","doi":"10.1186/s12859-018-2146-x","title":"Prediction of microRNA-disease associations based on distance correlation set","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Construct Program of the Key Discipline in Hunan Province; Xiangtan University; National Natural Science Foundation of China","keywords":"Correlation; microRNA; DNA microarray; Computational biology; Set (abstract data type); Biology; Disease; Computer science; Bioinformatics; Genetics; Mathematics; Medicine; Gene; Pathology; Gene expression","score_opus":0.022365185662987383,"score_gpt":0.2693788444475479,"score_spread":0.2470136587845605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801476357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007219643,0.000035242836,0.9888603,0.000045099692,0.00022704828,0.00029589693,0.0007166147,0.000020627109,0.0025795025],"genre_scores_gemma":[0.9742581,0.0000238591,0.022791464,0.0002844326,0.00021574671,0.000026328551,0.001992347,0.000026463187,0.0003812617],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990645,0.000048288035,0.00029138956,0.00013281424,0.00028681595,0.00017616553],"domain_scores_gemma":[0.999077,0.000021967147,0.00018380901,0.00038338892,0.00024055623,0.00009323106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023239285,0.00010689653,0.00009096475,0.00008323565,0.00009451839,0.000019031548,0.0001306035,0.00013711696,0.000023818231],"category_scores_gemma":[0.00038737044,0.000109645836,0.000079911384,0.00017189003,0.00008444185,0.000008291042,0.000041101048,0.000085257554,0.000032649117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058879596,0.0019198095,0.033561092,0.0020457616,0.00064530177,0.000004092346,0.001965179,0.31279376,0.49203858,0.010960637,0.11452725,0.023650592],"study_design_scores_gemma":[0.0008988364,0.00054153154,0.005866724,0.000056452343,0.00003268528,7.209056e-7,0.000046718524,0.9282866,0.053024452,0.00009361286,0.0110109,0.00014072761],"about_ca_topic_score_codex":0.0000041594803,"about_ca_topic_score_gemma":0.000019768477,"teacher_disagreement_score":0.96703845,"about_ca_system_score_codex":0.000055618682,"about_ca_system_score_gemma":0.00022366275,"threshold_uncertainty_score":0.44712272},"labels":[],"label_agreement":null},{"id":"W2803405718","doi":"10.1186/s12859-018-2184-4","title":"Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Brain Tumour Foundation of Canada; Brain Tumour Research; Nvidia","keywords":"Dimensionality reduction; Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Computer science; Nonlinear dimensionality reduction; Anomaly (physics); Reduction (mathematics); Feature vector; Space (punctuation); Curse of dimensionality; Physics; Mathematics","score_opus":0.03943739908664989,"score_gpt":0.2879302342849939,"score_spread":0.24849283519834403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803405718","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24078546,0.000079919315,0.75779915,0.00007422459,0.00064233656,0.0001410116,4.785681e-7,0.00022208621,0.0002553532],"genre_scores_gemma":[0.46933618,0.000016346674,0.5303384,0.00003122237,0.00021291964,0.0000043368454,0.0000027511674,0.0000081848875,0.00004963793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885714,0.000101675774,0.00029404057,0.0002646575,0.00026199405,0.0002205107],"domain_scores_gemma":[0.99899125,0.000041180636,0.0003662718,0.00032406847,0.00020857753,0.000068627945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005418698,0.00015601305,0.00013750583,0.0001649333,0.00061838387,0.00016572452,0.00017019444,0.00017031487,0.0000024093329],"category_scores_gemma":[0.00011516986,0.00015189858,0.0000405549,0.00047974914,0.00013932004,0.001154023,0.00014540342,0.00024688555,0.000021376743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031012634,0.00022882022,0.020702615,0.0010691573,0.00007508204,0.000006950402,0.0204426,0.010430364,0.3088359,0.010088249,0.0002355987,0.62757456],"study_design_scores_gemma":[0.00016263888,0.00017388858,0.011829604,0.00002721054,0.000013805982,0.00022808855,0.0004527431,0.97951555,0.0059055225,0.00020681878,0.0013026886,0.00018146256],"about_ca_topic_score_codex":0.000022321628,"about_ca_topic_score_gemma":0.0000249332,"teacher_disagreement_score":0.96908516,"about_ca_system_score_codex":0.00030745514,"about_ca_system_score_gemma":0.000056200544,"threshold_uncertainty_score":0.6194244},"labels":[],"label_agreement":null},{"id":"W2805544673","doi":"10.1186/s12859-018-2185-3","title":"Robust joint score tests in the application of DNA methylation data analysis","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Statistics; DNA methylation; Power analysis; Mathematics; Statistical power; Biology; Algorithm; Genetics; Gene; Gene expression","score_opus":0.08401537177493584,"score_gpt":0.3076311488138606,"score_spread":0.22361577703892477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805544673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3212303,0.00017619108,0.6771531,0.000033269098,0.000030381247,0.00023107236,0.000040742685,0.0000043811606,0.0011005631],"genre_scores_gemma":[0.9280732,0.00006213776,0.07042875,0.00005380177,0.00010082522,0.000009236337,0.001252772,0.000006066712,0.000013187774],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990627,0.000055476794,0.00043435328,0.00015264205,0.00017789108,0.00011692013],"domain_scores_gemma":[0.9985677,0.000028343768,0.0002536861,0.0010079638,0.000119166005,0.000023141638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089869084,0.00009031331,0.00012885773,0.00012306744,0.00004717563,0.000021936377,0.00036969793,0.000101166675,0.0000047055537],"category_scores_gemma":[0.00018988304,0.00006740491,0.000053913755,0.0005331232,0.00008067408,0.000012739384,0.00013130941,0.00004626754,0.000007670826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017495027,0.00059182267,0.40728122,0.0005691184,0.00068022846,4.787337e-7,0.004086518,0.047845807,0.4220355,0.002520056,0.0014247885,0.11278954],"study_design_scores_gemma":[0.00038163923,0.0002083676,0.22585343,0.000011282153,0.00022082741,9.2873313e-7,0.00040215632,0.69974244,0.06903392,0.00036253786,0.0035767872,0.00020566816],"about_ca_topic_score_codex":0.000034135777,"about_ca_topic_score_gemma":0.00082135363,"teacher_disagreement_score":0.65189666,"about_ca_system_score_codex":0.0000073841134,"about_ca_system_score_gemma":0.000049127906,"threshold_uncertainty_score":0.27486923},"labels":[],"label_agreement":null},{"id":"W2806785716","doi":"10.1186/s12859-018-2202-6","title":"Correction to: Identification and characterization of conserved lncRNAs in human and rat brain","year":2018,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; Hamilton Health Sciences Foundation; National Institute for Health and Care Research","keywords":"Statement (logic); Acknowledgement; Identification (biology); Computational biology; Computer science; DNA microarray; Bioinformatics; Information retrieval; Data science; Natural language processing; Biology; Genetics; Linguistics; Philosophy; Gene; Ecology; Computer security","score_opus":0.012937076468085007,"score_gpt":0.2772080472680571,"score_spread":0.2642709707999721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806785716","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5540214,0.0013462526,0.40065196,0.0005809966,0.03043933,0.0056626415,0.0005656219,0.000081696424,0.0066500483],"genre_scores_gemma":[0.26066208,0.0108228745,0.021672167,0.0032448026,0.005458362,0.0008423552,0.07176136,0.00074069615,0.6247953],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99879956,0.0000678098,0.0005194898,0.00023626658,0.0001943783,0.000182499],"domain_scores_gemma":[0.99908024,0.000013672328,0.00031226283,0.000331652,0.00018416543,0.000077995566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037830556,0.0001831356,0.00022477123,0.0002532192,0.000063027306,0.00006698073,0.0001314242,0.00044917854,0.000009262774],"category_scores_gemma":[0.00029667345,0.00020199303,0.00003822632,0.00017765167,0.00010258268,0.000011644759,0.00017887905,0.00022090397,0.00000454818],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006416551,0.000020924264,0.000059249345,0.0005190422,0.000023142245,3.71386e-7,0.00021931516,0.000007770681,0.85956323,0.000020846426,0.13807543,0.0014264926],"study_design_scores_gemma":[0.0016801392,0.0011925945,0.007845562,0.0010401575,0.00007021752,0.000053771266,0.0003122849,0.042586334,0.7515314,0.000055503846,0.19278407,0.00084791624],"about_ca_topic_score_codex":0.000040275732,"about_ca_topic_score_gemma":0.00047070612,"teacher_disagreement_score":0.6181453,"about_ca_system_score_codex":0.000037610203,"about_ca_system_score_gemma":0.0001931417,"threshold_uncertainty_score":0.82370365},"labels":[],"label_agreement":null},{"id":"W2811242925","doi":"10.1186/s12859-018-2255-6","title":"BROCKMAN: deciphering variance in epigenomic regulators by k-mer factorization","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Human Genome Research Institute; Howard Hughes Medical Institute","keywords":"Epigenomics; Variance (accounting); Computational biology; Computer science; Biology; Bioinformatics; Genetics; Business; DNA methylation; Gene; Gene expression","score_opus":0.006188141073960664,"score_gpt":0.2146536632581338,"score_spread":0.20846552218417314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811242925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7229313,0.00009508309,0.27518225,0.000013839274,0.00022407892,0.00015380577,0.000026276612,0.000014052389,0.0013592595],"genre_scores_gemma":[0.9445754,0.00009089318,0.05425945,0.00014208382,0.00017189703,0.000009057605,0.00023201876,0.000028373273,0.0004908171],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991007,0.000015197932,0.00037341242,0.00015958962,0.0000947735,0.00025634246],"domain_scores_gemma":[0.9994028,0.00000714809,0.00014147928,0.00033355187,0.000052496416,0.00006248628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012139679,0.00015249159,0.00012450396,0.000040057825,0.00008179041,0.00004226042,0.00020988418,0.00016603297,0.000017566746],"category_scores_gemma":[0.000040967036,0.00015744842,0.000043537202,0.000115403986,0.000067367,0.000011536442,0.00010542063,0.000058451227,0.000046949237],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030963813,0.0005144371,0.15609434,0.0006951368,0.00021106485,0.000002335683,0.0043659694,0.011746591,0.7762294,0.002590891,0.024059065,0.023181157],"study_design_scores_gemma":[0.0040216716,0.00084189535,0.045607287,0.00013018725,0.0000451587,0.00003938371,0.0012671478,0.66010267,0.15335721,0.0008299586,0.13183191,0.0019255157],"about_ca_topic_score_codex":0.00001272046,"about_ca_topic_score_gemma":0.00012090363,"teacher_disagreement_score":0.6483561,"about_ca_system_score_codex":0.000044630007,"about_ca_system_score_gemma":0.00007336806,"threshold_uncertainty_score":0.64205605},"labels":[],"label_agreement":null},{"id":"W2811465744","doi":"10.1186/s12859-018-2258-3","title":"Correction to: Realizing drug repositioning by adapting a recommendation system to handle the process","year":2018,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Process (computing); Drug repositioning; Drug; Information retrieval; Data science; World Wide Web; Computational biology; Medicine; Biology; Pharmacology; Programming language","score_opus":0.01998176224378667,"score_gpt":0.30039261567210024,"score_spread":0.28041085342831357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811465744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036671863,0.00003310518,0.9296449,0.0006579655,0.02828345,0.00082578725,0.00003503607,0.00036275748,0.04012034],"genre_scores_gemma":[0.00088360975,0.000008367679,0.9640451,0.0017674089,0.0022500241,0.0003358822,0.000986007,0.00008045849,0.029643113],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970483,0.0003021557,0.0010481939,0.00044599312,0.0007292255,0.00042611765],"domain_scores_gemma":[0.9969918,0.0006797385,0.0008822477,0.0007384342,0.00053554436,0.00017224626],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022464169,0.00036407632,0.00036071317,0.00031369636,0.00082154665,0.0013310282,0.0012488752,0.00015806327,0.000004962226],"category_scores_gemma":[0.0008251577,0.00030372312,0.0001162451,0.0012211081,0.00002809922,0.0010662965,0.00059032836,0.00053646724,0.0001660739],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008950314,0.000012025903,0.0000038682806,0.0004186122,0.000018370672,3.66894e-7,0.005398178,0.0185455,0.0000011608307,0.00044764328,0.96123064,0.013914683],"study_design_scores_gemma":[0.00008571867,0.00007166767,0.000019413403,0.001562831,0.000021641392,0.000064351276,0.0021202455,0.89555067,0.00007474237,0.00006563981,0.10000981,0.0003532687],"about_ca_topic_score_codex":0.00012527978,"about_ca_topic_score_gemma":0.00010923891,"teacher_disagreement_score":0.87700516,"about_ca_system_score_codex":0.00058745546,"about_ca_system_score_gemma":0.0005897152,"threshold_uncertainty_score":0.99994147},"labels":[],"label_agreement":null},{"id":"W2883667799","doi":"10.1186/s12859-018-2251-x","title":"An integrative network-based approach to identify novel disease genes and pathways: a case study in the context of inflammatory bowel disease","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation","funders":"Mitacs; Nara Institute of Science and Technology; Research Manitoba; Health Sciences Centre Foundation","keywords":"Inflammatory bowel disease; Context (archaeology); Disease; DNA microarray; Computational biology; Gene; Gene regulatory network; Bioinformatics; Biology; Medicine; Genetics; Gene expression; Pathology","score_opus":0.022723043864488365,"score_gpt":0.2716813573990211,"score_spread":0.24895831353453274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883667799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87997335,0.00025845805,0.1180551,0.000017629047,0.000088796856,0.0013127442,0.00011887835,0.00001060994,0.00016441329],"genre_scores_gemma":[0.98358786,0.000013444844,0.0151352165,0.000818607,0.00019654928,0.00010437133,0.00011961216,0.000017354096,0.000006991799],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852085,0.000095366915,0.00065041956,0.00021648715,0.00020384383,0.00031303382],"domain_scores_gemma":[0.9985714,0.00003888017,0.00022876724,0.0007308372,0.0001390327,0.00029110568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072235777,0.00026402445,0.00021389857,0.00008447714,0.00015289427,0.00009918287,0.00037390547,0.00009688018,0.0000014646647],"category_scores_gemma":[0.00006373037,0.00018429523,0.00007799114,0.00017209833,0.0002407699,0.00002427184,0.00015680784,0.00011921691,0.0000027070253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0079607805,0.010374445,0.6357947,0.0039823945,0.0007728305,0.00030964956,0.16973566,0.08027809,0.004332688,0.0070753787,0.0070671006,0.07231629],"study_design_scores_gemma":[0.0031196908,0.0014472987,0.041180644,0.00012957702,0.00015174226,0.00007757638,0.076792404,0.8750675,0.00022690439,0.00012141542,0.00095148967,0.00073375995],"about_ca_topic_score_codex":0.000037590828,"about_ca_topic_score_gemma":0.0005868826,"teacher_disagreement_score":0.79478943,"about_ca_system_score_codex":0.000014890295,"about_ca_system_score_gemma":0.00023961467,"threshold_uncertainty_score":0.75153416},"labels":[],"label_agreement":null},{"id":"W2886919764","doi":"10.1186/s12859-019-2737-1","title":"Multiscale modeling reveals angiogenesis-induced drug resistance in brain tumors and predicts a synergistic drug combination targeting EGFR and VEGFR pathways","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Guangdong Province Key Laboratory of Computational Science; Sun Yat-sen University; National Natural Science Foundation of China; York University","keywords":"Angiogenesis; Drug; Drug resistance; VEGF receptors; Cancer research; EGFR inhibitors; DNA microarray; Computational biology; Epidermal growth factor receptor; Biology; Medicine; Bioinformatics; Pharmacology; Receptor; Genetics; Gene; Gene expression","score_opus":0.026850568775776608,"score_gpt":0.2511634707739949,"score_spread":0.22431290199821832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886919764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9847664,0.0002390413,0.011606503,0.00019591705,0.00008672151,0.0010630536,0.000032933054,0.00014416841,0.0018652568],"genre_scores_gemma":[0.856191,0.00001232626,0.1431859,0.00010166328,0.000023171953,0.00004516485,0.000031518677,0.000039537856,0.0003697562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973616,0.00017997065,0.0012331316,0.0003376047,0.0003678057,0.0005199159],"domain_scores_gemma":[0.9971978,0.0016727822,0.00042891863,0.0004271822,0.00010274085,0.0001705402],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019334016,0.0003590806,0.0006784103,0.00024058174,0.00013087712,0.00008192623,0.00023780874,0.0001636315,0.000012251311],"category_scores_gemma":[0.0021533307,0.00032180475,0.00007178801,0.00028427845,0.00009322932,0.00037223933,0.00021672,0.0002647423,0.000028134842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005139313,0.0014107657,0.08050105,0.052357476,0.0002360145,0.00007886625,0.085890085,0.0008760048,0.01926578,0.749287,0.008225782,0.0013572724],"study_design_scores_gemma":[0.0019504374,0.00004718595,0.0012996328,0.0011888248,0.000041251442,0.00001499926,0.0024691978,0.8814883,0.00060558197,0.1103495,0.000014676487,0.00053039263],"about_ca_topic_score_codex":0.0000132439545,"about_ca_topic_score_gemma":0.00010472781,"teacher_disagreement_score":0.8806123,"about_ca_system_score_codex":0.000096358446,"about_ca_system_score_gemma":0.00006392627,"threshold_uncertainty_score":0.9999234},"labels":[],"label_agreement":null},{"id":"W2889813947","doi":"10.1186/s12859-018-2350-8","title":"SuperNoder: a tool to discover over-represented modular structures in networks","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Università degli Studi di Cagliari; National Science Foundation","keywords":"Computer science; Network motif; Disjoint sets; Modular design; Theoretical computer science; Motif (music); Network analysis; Artificial intelligence; Complex network; Data mining; World Wide Web; Mathematics","score_opus":0.008945370019507059,"score_gpt":0.2444919388931529,"score_spread":0.23554656887364583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889813947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53511655,0.0001415832,0.46053928,0.0000614126,0.00046128972,0.0005622675,0.000045450408,0.000027774244,0.0030444236],"genre_scores_gemma":[0.93081814,0.000055699857,0.065416254,0.0020776163,0.0007982239,0.00003165752,0.0002696057,0.000041621806,0.00049119414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983378,0.00002600045,0.0006395135,0.00023935536,0.00020874864,0.0005485963],"domain_scores_gemma":[0.99890304,0.000014381619,0.00012145518,0.00073258503,0.00008199259,0.00014657763],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025719657,0.00027785357,0.00024385027,0.00011327035,0.000102053644,0.000114742594,0.00040589672,0.00028311962,0.000059950806],"category_scores_gemma":[0.00007757815,0.00024558825,0.00011277825,0.0002630156,0.000114306444,0.000025842515,0.00040202407,0.00015895584,0.000058128408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002924935,0.00059498043,0.12341751,0.0008265728,0.0006937282,0.00001854987,0.0077337427,0.4997761,0.018793344,0.013159852,0.22144817,0.11061251],"study_design_scores_gemma":[0.0014428186,0.00040651334,0.021013899,0.000052269897,0.000019531024,0.000022565062,0.00033177139,0.9254943,0.0019193151,0.0006155791,0.04796483,0.00071661116],"about_ca_topic_score_codex":0.00004272842,"about_ca_topic_score_gemma":0.00038347387,"teacher_disagreement_score":0.4257182,"about_ca_system_score_codex":0.000032399093,"about_ca_system_score_gemma":0.0000926088,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W2896411685","doi":"10.1186/s12859-018-2286-z","title":"Dense neural networks for predicting chromatin conformation","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation pour la Recherche Médicale","keywords":"Chromatin; Sequence (biology); Computer science; Histone; Computational biology; Convolutional neural network; Nucleosome; ChIA-PET; Artificial neural network; Algorithm; DNA; Biological system; Biology; Artificial intelligence; Genetics","score_opus":0.010213924458796984,"score_gpt":0.23309639881696703,"score_spread":0.22288247435817005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896411685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43383655,0.00005874493,0.56391495,0.00001886256,0.00035535364,0.00039992272,0.00004281044,0.00003403343,0.0013387565],"genre_scores_gemma":[0.8607917,0.000028895198,0.13702625,0.00044173002,0.00078532204,0.000042415286,0.00068312493,0.00003037875,0.0001701753],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897224,0.000013858464,0.00046972034,0.000125362,0.00010161175,0.0003172266],"domain_scores_gemma":[0.99914384,0.000023957615,0.00025415941,0.00032004758,0.00017699129,0.000080998245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002528741,0.00016856658,0.00013508722,0.0000392363,0.00021057717,0.000058277623,0.00020498723,0.00017632074,0.00000956822],"category_scores_gemma":[0.000115508185,0.00016048994,0.00009705569,0.00006916074,0.00009271968,0.000015729132,0.00010514381,0.000059690505,0.000014963714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030191662,0.00087443704,0.084202915,0.0061008977,0.0014470723,0.000003841664,0.014639176,0.38743922,0.090633705,0.00996816,0.17928122,0.2223902],"study_design_scores_gemma":[0.0006534819,0.00038411075,0.0008141546,0.000013319985,0.000019761925,0.000024073554,0.0003220238,0.9914296,0.00217832,0.00004624102,0.0039135762,0.0002012963],"about_ca_topic_score_codex":0.000002742142,"about_ca_topic_score_gemma":0.00004541615,"teacher_disagreement_score":0.60399044,"about_ca_system_score_codex":0.000018634717,"about_ca_system_score_gemma":0.000057080884,"threshold_uncertainty_score":0.654459},"labels":[],"label_agreement":null},{"id":"W2899194228","doi":"10.1186/s12859-018-2430-9","title":"A comparative study of survival models for breast cancer prognostication revisited: the benefits of multi-gene models","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Breast cancer; Computational biology; DNA microarray; Gene; Biology; Bioinformatics; Computer science; Cancer; Gene expression; Genetics","score_opus":0.13615996009016712,"score_gpt":0.3501244586300445,"score_spread":0.21396449853987737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899194228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8014571,0.00070369797,0.18956234,0.00020342176,0.00016313234,0.0059303595,0.0011192426,0.000043959062,0.0008167462],"genre_scores_gemma":[0.96673596,0.0001015072,0.032661997,0.00005738276,0.000091054375,0.00028576868,0.000027902091,0.000013387914,0.000025031104],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866074,0.00003045255,0.00066976703,0.00012334659,0.0003381214,0.00017756068],"domain_scores_gemma":[0.9979365,0.00010425842,0.00042187874,0.00037626928,0.0011023595,0.00005874175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032108955,0.00015192284,0.00048513248,0.00007324391,0.00008473867,0.000012570811,0.00016277414,0.00006059239,0.000013478307],"category_scores_gemma":[0.00002527802,0.000095746625,0.00009082374,0.00028147115,0.00013434251,0.00020351127,0.00005493373,0.00006683945,0.0000018548484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009901243,0.017601518,0.14426583,0.013384541,0.004165854,3.7198285e-7,0.36303735,0.29130343,0.0014019946,0.02088619,0.004306197,0.12974547],"study_design_scores_gemma":[0.002304246,0.00093400053,0.021300886,0.00027106213,0.00039023845,0.0000030555834,0.006763187,0.96573466,0.0021153556,0.000060187198,0.000013365704,0.00010975948],"about_ca_topic_score_codex":0.00010730116,"about_ca_topic_score_gemma":0.00017344434,"teacher_disagreement_score":0.6744312,"about_ca_system_score_codex":0.00003692592,"about_ca_system_score_gemma":0.00014336618,"threshold_uncertainty_score":0.39044338},"labels":[],"label_agreement":null},{"id":"W2899264342","doi":"10.1186/s12859-018-2363-3","title":"Cluster oligonucleotide signatures for rapid identification by sequencing","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada","keywords":"Computational biology; In silico; DNA sequencing; Biology; Identification (biology); DNA microarray; Oligonucleotide; Pipeline (software); Phylogenetic tree; Sequence (biology); Cluster analysis; Genetics; Computer science; DNA; Gene; Artificial intelligence","score_opus":0.01587598900723189,"score_gpt":0.24672767650827784,"score_spread":0.23085168750104595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899264342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6298487,0.0016086719,0.362618,0.00015824016,0.0008008082,0.00095862173,0.0002892434,0.000020860673,0.0036968207],"genre_scores_gemma":[0.89904946,0.00017855145,0.098031804,0.001094032,0.0005558224,0.00005586456,0.00025205535,0.000028755758,0.0007536414],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992567,0.0000127400845,0.00029770107,0.00014454684,0.00007633531,0.000212],"domain_scores_gemma":[0.99937695,0.000020964242,0.00013383097,0.00027247772,0.00014927071,0.000046527322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021005918,0.00012772846,0.00010231139,0.000028436454,0.0001619795,0.00004584526,0.00016868889,0.000110682726,0.00000596289],"category_scores_gemma":[0.00009888382,0.00011628687,0.000075150754,0.000045572644,0.00009730871,0.0000023750104,0.00008032919,0.00003296463,0.000022887041],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103070444,0.000025182419,0.00057039404,0.00016070683,0.000104593375,4.1443e-8,0.00069110654,0.00025513416,0.8693509,0.00024270061,0.12138452,0.00711166],"study_design_scores_gemma":[0.0012478282,0.0006575874,0.0016021995,0.000020614341,0.00006922761,0.00000771166,0.00097186986,0.054445863,0.6616165,0.00047085516,0.27831385,0.0005758905],"about_ca_topic_score_codex":0.0000033277631,"about_ca_topic_score_gemma":0.000019056546,"teacher_disagreement_score":0.26920074,"about_ca_system_score_codex":0.000015373336,"about_ca_system_score_gemma":0.000052048475,"threshold_uncertainty_score":0.47420412},"labels":[],"label_agreement":null},{"id":"W2900916532","doi":"10.1186/s12859-018-2378-9","title":"The predictive performance of short-linear motif features in the prediction of calmodulin-binding proteins","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Calmodulin; Motif (music); Computational biology; DNA microarray; Calmodulin-binding proteins; Bioinformatics; Biology; Computer science; Genetics; Biochemistry; Gene; Gene expression","score_opus":0.012059938183981482,"score_gpt":0.2541088111200603,"score_spread":0.2420488729360788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900916532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797376,0.00006511018,0.014271538,0.000041897547,0.00018271086,0.0007521593,0.00008957607,0.000014392283,0.004845036],"genre_scores_gemma":[0.97751445,0.000106729574,0.021887312,0.00004391103,0.00018112539,0.00003068243,0.000101636004,0.000012796552,0.00012137718],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854445,0.00007148657,0.00069008983,0.00009724058,0.00035092313,0.0002458104],"domain_scores_gemma":[0.9988327,0.00006772926,0.00033082915,0.00054850517,0.0001897238,0.00003051789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085644925,0.00015996551,0.00016094456,0.00006892593,0.00017975937,0.000021049587,0.00051387906,0.0001650869,0.0000029558569],"category_scores_gemma":[0.0003935044,0.00009375156,0.00007971027,0.00023222598,0.00040428748,0.00002168232,0.00013797743,0.00022995312,0.0000048492575],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032645655,0.0008472534,0.7936194,0.005317934,0.0006394318,0.0000013980239,0.04399073,0.043514106,0.048762165,0.0023259008,0.011762393,0.045954723],"study_design_scores_gemma":[0.00065701245,0.0023492847,0.08889022,0.00016816481,0.000042280666,0.00003831708,0.0029231904,0.83505565,0.0654189,0.000020713678,0.0042304588,0.00020582757],"about_ca_topic_score_codex":0.000010417991,"about_ca_topic_score_gemma":0.000046877183,"teacher_disagreement_score":0.7915415,"about_ca_system_score_codex":0.000016255006,"about_ca_system_score_gemma":0.00010331865,"threshold_uncertainty_score":0.38230777},"labels":[],"label_agreement":null},{"id":"W2902011814","doi":"10.1186/s12859-018-2501-y","title":"SMuRF: a novel tool to identify regulatory elements enriched for somatic point mutations","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Princess Margaret Cancer Centre; University Health Network","funders":"Institute of Cancer Research; Prostate Cancer Canada; Government of Canada; Ontario Institute for Cancer Research; American Association for Cancer Research; Movember Foundation; Princess Margaret Cancer Foundation; Canadian Institutes of Health Research; Genome Canada; Stand Up To Cancer; Entertainment Industry Foundation; Government of Ontario","keywords":"Biology; Genetics; Point mutation; Computational biology; Gene; Context (archaeology); Mutation; Somatic cell; DNA microarray; Single-nucleotide polymorphism; Identification (biology); Genome; Gene expression; Genotype","score_opus":0.01517129533268553,"score_gpt":0.2824969322047588,"score_spread":0.2673256368720733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902011814","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57224625,0.000011666935,0.42636952,0.000042514523,0.00019806932,0.00057221076,0.000101836056,0.000018554481,0.00043939953],"genre_scores_gemma":[0.42130113,0.0000041482936,0.57674426,0.00063060893,0.00022827472,0.00011290522,0.0004464897,0.000033663455,0.00049852626],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986963,0.000009322779,0.0006098511,0.00019023739,0.00015999576,0.0003342466],"domain_scores_gemma":[0.99890375,0.000018892102,0.00021299912,0.0005329755,0.00022049504,0.00011087355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003049167,0.00019024237,0.00016373069,0.000080697435,0.0001930194,0.000084045154,0.0002841424,0.00013326069,0.000019362757],"category_scores_gemma":[0.00021247864,0.00019002051,0.00012149549,0.000116733114,0.000063936386,0.000012830426,0.00016983344,0.00004091957,0.00009899988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017575549,0.00037376612,0.0023057226,0.00090304454,0.0003202407,4.0474455e-7,0.00264655,0.0015219097,0.9644375,0.0040590656,0.01665641,0.0065996516],"study_design_scores_gemma":[0.0069197235,0.0023468612,0.049914207,0.00014266947,0.000273317,0.000071816634,0.0037484264,0.8329488,0.05814763,0.0038774866,0.039499875,0.002109157],"about_ca_topic_score_codex":0.0000024624565,"about_ca_topic_score_gemma":0.000044113396,"teacher_disagreement_score":0.9062899,"about_ca_system_score_codex":0.000041622803,"about_ca_system_score_gemma":0.0001458389,"threshold_uncertainty_score":0.7748811},"labels":[],"label_agreement":null},{"id":"W2902892882","doi":"10.1186/s12859-018-2499-1","title":"Integrated genome sizing (IGS) approach for the parallelization of whole genome analysis","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada)","funders":"INNOPOLIS Foundation; Korea Health Industry Development Institute","keywords":"Genome; Computer science; Reference genome; Whole genome sequencing; Leverage (statistics); Computational biology; Genome project; DNA sequencing; Biology; Genetics; Gene; Artificial intelligence","score_opus":0.024951918293970355,"score_gpt":0.24383852589272173,"score_spread":0.21888660759875136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902892882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0961089,0.001040574,0.9012575,0.000021121503,0.000054585646,0.0003974642,0.00019618848,0.0000042357383,0.0009194308],"genre_scores_gemma":[0.80007607,0.00022931857,0.19832307,0.00013418874,0.00018702871,0.000044380642,0.0007862218,0.000014614643,0.00020513921],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923015,0.00001606814,0.00035661817,0.00012817077,0.00008704848,0.00018194935],"domain_scores_gemma":[0.9991406,0.000025258983,0.0001935134,0.00035965373,0.00024894177,0.00003202929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024634783,0.0001293998,0.00018464682,0.00006583232,0.00015328846,0.000025471101,0.000245828,0.00008701686,0.000005139816],"category_scores_gemma":[0.00006307731,0.00008956077,0.00016512771,0.00027810762,0.00014063013,0.0000016670572,0.000102785496,0.000030888066,0.0000032522305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005043601,0.00031023336,0.020577101,0.0007568755,0.007169863,1.2322765e-7,0.007298942,0.18042783,0.7717519,0.0012536381,0.0012116384,0.008737527],"study_design_scores_gemma":[0.0010982521,0.00069334055,0.036970362,0.000006566012,0.0011284612,0.0000037018817,0.004419226,0.8395251,0.010284924,0.00010050298,0.1052402,0.0005293776],"about_ca_topic_score_codex":0.000009748002,"about_ca_topic_score_gemma":0.000037264985,"teacher_disagreement_score":0.7614669,"about_ca_system_score_codex":0.000008472565,"about_ca_system_score_gemma":0.000052505293,"threshold_uncertainty_score":0.36521825},"labels":[],"label_agreement":null},{"id":"W2903125175","doi":"10.1186/s12859-018-2485-7","title":"Purge Haplotigs: allelic contig reassignment for third-gen diploid genome assemblies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1285,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Wine Australia; Australian Government; Alberta Water Research Institute; Bioplatforms Australia","keywords":"Contig; Genome; Ploidy; Biology; Haplotype; Genetics; Sequence assembly; Purge; Computational biology; Allele; Gene; Transcriptome","score_opus":0.024740876154589482,"score_gpt":0.2563884776234654,"score_spread":0.23164760146887592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903125175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7860372,0.0037237178,0.1745552,0.0004508551,0.001759093,0.0036087246,0.008016101,0.000087009634,0.021762118],"genre_scores_gemma":[0.8201049,0.001303849,0.1677058,0.0024491837,0.0022088385,0.00044689653,0.0034874107,0.00010122536,0.0021918735],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878436,0.000018905563,0.00043542383,0.00021883278,0.00014478613,0.00039769986],"domain_scores_gemma":[0.9990167,0.0000281226,0.00018184775,0.00046711447,0.00019684089,0.00010936718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026040408,0.0002377304,0.00023125063,0.00005099885,0.0002274636,0.000062948064,0.0002981121,0.00015369739,0.000010288799],"category_scores_gemma":[0.00010475916,0.00020693016,0.00015407722,0.00006276802,0.00015651122,0.0000030699307,0.00021762765,0.00004491089,0.000050949548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005890168,0.0003561572,0.0068123783,0.0006917991,0.0011741435,0.0000011403706,0.002642999,0.00038922133,0.76364714,0.0019243733,0.21830161,0.0034700194],"study_design_scores_gemma":[0.0015188187,0.0013278543,0.010499879,0.00001945726,0.000096185264,0.000014424121,0.0009748314,0.0026939455,0.044317123,0.0004634516,0.9373907,0.00068334385],"about_ca_topic_score_codex":0.0000073205756,"about_ca_topic_score_gemma":0.000069332695,"teacher_disagreement_score":0.71933,"about_ca_system_score_codex":0.000019901905,"about_ca_system_score_gemma":0.00009571228,"threshold_uncertainty_score":0.84383667},"labels":[],"label_agreement":null},{"id":"W2904436729","doi":"10.1186/s12859-018-2470-1","title":"Towards a supervised classification of neocortical interneuron morphologies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"Horizon 2020 Framework Programme; Consejería de Educación, Juventud y Deporte, Comunidad de Madrid; Banco Bilbao Vizcaya Argentaria; Ministerio de Economía y Competitividad; École Polytechnique Fédérale de Lausanne; European Commission; Fundación BBVA","keywords":"Interneuron; Neuroscience; Neocortex; Biology; Computer science; Artificial intelligence","score_opus":0.08261878739241624,"score_gpt":0.29348978196076975,"score_spread":0.2108709945683535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904436729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9149373,0.0000017811412,0.07317924,0.00020396254,0.00053554564,0.00021721408,0.000017340955,0.00010676872,0.010800858],"genre_scores_gemma":[0.9880944,0.000009995439,0.011260838,0.0004315272,0.000055187404,0.000006572213,0.000005202279,0.00000813245,0.00012816756],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990795,0.00003584181,0.00037458786,0.00012676079,0.0002147303,0.00016857711],"domain_scores_gemma":[0.99937683,0.00010389124,0.00014015047,0.00026776016,0.000066629065,0.00004473305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010609439,0.000098097116,0.00012236627,0.00008460203,0.000056445417,0.000039397237,0.0002278981,0.00006283467,0.00005954864],"category_scores_gemma":[0.0007075906,0.0000764824,0.000057813635,0.00022402736,0.00028023886,0.00025234252,0.00009787181,0.00008519936,0.0001458627],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031930214,0.00024485093,0.004648154,0.00034176162,0.0000073337937,0.000003610739,0.0014631314,0.00006213935,0.8584104,0.053067442,0.0022305339,0.079201326],"study_design_scores_gemma":[0.0002751095,0.0004132734,0.018965615,0.000016513493,0.000008386322,0.000022010363,0.00017272985,0.8728016,0.10576701,0.00073263847,0.0007100693,0.00011506101],"about_ca_topic_score_codex":0.000005391743,"about_ca_topic_score_gemma":0.0000055431847,"teacher_disagreement_score":0.87273943,"about_ca_system_score_codex":0.000019841327,"about_ca_system_score_gemma":0.000040536834,"threshold_uncertainty_score":0.3118862},"labels":[],"label_agreement":null},{"id":"W2906953716","doi":"10.1186/s12859-018-2522-6","title":"DWNN-RLS: regularized least squares method for predicting circRNA-disease associations","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Kronecker product; Similarity (geometry); Computational biology; Computer science; Kernel (algebra); Disease; Data mining; Kronecker delta; Bioinformatics; Mathematics; Artificial intelligence; Biology; Medicine","score_opus":0.02468362127228896,"score_gpt":0.31545334908923983,"score_spread":0.2907697278169509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906953716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025377527,0.00025199095,0.96969914,0.00011827671,0.00043857578,0.0007852773,0.000735629,0.00010082381,0.0024927491],"genre_scores_gemma":[0.15626013,0.000030295041,0.8377056,0.0010000806,0.0018609809,0.0002146633,0.0019845648,0.00008758274,0.0008560942],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985722,0.00008357475,0.00047285535,0.00024699947,0.00024904226,0.00037533592],"domain_scores_gemma":[0.99842614,0.00009934594,0.0002831536,0.0006265483,0.00033842595,0.00022641361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055019406,0.00020806618,0.00019653425,0.00007447502,0.00031553302,0.00009796794,0.00031982583,0.0001692942,0.000020463314],"category_scores_gemma":[0.0029266644,0.0002136137,0.0002563506,0.00013587062,0.00011700101,0.000020741103,0.00015557598,0.00006863658,0.000027180531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004262636,0.0030046515,0.35807478,0.006663891,0.0039006185,0.000008135669,0.005926589,0.008568905,0.17595968,0.026340278,0.26198238,0.14530745],"study_design_scores_gemma":[0.005312102,0.0007735782,0.049556196,0.0001748842,0.0007530877,0.000020330808,0.0012953397,0.81690514,0.02337344,0.0035524033,0.09685828,0.0014252202],"about_ca_topic_score_codex":0.000007796818,"about_ca_topic_score_gemma":0.00004094911,"teacher_disagreement_score":0.80833626,"about_ca_system_score_codex":0.000041703915,"about_ca_system_score_gemma":0.0002799931,"threshold_uncertainty_score":0.8710914},"labels":[],"label_agreement":null},{"id":"W2914488418","doi":"10.1186/s12859-019-2611-1","title":"sim1000G: a user-friendly genetic variant simulator in R for unrelated individuals and family-based designs","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Linkage disequilibrium; Population; Context (archaeology); Pedigree chart; Computer science; Genetics; Biology; Haplotype; Allele","score_opus":0.018971536646536783,"score_gpt":0.2630115897239511,"score_spread":0.24404005307741433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914488418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7560434,0.00019885981,0.24263719,0.000037751175,0.00009780715,0.00072913896,0.00007305884,0.0000122780575,0.00017051176],"genre_scores_gemma":[0.7146267,0.00003944428,0.28431228,0.0005691352,0.000032706565,0.000051477688,0.00019453972,0.000021187374,0.00015247428],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868065,0.00007459887,0.00055124064,0.00022482665,0.00009740151,0.00037125958],"domain_scores_gemma":[0.9991241,0.00018009749,0.00020908336,0.00032316483,0.00007545305,0.00008807799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050763984,0.00018929389,0.00027583528,0.00010121262,0.00005740906,0.000028178352,0.00015815276,0.00034132093,0.000013754348],"category_scores_gemma":[0.00030565786,0.00017633496,0.000079464684,0.00012630232,0.0000464776,0.000006710309,0.000074509204,0.00008375905,0.00002395733],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018651054,0.0002021498,0.79306805,0.00046673688,0.00017098915,0.0000013937814,0.0003819446,0.18640439,0.012144446,0.00059222523,0.0040740264,0.0023071517],"study_design_scores_gemma":[0.0042096074,0.0009448563,0.24167109,0.00004341017,0.00006028402,0.000008338874,0.0004351139,0.7347952,0.0010610647,0.00020582568,0.016052535,0.0005126327],"about_ca_topic_score_codex":0.000013326867,"about_ca_topic_score_gemma":0.000023974744,"teacher_disagreement_score":0.55139697,"about_ca_system_score_codex":0.000023194789,"about_ca_system_score_gemma":0.00019937422,"threshold_uncertainty_score":0.7190731},"labels":[],"label_agreement":null},{"id":"W2931795699","doi":"10.1186/s12859-019-2649-0","title":"Protein complex detection based on flower pollination mechanism in multi-relation reconstructed dynamic protein networks","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Pollination; Relation (database); Computer science; Field (mathematics); Algorithm; Biological system; Pollen; Data mining; Biology; Botany; Mathematics","score_opus":0.01130909627175362,"score_gpt":0.222545292909813,"score_spread":0.2112361966380594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2931795699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26555243,0.000013390906,0.731569,0.000026174119,0.00021702955,0.0018092296,0.000017433318,0.000035329682,0.0007599812],"genre_scores_gemma":[0.9039404,0.000004135878,0.09490359,0.00017645016,0.000039714036,0.000080115264,0.0005033988,0.00002833151,0.0003239111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848586,0.00006359101,0.00067941146,0.00022309904,0.00019473932,0.00035327327],"domain_scores_gemma":[0.9990357,0.000014188917,0.0003398341,0.00044645285,0.00008958057,0.00007423997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041468872,0.0002652655,0.00021542983,0.00019095585,0.00008726043,0.00006231729,0.00018452668,0.0004450253,0.00003987252],"category_scores_gemma":[0.000044521414,0.00025854874,0.000101253296,0.00024021439,0.000038139853,0.00002831503,0.000059797305,0.00026570374,0.000076611046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014115837,0.00054364844,0.0020769744,0.0009558661,0.00010810452,0.0000019682136,0.00042154823,0.7205027,0.20295614,0.003241114,0.0001206551,0.06765973],"study_design_scores_gemma":[0.0019511273,0.0002982317,0.0022757337,0.00010597812,0.000006809078,0.000003802451,0.00009316851,0.9899288,0.0045694555,0.00014943496,0.00028931,0.00032816906],"about_ca_topic_score_codex":0.000009167928,"about_ca_topic_score_gemma":0.00030533303,"teacher_disagreement_score":0.6383879,"about_ca_system_score_codex":0.00010186231,"about_ca_system_score_gemma":0.00009132003,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W2942866405","doi":"10.1186/s12859-019-2659-y","title":"IMMAN: an R/Bioconductor package for Interolog protein network reconstruction, mapping and mining analysis","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Directorate for Biological Sciences; Institute for Research in Fundamental Sciences","keywords":"Benchmark (surveying); Bioconductor; Computer science; Network analysis; Protein–protein interaction; Biological network; Data mining; Computational biology; Biology; Machine learning; Theoretical computer science; Artificial intelligence; Genetics; Gene; Geography; Cartography","score_opus":0.014502702304429302,"score_gpt":0.22769188452797498,"score_spread":0.2131891822235457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942866405","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7701499,0.00015918312,0.22808915,0.000024582778,0.00024277729,0.0007792165,0.00004098052,0.000023642346,0.0004905674],"genre_scores_gemma":[0.54714394,0.000040783914,0.45042786,0.00045144535,0.00045378873,0.00008104513,0.0007371921,0.00003368438,0.0006302658],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867475,0.000028090453,0.0005868095,0.00023379202,0.00008617062,0.00039036025],"domain_scores_gemma":[0.99894387,0.000021700882,0.0003191679,0.0004957633,0.00009564281,0.00012386996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048001288,0.00022430714,0.0003128129,0.000111780995,0.000131281,0.00011055328,0.00020349551,0.0002597072,0.000019905343],"category_scores_gemma":[0.000031926298,0.00020634415,0.0001567722,0.00021104247,0.00008029405,0.00003714292,0.00013471051,0.00009543638,0.000010713705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024316364,0.0004091649,0.5270987,0.0055443696,0.010625444,0.0000026713171,0.012048582,0.048473533,0.119999565,0.00807386,0.01654682,0.24874564],"study_design_scores_gemma":[0.003060337,0.0014998612,0.0062562837,0.00014255349,0.0004765564,0.00008345447,0.005577872,0.95316803,0.00461978,0.0010526474,0.022641879,0.001420735],"about_ca_topic_score_codex":0.00000246237,"about_ca_topic_score_gemma":0.000047514568,"teacher_disagreement_score":0.9046945,"about_ca_system_score_codex":0.000013936939,"about_ca_system_score_gemma":0.00005542689,"threshold_uncertainty_score":0.841447},"labels":[],"label_agreement":null},{"id":"W2947100013","doi":"10.1186/s12859-019-2801-x","title":"Automated assessment of biological database assertions using the scientific literature","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Bhabha Atomic Research Centre; Australian Research Council","keywords":"Computer science; Consistency (knowledge bases); Information retrieval; Assertion; Relevance (law); Relation (database); Biological database; Classifier (UML); Set (abstract data type); Data mining; Data science; Database; Bioinformatics; Artificial intelligence; Biology; Programming language","score_opus":0.045762540862951104,"score_gpt":0.34215141589784726,"score_spread":0.29638887503489614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947100013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95853174,0.00036112542,0.03956912,0.00005168478,0.00042213014,0.00024072359,0.00012749931,0.00006182243,0.000634165],"genre_scores_gemma":[0.7415978,0.00003415979,0.25737888,0.00011727679,0.0000470255,0.000005998515,0.0006057681,0.0000071034565,0.00020602951],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999163,0.000053132368,0.00029280226,0.00013771982,0.00016984102,0.00018352107],"domain_scores_gemma":[0.99917245,0.000039725834,0.00014438856,0.0004960472,0.00010320063,0.000044187374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044269834,0.000107235246,0.00012924304,0.000048173217,0.00011555581,0.000069479654,0.00028487493,0.00016937428,0.00001849278],"category_scores_gemma":[0.0001454799,0.00006089222,0.00007749702,0.0002525433,0.00026853068,0.00000752863,0.0001865434,0.00010902108,0.000009212535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097839016,0.0004672158,0.128103,0.00092887727,0.00023326637,0.0000028302375,0.0010666783,0.002726504,0.84124887,0.0025114678,0.016927486,0.0056859558],"study_design_scores_gemma":[0.00068622094,0.00036139804,0.021456437,0.00017937193,0.000033314245,0.000044816905,0.0013134987,0.9382694,0.014068293,0.00004206915,0.023250492,0.00029470795],"about_ca_topic_score_codex":0.0000022322283,"about_ca_topic_score_gemma":0.0000034352454,"teacher_disagreement_score":0.9355429,"about_ca_system_score_codex":0.000009222084,"about_ca_system_score_gemma":0.00016098664,"threshold_uncertainty_score":0.24831127},"labels":[],"label_agreement":null},{"id":"W2947681169","doi":"10.1186/s12859-019-2902-6","title":"Pairwise visual comparison of small RNA secondary structures with base pair probabilities","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; National Research Council Canada","funders":"","keywords":"Pairwise comparison; Protein secondary structure; Nucleic acid secondary structure; Computer science; Base pair; RNA; Visualization; Base (topology); Graph; Web server; Nucleic acid structure; Algorithm; Computational biology; Theoretical computer science; Bioinformatics; Data mining; Biology; Mathematics; Artificial intelligence; DNA; Genetics; The Internet","score_opus":0.015766328157067185,"score_gpt":0.23911802043266156,"score_spread":0.22335169227559437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947681169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657306,0.00022230028,0.03121437,0.000018998659,0.00008800513,0.00056856876,0.000037651753,0.000022159149,0.0020973282],"genre_scores_gemma":[0.8752527,0.0000076083156,0.12401368,0.00009256892,0.00004924202,0.000020562167,0.00009385925,0.000021244787,0.00044850758],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999013,0.000047922967,0.0004046182,0.00014997646,0.0001698427,0.00021463344],"domain_scores_gemma":[0.9991529,0.000032597785,0.00024471842,0.0003892205,0.000111836,0.000068712594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018623102,0.00018978154,0.00026409488,0.00004679769,0.00004175297,0.00002463533,0.00019569219,0.00015790031,0.00009849564],"category_scores_gemma":[0.000052233518,0.00014145391,0.00008799366,0.000059387145,0.00008440813,0.000010496997,0.00008359325,0.00008437307,0.000016360142],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003286982,0.0008531373,0.13106394,0.012419162,0.0006947697,0.000003228102,0.006010474,0.010204043,0.6736496,0.006491805,0.004254759,0.15106809],"study_design_scores_gemma":[0.0009146954,0.0017538603,0.0012311649,0.00007410301,0.000032206965,0.000010410892,0.0027978707,0.011990706,0.9772354,0.00049305434,0.0030943002,0.0003722611],"about_ca_topic_score_codex":0.000008636574,"about_ca_topic_score_gemma":0.00002692232,"teacher_disagreement_score":0.30358577,"about_ca_system_score_codex":0.000010748864,"about_ca_system_score_gemma":0.0002136416,"threshold_uncertainty_score":0.5768323},"labels":[],"label_agreement":null},{"id":"W2949158578","doi":"10.1186/s12859-019-2647-2","title":"SplicedFamAlign: CDS-to-gene spliced alignment and identification of transcript orthology groups","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Exon; RNA splicing; Intron; Biology; Genetics; Gene; Computational biology; Sequence alignment; Alternative splicing; Genome; DNA microarray; Gene prediction; Sequence analysis; Alignment-free sequence analysis; Peptide sequence; Gene expression; RNA","score_opus":0.01001318829358899,"score_gpt":0.22447683452546693,"score_spread":0.21446364623187794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949158578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98573923,0.00032286532,0.012556758,0.00005137342,0.00019604061,0.00041285288,0.00005858444,0.0000035919668,0.00065870886],"genre_scores_gemma":[0.9806716,0.0002240881,0.018491162,0.00022856516,0.00004100786,0.000019902569,0.000049661194,0.000013093777,0.00026095271],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905694,0.000018337003,0.00045367947,0.00018123741,0.00010485425,0.000184937],"domain_scores_gemma":[0.99932927,0.000010734518,0.00015665166,0.00036775135,0.000068017056,0.0000675781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020817202,0.00014024402,0.00019064848,0.000054486052,0.000039251365,0.000014668422,0.00014441533,0.0001038624,0.0000062059034],"category_scores_gemma":[0.000016633843,0.0001326295,0.00006187132,0.000072318755,0.000051243565,0.000001995871,0.000105241576,0.00003134432,0.000029296381],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045813114,0.000026330372,0.009976255,0.00013160928,0.000048510894,9.6695516e-8,0.0006620171,0.00025469653,0.98742366,0.00045814842,0.00013743818,0.0008354124],"study_design_scores_gemma":[0.0014240979,0.0008562656,0.11419566,0.000021886653,0.00008437589,0.00003301162,0.0018057503,0.0025929804,0.8686486,0.00017636582,0.009667172,0.0004938287],"about_ca_topic_score_codex":0.000006655726,"about_ca_topic_score_gemma":0.000015973723,"teacher_disagreement_score":0.11877507,"about_ca_system_score_codex":0.000006945142,"about_ca_system_score_gemma":0.000028991153,"threshold_uncertainty_score":0.5408474},"labels":[],"label_agreement":null},{"id":"W2949244194","doi":"10.1186/s12859-017-1553-8","title":"MINT: a multivariate integrative method to identify reproducible molecular signatures across independent experiments and platforms","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Diamantina Institute, University of Queensland; National Health and Medical Research Council; Medical Research Council; Australian Research Council; University of Queensland; Australian Cancer Research Foundation","keywords":"Multivariate statistics; Overfitting; Computer science; Data mining; Computational biology; DNA microarray; Artificial intelligence; Machine learning; Biology; Gene; Genetics","score_opus":0.04099443180788442,"score_gpt":0.41060038708721674,"score_spread":0.3696059552793323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949244194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42721367,0.00028280896,0.5702626,0.00010601912,0.00026109608,0.0004951203,0.000034128192,0.000018286095,0.0013262905],"genre_scores_gemma":[0.8250703,0.000031197094,0.17360164,0.00034114212,0.000067347086,0.00008683111,0.000052783776,0.000018597955,0.0007301535],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988134,0.000024751296,0.00032461958,0.00037585973,0.00020882316,0.0002525266],"domain_scores_gemma":[0.9984134,0.000008642294,0.00028179382,0.0010290507,0.00011734276,0.00014977218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047446263,0.0002001933,0.00016910046,0.00005040545,0.00032739463,0.00025776442,0.00040627253,0.00019161396,0.0000073849183],"category_scores_gemma":[0.00032740223,0.00015550811,0.00006865991,0.00004709475,0.00006557583,0.000032606236,0.0004997745,0.00011683738,0.000016859443],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016451946,0.000050233026,0.0012408566,0.000057307036,0.000059743896,0.0000014407868,0.0034591544,0.00021781448,0.97865945,0.00038182325,0.0015403723,0.014167263],"study_design_scores_gemma":[0.00087881676,0.0001473998,0.018066438,0.000058921338,0.000013817943,0.000008885726,0.0027834368,0.0034684746,0.96661526,0.00031082373,0.00733797,0.00030978507],"about_ca_topic_score_codex":0.000039005576,"about_ca_topic_score_gemma":0.000026820584,"teacher_disagreement_score":0.39785665,"about_ca_system_score_codex":0.00002125282,"about_ca_system_score_gemma":0.00006333346,"threshold_uncertainty_score":0.6341437},"labels":[],"label_agreement":null},{"id":"W2949294873","doi":"10.1186/s12859-018-2425-6","title":"Tigmint: correcting assembly errors using linked reads from large molecules","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome British Columbia","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Sequence assembly; Genome; Computational biology; Hybrid genome assembly; Reference genome; Contig; Genomics; Whole genome sequencing; Sequence (biology); Biology; DNA sequencing; Computer science; Genetics; DNA; Gene","score_opus":0.029060927699152965,"score_gpt":0.27393547331175083,"score_spread":0.24487454561259786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949294873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9040834,0.00034770466,0.091952376,0.000015877627,0.00055420975,0.00015782732,0.00008886412,0.00001238412,0.002787376],"genre_scores_gemma":[0.8388831,0.000061243925,0.15981983,0.00034850862,0.0006175492,0.000005747649,0.00010447712,0.00002926498,0.0001303107],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988829,0.000029285866,0.00038279468,0.00020798574,0.00013280087,0.00036424934],"domain_scores_gemma":[0.99914175,0.000024566492,0.00019666366,0.00040320496,0.00014857172,0.00008524516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019253558,0.00021192602,0.00019279197,0.000045727884,0.00024385728,0.000048398222,0.00022387212,0.00018051207,0.00001561451],"category_scores_gemma":[0.00013973183,0.00019970261,0.000101092985,0.00009636422,0.00009987986,0.00000272625,0.0002774873,0.00008340206,0.00005282658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002811535,0.00025157817,0.0793599,0.00020223674,0.00066792517,0.00000487455,0.0066187507,0.0012654089,0.8871144,0.00033601333,0.006961056,0.016936716],"study_design_scores_gemma":[0.0029150136,0.00109479,0.031791866,0.0001665989,0.0002802606,0.0000756465,0.007650465,0.54130197,0.34629723,0.00055139395,0.06595384,0.0019209113],"about_ca_topic_score_codex":0.000060919552,"about_ca_topic_score_gemma":0.00017465049,"teacher_disagreement_score":0.54081714,"about_ca_system_score_codex":0.00001793522,"about_ca_system_score_gemma":0.00009290656,"threshold_uncertainty_score":0.8143636},"labels":[],"label_agreement":null},{"id":"W2949358764","doi":"10.1186/s12859-019-2905-3","title":"Testing adequacy for DNA substitution models","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Model selection; Goodness of fit; Inference; Computer science; Type I and type II errors; Simple (philosophy); Tree (set theory); Data mining; Range (aeronautics); Statistical hypothesis testing; Substitution (logic); Selection (genetic algorithm); Algorithm; Statistics; Mathematics; Machine learning; Artificial intelligence; Engineering","score_opus":0.03981830111788477,"score_gpt":0.2454632519774044,"score_spread":0.20564495085951962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949358764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8548052,0.00033382993,0.13702962,0.000016063323,0.00027289081,0.0005576783,0.000051221075,0.000009358757,0.006924194],"genre_scores_gemma":[0.8250896,0.000028943949,0.17421919,0.00014795952,0.00012451377,0.000029979874,0.00007284613,0.000013568126,0.00027340182],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993726,0.0000058715623,0.00022927446,0.00012073674,0.000068164096,0.00020334846],"domain_scores_gemma":[0.99949425,0.000028606893,0.00009404236,0.00023926582,0.00010429452,0.000039537797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012736909,0.00011622637,0.000111971305,0.000024820527,0.000075795746,0.000023725133,0.00012402472,0.00008590795,0.0000023257746],"category_scores_gemma":[0.00007262775,0.00010607301,0.00006956866,0.000051445597,0.000028332202,0.0000026445218,0.00007570558,0.000028460578,0.000026975347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037924372,0.00019779404,0.059814967,0.0018309223,0.000348191,4.1602775e-7,0.0012618218,0.13940777,0.7421791,0.026062787,0.004837764,0.023679225],"study_design_scores_gemma":[0.0023663074,0.00082841946,0.008898512,0.000052809435,0.00006505188,0.000019601357,0.0006026938,0.8903406,0.045753345,0.0033854775,0.04690177,0.0007853689],"about_ca_topic_score_codex":0.0000025397442,"about_ca_topic_score_gemma":0.000004925266,"teacher_disagreement_score":0.7509329,"about_ca_system_score_codex":0.000009096043,"about_ca_system_score_gemma":0.00007068643,"threshold_uncertainty_score":0.43255317},"labels":[],"label_agreement":null},{"id":"W2949514040","doi":"10.1186/s12859-018-2284-1","title":"De novo profile generation based on sequence context specificity with the long short-term memory network","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Medical Science, University of Tokyo; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Context (archaeology); Term (time); Sequence (biology); DNA microarray; Long short term memory; Computational biology; Computer science; Biology; Genetics; Artificial intelligence; Gene; Artificial neural network; Recurrent neural network; Gene expression; Paleontology","score_opus":0.025768379538747735,"score_gpt":0.2655191005374179,"score_spread":0.23975072099867017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949514040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38664985,0.000034070086,0.5940933,0.00019277626,0.00024186974,0.00072448584,0.00003287358,0.00006317654,0.017967578],"genre_scores_gemma":[0.8848834,0.000007996625,0.10996048,0.002898602,0.0012338668,0.000040531122,0.00038437074,0.00003305066,0.0005576843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986901,0.000077450684,0.00036593468,0.000165204,0.0002916577,0.00040961694],"domain_scores_gemma":[0.9987957,0.000042519994,0.00020072708,0.0006967269,0.00016977367,0.00009457053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055951346,0.0002465377,0.00015381478,0.000036136404,0.00034190645,0.00014103812,0.00037094418,0.00017061095,0.00007078165],"category_scores_gemma":[0.000093907474,0.0001623491,0.00006765841,0.00015066766,0.00030286668,0.000018404156,0.00008589011,0.00022019983,0.00008294318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036188709,0.00060255907,0.21060085,0.0016369362,0.00049700215,0.000030053061,0.0070971544,0.4590696,0.031462044,0.0031029237,0.17850637,0.10377564],"study_design_scores_gemma":[0.00049249263,0.0010365585,0.003420425,0.000057627596,0.000029361747,0.00005844142,0.00022106312,0.9669034,0.021313831,0.0000034507048,0.0061144424,0.00034893342],"about_ca_topic_score_codex":0.000004831892,"about_ca_topic_score_gemma":0.00021241081,"teacher_disagreement_score":0.5078338,"about_ca_system_score_codex":0.000047973437,"about_ca_system_score_gemma":0.0002369245,"threshold_uncertainty_score":0.6620404},"labels":[],"label_agreement":null},{"id":"W2949538565","doi":"10.1186/s12859-019-2610-2","title":"BPG: Seamless, automated and interactive visualization of scientific data","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Government of Ontario; Government of Canada; Canadian Institutes of Health Research; National Science Foundation; Ontario Institute for Cancer Research; Center for Translational Molecular Medicine; University of Pennsylvania; Ontario Genomics Institute; Movember Foundation; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Ontario Genomics; Genome Canada; Prostate Cancer Canada","keywords":"Visualization; Computer science; Data science; Data visualization; World Wide Web; Information retrieval; Data mining","score_opus":0.16096035470620532,"score_gpt":0.41811129736815916,"score_spread":0.2571509426619538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949538565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49839014,0.000061008985,0.48165056,0.000088484485,0.0039426708,0.0007497753,0.0005106696,0.00033251045,0.014274184],"genre_scores_gemma":[0.92673576,0.0000033926224,0.06903165,0.00007377782,0.000022019029,0.0000013400197,0.0007017844,0.000008487997,0.00342179],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755967,0.00006642888,0.0007465061,0.0003933219,0.0010739727,0.00016013061],"domain_scores_gemma":[0.9965407,0.0005490034,0.0004728567,0.0020767448,0.00029974183,0.000060917708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049036057,0.000093403585,0.0001915178,0.00041311738,0.00011955441,0.0009481068,0.0013148788,0.000034687248,0.00012582037],"category_scores_gemma":[0.0018069994,0.00006852594,0.000025298727,0.0011476587,0.00015259672,0.0014696073,0.0017881044,0.000044422908,0.00058796024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011447948,0.00037817942,0.117053285,0.0007437182,0.00009803671,0.0000015605975,0.011823754,0.005906436,0.0004465845,0.021920253,0.57161295,0.26990077],"study_design_scores_gemma":[0.00021681061,0.00002117594,0.008521204,0.000039791197,0.000007998694,0.0000020751295,0.0022540442,0.96847445,0.00009686071,0.0003945836,0.019886963,0.00008402595],"about_ca_topic_score_codex":0.000010669645,"about_ca_topic_score_gemma":0.000017421298,"teacher_disagreement_score":0.96256804,"about_ca_system_score_codex":0.000014570861,"about_ca_system_score_gemma":0.00008587558,"threshold_uncertainty_score":0.9142616},"labels":[],"label_agreement":null},{"id":"W2951265437","doi":"10.1186/s12859-018-2243-x","title":"ARKS: chromosome-scale scaffolding of human genome drafts with linked read kmers","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":142,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; Genome Alberta; Genome British Columbia; Genome Canada","keywords":"Genome; Computer science; Human genome; Sequence assembly; Computational biology; Genomics; Reference genome; Whole genome sequencing; Biology; Genetics; Gene; Transcriptome","score_opus":0.014628542740856858,"score_gpt":0.24061249135199989,"score_spread":0.22598394861114302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951265437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98720795,0.0002619341,0.003445855,0.000013938335,0.000088183486,0.00021748887,0.00003797326,0.000007492513,0.00871921],"genre_scores_gemma":[0.9541195,0.00010172444,0.04502319,0.000095847085,0.00025640609,0.0000109172615,0.00006517927,0.000023529932,0.0003037183],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990148,0.000014705263,0.00038054062,0.00016926898,0.00014337864,0.00027732766],"domain_scores_gemma":[0.99908817,0.000008894559,0.00022579257,0.00043147604,0.00016782904,0.0000778341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014844297,0.00018796237,0.00022404736,0.000058128826,0.00015612278,0.000021104337,0.0002332489,0.000121058816,0.00002188076],"category_scores_gemma":[0.000015543588,0.0001556327,0.000076603465,0.00010045952,0.0003214257,0.0000026271362,0.00015757879,0.00004761337,0.000016040542],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109190296,0.00008073469,0.01032258,0.00025329032,0.00021509189,6.3470344e-7,0.001978178,0.00018606235,0.9848957,0.00014744983,0.00040350904,0.0014075439],"study_design_scores_gemma":[0.0068730894,0.010889635,0.17471173,0.0003627096,0.0004515543,0.000118740885,0.0068752514,0.0077241524,0.7166795,0.00046946344,0.072083525,0.0027606366],"about_ca_topic_score_codex":0.000011945219,"about_ca_topic_score_gemma":0.00009263498,"teacher_disagreement_score":0.26821622,"about_ca_system_score_codex":0.000012643011,"about_ca_system_score_gemma":0.000071389564,"threshold_uncertainty_score":0.6346517},"labels":[],"label_agreement":null},{"id":"W2951375448","doi":"10.1186/s12859-019-2897-z","title":"Identification of critical connectors in the directed reaction-centric graphs of microbial metabolic networks","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; National Research Foundation","keywords":"Identification (biology); Computational biology; DNA microarray; Computer science; Biology; Data science; Genetics; Gene; Ecology; Gene expression","score_opus":0.006113777070007351,"score_gpt":0.22234721154885362,"score_spread":0.21623343447884627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951375448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917971,0.0005301249,0.0067895954,0.000021637754,0.00051797245,0.00023950722,0.000016621336,0.0000097097545,0.00007776627],"genre_scores_gemma":[0.9979491,0.00018474813,0.0016684107,0.00002042093,0.00007033774,0.0000041812273,0.000068437366,0.0000063902085,0.000027925462],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917716,0.000050237188,0.0004595264,0.00009639903,0.00009032596,0.0001263817],"domain_scores_gemma":[0.99941266,0.000019042543,0.0001594397,0.00029512472,0.000097224176,0.000016528447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004086019,0.000088136476,0.00015199732,0.00009405989,0.000016456359,0.000008827366,0.00014403129,0.00010554399,0.0000040757172],"category_scores_gemma":[0.00020955937,0.000067316185,0.00007420472,0.00032894913,0.00005955702,0.000009026069,0.000022018365,0.00007554324,0.000003821954],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036792833,0.00009343462,0.001832761,0.0001880978,0.00001782674,3.7115118e-8,0.00017445954,0.0016927944,0.9943497,0.0008812767,0.00022213772,0.00051064737],"study_design_scores_gemma":[0.0011666819,0.00017465813,0.0597308,0.00006275356,0.00010337557,0.00004007576,0.0007540694,0.040307514,0.89077634,0.000053310323,0.006458269,0.0003721517],"about_ca_topic_score_codex":0.000017126411,"about_ca_topic_score_gemma":0.000008397914,"teacher_disagreement_score":0.10357339,"about_ca_system_score_codex":0.000003646081,"about_ca_system_score_gemma":0.000025792258,"threshold_uncertainty_score":0.27450743},"labels":[],"label_agreement":null},{"id":"W2951901532","doi":"10.1186/s12859-018-2187-1","title":"Genome-wide prediction of cis-regulatory regions using supervised deep learning methods","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":129,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; BC Children's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Michael Smith Health Research BC; Genome British Columbia; National Institute of General Medical Sciences; Western Canada Research Grid; Compute Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Genome; ENCODE; Human genome; Computational biology; Genomics; Biology; Genome project; Enhancer; Regulatory sequence; DNA sequencing; Functional genomics; Gene Annotation; Noncoding DNA; DNA microarray; Deep learning; Gene; Genetics; Regulation of gene expression; Computer science; Artificial intelligence; Transcription factor; Gene expression","score_opus":0.021935659757517,"score_gpt":0.2688406461527417,"score_spread":0.24690498639522473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951901532","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.503708,0.00010940686,0.495127,0.0000035615487,0.00011012129,0.00010458261,0.000012061533,0.000013839708,0.0008114296],"genre_scores_gemma":[0.43386614,0.000074342905,0.56552005,0.000053882508,0.00016304049,0.0000039087754,0.00017551337,0.00002568727,0.00011741808],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989488,0.00006824246,0.00048640792,0.00014280871,0.00012317346,0.00023055995],"domain_scores_gemma":[0.9990466,0.00002399071,0.00025769765,0.00041166568,0.00018178094,0.00007824363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004069051,0.00015465888,0.00017779607,0.00007950501,0.00015624567,0.000022872693,0.00019998108,0.0001916393,0.000021392822],"category_scores_gemma":[0.00012134332,0.00015503021,0.00011456065,0.000109857625,0.00017277505,0.00001058452,0.00015294389,0.00008947474,0.00000879396],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120066456,0.00011472751,0.031357754,0.0005568459,0.00024472596,4.879359e-7,0.0025963366,0.019389829,0.93782216,0.00040628665,0.0001818604,0.007208935],"study_design_scores_gemma":[0.0005919801,0.00043101053,0.018120946,0.000026531132,0.000070020506,0.000025100713,0.0012203922,0.94332933,0.03067315,0.00015468361,0.0050976137,0.00025923867],"about_ca_topic_score_codex":0.0000049790788,"about_ca_topic_score_gemma":0.000013822297,"teacher_disagreement_score":0.9239395,"about_ca_system_score_codex":0.000030153293,"about_ca_system_score_gemma":0.00010644457,"threshold_uncertainty_score":0.6321949},"labels":[],"label_agreement":null},{"id":"W2952523648","doi":"10.1186/s12859-017-1865-8","title":"A rapid and accurate approach for prediction of interactomes from co-elution data (PrInCE)","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Canadian Institutes of Health Research; Genome British Columbia; Genome Canada","keywords":"Interactome; Computational biology; Elution; Executable; Computer science; Protein–protein interaction; Stable isotope labeling by amino acids in cell culture; Proteomics; Biology; Data mining; Chemistry; Programming language; Chromatography; Biochemistry","score_opus":0.05843736934127653,"score_gpt":0.2942363894918856,"score_spread":0.23579902015060905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952523648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060515292,0.0004071934,0.93031275,0.000032063548,0.00025242352,0.0006373792,0.0044251615,0.000014419009,0.0034033358],"genre_scores_gemma":[0.6291238,0.00085007533,0.3575394,0.000103874976,0.00035872328,0.000026016629,0.01186502,0.000020388221,0.00011273046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991637,0.000010188927,0.0004252744,0.00015466145,0.00008667567,0.00015952853],"domain_scores_gemma":[0.99829155,0.000022931066,0.0004892095,0.0010748903,0.0000624773,0.00005893396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003142204,0.00013312265,0.00017294163,0.000029397268,0.00018053157,0.00011064035,0.0005220067,0.00016391423,0.000004216144],"category_scores_gemma":[0.0001227187,0.0001160646,0.000047948462,0.000014276042,0.00013343197,0.00005730036,0.0004027627,0.000064399945,0.000001729001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031060816,0.0007968374,0.06722904,0.0059326706,0.0021061029,7.457025e-7,0.0066447253,0.0021754126,0.03843791,0.0023138835,0.11905335,0.7522032],"study_design_scores_gemma":[0.001480054,0.00020081595,0.012077265,0.000042143965,0.000063109015,0.0000062667377,0.000560016,0.9613473,0.003315768,0.0001566686,0.020549743,0.00020086205],"about_ca_topic_score_codex":0.000011169532,"about_ca_topic_score_gemma":0.0000108527975,"teacher_disagreement_score":0.9591719,"about_ca_system_score_codex":0.000006489426,"about_ca_system_score_gemma":0.000056347813,"threshold_uncertainty_score":0.4732977},"labels":[],"label_agreement":null},{"id":"W2952683761","doi":"10.1186/s12859-018-2289-9","title":"PRS-on-Spark (PRSoS): a novel, efficient and flexible approach for generating polygenic risk scores","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Canadian Institute for Advanced Research; University of British Columbia; McGill University; Douglas Mental Health University Institute","funders":"Health Canada; Ludmer Centre for Neuroinformatics and Mental Health; Fondation Brain Canada; McGill University; Canadian Institute for Advanced Research","keywords":"Single-nucleotide polymorphism; SNP; Major depressive disorder; Software; Biology; Computer science; Computational biology; Statistics; Genetics; Mathematics; Gene; Genotype","score_opus":0.026161680960704148,"score_gpt":0.2715539279775312,"score_spread":0.24539224701682705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952683761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4106289,0.0001569868,0.5877807,0.000019856216,0.0001018636,0.0003343793,0.00008092858,0.000015283053,0.00088104594],"genre_scores_gemma":[0.3740638,0.00005641321,0.62453026,0.0004077427,0.00044121518,0.00006917753,0.00016565579,0.000019068832,0.00024669213],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889576,0.00003596844,0.0003911236,0.00023111756,0.000094113784,0.00035192058],"domain_scores_gemma":[0.99917173,0.00006220336,0.00025523923,0.00030815942,0.00011360524,0.000089032976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054962153,0.00017618842,0.00019173179,0.000055736233,0.00031165243,0.000039178194,0.00013887661,0.00019630515,0.0000031034692],"category_scores_gemma":[0.00047358932,0.00014844116,0.00008553178,0.00008311857,0.00013386249,0.0000032070457,0.000106040934,0.00007180241,0.000009604653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018934375,0.0022379025,0.38563645,0.0018324993,0.0018028831,5.188594e-7,0.009249225,0.28478256,0.1016498,0.0076846634,0.11493703,0.088293046],"study_design_scores_gemma":[0.0010996545,0.00083274196,0.009543168,0.000011254362,0.000046629393,0.00001121917,0.00045419208,0.9800607,0.004208371,0.000040142688,0.0034014985,0.00029041086],"about_ca_topic_score_codex":0.000012415447,"about_ca_topic_score_gemma":0.000018183964,"teacher_disagreement_score":0.69527817,"about_ca_system_score_codex":0.0000150308215,"about_ca_system_score_gemma":0.00008155701,"threshold_uncertainty_score":0.6053255},"labels":[],"label_agreement":null},{"id":"W2962703814","doi":"10.1186/s12859-018-2347-3","title":"DM-PhyClus: a Bayesian phylogenetic algorithm for infectious disease transmission cluster inference","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Jewish General Hospital; HEC Montréal; Centre Hospitalier de l’Université de Montréal; McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Centre de Recherches Mathématiques; Canadian Institutes of Health Research; Ministère de la Santé; Ministère de la Santé et des Services sociaux; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke; McGill University; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Cluster analysis; Phylogenetic tree; Bayesian probability; Inference; Bayesian inference; Computer science; Cluster (spacecraft); Data mining; Algorithm; A priori and a posteriori; Set (abstract data type); Artificial intelligence; Machine learning; Biology; Statistics; Mathematics; Genetics","score_opus":0.011749222327809337,"score_gpt":0.2558560780779773,"score_spread":0.24410685575016794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962703814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03690815,0.0005552004,0.9602664,0.0000556167,0.00027491053,0.00066584174,0.000120107165,0.000014896269,0.0011388608],"genre_scores_gemma":[0.61693954,0.00040629483,0.37986347,0.0010297021,0.00088284805,0.00015457513,0.00016534112,0.000053005933,0.0005052059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884045,0.0000265155,0.00037895775,0.00025037277,0.00012916976,0.00037450547],"domain_scores_gemma":[0.9990395,0.000035904894,0.00012511844,0.0003993312,0.0001914157,0.00020878084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015054685,0.00025343234,0.00018950939,0.00006134893,0.00024840338,0.000051161853,0.00022194987,0.00013992283,0.000013011418],"category_scores_gemma":[0.00007556492,0.00022335588,0.0001575365,0.00009405476,0.0001715889,0.0000029707617,0.0001296256,0.000053628355,0.000021735445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006905343,0.00050871586,0.021378728,0.0010908875,0.00049160904,0.000001793489,0.00253626,0.0021994861,0.036038354,0.00030357038,0.011164429,0.9235956],"study_design_scores_gemma":[0.00344041,0.0019661505,0.00922738,0.000079608675,0.00019035394,0.000016999375,0.00024274757,0.7838386,0.014669726,0.0018400076,0.18340254,0.0010854538],"about_ca_topic_score_codex":0.000005393725,"about_ca_topic_score_gemma":0.000028437438,"teacher_disagreement_score":0.9225102,"about_ca_system_score_codex":0.000014861338,"about_ca_system_score_gemma":0.00016218936,"threshold_uncertainty_score":0.9108189},"labels":[],"label_agreement":null},{"id":"W2982540799","doi":"10.1186/s12859-019-3100-2","title":"RACS: rapid analysis of ChIP-Seq data for contig based genomes","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Canada Research Chairs; Toronto Metropolitan University","funders":"University of Toronto","keywords":"Genome; Contig; Pipeline (software); DNA microarray; Intergenic region; Gene prediction; Gene; Genomics; Model organism","score_opus":0.018268240161205464,"score_gpt":0.2498390884317334,"score_spread":0.23157084827052796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982540799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7312403,0.0006322165,0.26230508,0.00004298736,0.00023761769,0.0008285315,0.0029857203,0.000016264155,0.0017113128],"genre_scores_gemma":[0.6442903,0.0002036696,0.3380377,0.0004124181,0.0000825404,0.00002044677,0.016442683,0.000037023023,0.00047320497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989644,0.00001506027,0.00048283866,0.00019578007,0.000117189025,0.00022468668],"domain_scores_gemma":[0.99816674,0.00004430123,0.0003118577,0.0013124956,0.00010556547,0.00005904646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034415262,0.00014862767,0.00031875644,0.00012701355,0.000035232417,0.00002871484,0.0005832216,0.00013327188,0.000049184506],"category_scores_gemma":[0.00007262197,0.0001361056,0.0001982644,0.0001901685,0.00004303073,0.000008664785,0.00020597433,0.00003816537,0.00001102246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017528604,0.0013721768,0.28738722,0.00884902,0.016761227,0.0000013071792,0.0015534918,0.3660178,0.23279193,0.0039315317,0.026240902,0.053340532],"study_design_scores_gemma":[0.00081929326,0.00016749931,0.0028662935,0.000008221512,0.00039274158,4.5043254e-7,0.00021235945,0.9782529,0.0026981654,0.000016178996,0.01436708,0.00019882228],"about_ca_topic_score_codex":0.0000039543756,"about_ca_topic_score_gemma":0.000045000077,"teacher_disagreement_score":0.6122351,"about_ca_system_score_codex":0.0000103099965,"about_ca_system_score_gemma":0.00015476064,"threshold_uncertainty_score":0.55502254},"labels":[],"label_agreement":null},{"id":"W2986366856","doi":"10.1186/s12859-019-3174-x","title":"omicplotR: visualizing omic datasets as compositions","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Computer science; Visualization; Graphical user interface; Software; Scripting language; Cluster analysis; Data mining; Hierarchical clustering; Set (abstract data type); Interface (matter); Principal component analysis; Machine learning; Artificial intelligence; Programming language; Operating system","score_opus":0.01666856512170442,"score_gpt":0.25611391975791,"score_spread":0.23944535463620556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986366856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019717256,0.000052482428,0.8212533,0.0013054827,0.0006330478,0.00042946878,0.000074705684,0.0005207314,0.15601353],"genre_scores_gemma":[0.30950195,0.000020813251,0.68395066,0.0030343519,0.0000962422,0.000018277338,0.0005676796,0.000008309591,0.002801709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991034,0.000017945033,0.0002987822,0.00014687983,0.00017164905,0.00026129754],"domain_scores_gemma":[0.99896216,0.000092358205,0.000126263,0.00069523806,0.0000415464,0.00008242544],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001978574,0.00012347694,0.00013842924,0.000055906592,0.00011663958,0.00016021323,0.0007527665,0.00006910384,0.00008870599],"category_scores_gemma":[0.000048647224,0.00011436054,0.00005299615,0.00018962257,0.00002835788,0.0006437978,0.00040892835,0.00011452304,0.002953961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004272366,0.0004594182,0.011787565,0.0024537814,0.0001586292,0.000027763615,0.008205556,0.023391131,0.0076736044,0.7583903,0.17721419,0.010195314],"study_design_scores_gemma":[0.00037199908,0.0000481391,0.00046094577,0.00005422694,0.000005960352,0.000091881324,0.00022752,0.9074303,0.002328886,0.0023375764,0.08638854,0.00025401163],"about_ca_topic_score_codex":0.000007932369,"about_ca_topic_score_gemma":0.0000015629511,"teacher_disagreement_score":0.88403916,"about_ca_system_score_codex":0.0000244179,"about_ca_system_score_gemma":0.00007190007,"threshold_uncertainty_score":0.99782234},"labels":[],"label_agreement":null},{"id":"W2991321419","doi":"10.1186/s12859-019-3076-y","title":"DeepEP: a deep learning framework for identifying essential proteins","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; Fundamental Research Funds for the Central Universities; Central South University; National Natural Science Foundation of China","keywords":"Computational biology; Computer science; DNA microarray; Data science; Bioinformatics; Artificial intelligence; Biology; Genetics; Gene; Gene expression","score_opus":0.01332949612210963,"score_gpt":0.2613690999301562,"score_spread":0.2480396038080466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991321419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036803428,0.00025933175,0.95899206,0.000025648878,0.00051054463,0.0010434521,0.000013424574,0.00004176575,0.0023103433],"genre_scores_gemma":[0.22566652,0.00008576447,0.77130127,0.0003834473,0.0005675877,0.00011544493,0.00042216017,0.00005972423,0.0013980792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985795,0.000016049502,0.0005450436,0.00019948605,0.00018374494,0.00047619414],"domain_scores_gemma":[0.998982,0.000047749072,0.00030931176,0.00044374648,0.00010587311,0.000111284666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036273614,0.00023774906,0.00023025523,0.00006676795,0.00017981506,0.00014958465,0.0003192591,0.00035926403,0.0000622931],"category_scores_gemma":[0.00014069976,0.00022717602,0.00021262138,0.00011252932,0.000049142724,0.00002269225,0.00020002255,0.00023638859,0.00018574778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041739843,0.0011619319,0.04128299,0.022761846,0.0029350978,0.000007388162,0.022345247,0.16202748,0.09902291,0.2424851,0.018543376,0.38325262],"study_design_scores_gemma":[0.002912004,0.0010141393,0.000658436,0.0002717677,0.00011023923,0.000049474722,0.003308535,0.87882936,0.013265233,0.008094067,0.09009608,0.0013906849],"about_ca_topic_score_codex":0.0000024630856,"about_ca_topic_score_gemma":0.000015095855,"teacher_disagreement_score":0.7168019,"about_ca_system_score_codex":0.000020365333,"about_ca_system_score_gemma":0.000083705534,"threshold_uncertainty_score":0.9263969},"labels":[],"label_agreement":null},{"id":"W2995213394","doi":"10.1186/s12859-019-3207-5","title":"SimSpliceEvol: alternative splicing-aware simulation of biological sequence evolution","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Computational biology; Biology; RNA splicing; Alternative splicing; Alignment-free sequence analysis; Intron; Genetics; Gene; Exon; Sequence analysis; Multiple sequence alignment; Sequence (biology); Inference; Sequence alignment; Computer science; RNA; Peptide sequence; Artificial intelligence","score_opus":0.04217693886673031,"score_gpt":0.3160184066930021,"score_spread":0.2738414678262718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995213394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8073889,0.000045430195,0.19132063,0.0000072394205,0.000049593324,0.00027191456,0.000024946643,0.0000117721365,0.00087960425],"genre_scores_gemma":[0.99356353,0.000025525023,0.005778033,0.00005152656,0.00006108066,0.000005667155,0.00011155221,0.000008631407,0.00039442594],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990557,0.00003491711,0.0003224724,0.00014905963,0.00020366127,0.00023421786],"domain_scores_gemma":[0.999229,0.0000469389,0.0001752922,0.00031003988,0.00017035851,0.00006838042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022822848,0.00012106936,0.00015057699,0.00006349556,0.000041105654,0.000015067413,0.00020523545,0.00014077165,0.000023542263],"category_scores_gemma":[0.00014881082,0.000098713754,0.0000807735,0.00012144309,0.00007004533,0.000016867298,0.00011546828,0.0000845909,0.000073081465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003291263,0.00008666541,0.1067366,0.00037499858,0.00006927642,7.9385376e-7,0.00018627458,0.29070994,0.5968348,0.0014952869,0.00022114135,0.002955142],"study_design_scores_gemma":[0.00048196252,0.0004556563,0.0048683584,0.000038264676,0.000004695743,0.000003944124,0.00038770068,0.9590873,0.034020927,0.00008538208,0.00041127403,0.00015450644],"about_ca_topic_score_codex":0.00003598246,"about_ca_topic_score_gemma":0.000011691508,"teacher_disagreement_score":0.6683774,"about_ca_system_score_codex":0.000034483666,"about_ca_system_score_gemma":0.00008788309,"threshold_uncertainty_score":0.402543},"labels":[],"label_agreement":null},{"id":"W2995300996","doi":"10.1186/s12859-019-3202-x","title":"Distinguishing successive ancient polyploidy levels based on genome-internal syntenic alignment","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Plant Reproductive Biology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Ploidy; Computational biology; Evolutionary biology; Genetics; Gene","score_opus":0.014250251769733331,"score_gpt":0.24168979627093648,"score_spread":0.22743954450120316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995300996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9304572,0.00014531914,0.057736233,0.00008804317,0.0008228152,0.0005961618,0.00027657952,0.00004142272,0.0098362705],"genre_scores_gemma":[0.98328644,0.0000056375065,0.014509542,0.00091308437,0.0001984823,0.000015413127,0.0003262375,0.000020472207,0.0007246731],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985833,0.00004938662,0.0003828234,0.00035258124,0.00023446727,0.0003973993],"domain_scores_gemma":[0.9988626,0.000050382394,0.00026020408,0.0006252303,0.00009659121,0.000104969426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032824042,0.0002357559,0.00021456908,0.0000763651,0.00006694318,0.000047954596,0.00037635898,0.00014771782,0.000051220657],"category_scores_gemma":[0.00037257856,0.00019644004,0.00011761627,0.00007543313,0.00006787132,0.000009296295,0.0001794896,0.00012513046,0.00022669997],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000866964,0.00040967055,0.09088542,0.00052347156,0.00023273418,0.000015098682,0.00052880123,0.016328821,0.88456696,0.0005635837,0.0035849412,0.0014935082],"study_design_scores_gemma":[0.0056536226,0.0045626187,0.16028643,0.00045023754,0.00012892476,0.0002191864,0.0016690241,0.3478513,0.37033883,0.000069901085,0.10595704,0.0028128726],"about_ca_topic_score_codex":0.000011710776,"about_ca_topic_score_gemma":0.000013560751,"teacher_disagreement_score":0.51422817,"about_ca_system_score_codex":0.000079929065,"about_ca_system_score_gemma":0.00015204897,"threshold_uncertainty_score":0.80105925},"labels":[],"label_agreement":null},{"id":"W2995791792","doi":"10.1186/s12859-019-3221-7","title":"Longitudinal linear combination test for gene set analysis","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Alberta","funders":"","keywords":"DNA microarray; Computational biology; Set (abstract data type); Test (biology); Genetics; Biology; Gene; Computer science; Gene expression; Programming language","score_opus":0.02564994100882009,"score_gpt":0.28636622829989716,"score_spread":0.2607162872910771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995791792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3207241,0.00011363077,0.67608696,0.000094023366,0.00025102796,0.00059772626,0.00013654254,0.00002803686,0.0019679524],"genre_scores_gemma":[0.93435746,0.00005720523,0.061061785,0.0001953144,0.00010912447,0.00005277781,0.0019864559,0.000013884104,0.0021660128],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993468,0.00000965094,0.00024500495,0.00014368039,0.00011693966,0.00013793484],"domain_scores_gemma":[0.9993027,0.00002048719,0.00014649182,0.00034763475,0.00013324922,0.000049467835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014817728,0.00009896276,0.00012008166,0.000099243465,0.000052345644,0.00002630418,0.00013426942,0.000108005406,0.000031011627],"category_scores_gemma":[0.00006936985,0.00008940153,0.00013291484,0.00022911646,0.00001787958,0.000007979713,0.000040010866,0.00003345801,0.00005423273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033359975,0.0004363035,0.6088491,0.0006711771,0.0007336598,2.1549324e-7,0.00043970058,0.015079785,0.3305465,0.0011332065,0.03594315,0.0058336034],"study_design_scores_gemma":[0.0023321728,0.000660248,0.0692365,0.000015241158,0.00033538442,0.0000047433896,0.0003881279,0.6788151,0.18152066,0.0000816997,0.066116564,0.0004935553],"about_ca_topic_score_codex":0.0000016551273,"about_ca_topic_score_gemma":0.0000071257678,"teacher_disagreement_score":0.66373533,"about_ca_system_score_codex":0.000014021097,"about_ca_system_score_gemma":0.000060002392,"threshold_uncertainty_score":0.36456886},"labels":[],"label_agreement":null},{"id":"W2995918088","doi":"10.1186/s12859-019-3158-x","title":"Benchmarking machine learning models for late-onset alzheimer’s disease prediction from genomic data","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; IXICO; Centre hospitalier régional universitaire de Lille; H. Lundbeck A/S; Development of Innovative Strategies for a Transdisciplinary approach to ALZheimer's disease; Eisai; Genentech; Erasmus Medisch Centrum; Servier; Institut National de la Santé et de la Recherche Médicale; Bundesministerium für Bildung und Forschung; Hjartavernd; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Consejo Nacional de Ciencia y Tecnología; Wellcome Trust; University of Southern California; Université de Lille; Eli Lilly and Company; U.S. Department of Defense; Medical Research Council; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Machine learning; Computer science; Artificial intelligence; Disease; Benchmarking; Neuroimaging; Dementia; Selection (genetic algorithm); Medicine; Bioinformatics; Biology; Pathology; Psychiatry","score_opus":0.08631620591382395,"score_gpt":0.31297661523466136,"score_spread":0.22666040932083742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995918088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7561279,0.00089520024,0.23269035,0.00016891066,0.00035221362,0.0028539363,0.0032366284,0.0001728343,0.0035020565],"genre_scores_gemma":[0.9108618,0.00023237549,0.06414604,0.00036883043,0.00022048612,0.000061421095,0.023154842,0.000040535917,0.00091366284],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986549,0.000030863157,0.00038901233,0.00022557999,0.00037185356,0.00032779184],"domain_scores_gemma":[0.99885774,0.00015103549,0.00012342237,0.0005513949,0.00009517065,0.00022122017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004377234,0.00015705317,0.00021553965,0.00011853922,0.00011601552,0.00007481334,0.00022325928,0.000063521904,0.00034597365],"category_scores_gemma":[0.00008454007,0.00013528003,0.000079648315,0.0000921375,0.000032563028,0.00058151764,0.00029413315,0.00020140194,0.00019586479],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010312556,0.00015423301,0.97201365,0.0005101963,0.0003155201,0.0000032940113,0.00041081358,0.0034373996,0.00007754714,0.000039035687,0.0019019585,0.020105096],"study_design_scores_gemma":[0.0019492559,0.00023739904,0.112621136,0.00011152371,0.0003744627,0.000002889256,0.00016369789,0.8808078,0.000030641564,0.00019782178,0.003382709,0.0001206488],"about_ca_topic_score_codex":0.00003715528,"about_ca_topic_score_gemma":0.000008327998,"teacher_disagreement_score":0.8773704,"about_ca_system_score_codex":0.00004133176,"about_ca_system_score_gemma":0.00021460511,"threshold_uncertainty_score":0.551656},"labels":[],"label_agreement":null},{"id":"W2996010403","doi":"10.1186/s12859-019-3204-8","title":"Deconvoluting the diversity of within-host pathogen strains in a multi-locus sequence typing framework","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Vector-borne infectious diseases","field":"Immunology and Microbiology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada; Alfred P. Sloan Foundation","keywords":"Multilocus sequence typing; Biology; Locus (genetics); Typing; Genetics; Genome; Computational biology; Pathogen; Borrelia burgdorferi; Allele; Genotype; Gene","score_opus":0.036781714347454066,"score_gpt":0.2643672236064904,"score_spread":0.22758550925903634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996010403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914308,0.00043778308,0.00660491,0.000012814463,0.0005264804,0.00038813404,0.00007895566,0.000054530494,0.00046554513],"genre_scores_gemma":[0.9932631,0.000015497058,0.0064842803,0.00013200424,0.000007021557,0.0000041450994,0.000019015813,0.000008009973,0.000066872766],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990615,0.00009031522,0.00041755132,0.000112255846,0.000040092782,0.00027824135],"domain_scores_gemma":[0.9989921,0.00027638444,0.0003023083,0.00034814273,0.000062717685,0.000018373226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003657748,0.00013827378,0.00021997454,0.000086481465,0.00017089884,0.000013142867,0.00033056515,0.00020674207,0.00010720955],"category_scores_gemma":[0.00033585928,0.00010532727,0.00008418033,0.00020545312,0.00018293221,0.00016868422,0.00034071758,0.00032804854,0.00038406494],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038498005,0.00012270089,0.97941476,0.00018729949,0.00009217697,0.0000012480268,0.009805105,0.0011435447,0.0065640872,0.0021264267,0.00005893548,0.00044523994],"study_design_scores_gemma":[0.0034714292,0.00030302984,0.9236479,0.0006540287,0.00015461998,0.0001044238,0.024157425,0.041993484,0.003641272,0.0006238965,0.00044032943,0.00080818625],"about_ca_topic_score_codex":0.00023561985,"about_ca_topic_score_gemma":0.0005879336,"teacher_disagreement_score":0.055766862,"about_ca_system_score_codex":0.00006827021,"about_ca_system_score_gemma":0.00013835412,"threshold_uncertainty_score":0.49365062},"labels":[],"label_agreement":null},{"id":"W2996627222","doi":"10.1186/s12859-019-3313-4","title":"perfectphyloR: An R package for reconstructing perfect phylogenies","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Partition (number theory); Phylogenetics; Sequence (biology); R package; Evolutionary biology; Biology; Binary number; Computer science; Tree (set theory); Computational biology; Theoretical computer science; Combinatorics; Genetics; Mathematics; Gene; Programming language","score_opus":0.018901358297216276,"score_gpt":0.26608482746657935,"score_spread":0.24718346916936307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996627222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9450491,0.00009611813,0.051115267,0.00002638871,0.00034127876,0.00044304662,0.000062691906,0.000021937234,0.0028441546],"genre_scores_gemma":[0.787233,0.000035767094,0.21122478,0.00027234785,0.00024075015,0.000039704017,0.0003595868,0.000023430617,0.000570652],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898756,0.000055300432,0.0003596996,0.00019761958,0.00006903525,0.00033079402],"domain_scores_gemma":[0.9991441,0.00006964358,0.00019578834,0.00041801666,0.00009766162,0.000074838594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048418326,0.00015964116,0.00021285367,0.000045331915,0.00012154528,0.000031093547,0.00018340601,0.00020843885,0.000034828972],"category_scores_gemma":[0.00028738656,0.00014573059,0.00014698657,0.000056215053,0.000047162102,0.000010087947,0.00006531865,0.00006834438,0.00006988648],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015397015,0.00010098154,0.88009197,0.00047285567,0.00019001163,1.7106656e-7,0.0009878818,0.0018923681,0.084336154,0.00082685857,0.0047160382,0.026230741],"study_design_scores_gemma":[0.009055852,0.008818242,0.21030088,0.000105537954,0.00030456146,0.00025739224,0.01989105,0.5743595,0.07101799,0.0023998497,0.09989493,0.0035942497],"about_ca_topic_score_codex":0.000005082757,"about_ca_topic_score_gemma":0.000028175202,"teacher_disagreement_score":0.6697911,"about_ca_system_score_codex":0.00001601496,"about_ca_system_score_gemma":0.000086353706,"threshold_uncertainty_score":0.59427214},"labels":[],"label_agreement":null},{"id":"W2996835999","doi":"10.1186/s12859-019-3090-0","title":"CSA: a web service for the complete process of ChIP-Seq analysis","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Chromatin immunoprecipitation; Visualization; Chip; Workflow; Personalization; Web service; Bioconductor; Data visualization; Data mining; Computational biology; World Wide Web; Database; Biology; Genetics","score_opus":0.011190339897307547,"score_gpt":0.23813488634227506,"score_spread":0.2269445464449675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996835999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.956624,0.00014732845,0.040819976,0.000093264774,0.000099311306,0.000578894,0.00033715402,0.000008705825,0.0012913898],"genre_scores_gemma":[0.9722821,0.000034705634,0.0265241,0.000361076,0.00004832299,0.000028871445,0.00050938525,0.000016268594,0.00019517726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925727,0.000009106682,0.00033724168,0.00010260291,0.00012886383,0.00016490291],"domain_scores_gemma":[0.9989913,0.000031389147,0.00023454314,0.0004510019,0.0002511406,0.00004064407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002277804,0.00011872835,0.0001956561,0.000045898127,0.000046469773,0.000023006887,0.00034201087,0.000088174704,0.000010445172],"category_scores_gemma":[0.000031065167,0.000084991974,0.00015349845,0.00027487235,0.00002948847,0.000004309557,0.00009028171,0.000041115523,0.000013796884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009226138,0.00051608175,0.10064701,0.009439407,0.007071194,3.5744895e-7,0.007356531,0.6985979,0.16238038,0.0033501936,0.0059361598,0.0037821664],"study_design_scores_gemma":[0.0005964472,0.000116396,0.0013952705,0.0000076604765,0.0002474427,0.000002054073,0.0011343672,0.991346,0.001447078,0.00009206367,0.0034704981,0.00014469506],"about_ca_topic_score_codex":0.000006995047,"about_ca_topic_score_gemma":0.00014153948,"teacher_disagreement_score":0.29274812,"about_ca_system_score_codex":0.000008277762,"about_ca_system_score_gemma":0.00015653855,"threshold_uncertainty_score":0.3465872},"labels":[],"label_agreement":null},{"id":"W2996913857","doi":"10.1186/s12859-019-3292-5","title":"LMAP_S: Lightweight Multigene Alignment and Phylogeny eStimation","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Australian National University; University of Ottawa; Konkuk University; Helsingin Yliopisto","keywords":"Workflow; Computer science; Software; Data mining; File format; DNA microarray; Workstation; Biology; Database; Gene; Programming language","score_opus":0.008499432732594413,"score_gpt":0.21809406372563014,"score_spread":0.20959463099303574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996913857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98317903,0.0011021112,0.012124041,0.000030651314,0.00022883843,0.00036197685,0.00002686662,0.000006670784,0.0029398017],"genre_scores_gemma":[0.89076346,0.0004493769,0.10782066,0.00024416516,0.00007522611,0.000015678925,0.000060947772,0.0000147516175,0.0005557506],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928325,0.000012716253,0.00025317125,0.00015536958,0.00010386352,0.00019164218],"domain_scores_gemma":[0.9994954,0.000012658353,0.000099050594,0.00028765362,0.00004126043,0.000064011234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113986156,0.00015170506,0.0001364741,0.00003286156,0.00006727871,0.000030019879,0.00010397835,0.00009867812,0.000012173228],"category_scores_gemma":[0.000020669877,0.0001312595,0.00004953632,0.000040358816,0.000041591884,0.0000019904944,0.00014576453,0.00003527288,0.00007679445],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016298027,0.00019821995,0.09248645,0.0008323206,0.00042458225,0.0000011360564,0.0025461654,0.008059675,0.8485052,0.0019234981,0.0048798337,0.039979946],"study_design_scores_gemma":[0.004600405,0.0015496234,0.17210382,0.00009199664,0.00014733043,0.00007266266,0.0018684624,0.35526878,0.28889284,0.00081943575,0.17281187,0.001772787],"about_ca_topic_score_codex":0.0000040953837,"about_ca_topic_score_gemma":0.000008054494,"teacher_disagreement_score":0.55961233,"about_ca_system_score_codex":0.000009552887,"about_ca_system_score_gemma":0.00003332231,"threshold_uncertainty_score":0.5352607},"labels":[],"label_agreement":null},{"id":"W2997053614","doi":"10.1186/s12859-019-3315-2","title":"Improvement of the memory function of a mutual repression network in a stochastic environment by negative autoregulation","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bistability; Biological network; Computer science; Gene regulatory network; Autoregulation; Function (biology); Stochastic process; Robustness (evolution); Mathematics; Biology; Physics; Bioinformatics; Genetics","score_opus":0.004249827032259076,"score_gpt":0.1854823751677977,"score_spread":0.18123254813553863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997053614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9545335,0.00015397416,0.044596933,0.000007990142,0.000107815285,0.00044029133,0.000009100033,0.000002803011,0.00014755595],"genre_scores_gemma":[0.9972555,0.000008432969,0.002312772,0.000024822308,0.00003534506,0.000011977857,0.000051810326,0.000008203169,0.0002911319],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990291,0.000040190087,0.00045459115,0.00012573514,0.00021151369,0.00013889009],"domain_scores_gemma":[0.9990517,0.000017186463,0.0004253566,0.00045340142,0.000028122644,0.000024216262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002406128,0.000108717824,0.00016303362,0.000030134886,0.000023929038,0.000003677545,0.0001262181,0.00010710266,0.000023250766],"category_scores_gemma":[0.000021426145,0.000081337006,0.0001021811,0.0001253125,0.000060285325,0.0000070541064,0.0001406182,0.000051390158,0.0000040856585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014275526,0.000057359153,0.012967882,0.00008066083,0.00006455838,1.1173786e-8,0.00023086485,0.8972833,0.084952824,0.00001894186,0.00083169807,0.0033691393],"study_design_scores_gemma":[0.0016358668,0.000622247,0.0713605,0.00013863265,0.00012674251,0.0000010595328,0.0007739938,0.8283441,0.09614475,0.00018039995,0.0003982468,0.00027342842],"about_ca_topic_score_codex":0.0000080637365,"about_ca_topic_score_gemma":0.000011943812,"teacher_disagreement_score":0.06893917,"about_ca_system_score_codex":0.000031014344,"about_ca_system_score_gemma":0.00004734723,"threshold_uncertainty_score":0.33168268},"labels":[],"label_agreement":null},{"id":"W2997277473","doi":"10.1186/s12859-019-3093-x","title":"DDIGIP: predicting drug-drug interactions based on Gaussian interaction profile kernels","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Drug; Drug-drug interaction; Cross-validation; Computer science; Drug discovery; Drug development; Computational biology; Pharmacology; Data mining; Machine learning; Bioinformatics; Medicine; Biology","score_opus":0.021704322912649888,"score_gpt":0.29665587510186947,"score_spread":0.2749515521892196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997277473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026784005,0.0000046228574,0.91604316,0.00046305245,0.0022399505,0.00057089067,0.000020982856,0.0003539803,0.053519364],"genre_scores_gemma":[0.3832601,0.000001056778,0.61429113,0.00067371235,0.00012114298,0.00004081124,0.000055714318,0.000019933183,0.0015363959],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980958,0.00014886139,0.0006096017,0.0002849576,0.0005422695,0.00031851968],"domain_scores_gemma":[0.99736446,0.0013041517,0.00037775913,0.00071515393,0.00011835336,0.00012010861],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006074358,0.00023168362,0.0002104518,0.00034465687,0.00014754856,0.0004091444,0.0006744473,0.000036219644,0.00012348134],"category_scores_gemma":[0.00022195539,0.00021242663,0.00014363111,0.00051163376,0.000026346825,0.0023339721,0.00023957265,0.00034945423,0.0013507573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007318278,0.00030481283,0.008138971,0.0004394506,0.000039157,0.0000028395698,0.004815505,0.91204196,0.00004200069,0.017759202,0.00721252,0.049130417],"study_design_scores_gemma":[0.0003943925,0.000044465905,0.0028607203,0.00019408902,0.000006685302,0.0000139551785,0.0004543417,0.9900957,0.0006467538,0.00047010565,0.0045826947,0.00023612332],"about_ca_topic_score_codex":0.000021170476,"about_ca_topic_score_gemma":0.000017630464,"teacher_disagreement_score":0.3564761,"about_ca_system_score_codex":0.00020792641,"about_ca_system_score_gemma":0.00025726404,"threshold_uncertainty_score":0.9994268},"labels":[],"label_agreement":null},{"id":"W2997640910","doi":"10.1186/s12859-019-3266-7","title":"A systematic evaluation of copy number alterations detection methods on real SNP array and deep sequencing data","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; McGill University; National Science Foundation","keywords":"Computer science; Benchmark (surveying); Data mining; SNP array; SNP; Scale (ratio); Computational biology; Biology; Single-nucleotide polymorphism; Genetics; Gene","score_opus":0.057937045641693906,"score_gpt":0.34181766453312307,"score_spread":0.2838806188914292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997640910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68892294,0.0001113029,0.30393708,0.000008134399,0.00022689636,0.0008645672,0.000060272083,0.000013157334,0.005855687],"genre_scores_gemma":[0.87585133,0.000046210454,0.123623386,0.000030616113,0.000043685544,0.000027290687,0.00027535285,0.00000908869,0.00009306352],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989302,0.000185453,0.00044540412,0.00013754568,0.00019176386,0.00010960864],"domain_scores_gemma":[0.9988974,0.00005474026,0.00025543876,0.0005916136,0.00016753943,0.000033271856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012907054,0.00010723419,0.00016910055,0.000040017017,0.00006788519,0.00003866151,0.00013920185,0.000092715425,0.000025542535],"category_scores_gemma":[0.00019237012,0.00009302811,0.00003341602,0.000065559354,0.000024713438,0.00002688983,0.00007233243,0.000046132365,0.000023527888],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041090077,0.00039368693,0.03596271,0.058483396,0.0016478207,5.5267134e-7,0.018358443,0.050888952,0.7989518,0.010234946,0.00035517188,0.024311638],"study_design_scores_gemma":[0.0012323725,0.00033693417,0.0015089173,0.000569883,0.0003824532,0.0000711759,0.006121152,0.81593055,0.17299275,0.00032918126,0.00015169012,0.00037294268],"about_ca_topic_score_codex":0.000021216247,"about_ca_topic_score_gemma":0.00008387514,"teacher_disagreement_score":0.7650416,"about_ca_system_score_codex":0.00004051808,"about_ca_system_score_gemma":0.00013292556,"threshold_uncertainty_score":0.3793576},"labels":[],"label_agreement":null},{"id":"W2997828579","doi":"10.1186/s12859-019-3054-4","title":"Antimicrobial resistance genetic factor identification from whole-genome sequence data using deep feature selection","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Identification (biology); Computational biology; Feature selection; Whole genome sequencing; Biology; Selection (genetic algorithm); DNA microarray; Genetics; Genome; Artificial intelligence; Bioinformatics; Computer science; Gene; Gene expression","score_opus":0.03449597150938384,"score_gpt":0.2599799649302015,"score_spread":0.22548399342081765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997828579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9358213,0.001051427,0.060008943,0.000040979663,0.00047870533,0.00037965763,0.002100873,0.000010493783,0.00010761149],"genre_scores_gemma":[0.74296594,0.00033493442,0.25165167,0.00019614129,0.0003517354,0.0000054648795,0.0035336288,0.000037659403,0.00092282286],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890983,0.000029575996,0.00033852068,0.0003408814,0.00013770675,0.00024351022],"domain_scores_gemma":[0.9987552,0.000012391955,0.0002441483,0.00082739344,0.00010821787,0.000052602274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009305196,0.00019242524,0.00016694571,0.000041548432,0.00012728483,0.000095298565,0.00048613249,0.00017264341,0.0000114252625],"category_scores_gemma":[0.00003741147,0.00019276161,0.000052217652,0.00011702932,0.00005045822,0.000009703509,0.00028456937,0.000089345165,0.000054509514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030636795,0.000013967188,0.010824034,0.00008168784,0.00005462867,1.9581668e-7,0.0001433303,0.0019275954,0.9861483,0.0000037917507,0.00043892013,0.00033292628],"study_design_scores_gemma":[0.002354993,0.00020376069,0.25108412,0.0001305195,0.00027826225,0.000057688885,0.00071069784,0.42130652,0.1016891,0.00011955108,0.21999039,0.0020744097],"about_ca_topic_score_codex":0.000031068124,"about_ca_topic_score_gemma":0.00024613296,"teacher_disagreement_score":0.8844592,"about_ca_system_score_codex":0.000033656077,"about_ca_system_score_gemma":0.00011023007,"threshold_uncertainty_score":0.7860591},"labels":[],"label_agreement":null},{"id":"W2998018748","doi":"10.1186/s12859-019-3278-3","title":"IILLS: predicting virus-receptor interactions based on similarity and semi-supervised learning","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Similarity (geometry); Computational biology; Artificial intelligence; Computer science; Cross-validation; Virus; Pattern recognition (psychology); Machine learning; Biology; Virology","score_opus":0.008804090554234723,"score_gpt":0.24521196154674885,"score_spread":0.23640787099251412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998018748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89966476,0.00005409099,0.06258327,0.00016085753,0.0006212471,0.0007479401,0.00008679169,0.00018416544,0.035896856],"genre_scores_gemma":[0.84919703,0.00007033173,0.14566034,0.0018229854,0.00026875772,0.000030453239,0.00093389803,0.00007214793,0.0019440454],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863905,0.00007615012,0.0004961925,0.00020473603,0.00025898774,0.00032490084],"domain_scores_gemma":[0.99895,0.00012627721,0.000258362,0.0004447194,0.00008844717,0.00013218539],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040487124,0.000266674,0.00021513915,0.000117330674,0.00019952709,0.00010983784,0.00021045026,0.000198156,0.0001795789],"category_scores_gemma":[0.0005544544,0.00024737124,0.0001031425,0.00012853423,0.00006371483,0.000033499877,0.00017961292,0.00047541512,0.00022292773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000718553,0.00036962665,0.6636577,0.0024583684,0.00022181464,0.0000011416018,0.0032066896,0.26881662,0.035384506,0.0003060511,0.008844152,0.016014757],"study_design_scores_gemma":[0.0008561931,0.0004513575,0.0023981044,0.000094812334,0.000018516279,0.000008789023,0.0006116431,0.9441281,0.0033743011,0.0000034078516,0.047747627,0.00030713007],"about_ca_topic_score_codex":0.000010808764,"about_ca_topic_score_gemma":0.000018411583,"teacher_disagreement_score":0.6753115,"about_ca_system_score_codex":0.000030278516,"about_ca_system_score_gemma":0.00008918598,"threshold_uncertainty_score":0.99999785},"labels":[],"label_agreement":null},{"id":"W2998581384","doi":"10.1186/s12859-019-3268-5","title":"Using discriminative vector machine model with 2DPCA to predict interactions among proteins","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Discriminative model; Computational biology; Computer science; Support vector machine; Artificial intelligence; DNA microarray; Machine learning; Vector (molecular biology); Pattern recognition (psychology); Bioinformatics; Biology; Genetics; Gene expression","score_opus":0.01863703357937437,"score_gpt":0.25302364867889704,"score_spread":0.23438661509952266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998581384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2994907,0.000021125848,0.69366366,0.000037570917,0.0001349766,0.00095360144,0.00010655554,0.000024422015,0.0055673695],"genre_scores_gemma":[0.67816925,0.000006236531,0.319691,0.00028063642,0.00009583089,0.000042596348,0.00019882055,0.000034527726,0.0014811044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988851,0.000015443482,0.0003983538,0.00017797647,0.0001854425,0.00033768994],"domain_scores_gemma":[0.99903655,0.000010664044,0.000199576,0.00048257102,0.000106112944,0.00016449677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013690413,0.00024535798,0.00020363276,0.00008660139,0.00010644276,0.00007518256,0.000242842,0.00011661355,0.000024565565],"category_scores_gemma":[0.000021839856,0.00019079859,0.00008252828,0.00014004941,0.000063100786,0.00003938408,0.00020727962,0.0001687534,0.0000543162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007823117,0.00026304854,0.017612565,0.00079440256,0.00038702172,0.0000016509589,0.0050603044,0.9489784,0.016196799,0.0015771962,0.003942914,0.004403361],"study_design_scores_gemma":[0.00054648885,0.00035627786,0.0007855014,0.00009060188,0.000035607125,0.000017583563,0.0005581499,0.99359727,0.0022869431,0.000034322584,0.0013704391,0.0003207981],"about_ca_topic_score_codex":0.000022858068,"about_ca_topic_score_gemma":0.00020809982,"teacher_disagreement_score":0.37867853,"about_ca_system_score_codex":0.000046029123,"about_ca_system_score_gemma":0.00014646466,"threshold_uncertainty_score":0.77805406},"labels":[],"label_agreement":null},{"id":"W2998682161","doi":"10.1186/s12859-019-3293-4","title":"Rearrangement analysis of multiple bacterial genomes","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute for Basic Biology; Institute of Genetics; National Cancer Institute; National Bioscience Database Center; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Genome; Computational biology; Bacterial genome size; DNA microarray; Biology; Computer science; Genetics; Gene; Gene expression","score_opus":0.011779181864968055,"score_gpt":0.22678324183369095,"score_spread":0.2150040599687229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998682161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98531574,0.00015893132,0.010391007,0.000009412275,0.00021156065,0.00036090004,0.000096530726,0.000011928515,0.00344399],"genre_scores_gemma":[0.89287436,0.00019879594,0.1037493,0.00007701505,0.00012965134,0.000019056595,0.0014723429,0.000026011234,0.001453487],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990773,0.0000197155,0.0003808504,0.00013762226,0.00018644871,0.00019806645],"domain_scores_gemma":[0.9991735,0.000013125203,0.00018666242,0.00049438723,0.0000794068,0.00005289709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019052728,0.0001310098,0.00024688276,0.00017631316,0.000021519074,0.00001872387,0.00020455151,0.000094323754,0.00027588563],"category_scores_gemma":[0.00002662732,0.00011954566,0.00020022507,0.0002859056,0.000032632015,0.000006527774,0.00012876837,0.000033908036,0.000090941365],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027781274,0.00022702357,0.4697801,0.000563244,0.0037964918,4.9329395e-7,0.0010692999,0.009005863,0.5041354,0.00010521423,0.0016629009,0.009376211],"study_design_scores_gemma":[0.0066964007,0.0014863829,0.26240185,0.00004736423,0.0023668716,0.0000058022874,0.002618462,0.39619532,0.11325571,0.00002534195,0.21336025,0.0015402258],"about_ca_topic_score_codex":0.000008427372,"about_ca_topic_score_gemma":0.000038888666,"teacher_disagreement_score":0.39087966,"about_ca_system_score_codex":0.000013819619,"about_ca_system_score_gemma":0.00004369099,"threshold_uncertainty_score":0.48749304},"labels":[],"label_agreement":null},{"id":"W3000659041","doi":"10.1186/s12859-019-3312-5","title":"Optimization and expansion of non-negative matrix factorization","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Ontario Genomics; Genome Canada; Government of Canada; Ontario Institute for Cancer Research; Ontario Genomics Institute; Movember Foundation","keywords":"Non-negative matrix factorization; Computer science; Matrix (chemical analysis); Matrix decomposition; Computational biology; Biology; Mathematics; Physics; Chemistry","score_opus":0.044048035217136294,"score_gpt":0.30938569971251123,"score_spread":0.26533766449537494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000659041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015877264,0.000004954021,0.9825208,0.00018643976,0.00002086657,0.0003210225,0.000036479367,0.00006918265,0.00096295855],"genre_scores_gemma":[0.20856601,0.000019033781,0.7912152,0.0000961863,0.00002364821,0.000008960129,0.00003509957,0.000010337954,0.000025558253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993037,0.000013288761,0.00038907677,0.000073029376,0.00014259372,0.0000783061],"domain_scores_gemma":[0.9993095,0.000138256,0.00024850864,0.00012190249,0.00010614249,0.00007571387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000056019755,0.000092184964,0.00015430966,0.00004506541,0.000058645943,0.000023345288,0.00007005116,0.00006096328,0.00004683788],"category_scores_gemma":[0.00014654879,0.00008297893,0.000033123684,0.00020352328,0.00003655343,0.00021055428,0.000037512564,0.00005379953,0.000013914446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005016463,0.0009955904,0.0112472195,0.014832122,0.00037797747,0.0000023707098,0.15639521,0.2337619,0.028745532,0.5002096,0.03303947,0.019891284],"study_design_scores_gemma":[0.00045657335,0.000056344965,0.00033283647,0.000030150826,0.000027678148,0.0000018486179,0.0010827935,0.9906546,0.004343929,0.0028146575,0.00008848124,0.0001101331],"about_ca_topic_score_codex":0.0000014136815,"about_ca_topic_score_gemma":5.054037e-7,"teacher_disagreement_score":0.7568927,"about_ca_system_score_codex":0.000010685833,"about_ca_system_score_gemma":0.000026263657,"threshold_uncertainty_score":0.33837825},"labels":[],"label_agreement":null},{"id":"W3003647270","doi":"10.1186/s12859-019-3190-x","title":"DeepECA: an end-to-end learning framework for protein contact prediction from a multiple sequence alignment","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; University of Tokyo; Japan Agency for Medical Research and Development","keywords":"End-to-end principle; Computational biology; Sequence (biology); Computer science; Sequence alignment; Multiple sequence alignment; DNA microarray; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Genetics; Gene","score_opus":0.022764288424854583,"score_gpt":0.258106808117291,"score_spread":0.23534251969243639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003647270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20967555,0.000042450047,0.7887017,0.0000983298,0.00007637683,0.0008991326,0.00038351194,0.000047577047,0.00007536454],"genre_scores_gemma":[0.5575662,0.0000070067413,0.4404659,0.0006489587,0.00027284704,0.00011211648,0.00089284027,0.00001816936,0.000015911528],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998937,0.000032685763,0.00034452748,0.00024699103,0.00017586623,0.00026290768],"domain_scores_gemma":[0.9992528,0.00002768632,0.00015554708,0.00027346003,0.00006914811,0.00022134895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110574016,0.0001921257,0.00017049356,0.000022733117,0.00012610324,0.00006406996,0.00021991486,0.00024439773,0.000014519044],"category_scores_gemma":[0.00050291646,0.000181062,0.00008304913,0.000077140045,0.000028334234,0.00002108817,0.00010558179,0.00015557541,0.0000126587],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015697479,0.00010367278,0.014030064,0.00053329975,0.0002446899,0.0000034710556,0.005397214,0.018021883,0.92012894,0.003977317,0.0005093218,0.0354804],"study_design_scores_gemma":[0.0018162527,0.0030773978,0.0016092738,0.00011831808,0.00007126474,0.000007107616,0.0016526334,0.7597227,0.19812542,0.0019871737,0.03110752,0.00070492254],"about_ca_topic_score_codex":0.000023502675,"about_ca_topic_score_gemma":0.000036243302,"teacher_disagreement_score":0.7417008,"about_ca_system_score_codex":0.000028412473,"about_ca_system_score_gemma":0.000096227435,"threshold_uncertainty_score":0.73834944},"labels":[],"label_agreement":null},{"id":"W30089455","doi":"10.1186/s12859-018-2289-9","title":"A Position Between Two Curves site specific installation","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Conservation Techniques and Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fondation Brain Canada; Canadian Institute for Advanced Research","keywords":"Exhibition; Microphone; Loudspeaker; Noise (video); Space (punctuation); Position (finance); Point (geometry); Acoustics; Scale (ratio); Sound (geography); Computer science; Visual arts; Physics; Art; Mathematics; Artificial intelligence; Geometry","score_opus":0.07189833449293616,"score_gpt":0.25813552594355377,"score_spread":0.18623719145061762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30089455","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056060273,0.0009817504,0.048064783,0.0006597574,0.00038946397,0.00078936643,0.00016034368,0.0005479892,0.89234626],"genre_scores_gemma":[0.8663671,0.0017040863,0.11074901,0.0035678428,0.0009210355,0.00008669224,0.0008009131,0.000058982754,0.015744362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993248,0.000021400192,0.0003278958,0.000059539554,0.00014269247,0.00012367697],"domain_scores_gemma":[0.99955237,0.000051439627,0.0001227783,0.0001340658,0.00011150401,0.000027867154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017286176,0.00010029282,0.00012690848,0.0000716225,0.0002594675,0.00011869422,0.000049582217,0.000022174581,0.0005434656],"category_scores_gemma":[0.00002394197,0.00008696238,0.000055655022,0.000042112297,0.000069098474,0.00029713364,0.000018116032,0.00006149584,0.00016591532],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008397711,0.000043821805,0.018117031,0.00055904355,0.000035814344,5.9724124e-7,0.022995504,0.000011885773,0.0000091396105,0.8617052,0.090041704,0.006471885],"study_design_scores_gemma":[0.00032794886,0.00006385183,0.003073935,0.00016189717,0.000027831591,0.000002390601,0.0018492109,0.001224136,0.00009616385,0.0035823893,0.9893438,0.00024644544],"about_ca_topic_score_codex":0.000024735493,"about_ca_topic_score_gemma":0.00027054912,"teacher_disagreement_score":0.89930207,"about_ca_system_score_codex":0.00002748695,"about_ca_system_score_gemma":0.000020362719,"threshold_uncertainty_score":0.5950567},"labels":[],"label_agreement":null},{"id":"W3010830252","doi":"10.1186/s12859-020-3346-8","title":"Ensemble disease gene prediction by clinical sample-based networks","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"DNA microarray; Computational biology; Ensemble learning; Computer science; Disease; Artificial intelligence; Gene; Bioinformatics; Genetics; Biology; Medicine; Gene expression; Pathology","score_opus":0.024874482279030368,"score_gpt":0.2560171676417269,"score_spread":0.23114268536269653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010830252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009656793,0.0004579446,0.9878763,0.0002843776,0.00034048333,0.0003960585,0.00042639452,0.00006306763,0.0004985833],"genre_scores_gemma":[0.6389914,0.00088036904,0.3202265,0.02457083,0.003117351,0.000084982035,0.011775818,0.00012169243,0.00023105265],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982491,0.000049751834,0.0008788069,0.00023727215,0.00019703797,0.00038799815],"domain_scores_gemma":[0.9985662,0.000059447724,0.0002711123,0.00045501895,0.00007756624,0.0005706726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032159922,0.00025288807,0.0002411828,0.000022275832,0.0001266509,0.000079654346,0.00030493946,0.0002925244,0.000025074163],"category_scores_gemma":[0.00021351609,0.0002369266,0.00022711544,0.00012859158,0.00010959519,0.000014717203,0.000145312,0.0002156942,0.000049083257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018162697,0.00039515953,0.04618213,0.00066217536,0.00030447822,0.000003779221,0.00025237692,0.19057865,0.0017791053,0.0002910927,0.7151392,0.042595543],"study_design_scores_gemma":[0.0011083889,0.0003340317,0.00075468596,0.000012268796,0.00005006733,0.0000016807286,0.000041302137,0.9193994,0.0005643089,0.00003602063,0.07741642,0.00028142988],"about_ca_topic_score_codex":0.0000024102928,"about_ca_topic_score_gemma":0.0000034020213,"teacher_disagreement_score":0.72882074,"about_ca_system_score_codex":0.000013777236,"about_ca_system_score_gemma":0.00019041209,"threshold_uncertainty_score":0.9661586},"labels":[],"label_agreement":null},{"id":"W3011481967","doi":"10.1186/s12859-020-3397-x","title":"CNV Radar: an improved method for somatic copy number alteration characterization in oncology","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research; University of Calgary","funders":"Janssen Research and Development","keywords":"Copy-number variation; Concordance; Loss of heterozygosity; Copy number analysis; Oncology; Biology; Medicine; Bioinformatics; Genetics; Allele; Gene; Genome","score_opus":0.021740245374512534,"score_gpt":0.31035138363434267,"score_spread":0.28861113825983015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011481967","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1201464,0.000013057298,0.87830484,0.00029109095,0.00016781408,0.00062777713,0.00018742523,0.000014955457,0.00024662729],"genre_scores_gemma":[0.11198252,0.00012519804,0.87821823,0.0044661984,0.00060195563,0.00015340534,0.004363021,0.0000418083,0.000047682628],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991069,0.00003781483,0.00043816588,0.00016305123,0.000060660237,0.00019341754],"domain_scores_gemma":[0.99939954,0.00004543019,0.00018962653,0.00018661986,0.00007281345,0.00010599017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018977058,0.00013484577,0.0001859954,0.00002619898,0.000047623933,0.000052087114,0.00013046741,0.00016664367,0.000012135606],"category_scores_gemma":[0.00018287101,0.00013907916,0.000057150995,0.00008031802,0.000018140876,0.000020370735,0.00005319919,0.000058637477,0.000012677217],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010008415,0.00029260232,0.010978903,0.00081050716,0.000070292816,0.0000013343058,0.0044073174,0.00166013,0.9070537,0.0012968518,0.0015559628,0.07087153],"study_design_scores_gemma":[0.0024132377,0.0010690165,0.0018468233,0.000013549121,0.00003367802,0.000008075682,0.0003028157,0.87807375,0.078484505,0.00014892,0.037264034,0.00034157035],"about_ca_topic_score_codex":0.0000100804145,"about_ca_topic_score_gemma":0.000069515045,"teacher_disagreement_score":0.87641364,"about_ca_system_score_codex":0.000040898776,"about_ca_system_score_gemma":0.00021788091,"threshold_uncertainty_score":0.5671484},"labels":[],"label_agreement":null},{"id":"W3012154856","doi":"10.1186/s12859-020-3426-9","title":"PESM: predicting the essentiality of miRNAs based on gradient boosting machines and sequences","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Boosting (machine learning); Support vector machine; Computer science; Bayes' theorem; microRNA; Machine learning; Gradient boosting; Naive Bayes classifier; Artificial intelligence; Computational biology; DNA microarray; Data mining; Biology; Bayesian probability; Random forest; Gene; Genetics; Gene expression","score_opus":0.019176273843448458,"score_gpt":0.24489331344234425,"score_spread":0.22571703959889577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012154856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760035,0.00018475945,0.022390544,0.0004123286,0.00005676468,0.00023123548,0.00004627568,0.000014675345,0.0006599084],"genre_scores_gemma":[0.9906231,0.000010024674,0.008882835,0.00033047795,0.00007719529,0.0000038973317,0.000061832085,0.000005834465,0.0000048126067],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994143,0.000035597557,0.0002454533,0.00008952555,0.00012060633,0.000094510666],"domain_scores_gemma":[0.999541,0.000032548236,0.00017834382,0.00015492407,0.000041208463,0.000051971474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016333634,0.00008630485,0.00008008505,0.000013418496,0.00007695559,0.000021189342,0.00010406704,0.00004768497,0.000004456791],"category_scores_gemma":[0.0002363081,0.000060275426,0.000045848785,0.00005935507,0.000089629764,0.0000052382657,0.000059991853,0.00004410752,0.0000011094294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086620176,0.0002423144,0.44100788,0.0061205714,0.00028021523,0.0000030289395,0.005613332,0.07203255,0.44920146,0.001119076,0.004085792,0.019427558],"study_design_scores_gemma":[0.00033170197,0.00013971623,0.01818403,0.000048321457,0.000034585122,0.000003424793,0.00028273507,0.9365359,0.04375991,0.000026862437,0.00054345606,0.00010936958],"about_ca_topic_score_codex":0.000008850434,"about_ca_topic_score_gemma":0.0000063937578,"teacher_disagreement_score":0.8645033,"about_ca_system_score_codex":0.000004720321,"about_ca_system_score_gemma":0.000053923308,"threshold_uncertainty_score":0.24579605},"labels":[],"label_agreement":null},{"id":"W3012532670","doi":"10.1186/s12859-020-3345-9","title":"Prediction of tumor location in prostate cancer tissue using a machine learning system on gene expression data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; University of Windsor","keywords":"Laterality; Prostate cancer; Prostate; Gene; Human leukocyte antigen; Computational biology; DNA microarray; Cancer; Gene expression; Biology; Artificial intelligence; Computer science; Genetics; Neuroscience; Antigen","score_opus":0.041854032633337535,"score_gpt":0.2834448822248406,"score_spread":0.24159084959150307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012532670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77820426,0.00064055476,0.21815516,0.0000862745,0.00027287455,0.0011755979,0.0007173828,0.00011101708,0.00063687196],"genre_scores_gemma":[0.8654811,0.00008133482,0.1322898,0.00013483486,0.00015464587,0.000017431757,0.0017741257,0.000034173947,0.000032576478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986051,0.00007184102,0.0006810094,0.0001922547,0.00025148838,0.00019831704],"domain_scores_gemma":[0.99886525,0.000016585587,0.00049078173,0.0004580094,0.00008976797,0.000079593905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032034627,0.00018008283,0.00021087761,0.00007951256,0.00006755008,0.000026250998,0.00032951517,0.00009401711,0.000006091477],"category_scores_gemma":[0.00029717217,0.00016317677,0.000025370531,0.00023547998,0.00003770146,0.000035792968,0.00030358374,0.00021219908,0.000008807802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006680471,0.00008924527,0.079197735,0.0057207765,0.00004712653,0.0000031216807,0.002644676,0.6845847,0.2231278,0.000040985047,0.000491725,0.0033840772],"study_design_scores_gemma":[0.0006417696,0.00036721822,0.00054564496,0.00029118574,0.000017609003,0.000012707452,0.0004714555,0.92153305,0.074187644,4.307297e-7,0.0017953283,0.00013594546],"about_ca_topic_score_codex":0.00006580559,"about_ca_topic_score_gemma":0.000020487787,"teacher_disagreement_score":0.23694837,"about_ca_system_score_codex":0.00004392649,"about_ca_system_score_gemma":0.00014385919,"threshold_uncertainty_score":0.6654155},"labels":[],"label_agreement":null},{"id":"W3012879287","doi":"10.1186/s12859-020-3368-2","title":"GenEpi: gene-based epistasis discovery using machine learning","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China; Eisai; U.S. National Library of Medicine; IXICO; Northern California Institute for Research and Education; Ministry of Science and Technology, Taiwan; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Scheme for Promotion of Academic and Research Collaboration; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; National Science Foundation","keywords":"Epistasis; Genome-wide association study; Computational biology; Computer science; Machine learning; Biology; Artificial intelligence; Genetics; Gene; Single-nucleotide polymorphism; Genotype","score_opus":0.0393174571091678,"score_gpt":0.26343535917751904,"score_spread":0.22411790206835125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012879287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38904077,0.00034939044,0.6097768,0.00025274899,0.00007494613,0.00012889972,0.00006568719,0.000025545542,0.00028521396],"genre_scores_gemma":[0.56286865,0.00010709355,0.43325463,0.0026536619,0.00027453093,0.000008514164,0.0006600325,0.000032446074,0.0001404256],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988938,0.00008907586,0.00042270124,0.00018322923,0.000115282484,0.00029591713],"domain_scores_gemma":[0.9993355,0.000033294462,0.00023386403,0.0002141355,0.00005720263,0.0001259658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022576156,0.00017367474,0.00021250479,0.000032750504,0.00014853584,0.000042192718,0.0001764761,0.00017176368,0.00001692376],"category_scores_gemma":[0.0004467015,0.00016280607,0.00014323917,0.00012238575,0.000054691158,0.000008991657,0.00011694086,0.0001204061,0.00002978503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015632491,0.00008244136,0.5322097,0.0002937964,0.00018761549,0.0000029485486,0.00038747923,0.38985446,0.071338415,0.000096509204,0.0024503192,0.0029400017],"study_design_scores_gemma":[0.00059290964,0.00020925375,0.004309547,0.0000064442315,0.000043726624,0.0000067423,0.00015431769,0.9684915,0.012396127,0.000015069988,0.013488209,0.00028615436],"about_ca_topic_score_codex":0.00002724251,"about_ca_topic_score_gemma":0.00002095316,"teacher_disagreement_score":0.578637,"about_ca_system_score_codex":0.00002268675,"about_ca_system_score_gemma":0.00015852977,"threshold_uncertainty_score":0.6639039},"labels":[],"label_agreement":null},{"id":"W3014189804","doi":"10.1186/s12859-020-3415-z","title":"Visualizing metabolic network dynamics through time-series metabolomic data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institutes of Health; Novo Nordisk; National Institute of General Medical Sciences; Landspítali Háskólasjúkrahús; Háskóli Íslands; National Center for Advancing Translational Sciences; Danmarks Tekniske Universitet; Eberhard Karls Universität Tübingen; Novo Nordisk Fonden; Google; Deutsches Zentrum für Infektionsforschung; Deutsche Forschungsgemeinschaft","keywords":"Visualization; Metabolic network; Metabolomics; Computer science; Context (archaeology); Metabolome; Data visualization; Big data; Data science; Data mining; Computational biology; Bioinformatics; Biology","score_opus":0.039005607178237194,"score_gpt":0.2777569274503506,"score_spread":0.23875132027211338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014189804","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1005889,0.052195538,0.78263193,0.0037806572,0.002125256,0.0022507815,0.0033830658,0.00052664697,0.052517217],"genre_scores_gemma":[0.019459235,0.012144656,0.94986314,0.005896645,0.002424321,0.000040081028,0.0073781135,0.00015207908,0.0026417421],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982382,0.000055538738,0.00057918654,0.0003962728,0.00022469029,0.0005060825],"domain_scores_gemma":[0.9985426,0.000025188952,0.00028039806,0.0009419117,0.00006903198,0.00014085835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030342973,0.00032625822,0.000493189,0.000028048504,0.00026039098,0.00007442242,0.00079976756,0.00016075802,0.00007485299],"category_scores_gemma":[0.0003013329,0.0002919759,0.00012903706,0.00030563446,0.00013059018,0.00004961309,0.0019100604,0.00012806758,0.0002258473],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023604252,0.0003679451,0.018558616,0.0014868208,0.004941373,0.000015566997,0.003201111,0.008632762,0.069944456,0.108822934,0.77014637,0.011521647],"study_design_scores_gemma":[0.00081906933,0.00022191026,0.0007012163,0.000010313245,0.00026095536,0.00002572342,0.00046790234,0.1535575,0.0067221634,0.00025125654,0.8362809,0.0006811145],"about_ca_topic_score_codex":0.0000060671014,"about_ca_topic_score_gemma":0.000059150283,"teacher_disagreement_score":0.1672312,"about_ca_system_score_codex":0.000016651853,"about_ca_system_score_gemma":0.00009016339,"threshold_uncertainty_score":0.9999532},"labels":[],"label_agreement":null},{"id":"W3020323696","doi":"10.1186/s12859-019-3311-6","title":"TooT-T: discrimination of transport proteins from non-transport proteins","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Computational biology; Classifier (UML); Membrane protein; Membrane transport protein; Protein function prediction; Computer science; Function (biology); Protein sequencing; Transport protein; Protein function; Artificial intelligence; Machine learning; Membrane; Bioinformatics; Chemistry; Biology; Peptide sequence; Biochemistry; Genetics; Gene","score_opus":0.014126327398125518,"score_gpt":0.2362567035197294,"score_spread":0.22213037612160388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020323696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31800786,0.000051896244,0.6723864,0.0002702119,0.00013243298,0.0012746176,0.00035701334,0.000063681015,0.0074558696],"genre_scores_gemma":[0.67170084,0.00003936114,0.32540527,0.00048832747,0.00023839848,0.000053832726,0.0018831656,0.000039682745,0.0001511163],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981178,0.0000243749,0.000945591,0.00020982506,0.00040481283,0.00029759848],"domain_scores_gemma":[0.9987331,0.000013934032,0.00045835922,0.00047997132,0.0001359935,0.0001786249],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019374608,0.000296921,0.00033645588,0.00005701087,0.00007805634,0.000017542801,0.0004401636,0.00026390605,0.00006526803],"category_scores_gemma":[0.00013639554,0.00027040442,0.00019657185,0.0001910599,0.0001222129,0.000037669924,0.00007201303,0.00022289918,0.000043569526],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034611726,0.0017233787,0.4227405,0.024563117,0.0014054633,0.000026405978,0.08017759,0.055994544,0.36560264,0.0027713487,0.010253275,0.03128059],"study_design_scores_gemma":[0.005233729,0.0029300656,0.10443992,0.0004957676,0.00038156196,0.000019623825,0.00344313,0.5330232,0.294866,0.00014866289,0.05295897,0.0020593854],"about_ca_topic_score_codex":0.00006774094,"about_ca_topic_score_gemma":0.00009524088,"teacher_disagreement_score":0.47702864,"about_ca_system_score_codex":0.00001456324,"about_ca_system_score_gemma":0.00020105112,"threshold_uncertainty_score":0.9999748},"labels":[],"label_agreement":null},{"id":"W3021761165","doi":"10.1186/s12859-020-3441-x","title":"Intrinsic limitations in mainstream methods of identifying network motifs in biology","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Young Scientists Fund; Medical Research Council; National Health and Medical Research Council; National Natural Science Foundation of China; National Science Foundation","keywords":"Motif (music); Biological network; Mainstream; Spurious relationship; Computational biology; Data science; Network motif; Systems biology; Computer science; Gene regulatory network; Underpinning; Network analysis; Identification (biology); Synthetic biology; Biology; Machine learning; Genetics; Gene","score_opus":0.06509519079156656,"score_gpt":0.3180088046397023,"score_spread":0.25291361384813577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021761165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09621565,0.0010682355,0.8922514,0.000256171,0.00034455155,0.00064044684,0.000035675166,0.0000234482,0.009164445],"genre_scores_gemma":[0.47040176,0.00037846476,0.5282568,0.0005714848,0.00015109983,0.000017195503,0.00018057873,0.000017203307,0.000025466852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984401,0.00008959211,0.0009050176,0.00014894403,0.000070542665,0.0003458141],"domain_scores_gemma":[0.9992459,0.0000798202,0.00026834133,0.00026355535,0.00005096568,0.00009144694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005552295,0.00016958144,0.0002978799,0.00010244601,0.00003071086,0.0000201892,0.00027166092,0.00023674004,0.000007377669],"category_scores_gemma":[0.00026102507,0.0001677435,0.00009276008,0.00044522827,0.00008859978,0.000015264171,0.00022048791,0.00018362439,0.000011737648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005503951,0.00036141172,0.17375718,0.0022322782,0.00026212723,0.0000058949813,0.011522806,0.23673846,0.014507599,0.02369418,0.006358154,0.5300095],"study_design_scores_gemma":[0.0037516137,0.0007281558,0.025599988,0.0002072166,0.000043582186,0.00001664245,0.0040130066,0.9324831,0.004814423,0.0077417768,0.019664876,0.0009356395],"about_ca_topic_score_codex":0.000012155056,"about_ca_topic_score_gemma":0.00025224715,"teacher_disagreement_score":0.69574463,"about_ca_system_score_codex":0.000020776852,"about_ca_system_score_gemma":0.00011239515,"threshold_uncertainty_score":0.68403816},"labels":[],"label_agreement":null},{"id":"W3027464055","doi":"10.1186/s12859-020-3494-x","title":"MEPHAS: an interactive graphical user interface for medical and pharmaceutical statistical analysis with R and Shiny","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Chinese Government Scholarship; China Scholarship Council","keywords":"Computer science; Graphical user interface; Visualization; Interface (matter); Analytics; Workstation; User interface; Scatter plot; OS X; Data visualization; Statistical analysis; Data mining; Software; Programming language; Machine learning; Operating system; Statistics","score_opus":0.029111670027291998,"score_gpt":0.333294396465094,"score_spread":0.30418272643780203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027464055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012579864,0.000035667792,0.9853714,0.0015203535,0.000026136026,0.00022110208,0.00009090769,0.0000934402,0.00006110046],"genre_scores_gemma":[0.3026122,0.000026330228,0.695275,0.0019534952,0.000035278645,0.0000169962,0.000065627195,0.000010227695,0.0000048790707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981732,0.00008385466,0.0004927076,0.00038315373,0.000558544,0.00030858567],"domain_scores_gemma":[0.998018,0.0005906653,0.00012698851,0.00034788836,0.00010582655,0.0008105864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046183757,0.00021721823,0.00043454484,0.000184128,0.000098126606,0.00043914863,0.0006324287,0.00010033212,0.000041985884],"category_scores_gemma":[0.00044264004,0.00015665503,0.00006166896,0.00077899994,0.0002811788,0.0014921533,0.00043572977,0.00027972163,0.000008012543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00478821,0.0018667469,0.2148993,0.0037924869,0.014312385,0.00022055193,0.060897276,0.0024996747,0.00010580808,0.40128484,0.014227121,0.28110558],"study_design_scores_gemma":[0.00096041936,0.00039615034,0.0027990595,0.000016098751,0.0005044037,0.000032996097,0.0004674281,0.9927276,0.000049007365,0.00018759604,0.0016313719,0.00022791525],"about_ca_topic_score_codex":0.000008546842,"about_ca_topic_score_gemma":0.00008964643,"teacher_disagreement_score":0.9902279,"about_ca_system_score_codex":0.000015688425,"about_ca_system_score_gemma":0.00009558841,"threshold_uncertainty_score":0.6388207},"labels":[],"label_agreement":null},{"id":"W3028589227","doi":"10.1186/s12859-020-3535-5","title":"RintC: fast and accuracy-aware decomposition of distributions of RNA secondary structures with extended logsumexp","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Ministry of Education, Culture, Sports, Science and Technology; Japan Society for the Promotion of Science; Institute of Genetics; Artificial Intelligence Research Center; National Institute of Advanced Industrial Science and Technology","keywords":"Computation; Stability (learning theory); Computer science; Constraint (computer-aided design); RNA; Numerical analysis; Algorithm; Decomposition; Computational complexity theory; Statistical physics; Bioinformatics; Biological system; Mathematics; Biology; Physics; Ecology; Machine learning; Genetics","score_opus":0.01177219424403008,"score_gpt":0.24373674197201275,"score_spread":0.23196454772798267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028589227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43591434,0.00021138352,0.562546,0.00007536461,0.000027204354,0.00026190642,0.00043365252,0.000010969034,0.0005191529],"genre_scores_gemma":[0.933746,0.000054637698,0.06586753,0.000063954736,0.00002519165,0.0000058649634,0.00022404392,0.000007396205,0.0000053898502],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994016,0.000021416388,0.00027926988,0.00009563728,0.000097616845,0.00010445146],"domain_scores_gemma":[0.9994411,0.00001949179,0.00022103864,0.00017244075,0.00007559823,0.00007034327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005252766,0.000110982066,0.00015885604,0.000019934818,0.000043313627,0.000011981582,0.00011378971,0.00009107182,0.000025195573],"category_scores_gemma":[0.000052444855,0.00008820738,0.00004549836,0.000058245732,0.00008848411,0.000011696012,0.000077246645,0.000051006056,0.0000010833219],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059454504,0.00006795868,0.0011313058,0.0014077033,0.00016521133,0.0000012693365,0.0007413823,0.00026820786,0.9383679,0.0024865363,0.000477057,0.05429093],"study_design_scores_gemma":[0.0005259893,0.0005340223,0.0025066272,0.000036871737,0.000035997327,0.00001763516,0.00056665647,0.002882286,0.99206537,0.00029581288,0.0003876677,0.0001450783],"about_ca_topic_score_codex":0.0000034113239,"about_ca_topic_score_gemma":0.0000059529643,"teacher_disagreement_score":0.49783164,"about_ca_system_score_codex":0.000003279695,"about_ca_system_score_gemma":0.00007058892,"threshold_uncertainty_score":0.35969928},"labels":[],"label_agreement":null},{"id":"W3030951244","doi":"10.1186/s12859-020-03549-8","title":"BEAVR: a browser-based tool for the exploration and visualization of RNA-seq data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; London Health Sciences Centre; Western University","funders":"Canadian Institutes of Health Research; Institute of Cancer Research; London Health Sciences Centre","keywords":"Computer science; Visualization; Table (database); Documentation; Cluster analysis; Data mining; Data visualization; Unix; RNA-Seq; Data science; Software; Information retrieval; Machine learning; Programming language; Biology; Transcriptome","score_opus":0.09356307070348382,"score_gpt":0.2861941582142696,"score_spread":0.19263108751078575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030951244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019185374,0.00015869447,0.9797058,0.00032762837,0.00006265098,0.0003551227,0.00014226962,0.000010371782,0.000052069667],"genre_scores_gemma":[0.86529636,0.0003678999,0.1282411,0.0024115152,0.0003202924,0.000039590865,0.003248118,0.00003556574,0.00003954097],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946624,0.000012489624,0.0002539698,0.00010014385,0.00008354883,0.000083625295],"domain_scores_gemma":[0.99948573,0.000036205143,0.00010862577,0.00027169654,0.00006741278,0.000030312873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013624848,0.00008080864,0.000086757645,0.000012526401,0.00006121108,0.00003089424,0.00019625004,0.00007002828,0.0000020849354],"category_scores_gemma":[0.00017658119,0.00006106333,0.00003219896,0.000061265455,0.00004847132,0.000019939303,0.00005690782,0.000024838904,9.46203e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036790897,0.00055911683,0.021194266,0.0075895484,0.0004851976,5.535359e-7,0.0073890863,0.032730542,0.75113165,0.0048463163,0.041570373,0.12882423],"study_design_scores_gemma":[0.0008834679,0.000282764,0.00012732105,0.0000132764,0.000047157377,5.294397e-7,0.00023156003,0.91899365,0.065674126,0.000026946276,0.013604039,0.00011518356],"about_ca_topic_score_codex":0.0000045326974,"about_ca_topic_score_gemma":0.00001650869,"teacher_disagreement_score":0.8862631,"about_ca_system_score_codex":0.0000022880142,"about_ca_system_score_gemma":0.00006866983,"threshold_uncertainty_score":0.24900903},"labels":[],"label_agreement":null},{"id":"W3037659634","doi":"10.1186/s12859-020-03577-4","title":"NASQAR: a web-based platform for high-throughput sequencing data analysis and visualization","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Variety (cybernetics); Visualization; Toolbox; Source code; Software; World Wide Web; Data science; Data mining; Programming language; Artificial intelligence","score_opus":0.05769829710894775,"score_gpt":0.2836874729498316,"score_spread":0.22598917584088385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037659634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25850657,0.00032206124,0.73999196,0.00012124635,0.00005382319,0.00031375358,0.00055659295,0.000011390975,0.00012257787],"genre_scores_gemma":[0.7873164,0.00012831159,0.20986745,0.0010144196,0.00012735154,0.000015258049,0.0015044262,0.000015054363,0.000011367296],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992121,0.000008618761,0.00029667723,0.00022515233,0.00008815341,0.00016930088],"domain_scores_gemma":[0.9993202,0.000028277975,0.00013400547,0.00037131985,0.00006922779,0.00007697508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015115677,0.00013893112,0.00019112285,0.000046070447,0.00010910079,0.000047634334,0.0002087903,0.00008983634,0.0000029590244],"category_scores_gemma":[0.00013714406,0.00012794629,0.000058037655,0.00019324968,0.000046448324,0.00000454024,0.00022529667,0.000028256267,0.0000021459552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002114178,0.00035983644,0.19511768,0.00809827,0.011796568,0.000005965802,0.009757018,0.09863315,0.5747739,0.016003776,0.044390112,0.038949553],"study_design_scores_gemma":[0.0010947068,0.0002648441,0.0013424639,0.0000063556126,0.00041670876,0.0000013187295,0.00043135215,0.9743395,0.012624029,0.000075415875,0.00913834,0.00026495475],"about_ca_topic_score_codex":0.000011619008,"about_ca_topic_score_gemma":0.00009415982,"teacher_disagreement_score":0.8757064,"about_ca_system_score_codex":0.000010018609,"about_ca_system_score_gemma":0.00013021704,"threshold_uncertainty_score":0.52174985},"labels":[],"label_agreement":null},{"id":"W3040929481","doi":"10.1186/s12859-023-05509-4","title":"Cross-study analyses of microbial abundance using generalized common factor methods","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Nova Scotia Health Research Foundation","keywords":"Metagenomics; Interpretability; Computer science; Leverage (statistics); Microbiome; Bootstrapping (finance); Abundance (ecology); Covariance; Computational biology; Projection (relational algebra); Data mining; Machine learning; Data science; Biology; Ecology; Bioinformatics; Statistics; Mathematics; Algorithm; Genetics; Econometrics","score_opus":0.14838727491041914,"score_gpt":0.47929714693268616,"score_spread":0.330909872022267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040929481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97782195,0.000113508744,0.021272145,0.000005509624,0.00020834961,0.00030631674,0.00012275267,0.000028204791,0.00012129231],"genre_scores_gemma":[0.6413873,0.000095755415,0.3573847,0.00016679242,0.00014072451,0.0000073340047,0.0003211176,0.00003617723,0.0004601091],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986936,0.000115602386,0.00062709686,0.00015912626,0.00010406801,0.00030054763],"domain_scores_gemma":[0.9990809,0.000026034277,0.0002839493,0.00043378782,0.0001035118,0.00007184942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039128747,0.00017375607,0.00031450661,0.00011674412,0.00013037772,0.000042859552,0.00024253257,0.00014647753,0.000025414978],"category_scores_gemma":[0.00006547164,0.0001550879,0.00014298245,0.00031918284,0.000094742536,0.000009658325,0.00018971854,0.00008061509,0.00001853743],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057306526,0.00007267472,0.034068443,0.00020951717,0.0000657932,5.296328e-7,0.0004952941,0.0013829498,0.9626474,0.0000055262244,0.00037012945,0.000624483],"study_design_scores_gemma":[0.0029400834,0.00059714937,0.14216828,0.000049003578,0.00011589366,0.00002643626,0.0011298872,0.053815622,0.7931037,0.000019314699,0.0053978874,0.00063672743],"about_ca_topic_score_codex":0.00013782225,"about_ca_topic_score_gemma":0.00008939352,"teacher_disagreement_score":0.33643463,"about_ca_system_score_codex":0.00001893712,"about_ca_system_score_gemma":0.00015342922,"threshold_uncertainty_score":0.6324301},"labels":[],"label_agreement":null},{"id":"W3041251855","doi":"10.1186/s12859-020-03595-2","title":"Efficient implied alignment","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Robert J. Kleberg, Jr. and Helen C. Kleberg Foundation; Defense Sciences Office, DARPA; Defense Advanced Research Projects Agency; McGill University","keywords":"Algorithm; Tree traversal; Artificial intelligence; Computer science","score_opus":0.03399497211501743,"score_gpt":0.23570747319662025,"score_spread":0.20171250108160282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041251855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014409292,0.000031323343,0.99131256,0.0015244243,0.00006812489,0.00007690925,0.000010611147,0.0001505188,0.0053845956],"genre_scores_gemma":[0.19253479,0.00000891044,0.80220354,0.005091549,0.000058643483,0.000006369551,0.000015690182,0.0000034789075,0.00007705772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990403,0.000012583676,0.00029930414,0.00013704885,0.0002939338,0.00021684768],"domain_scores_gemma":[0.9992954,0.00005878328,0.00009132569,0.00034022675,0.000025614803,0.0001886601],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012862879,0.00009585734,0.00014447879,0.00007256016,0.00007001584,0.000121607954,0.0007693637,0.000037347556,0.00006112923],"category_scores_gemma":[0.000101289974,0.00006713211,0.000080952545,0.001014281,0.000026315558,0.00010741558,0.00046951606,0.000060870465,0.00095433387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025728423,0.00038318522,0.0023725517,0.00029302563,0.0001652587,0.000020983023,0.0073528946,0.119470194,0.00009529236,0.5999796,0.047827564,0.22201376],"study_design_scores_gemma":[0.0001629017,0.00005988204,0.00059096375,0.0000015671869,0.000007856786,0.00000223042,0.00011328076,0.9859258,0.000093532326,0.0002558278,0.012673667,0.00011250454],"about_ca_topic_score_codex":0.0000029542157,"about_ca_topic_score_gemma":4.0116606e-7,"teacher_disagreement_score":0.8664556,"about_ca_system_score_codex":0.000016362945,"about_ca_system_score_gemma":0.000026380274,"threshold_uncertainty_score":0.9998235},"labels":[],"label_agreement":null},{"id":"W3047407562","doi":"10.1186/s12859-020-03697-x","title":"GPU accelerated adaptive banded event alignment for rapid comparative nanopore signal analysis","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; University of Toronto; Ontario Institute for Cancer Research","funders":"University of Peradeniya; Government of Ontario; Government of Canada; Ontario Institute for Cancer Research; Genome Canada; Ontario Genomics; Innopolis University; University of New South Wales; Nvidia","keywords":"Computer science; Parallel computing; Overhead (engineering); Nanopore sequencing; Software; General-purpose computing on graphics processing units; Computational science; DNA sequencing; Graphics; DNA","score_opus":0.07105467821933206,"score_gpt":0.2832542641391247,"score_spread":0.21219958591979263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047407562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39083645,0.0013903894,0.60277116,0.00036283766,0.00016000107,0.0016892978,0.0007911671,0.000022297048,0.0019764171],"genre_scores_gemma":[0.95280886,0.00009679054,0.045791447,0.0006281669,0.00012238634,0.00006936936,0.00040311698,0.000011659342,0.000068182766],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892277,0.00002933424,0.0004314678,0.00021997496,0.0001388974,0.00025754233],"domain_scores_gemma":[0.9992842,0.000027244994,0.00020422242,0.00018896339,0.00016313435,0.00013221352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116426396,0.00021996467,0.00034326152,0.0000440285,0.00013141362,0.000034222834,0.00019016667,0.00009980241,0.00003164288],"category_scores_gemma":[0.000019178855,0.00019086643,0.000265024,0.00022092425,0.0000615088,0.000002111126,0.00012421882,0.000047288806,0.000011170609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061226757,0.0009812766,0.017518321,0.0009730896,0.029086793,0.0000049540045,0.037877697,0.26895943,0.53680116,0.002472599,0.08505375,0.014148223],"study_design_scores_gemma":[0.0033828146,0.002917829,0.004560674,0.000014125729,0.0012261843,0.00000291292,0.007757191,0.6984217,0.23401801,0.00012636451,0.046594884,0.0009772889],"about_ca_topic_score_codex":0.0000038086455,"about_ca_topic_score_gemma":0.000021829343,"teacher_disagreement_score":0.56197244,"about_ca_system_score_codex":0.000016633678,"about_ca_system_score_gemma":0.000091997186,"threshold_uncertainty_score":0.7783307},"labels":[],"label_agreement":null},{"id":"W3049762379","doi":"10.1186/s12859-020-03704-1","title":"Evaluation of variant calling tools for large plant genome re-sequencing","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; Genome Canada","keywords":"Concordance; Biology; Genetics; Germplasm; Genotyping; Genome; Computational biology; 1000 Genomes Project; SNP genotyping; Reference genome; Single-nucleotide polymorphism; Genotype; Gene","score_opus":0.16774170175173803,"score_gpt":0.2719729421515648,"score_spread":0.10423124039982679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049762379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9567789,0.00029309504,0.038248505,0.0005082319,0.0001576184,0.0008722058,0.0010050212,0.000040718925,0.0020957305],"genre_scores_gemma":[0.97709376,0.000033095745,0.021802695,0.0003959455,0.00023110626,0.000017037995,0.00041964944,8.3034104e-7,0.000005875596],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991717,0.000033849938,0.000309158,0.000081410326,0.00023203125,0.00017189924],"domain_scores_gemma":[0.9994974,0.00013167663,0.00011921523,0.000034183337,0.00015786466,0.000059657206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009075899,0.000074522075,0.00013775694,0.000006006107,0.00008312725,0.000035018358,0.00012115491,0.00007392212,0.00009350966],"category_scores_gemma":[0.00021058826,0.000030089039,0.00006699009,0.000097364114,0.000011217534,0.00008774934,0.00003218585,0.000040992607,0.000009189063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021253715,0.00014691302,0.0011152028,0.000663313,0.00010123221,0.0000036751712,0.009826528,0.0065893345,0.82454795,0.008252063,0.0010752237,0.147466],"study_design_scores_gemma":[0.00055828184,0.00059376174,0.0027740947,0.000023896017,0.00011243127,0.0000065779473,0.0026315674,0.97852916,0.0066578942,0.00066321914,0.007234874,0.00021427065],"about_ca_topic_score_codex":0.000005943801,"about_ca_topic_score_gemma":0.000083696286,"teacher_disagreement_score":0.9719398,"about_ca_system_score_codex":0.000015359732,"about_ca_system_score_gemma":0.000039446822,"threshold_uncertainty_score":0.122699544},"labels":[],"label_agreement":null},{"id":"W3081286367","doi":"10.1186/s12859-021-03997-w","title":"geneRFinder: gene finding in distinct metagenomic data complexities","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Vale Canada Limited","keywords":"Metagenomics; Benchmark (surveying); McNemar's test; Gene prediction; Computational biology; Gene Annotation; Computer science; Data mining; Annotation; Biology; Gene; Machine learning; Artificial intelligence; Statistics; Genetics; Genome; Mathematics; Geography","score_opus":0.08674744853583267,"score_gpt":0.28577810191656,"score_spread":0.19903065338072734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081286367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96983254,0.0046825227,0.019208983,0.000075440745,0.00032874316,0.0001901044,0.0005444024,0.000007748411,0.0051295045],"genre_scores_gemma":[0.80299586,0.000722028,0.19314487,0.00034395186,0.00026780227,0.000013507956,0.0018944036,0.000030477997,0.0005871016],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988865,0.000037460777,0.00041355498,0.00025958152,0.000109928726,0.00029293707],"domain_scores_gemma":[0.99888957,0.000026051483,0.0001064574,0.00086826424,0.00005324275,0.000056422356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023598602,0.00017610381,0.00021621193,0.00004633906,0.00010033437,0.000054958884,0.00041365606,0.00009192189,0.000021519196],"category_scores_gemma":[0.000109970875,0.00017450497,0.00005943917,0.00010731302,0.00007303165,0.0000031034303,0.00089196727,0.00007242661,0.00002260256],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025432237,0.00062609353,0.3237102,0.0012947472,0.0012613294,0.00007787766,0.0035905933,0.013130737,0.6063212,0.0042539956,0.021424187,0.024054669],"study_design_scores_gemma":[0.0054789945,0.00037944605,0.3045603,0.000101321726,0.00028689107,0.00039608908,0.007158889,0.17685832,0.21690309,0.0017787761,0.2832711,0.002826752],"about_ca_topic_score_codex":0.000016808133,"about_ca_topic_score_gemma":0.00059000327,"teacher_disagreement_score":0.38941813,"about_ca_system_score_codex":0.00001808496,"about_ca_system_score_gemma":0.00018954382,"threshold_uncertainty_score":0.71161056},"labels":[],"label_agreement":null},{"id":"W3088926825","doi":"10.1186/s12859-020-03729-6","title":"Theoretical characterisation of strand cross-correlation in ChIP-seq","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Canon Medical Systems Corporation","keywords":"Chip; Correlation; Cross-correlation; Consistency (knowledge bases); Metric (unit); Independence (probability theory); Noise (video); Measure (data warehouse); Correlation coefficient; Sensitivity (control systems); Computer science; Algorithm; Mathematics; Statistics; Data mining; Telecommunications; Engineering; Artificial intelligence; Electronic engineering","score_opus":0.009160658078495428,"score_gpt":0.23414556913504603,"score_spread":0.2249849110565506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088926825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9601181,0.000021340831,0.038295005,0.00005051268,0.00005016905,0.00013904119,0.000032663957,0.000005800727,0.0012873425],"genre_scores_gemma":[0.9869431,0.00003197078,0.012572423,0.00013270757,0.000050141283,0.0000031293005,0.00025151766,0.000008769288,0.0000062258773],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930674,0.000014179842,0.00038808447,0.000088153116,0.000088772445,0.00011408087],"domain_scores_gemma":[0.99962723,0.000009493732,0.00013981071,0.00013651761,0.00003800339,0.000048921487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119278455,0.00008926617,0.00011335846,0.000023795274,0.000019404075,0.000021981708,0.00010981075,0.00012406454,0.000030944328],"category_scores_gemma":[0.00008406363,0.0000853944,0.000050578743,0.00006889462,0.00008527101,0.000008450797,0.00004918216,0.000064233594,0.000010043268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009227814,0.00028820732,0.6301635,0.001627985,0.00009095902,0.0000019473212,0.006770745,0.04582014,0.24042927,0.06412591,0.00017375412,0.009584825],"study_design_scores_gemma":[0.00092748157,0.00021962446,0.10710457,0.000016832459,0.000009244085,0.0000031986895,0.00022814299,0.878683,0.011757256,0.00074499956,0.00013287543,0.00017282715],"about_ca_topic_score_codex":0.0000010757146,"about_ca_topic_score_gemma":0.0000046758905,"teacher_disagreement_score":0.8328628,"about_ca_system_score_codex":0.000007497169,"about_ca_system_score_gemma":0.0000514647,"threshold_uncertainty_score":0.34822828},"labels":[],"label_agreement":null},{"id":"W3091870415","doi":"10.1186/s12859-020-03747-4","title":"Application of OU processes to modelling temporal dynamics of the human microbiome, and calculating optimal sampling schemes","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microbiome; Stability (learning theory); Computer science; Dynamics (music); Series (stratigraphy); Biology; Machine learning; Bioinformatics; Psychology","score_opus":0.03374253322409365,"score_gpt":0.28624995014285887,"score_spread":0.2525074169187652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091870415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49892825,0.0000753908,0.50058,0.000114110495,0.00000789058,0.00021792715,0.00003541963,0.0000044286558,0.000036562484],"genre_scores_gemma":[0.757979,0.000013870601,0.24174468,0.000117445226,0.00002557623,0.0000034180441,0.00009910513,0.000008001386,0.000008914224],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933946,0.000009386678,0.0003606366,0.00009938489,0.00006488744,0.00012625735],"domain_scores_gemma":[0.9994424,0.000008029953,0.00021550474,0.00015230585,0.00012302172,0.000058741352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010366168,0.00008742633,0.00012620025,0.000024827823,0.000097378805,0.0000131883835,0.00014467494,0.00008501906,6.433578e-7],"category_scores_gemma":[0.00005104065,0.000073200354,0.00003502164,0.000145858,0.00006233091,0.000006323899,0.0001316795,0.00005286689,4.9469634e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006606556,0.00006862632,0.048770465,0.0067857793,0.000049190752,4.4039325e-8,0.0036938172,0.08450715,0.8522203,0.00162987,0.00012822454,0.002080475],"study_design_scores_gemma":[0.0006782253,0.00024651375,0.0013631566,0.00019807703,0.000046877438,0.000005699675,0.0022272663,0.8409897,0.14914198,0.000033556636,0.0047108815,0.00035804504],"about_ca_topic_score_codex":0.000029228393,"about_ca_topic_score_gemma":0.00004658705,"teacher_disagreement_score":0.7564826,"about_ca_system_score_codex":0.0000092875935,"about_ca_system_score_gemma":0.0001299878,"threshold_uncertainty_score":0.29850236},"labels":[],"label_agreement":null},{"id":"W3092695394","doi":"10.1186/s12859-020-03794-x","title":"Implementation of homology based and non-homology based computational methods for the identification and annotation of orphan enzymes: using Mycobacterium tuberculosis H37Rv as a case study","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Council of Scientific and Industrial Research, India","keywords":"In silico; Computational biology; Sequence alignment; Annotation; Biology; Genome; Homology (biology); Context (archaeology); Genetics; Mycobacterium tuberculosis; Homology modeling; Bioinformatics; Gene; Peptide sequence; Tuberculosis; Enzyme; Medicine","score_opus":0.027311041487814994,"score_gpt":0.37450429355805614,"score_spread":0.34719325207024115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092695394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47321752,0.000042376072,0.5259826,0.000082795785,0.00003264425,0.0005860032,0.00004797932,0.000004419522,0.000003646812],"genre_scores_gemma":[0.6574883,0.0000047134918,0.34205064,0.00021127702,0.000018318091,0.00002847619,0.00018771953,0.000009615207,9.276677e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986422,0.00016208507,0.00080249755,0.00014646837,0.000112062444,0.00013467763],"domain_scores_gemma":[0.99849826,0.0003277047,0.00067137275,0.0001933943,0.00025560573,0.000053635387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007649722,0.00015250716,0.00022523905,0.00008742083,0.00012487247,0.00003024594,0.000102390266,0.00010367725,0.000007791002],"category_scores_gemma":[0.00029587568,0.0001297127,0.00005693438,0.00014250448,0.00014335106,0.000023613855,0.00007549021,0.00006682085,3.6645525e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021206911,0.00090042397,0.32707265,0.013010406,0.0015883999,0.000014395818,0.053255197,0.27797928,0.21607435,0.00085292995,0.00056462706,0.10656665],"study_design_scores_gemma":[0.0016755149,0.0009967731,0.008183252,0.000009181857,0.00018455392,0.00010634038,0.008591539,0.9616368,0.018397016,0.000023274022,0.00006388743,0.00013186099],"about_ca_topic_score_codex":0.00012561986,"about_ca_topic_score_gemma":0.00004594546,"teacher_disagreement_score":0.6836575,"about_ca_system_score_codex":0.000010698951,"about_ca_system_score_gemma":0.00016692637,"threshold_uncertainty_score":0.5289531},"labels":[],"label_agreement":null},{"id":"W3093072871","doi":"10.1186/s12859-020-03779-w","title":"RepAHR: an improved approach for de novo repeat identification by assembly of the high-frequency reads","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; King Abdullah University of Science and Technology; National Natural Science Foundation of China","keywords":"Sequence assembly; Hybrid genome assembly; Identification (biology); Genome; Computational biology; Reference genome; Computer science; DNA sequencing; DNA microarray; Biology; Genetics; DNA; Gene","score_opus":0.01856362151659104,"score_gpt":0.23638895082227057,"score_spread":0.21782532930567952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093072871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7477105,0.0002992651,0.24998587,0.00021447428,0.00010907961,0.0006912344,0.00051527517,0.0000087762655,0.00046549703],"genre_scores_gemma":[0.83587873,0.000067927394,0.1631136,0.00040755878,0.00010146663,0.000050071827,0.0002757879,0.000016054455,0.00008881408],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999196,0.000025101917,0.00037905632,0.00015680045,0.0000810005,0.00016203073],"domain_scores_gemma":[0.9991405,0.000010571646,0.00024328128,0.00043774594,0.000109044464,0.000058870064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021523662,0.00011449434,0.00012988891,0.000010022513,0.00008499751,0.00001842454,0.00030352492,0.000108903914,6.3530644e-7],"category_scores_gemma":[0.00016839393,0.00008807662,0.0000925809,0.00006968717,0.000058837064,0.000002997387,0.00009424805,0.00004176216,5.575731e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004106795,0.0000387943,0.0016770891,0.00018372605,0.000042189746,1.4482683e-8,0.00046004937,0.0001954635,0.99441403,0.00017099708,0.0021539582,0.0006225943],"study_design_scores_gemma":[0.0012602865,0.00069314387,0.0061439397,0.000009254008,0.00012591964,0.0000100608995,0.0012427983,0.10592114,0.87969863,0.00024607344,0.004236401,0.00041236306],"about_ca_topic_score_codex":0.00001370584,"about_ca_topic_score_gemma":0.000007555544,"teacher_disagreement_score":0.114715435,"about_ca_system_score_codex":0.000010178718,"about_ca_system_score_gemma":0.00008425385,"threshold_uncertainty_score":0.35916603},"labels":[],"label_agreement":null},{"id":"W3093280245","doi":"10.1186/s12859-020-03754-5","title":"LDkit: a parallel computing toolkit for linkage disequilibrium analysis","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics and Developmental Biology, Chinese Academy of Sciences; Chinese Academy of Sciences; Institute of Genetics; National Natural Science Foundation of China","keywords":"Linkage disequilibrium; Graphical user interface; Computer science; Software; Linkage (software); Disequilibrium; Population; Interface (matter); Plot (graphics); Block (permutation group theory); Data mining; Biology; Genetics; Programming language; Single-nucleotide polymorphism; Operating system; Gene; Mathematics; Statistics","score_opus":0.03288581403397207,"score_gpt":0.28002338812433314,"score_spread":0.24713757409036108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093280245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08931624,0.00015774668,0.9086091,0.0006110831,0.0000681408,0.0002810997,0.0000949723,0.000027555741,0.0008340604],"genre_scores_gemma":[0.51830953,0.000043265478,0.47747377,0.0025008821,0.00036989886,0.000020472971,0.0010245885,0.000018010736,0.00023957928],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988934,0.000037581878,0.0004907582,0.00019169989,0.000082896986,0.00030368203],"domain_scores_gemma":[0.9992341,0.00006788586,0.00023006985,0.00024659367,0.00008616585,0.00013520694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002590944,0.00014878443,0.00028900552,0.000042432202,0.000099587865,0.000032133303,0.00021632647,0.00017372925,0.0000145918875],"category_scores_gemma":[0.0005037913,0.00013810753,0.0003059942,0.00023365513,0.00004028227,0.0000049609785,0.00013985753,0.00006315382,0.000030583742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038361366,0.00019558071,0.6020937,0.000989481,0.003535805,0.0000014709967,0.0031938704,0.28811875,0.0050911903,0.0013434117,0.08571301,0.009340099],"study_design_scores_gemma":[0.00064264494,0.00022650271,0.025952699,0.0000034797465,0.00028588765,0.0000013294003,0.00028659048,0.94659007,0.00014885076,0.00005565489,0.025554305,0.00025197968],"about_ca_topic_score_codex":0.000003189377,"about_ca_topic_score_gemma":0.000011010142,"teacher_disagreement_score":0.65847135,"about_ca_system_score_codex":0.000009841263,"about_ca_system_score_gemma":0.00007043957,"threshold_uncertainty_score":0.56318617},"labels":[],"label_agreement":null},{"id":"W3094445727","doi":"10.1186/s12859-020-03815-9","title":"MetaLAFFA: a flexible, end-to-end, distributed computing-compatible metagenomic functional annotation pipeline","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; University of Washington; National Institute on Aging; National Institutes of Health; Tel Aviv University; Israel Science Foundation","keywords":"Metagenomics; Computer science; Annotation; Pipeline (software); Personalization; Interoperability; Pipeline transport; Database; Data mining; World Wide Web; Operating system; Artificial intelligence; Engineering; Biology","score_opus":0.03207415185522694,"score_gpt":0.24420367441701127,"score_spread":0.21212952256178433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094445727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23613551,0.0004654896,0.76066995,0.00049372524,0.00026230983,0.00040595833,0.000458372,0.000030097173,0.0010785972],"genre_scores_gemma":[0.89311934,0.000047032558,0.103287816,0.0017269125,0.00039376586,0.000015040879,0.001246747,0.00002527761,0.00013808334],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986975,0.000032048978,0.0005178601,0.000255423,0.00019604947,0.00030107697],"domain_scores_gemma":[0.99917966,0.000028831424,0.00018114038,0.00025520002,0.00015698359,0.00019820656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001785867,0.00024239127,0.00026915633,0.000055284723,0.00015734967,0.00005741686,0.00020865066,0.00009264372,0.00004551914],"category_scores_gemma":[0.00012877384,0.00022862166,0.00014417597,0.00025183588,0.00005638326,0.0000037458567,0.0002485591,0.000086121094,0.00014897928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011523566,0.00037851336,0.022231506,0.0007747287,0.0013055812,0.00000450996,0.00393587,0.351907,0.49283305,0.001528637,0.097138904,0.026809324],"study_design_scores_gemma":[0.0036250108,0.0012612285,0.05597932,0.000028199476,0.0003614467,0.000043922995,0.0020747208,0.5750864,0.08473788,0.00015160386,0.27514648,0.0015037584],"about_ca_topic_score_codex":0.0000083957475,"about_ca_topic_score_gemma":0.000014760631,"teacher_disagreement_score":0.65738213,"about_ca_system_score_codex":0.000019454164,"about_ca_system_score_gemma":0.00011181211,"threshold_uncertainty_score":0.9322921},"labels":[],"label_agreement":null},{"id":"W3100449126","doi":"10.1186/s12859-020-03837-3","title":"Speeding up the core algorithm for the dual calculation of minimal cut sets in large metabolic networks","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Benchmark (surveying); Computation; Algorithm; Dimension (graph theory); Flexibility (engineering); Lemma (botany); Dual (grammatical number); Mathematical optimization; Theoretical computer science; Mathematics","score_opus":0.02615582391004195,"score_gpt":0.25906384041751035,"score_spread":0.2329080165074684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100449126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15381168,0.0019358527,0.84241176,0.0003335983,0.0006888642,0.00067099434,0.000091932714,0.000016528675,0.000038770268],"genre_scores_gemma":[0.93618584,0.00054277125,0.060742028,0.00050127425,0.0015321852,0.000032484062,0.00031650026,0.000027140877,0.00011980209],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993461,0.000011907357,0.0002969693,0.00009313388,0.00007976717,0.00017213741],"domain_scores_gemma":[0.9996253,0.000016106536,0.000114993505,0.00015813099,0.00005697112,0.000028470635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031879471,0.000102448306,0.00012706761,0.000018904077,0.000060583527,0.0000154526,0.00012399089,0.000092457565,0.0000021710157],"category_scores_gemma":[0.0001259958,0.000062738094,0.000080772355,0.00015023524,0.00003473803,0.0000067724704,0.000060226626,0.00008479159,0.0000012958935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082135893,0.00026526419,0.006330168,0.0012275281,0.00075759593,0.0000011956633,0.01278202,0.27225775,0.30879748,0.003514418,0.050665166,0.34258005],"study_design_scores_gemma":[0.0005305209,0.000058688925,0.0016864585,0.000009041346,0.000041437124,0.0000069251137,0.0003973903,0.9456441,0.017219268,0.000002877845,0.03430296,0.00010034799],"about_ca_topic_score_codex":0.0000051892703,"about_ca_topic_score_gemma":0.000012606225,"teacher_disagreement_score":0.78237414,"about_ca_system_score_codex":0.0000033401623,"about_ca_system_score_gemma":0.000026702826,"threshold_uncertainty_score":0.25583854},"labels":[],"label_agreement":null},{"id":"W3101058692","doi":"10.1186/s12859-020-03734-9","title":"MADA: a web service for analysing DNA methylation array data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Key Research and Development Program of China; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"DNA methylation; Methylation; Workflow; Bioconductor; Computer science; Computational biology; Visualization; Bioinformatics; Data mining; Biology; Database; Genetics; Gene; Gene expression","score_opus":0.08744543724510032,"score_gpt":0.3051757837573827,"score_spread":0.21773034651228237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101058692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042800818,0.00045382502,0.9547622,0.0005802632,0.00009331722,0.00034316105,0.00023654182,0.00002518776,0.0007046884],"genre_scores_gemma":[0.37143636,0.00022477737,0.6179187,0.0021701143,0.00075523544,0.000022983002,0.0073410063,0.00004727854,0.00008349736],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999021,0.000028067356,0.00039007806,0.00022525247,0.00014758256,0.00018803604],"domain_scores_gemma":[0.998976,0.000032233962,0.00019585402,0.0005474247,0.00014080593,0.000107678236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003225988,0.00014197791,0.00015273366,0.000035905025,0.000092372204,0.00006241526,0.00035139624,0.00013380381,0.000008323632],"category_scores_gemma":[0.00029916086,0.00013635933,0.000065621025,0.00020699359,0.000017717326,0.000021173435,0.00015222534,0.000053467866,0.000013667971],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017470175,0.000047270623,0.0015651279,0.00071402785,0.00016515779,2.0556573e-7,0.00068658317,0.010205097,0.9716709,0.00015993326,0.0030282706,0.0115827],"study_design_scores_gemma":[0.00060304586,0.00012903893,0.00015591158,0.0000095303485,0.00008327185,5.9404573e-7,0.00025119993,0.8156647,0.11700067,0.00010498473,0.065766126,0.00023090962],"about_ca_topic_score_codex":0.0000037126335,"about_ca_topic_score_gemma":0.00006839858,"teacher_disagreement_score":0.8546702,"about_ca_system_score_codex":0.000008463517,"about_ca_system_score_gemma":0.00013507647,"threshold_uncertainty_score":0.5560572},"labels":[],"label_agreement":null},{"id":"W3107863713","doi":"10.1186/s12859-020-03768-z","title":"MADloy: robust detection of mosaic loss of chromosome Y from genotype-array-intensity data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Ministerio de Economía y Competitividad; Centres de Recerca de Catalunya; Institució Catalana de Recerca i Estudis Avançats; Agencia Estatal de Investigación; Ministerio de Ciencia, Innovación y Universidades; Ministère de l'Économie, de l’Innovation et des Exportations du Québec","keywords":"Biology; Chromosome; Software; Population; Replicate; Computational biology; SNP array; Genotype; Computer science; Data mining; Genetics; Statistics; Gene; Single-nucleotide polymorphism; Medicine; Mathematics","score_opus":0.03455742967135808,"score_gpt":0.22143668606563424,"score_spread":0.18687925639427616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107863713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8023274,0.00024720645,0.19507398,0.00006226593,0.00015107066,0.0001771006,0.0016212801,0.000017988745,0.00032169424],"genre_scores_gemma":[0.9544272,0.00007552258,0.04379313,0.00013147821,0.00015482184,0.0000021945532,0.0013777681,0.000013043898,0.0000248682],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905056,0.000020359279,0.00048899447,0.0001636169,0.00013402184,0.00014247424],"domain_scores_gemma":[0.9988812,0.000012521745,0.0002933743,0.0006048374,0.00013689714,0.00007117663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096369666,0.00013166227,0.00022752336,0.000024209785,0.000043416385,0.000012970717,0.00040066478,0.00013518694,0.00003733652],"category_scores_gemma":[0.00009945854,0.00012575982,0.000069434136,0.000100246354,0.00008642049,0.000019757175,0.0002885068,0.00006902439,0.0000186346],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005456728,0.0001494011,0.017740903,0.0009997725,0.00040596206,0.0000016102414,0.0023242938,0.005075359,0.9681268,0.00013360256,0.0019058124,0.0025908223],"study_design_scores_gemma":[0.0008562801,0.00040116147,0.0068540988,0.000030309135,0.00011587955,0.000016538252,0.0015241117,0.051086836,0.9327069,0.00006763343,0.0060182665,0.0003220127],"about_ca_topic_score_codex":0.00010780329,"about_ca_topic_score_gemma":0.00006359659,"teacher_disagreement_score":0.15209974,"about_ca_system_score_codex":0.000009094184,"about_ca_system_score_gemma":0.00010189465,"threshold_uncertainty_score":0.51283365},"labels":[],"label_agreement":null},{"id":"W3111170609","doi":"10.1186/s12859-020-03919-2","title":"PyClone-VI: scalable inference of clonal population structures using whole genome data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":140,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Michael Smith Health Research BC","keywords":"Deconvolution; Computer science; Inference; Scalability; Software; Population; Computational biology; Bayesian probability; Genome; Data mining; Biology; Artificial intelligence; Algorithm; Genetics; Gene; Database","score_opus":0.056188144556107995,"score_gpt":0.29457957920893857,"score_spread":0.23839143465283058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111170609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.824294,0.0006067933,0.17235209,0.000067612615,0.00017534166,0.00027645228,0.0017803776,0.000016089158,0.00043126053],"genre_scores_gemma":[0.85415703,0.00009544157,0.14156923,0.00043217622,0.00025693703,0.0000014509499,0.0034593802,0.000016917753,0.000011434943],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999126,0.000011657234,0.00038559572,0.00016640908,0.00014411211,0.00016622081],"domain_scores_gemma":[0.9991181,0.000019486293,0.00021004408,0.0004829967,0.000073072275,0.00009630712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082488434,0.00012629695,0.0001610708,0.00002720866,0.0000536287,0.000037954534,0.00037579858,0.00010846808,0.00001961851],"category_scores_gemma":[0.00020164457,0.00012487567,0.000042075168,0.000101554324,0.00004977493,0.00001813661,0.00045662123,0.000063291394,0.000006690684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061678863,0.00018646139,0.16488566,0.0023295183,0.00031664106,0.000003531789,0.0016591406,0.29871464,0.50720704,0.0032186906,0.009223802,0.011638107],"study_design_scores_gemma":[0.0013121446,0.00033923335,0.03195001,0.000038238417,0.000113215065,0.000013914238,0.00043885616,0.9158523,0.012943895,0.00043887846,0.035905045,0.0006542533],"about_ca_topic_score_codex":0.00007778202,"about_ca_topic_score_gemma":0.000061568375,"teacher_disagreement_score":0.6171377,"about_ca_system_score_codex":0.000013077952,"about_ca_system_score_gemma":0.00016318179,"threshold_uncertainty_score":0.5092282},"labels":[],"label_agreement":null},{"id":"W3113308471","doi":"10.1186/s12859-020-03930-7","title":"Inter-protein residue covariation information unravels physically interacting protein dimers","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Coevolution; Computer science; Protein–protein interaction; Computational biology; Surface protein; Protein sequencing; Mutual information; Artificial intelligence; Support vector machine; Feature vector; Biology; Machine learning; Theoretical computer science; Genetics; Gene; Evolutionary biology; Peptide sequence","score_opus":0.010862866212746536,"score_gpt":0.22999357294230885,"score_spread":0.2191307067295623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113308471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10484249,0.00001708897,0.890411,0.00036606973,0.00011372653,0.00087972503,0.000048975013,0.00006775198,0.003253179],"genre_scores_gemma":[0.83083653,0.0000049176315,0.16666502,0.0013117945,0.00030550038,0.00005961632,0.0006942801,0.000022866756,0.00009948024],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987681,0.000043628756,0.0005660215,0.00015159207,0.00021566512,0.00025497298],"domain_scores_gemma":[0.99903244,0.000013658671,0.00038098014,0.0002961324,0.0001484991,0.00012831354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001565974,0.000221329,0.00017839597,0.000051212617,0.000099416466,0.00012619194,0.0002774632,0.00019327032,0.000015475338],"category_scores_gemma":[0.0006281785,0.00020615064,0.00010323551,0.00017063248,0.000049029186,0.00010259902,0.00021169033,0.00020998527,0.00010087386],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002024677,0.00012457675,0.0010485046,0.0027159022,0.0004034343,0.000004693348,0.010585439,0.0073708985,0.85424924,0.014903691,0.004723871,0.101845086],"study_design_scores_gemma":[0.0024319456,0.0012134115,0.0005790123,0.00023421602,0.000059046382,0.000022958227,0.001866186,0.4807522,0.47213906,0.00078944693,0.038727004,0.0011855055],"about_ca_topic_score_codex":0.000012112505,"about_ca_topic_score_gemma":0.000010172498,"teacher_disagreement_score":0.72599405,"about_ca_system_score_codex":0.000027287117,"about_ca_system_score_gemma":0.00014649058,"threshold_uncertainty_score":0.84065795},"labels":[],"label_agreement":null},{"id":"W3116132399","doi":"10.1186/s12859-020-03848-0","title":"Deep learning detection of informative features in tau PET for Alzheimer’s disease classification","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Servier; National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Entorhinal cortex; Positron emission tomography; Temporal lobe; Neuroscience; Alzheimer's disease; Neuroimaging; Medicine; Dementia; Artificial intelligence; Voxel; Deep learning; Temporal cortex; Psychology; Disease; Pathology; Hippocampus; Computer science","score_opus":0.047600836721933486,"score_gpt":0.3236986725723198,"score_spread":0.27609783585038633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116132399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36946458,0.0005022607,0.61452585,0.0014129597,0.0001180723,0.0047550057,0.00004684112,0.00016829379,0.0090061175],"genre_scores_gemma":[0.9885512,0.000046542064,0.010804882,0.00026157033,0.0000357176,0.00009038471,0.00015504235,0.00000908771,0.00004555395],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901515,0.000028029504,0.0004043076,0.00007740006,0.00028351616,0.00019158189],"domain_scores_gemma":[0.99928355,0.000094301904,0.0001756128,0.000088427245,0.00019188534,0.0001662162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021227256,0.00010190479,0.0001763226,0.00014836242,0.000054150227,0.000022262999,0.000064564716,0.00003775486,0.000022425154],"category_scores_gemma":[0.000557848,0.000087589746,0.00008488176,0.00027247472,0.000052520165,0.00030455977,0.000034599798,0.0001793223,0.000024745992],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008376627,0.0005887374,0.56412023,0.008299116,0.00036452094,0.000011745892,0.02360397,0.0017503249,0.0027648092,0.0012837204,0.00087648013,0.38795972],"study_design_scores_gemma":[0.001749561,0.00054795644,0.4275332,0.000067427136,0.00010520121,0.0000037998122,0.005867586,0.5607399,0.0025744848,0.00003061174,0.00069217733,0.0000881248],"about_ca_topic_score_codex":0.0000036891793,"about_ca_topic_score_gemma":0.0000090684625,"teacher_disagreement_score":0.6190866,"about_ca_system_score_codex":0.000032740103,"about_ca_system_score_gemma":0.000112867994,"threshold_uncertainty_score":0.35718063},"labels":[],"label_agreement":null},{"id":"W3116224340","doi":"10.1186/s12859-020-03891-x","title":"Integrative approach for detecting membrane proteins","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Transmembrane protein; Membrane topology; Membrane protein; Computer science; Topology (electrical circuits); Integral membrane protein; Transmembrane domain; Computational biology; Feature (linguistics); Artificial intelligence; Data mining; Bioinformatics; Pattern recognition (psychology); Machine learning; Membrane; Biology; Mathematics; Biochemistry","score_opus":0.02162475551480415,"score_gpt":0.257806208504307,"score_spread":0.23618145298950288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116224340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005484814,0.00004299287,0.98039645,0.00011929341,0.000060690207,0.0010962684,0.000047977726,0.000079538164,0.01267196],"genre_scores_gemma":[0.049830556,0.00001166427,0.9477741,0.001199016,0.0003048872,0.00012955767,0.00044394293,0.000037609916,0.00026868074],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875766,0.00003251135,0.0005164757,0.00018725936,0.00017943498,0.00032664492],"domain_scores_gemma":[0.9990882,0.000036258225,0.00028045126,0.00030451897,0.00013271584,0.00015782918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027529724,0.0002578267,0.00023486208,0.00004191936,0.00015543617,0.00007363824,0.00035113716,0.00019260652,0.000010064559],"category_scores_gemma":[0.0012083866,0.00021171063,0.00016325006,0.00015858657,0.00007200234,0.00001827299,0.00016499814,0.0002065684,0.000024117297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063472767,0.0012320238,0.018585982,0.040086765,0.0023516424,0.0000044823896,0.08643458,0.25259247,0.33289966,0.014155685,0.08917322,0.15613621],"study_design_scores_gemma":[0.0009160735,0.00062906236,0.000035582543,0.00001798523,0.00002733681,0.000013132768,0.0020667557,0.92794585,0.04583135,0.000014331569,0.02215053,0.000352024],"about_ca_topic_score_codex":0.0000024740075,"about_ca_topic_score_gemma":0.000004162969,"teacher_disagreement_score":0.67535335,"about_ca_system_score_codex":0.000014926096,"about_ca_system_score_gemma":0.0001102948,"threshold_uncertainty_score":0.8633309},"labels":[],"label_agreement":null},{"id":"W3116851193","doi":"10.1186/s12859-020-03877-9","title":"Effect of APOE ε4 on multimodal brain connectomic traits: a persistent homology study","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; Genentech; Fundamental Research Funds for the Central Universities; National Institutes of Health; Servier; National Natural Science Foundation of China; Eisai; H. Lundbeck A/S; IXICO; Natural Science Foundation of Heilongjiang Province; Harbin Engineering University; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Pennsylvania; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Apolipoprotein E; Neuroimaging; Connectome; Functional magnetic resonance imaging; Neuroscience; Discriminative model; Diffusion MRI; Imaging genetics; Artificial intelligence; Computer science; Computational biology; Medicine; Machine learning; Magnetic resonance imaging; Disease; Biology; Functional connectivity; Pathology","score_opus":0.0443465359365428,"score_gpt":0.2805188398877967,"score_spread":0.23617230395125388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116851193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926074,0.00001565811,0.0013756548,0.002427512,0.00024934625,0.001321187,0.00006990191,0.00013626485,0.0017970457],"genre_scores_gemma":[0.9937456,0.0000016369493,0.00079927244,0.0052852915,0.0000579085,0.000049148406,0.0000023094717,0.000017463719,0.000041350948],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981691,0.00037596503,0.0004570073,0.00030193926,0.0004101941,0.00028574897],"domain_scores_gemma":[0.987584,0.01183219,0.00021055798,0.0002276332,0.000039645696,0.00010599547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00045180158,0.00025153765,0.00046411846,0.00011633816,0.00015493076,0.000025707084,0.00030311107,0.00007341564,0.000032888485],"category_scores_gemma":[0.017928815,0.00020224933,0.000212702,0.0003376261,0.00019184424,0.00016106828,0.00016503027,0.00022175771,0.0001998796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.034262568,0.011147885,0.06945735,0.01661071,0.00223658,0.00028794154,0.34548232,0.10564118,0.14988014,0.0155618945,0.16650142,0.08293002],"study_design_scores_gemma":[0.016498217,0.057331715,0.011688162,0.00010957601,0.00026738254,0.0000957953,0.012293386,0.8362128,0.062066894,0.00005614921,0.002262188,0.0011177283],"about_ca_topic_score_codex":0.000008638196,"about_ca_topic_score_gemma":0.00000985784,"teacher_disagreement_score":0.7305716,"about_ca_system_score_codex":0.000057777797,"about_ca_system_score_gemma":0.00005871912,"threshold_uncertainty_score":0.9903436},"labels":[],"label_agreement":null},{"id":"W3118322235","doi":"10.1186/s12859-021-04179-4","title":"GWENA: gene co-expression networks analysis and extended modules characterization in a single Bioconductor package","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier universitaire de Québec; Université Laval","funders":"","keywords":"Bioconductor; Gene co-expression network; Computational biology; Phenotype; DNA microarray; Gene; Gene regulatory network; Biology; Gene expression; Gene expression profiling; Computer science; Systems biology; Pipeline (software); Expression (computer science); Biological network; Topology (electrical circuits); Genetics; Mathematics","score_opus":0.012078021885891105,"score_gpt":0.23056987602147563,"score_spread":0.21849185413558453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118322235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5511831,0.0003686218,0.4477454,0.000022160431,0.00009710951,0.0001730902,0.00010387294,0.000014460768,0.0002921703],"genre_scores_gemma":[0.9099045,0.0009000022,0.081103824,0.00046753374,0.00022273762,0.000024548068,0.007056315,0.000030501014,0.00029005564],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987133,0.000048704587,0.0005725184,0.00022285743,0.00012799655,0.0003146141],"domain_scores_gemma":[0.9991014,0.000016400061,0.00023722615,0.00044941768,0.000081639424,0.000113935785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021083951,0.0002146212,0.00028909036,0.00014198976,0.000085918946,0.00011802941,0.000128811,0.00028104166,0.000021736538],"category_scores_gemma":[0.000041864416,0.00020047439,0.00011333689,0.00040547986,0.00006868059,0.000029791261,0.0001644319,0.000119934186,0.0000056069293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012322339,0.00030360022,0.02664216,0.00026340157,0.00035780616,0.000009261893,0.0006666188,0.0050649405,0.94855386,0.00016430288,0.00048664986,0.017364156],"study_design_scores_gemma":[0.0017939402,0.00021081582,0.08429026,0.00008127749,0.00022279542,0.000052784344,0.00056728115,0.6346852,0.27242923,0.00009293522,0.0047130147,0.00086045003],"about_ca_topic_score_codex":0.0000025808706,"about_ca_topic_score_gemma":0.000059902755,"teacher_disagreement_score":0.67612463,"about_ca_system_score_codex":0.000020820338,"about_ca_system_score_gemma":0.0000613433,"threshold_uncertainty_score":0.81751084},"labels":[],"label_agreement":null},{"id":"W3118344282","doi":"10.1186/s12859-020-03770-5","title":"SPServer: split-statistical potentials for the analysis of protein structures and protein–protein interactions","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"European Regional Development Fund; Instituto de Salud Carlos III; Generalitat de Catalunya; Agència de Gestió d'Ajuts Universitaris i de Recerca; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Ministerio de Ciencia e Innovación","keywords":"Web server; Computer science; Protein structure prediction; Protein structure; Protein–protein interaction; Data mining; Amino acid residue; Computational biology; Protein tertiary structure; Bioinformatics; Database; Biology; Peptide sequence; The Internet; Biochemistry; World Wide Web","score_opus":0.012084555805854883,"score_gpt":0.2718247820414553,"score_spread":0.25974022623560045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118344282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2620535,0.0005533015,0.73531044,0.000110426954,0.000057699493,0.0011058558,0.00062302215,0.000010884363,0.00017489845],"genre_scores_gemma":[0.6643654,0.000021553346,0.3339303,0.00010013446,0.00008720513,0.0001683221,0.00067135,0.000017758037,0.00063796836],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889743,0.00004670911,0.00048178356,0.00019474381,0.0001666454,0.00021266457],"domain_scores_gemma":[0.99894106,0.00004818467,0.00023916968,0.00048245082,0.0002218462,0.00006726566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000187613,0.00017636201,0.00027722193,0.00007521191,0.0001456343,0.00006984594,0.00017735406,0.0001351576,0.000038732378],"category_scores_gemma":[0.00039591416,0.0001280426,0.00018693894,0.00024881127,0.00014707835,0.000013407339,0.0001644866,0.00010241349,8.858013e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093368423,0.00020944617,0.0016631233,0.0026884635,0.005748645,0.0000061852606,0.00071225356,0.004316832,0.7801132,0.14260001,0.00074152095,0.060266584],"study_design_scores_gemma":[0.0026211552,0.00063040457,0.022747574,0.00016584483,0.0032162352,0.000071807706,0.0015523124,0.33066413,0.5860706,0.020567283,0.030469665,0.0012229643],"about_ca_topic_score_codex":0.00002474564,"about_ca_topic_score_gemma":0.000225135,"teacher_disagreement_score":0.4023119,"about_ca_system_score_codex":0.0000101387095,"about_ca_system_score_gemma":0.00014013045,"threshold_uncertainty_score":0.5221425},"labels":[],"label_agreement":null},{"id":"W3124892619","doi":"10.1186/s12859-020-03950-3","title":"SNF-NN: computational method to predict drug-disease interactions using similarity network fusion and neural networks","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Artificial neural network; Similarity (geometry); Drug repositioning; Robustness (evolution); Drug discovery; Drug development; Deep learning; Drug; Data mining; Bioinformatics; Medicine; Biology; Pharmacology","score_opus":0.039244372198190415,"score_gpt":0.33385737926637127,"score_spread":0.29461300706818083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124892619","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064664967,0.00014917499,0.9912328,0.0006656373,0.0008625206,0.00026750253,0.000023726208,0.0001350677,0.00019707842],"genre_scores_gemma":[0.02092215,0.0000041524486,0.97687024,0.0018454422,0.00023812964,0.00000938565,0.0000639031,0.000012593063,0.000034002976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978517,0.0003976307,0.000585938,0.00033398272,0.0004592561,0.00037146415],"domain_scores_gemma":[0.99747574,0.0012461323,0.00018008098,0.00041238108,0.00029364467,0.00039199542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080622477,0.00022518265,0.00024912236,0.00013172715,0.0003850164,0.0004867344,0.00037702947,0.000049773862,0.000017523496],"category_scores_gemma":[0.00021112221,0.00023407562,0.000112054106,0.0009027405,0.00004046991,0.0011495248,0.0010530154,0.00026029092,0.0000073022625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016853279,0.00003698087,0.0016550417,0.000051265873,0.000015873424,0.0000080096725,0.00046159307,0.97525686,0.000001373324,0.004638574,0.0011352047,0.016722394],"study_design_scores_gemma":[0.00026422937,0.0000143181505,0.015250963,0.0000659227,0.000027860877,0.00008375149,0.00007511022,0.9774036,0.0000055138094,0.0059206327,0.0006429385,0.00024519168],"about_ca_topic_score_codex":0.000011753778,"about_ca_topic_score_gemma":0.000020000018,"teacher_disagreement_score":0.016477203,"about_ca_system_score_codex":0.00008913943,"about_ca_system_score_gemma":0.00034484663,"threshold_uncertainty_score":0.9545327},"labels":[],"label_agreement":null},{"id":"W3129593819","doi":"10.1186/s12859-020-03927-2","title":"WACS: improving ChIP-seq peak calling by optimally weighting controls","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Compute Canada","keywords":"Chromatin immunoprecipitation; Chip; Computer science; Noise (video); Weighting; DNA microarray; Bioconductor; Computational biology; Data mining; Genetics; Biology; Artificial intelligence; Telecommunications; Gene; Medicine","score_opus":0.005878323693093789,"score_gpt":0.20453734792653197,"score_spread":0.19865902423343818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129593819","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64997256,0.0014131316,0.34008217,0.00010055907,0.0003163512,0.00027459746,0.00014893794,0.000050868108,0.0076408163],"genre_scores_gemma":[0.44162133,0.00055595476,0.55164313,0.0012409458,0.0004728115,0.000027633398,0.0019415256,0.000099603574,0.0023970515],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986035,0.000028225166,0.00056020636,0.00023149395,0.00016854244,0.00040800712],"domain_scores_gemma":[0.9989947,0.000025971074,0.00024995615,0.0004540563,0.00014962252,0.00012569729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023845656,0.00023006454,0.00023225037,0.000027946266,0.00016733928,0.00015364298,0.0002585964,0.0002093185,0.000021718644],"category_scores_gemma":[0.0001681443,0.00022848077,0.00014469854,0.00008271137,0.000046333746,0.000012360744,0.00024617364,0.000145096,0.000028241262],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060935123,0.00012162528,0.0017638481,0.00052756927,0.00015988851,0.000008603185,0.00039764805,0.006538503,0.9777227,0.00079396175,0.002170344,0.009734374],"study_design_scores_gemma":[0.0016901316,0.00018796565,0.00035686392,0.000054689674,0.000069599046,0.000090618545,0.0012065789,0.9025465,0.074391745,0.000082229904,0.018583946,0.00073910493],"about_ca_topic_score_codex":0.000007732962,"about_ca_topic_score_gemma":0.00003373399,"teacher_disagreement_score":0.903331,"about_ca_system_score_codex":0.000030750372,"about_ca_system_score_gemma":0.0002412519,"threshold_uncertainty_score":0.9317175},"labels":[],"label_agreement":null},{"id":"W3137414883","doi":"10.1186/s12859-021-04055-1","title":"Juxtapose: a gene-embedding approach for comparing co-expression networks","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Set (abstract data type); Computer science; Biological network; Expression (computer science); Embedding; Cosine similarity; DNA microarray; Computational biology; Gene regulatory network; Gene; Artificial intelligence; Data mining; Gene expression; Theoretical computer science; Biology; Pattern recognition (psychology); Genetics","score_opus":0.024842362712033446,"score_gpt":0.2742495784601811,"score_spread":0.24940721574814767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137414883","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008969262,0.0007260573,0.98115015,0.000010552882,0.0002489507,0.00040766297,0.000039844086,0.00003503624,0.008412466],"genre_scores_gemma":[0.13883907,0.00020053053,0.85535276,0.0005808124,0.0006905195,0.00007979103,0.00349872,0.000050467588,0.0007072974],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842644,0.000028698678,0.0006314146,0.00024249694,0.00016300194,0.0005079634],"domain_scores_gemma":[0.99883455,0.0000330241,0.00025337024,0.0005717857,0.0001485814,0.00015871189],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003551421,0.00026795376,0.00030783255,0.000044538592,0.00025525317,0.00014559069,0.00028582738,0.00032777234,0.000009192051],"category_scores_gemma":[0.00005789711,0.00025437254,0.00021633905,0.00011855582,0.00006342086,0.000018505338,0.0002345381,0.00016389722,0.000008934344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005045933,0.0003935174,0.0057356786,0.0017461323,0.00037544497,0.00000352381,0.0010615848,0.83793116,0.03529306,0.0014953531,0.1004313,0.015028667],"study_design_scores_gemma":[0.0010776581,0.00007321601,0.000086605716,0.000034441513,0.00003120581,0.000057420148,0.00047713044,0.95774204,0.021120183,0.000046613393,0.01888184,0.00037165923],"about_ca_topic_score_codex":8.821477e-7,"about_ca_topic_score_gemma":0.0000040850055,"teacher_disagreement_score":0.1298698,"about_ca_system_score_codex":0.000025016338,"about_ca_system_score_gemma":0.00014484378,"threshold_uncertainty_score":0.9999908},"labels":[],"label_agreement":null},{"id":"W3146187752","doi":"10.1186/s12859-021-04018-6","title":"Reliable genomic strategies for species classification of plant genetic resources","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Newfoundland and Labrador; Ministerie van Landbouw, Natuur en Voedselkwaliteit","keywords":"Naive Bayes classifier; Classifier (UML); Documentation; Computer science; Data mining; Random forest; Variety (cybernetics); Bayes' theorem; Machine learning; Artificial intelligence; Support vector machine; Bayesian probability","score_opus":0.028445124261018858,"score_gpt":0.2325085918689675,"score_spread":0.20406346760794863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146187752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95788115,0.0022160425,0.034364894,0.000039759543,0.00017477747,0.00027126964,0.00034595045,0.0000050630324,0.004701069],"genre_scores_gemma":[0.7421289,0.0012903287,0.25442296,0.00012323585,0.00026568552,0.00005266553,0.0003885232,0.000028134658,0.0012995481],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992241,0.000011794993,0.00037018917,0.00013705839,0.00008270702,0.00017414194],"domain_scores_gemma":[0.9993021,0.000024002491,0.0001716845,0.0003149977,0.00015243511,0.00003476311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000094491166,0.000119160526,0.00016034102,0.00002973023,0.0000784377,0.000037810096,0.0001400745,0.00009116189,0.000006562777],"category_scores_gemma":[0.000041572417,0.000112145644,0.00009300545,0.000056545206,0.00007738623,0.0000016858218,0.00008873671,0.000029048082,0.0000035556477],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010588535,0.00006866784,0.009749845,0.00057059736,0.00013918473,4.657503e-7,0.0010497249,0.0038135492,0.97362065,0.0032162596,0.006842086,0.0008230933],"study_design_scores_gemma":[0.0019032015,0.0007497044,0.21609524,0.00006774512,0.0001654781,0.000050656956,0.020167308,0.03431569,0.17990698,0.0021789302,0.5436016,0.0007975038],"about_ca_topic_score_codex":0.000004202175,"about_ca_topic_score_gemma":0.000059202444,"teacher_disagreement_score":0.7937137,"about_ca_system_score_codex":0.000008694222,"about_ca_system_score_gemma":0.0001921694,"threshold_uncertainty_score":0.45731667},"labels":[],"label_agreement":null},{"id":"W3153503836","doi":"10.1186/s12859-021-04117-4","title":"MAPS: machine-assisted phenotype scoring enables rapid functional assessment of genetic variants by high-content microscopy","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Workflow; Computer science; Leverage (statistics); Deep learning; Artificial intelligence; Machine learning; PTEN; Software; Computational biology; Bioinformatics; Biology; Genetics; Database","score_opus":0.019422379557617022,"score_gpt":0.26188649321732815,"score_spread":0.24246411365971113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153503836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1439464,0.0023148248,0.8498571,0.00004267227,0.00016122701,0.00028280466,0.00015433763,0.00004911456,0.0031915104],"genre_scores_gemma":[0.31479117,0.00091548846,0.6799795,0.0003868144,0.000101930564,0.000031634532,0.0024545337,0.00003928148,0.001299672],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985624,0.000058193513,0.0006467259,0.00023682816,0.0002512703,0.00024459415],"domain_scores_gemma":[0.9987355,0.00002083879,0.0003039392,0.0005821782,0.00028064015,0.00007692589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020407827,0.0002066052,0.00027520934,0.00006993609,0.000076785785,0.000057510882,0.00019485499,0.00014455087,0.00012503614],"category_scores_gemma":[0.00007684202,0.0001986044,0.00016019818,0.00017877894,0.00007088984,0.000015073094,0.00021230578,0.00009993324,0.00000775053],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029663232,0.00018522555,0.0067851474,0.0002135801,0.00019459761,0.0000026852015,0.000019525805,0.00012341262,0.9773823,0.00005483948,0.011079463,0.003929547],"study_design_scores_gemma":[0.00097145885,0.00020039614,0.028961353,0.00006235793,0.0001682566,0.000032198415,0.00019285291,0.010454034,0.9516867,0.00004464206,0.006853499,0.00037229093],"about_ca_topic_score_codex":0.00005199989,"about_ca_topic_score_gemma":0.000044379012,"teacher_disagreement_score":0.17084476,"about_ca_system_score_codex":0.00003877125,"about_ca_system_score_gemma":0.00025217765,"threshold_uncertainty_score":0.80988526},"labels":[],"label_agreement":null},{"id":"W3157357664","doi":"10.1186/s12859-022-04693-z","title":"Evaluation of statistical approaches for association testing in noisy drug screening data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Université du Québec à Montréal; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Syöpäjärjestöt; Academy of Finland; European Commission","keywords":"Concordance; False positive paradox; Computer science; Statistical hypothesis testing; Pearson product-moment correlation coefficient; Data mining; Spearman's rank correlation coefficient; Correlation; Rank correlation; Statistics; Parametric statistics; Noise (video); Machine learning; Medicine; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.8876184499002661,"score_gpt":0.574548024450978,"score_spread":0.3130704254492881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157357664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024086956,0.000016824088,0.99223655,0.00006267713,0.00024597888,0.0014852169,0.0020927119,0.00004129368,0.0014100687],"genre_scores_gemma":[0.009410935,6.9392115e-7,0.99006885,0.000032100248,0.0000745474,0.00020442298,0.00015646273,0.000022903205,0.000029065446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99394774,0.0015842383,0.001943328,0.0002526901,0.00193416,0.0003378606],"domain_scores_gemma":[0.89470595,0.102798216,0.0012825753,0.0007308084,0.00041614275,0.000066288485],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05248438,0.000143663,0.00051334815,0.00013030325,0.00013486607,0.000033052,0.00054482406,0.0000801559,0.000102970924],"category_scores_gemma":[0.4063524,0.0001437612,0.000053035517,0.00042227725,0.00004715417,0.00019677677,0.0005439152,0.0002984733,0.0000024354792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040647184,0.0013516832,0.027298031,0.0034873884,0.0003511808,0.0000011389196,0.0035114938,0.030962944,0.0000160468,0.19977963,0.020258794,0.7125752],"study_design_scores_gemma":[0.0012766455,0.000058009497,0.001024588,0.000033018612,0.00023418665,8.531361e-7,0.00095513306,0.69781375,0.000011545431,0.29840866,0.00007057895,0.00011305826],"about_ca_topic_score_codex":0.000016209091,"about_ca_topic_score_gemma":0.000030407684,"teacher_disagreement_score":0.7124621,"about_ca_system_score_codex":0.00031974723,"about_ca_system_score_gemma":0.00034807675,"threshold_uncertainty_score":0.9756667},"labels":[],"label_agreement":null},{"id":"W3159624973","doi":"10.1186/s12859-021-04138-z","title":"Dynamic model updating (DMU) approach for statistical learning model building with missing data","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada","keywords":"Missing data; Categorical variable; Data mining; Imputation (statistics); Computer science; Cluster analysis; Closeness; Statistical model; Bayesian probability; Machine learning; Artificial intelligence; Mathematics","score_opus":0.14795907018902008,"score_gpt":0.39605897055970263,"score_spread":0.24809990037068255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159624973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014645785,0.000020062025,0.99531305,0.00003496603,0.000028415212,0.00034429625,0.00054765237,0.00013652301,0.0034285875],"genre_scores_gemma":[0.0023668709,0.0000062853883,0.9967127,0.00008746246,0.000024138773,0.000028134793,0.00058876275,0.000059608275,0.0001260227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977346,0.00008546229,0.0007996161,0.00039713611,0.00042419057,0.00055900856],"domain_scores_gemma":[0.9963557,0.0020932914,0.00032046766,0.0008123824,0.00023298418,0.00018515588],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010146744,0.00030165195,0.0005017215,0.00007035703,0.0003611585,0.00028476893,0.00045371221,0.00013920294,0.000016261181],"category_scores_gemma":[0.0050327047,0.00025054428,0.000051521958,0.0002105055,0.0001141543,0.00045470282,0.0003551122,0.0003925141,0.0000027014626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006807009,0.00015362626,0.00009587442,0.0033557152,0.0000726996,0.000004740206,0.00077166606,0.08280791,0.00013974318,0.8622508,0.00059628865,0.049682867],"study_design_scores_gemma":[0.00045848545,0.0000358667,0.0000043393784,0.0001311411,0.00012167314,0.000032453885,0.0006928246,0.77591443,0.000032680193,0.22225593,0.000016989936,0.0003032132],"about_ca_topic_score_codex":0.000001717067,"about_ca_topic_score_gemma":0.0000049587957,"teacher_disagreement_score":0.6931065,"about_ca_system_score_codex":0.00007123276,"about_ca_system_score_gemma":0.00050574826,"threshold_uncertainty_score":0.9999947},"labels":[],"label_agreement":null},{"id":"W3162362563","doi":"10.1186/s12859-020-03873-z","title":"Identifying cell types from single-cell data based on similarities and dissimilarities between cells","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Wuhan Institute of Technology; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Cluster analysis; Spectral clustering; Dimensionality reduction; Computer science; Categorical variable; Pattern recognition (psychology); Hierarchical clustering; Data mining; Similarity (geometry); Cell type; Clustering high-dimensional data; Artificial intelligence; Computational biology; Mathematics; Biology; Cell; Genetics; Machine learning","score_opus":0.06198245153201891,"score_gpt":0.250350994032811,"score_spread":0.1883685425007921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162362563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67413527,0.004054564,0.29489315,0.00023678494,0.0012330482,0.00051048375,0.007302042,0.00013105522,0.017503621],"genre_scores_gemma":[0.81208616,0.0003955763,0.1771478,0.001163435,0.00045341437,0.000005169571,0.007767062,0.00006410227,0.00091729284],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987343,0.000052093987,0.0003907709,0.00033026453,0.00021549895,0.0002770706],"domain_scores_gemma":[0.99875563,0.00011380132,0.00011548955,0.00082967774,0.00007010366,0.00011527854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014063805,0.0002453953,0.00024409717,0.000047731104,0.00015072277,0.00022957294,0.00036426404,0.0002314778,0.000033415425],"category_scores_gemma":[0.000052471594,0.00024487698,0.0000725072,0.00007519027,0.00010812975,0.000028395776,0.0002645524,0.00015593992,0.000010798223],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045003407,0.001537476,0.08899228,0.004818511,0.0003237494,0.000045524994,0.002476775,0.0028528834,0.85727286,0.00006658471,0.028973896,0.012189415],"study_design_scores_gemma":[0.0014632784,0.00022399612,0.0011113147,0.00012621588,0.00016999531,0.0000020121054,0.0013417045,0.05614721,0.9191539,0.0000976553,0.01954293,0.00061977544],"about_ca_topic_score_codex":0.000029823465,"about_ca_topic_score_gemma":0.00007803599,"teacher_disagreement_score":0.1379509,"about_ca_system_score_codex":0.000012496467,"about_ca_system_score_gemma":0.00013991968,"threshold_uncertainty_score":0.9985794},"labels":[],"label_agreement":null},{"id":"W3163273456","doi":"10.1186/s12859-021-04180-x","title":"Profile hidden Markov model sequence analysis can help remove putative pseudogenes from DNA barcoding and metabarcoding datasets","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Government of Canada; Ontario Genomics; Genome Canada","keywords":"Pseudogene; Barcode; Amplicon; Computational biology; DNA barcoding; Biology; Gene; Sequence analysis; Genetics; DNA sequencing; Coding region; Genome; Computer science; Polymerase chain reaction; Evolutionary biology","score_opus":0.037522168001210686,"score_gpt":0.24711458856696852,"score_spread":0.20959242056575783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163273456","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625749,0.00024565466,0.023054736,0.00023878964,0.000073239506,0.00038033046,0.010446418,0.00007599855,0.0029099535],"genre_scores_gemma":[0.1454425,0.00032476865,0.8519383,0.00035803058,0.000013939159,0.000011186454,0.0016146579,0.000011862219,0.0002847765],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833906,0.000060941522,0.00037150824,0.00038862193,0.00048370808,0.0003561773],"domain_scores_gemma":[0.9990897,0.00013349953,0.0001897681,0.0004164948,0.000009668765,0.00016083458],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020874022,0.00025946944,0.0003461701,0.00007137043,0.00038763488,0.00009994179,0.00027702958,0.000077633485,0.0004122403],"category_scores_gemma":[0.00009584797,0.00025013663,0.000108680615,0.0004841405,0.00036451494,0.0006272368,0.0013186667,0.00012811185,0.0001942235],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030427227,0.00010814736,0.94014156,0.0001347341,0.0010166613,0.00006142856,0.009314369,0.009245438,0.019138532,0.000032625863,0.0037429875,0.017033076],"study_design_scores_gemma":[0.00041105307,0.000022248387,0.106364086,0.00002641747,0.00090138393,0.000012790555,0.008741886,0.86340296,0.01914029,0.00021633439,0.00016652276,0.00059403246],"about_ca_topic_score_codex":0.00029420928,"about_ca_topic_score_gemma":0.00032918545,"teacher_disagreement_score":0.8541575,"about_ca_system_score_codex":0.0002523358,"about_ca_system_score_gemma":0.000015151804,"threshold_uncertainty_score":0.9999951},"labels":[],"label_agreement":null},{"id":"W3164474166","doi":"10.1186/s12859-021-04209-1","title":"SMILE: systems metabolomics using interpretable learning and evolution","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Queen's University","funders":"Queen's University; National Research Council Canada; Compute Canada","keywords":"Interpretability; Metabolomics; Machine learning; Computer science; Artificial intelligence; Visualization; Mechanism (biology); Process (computing); Interface (matter); Disease; Data science; Big data; Bioinformatics; Data mining; Biology; Medicine","score_opus":0.013210388016453174,"score_gpt":0.24776902086803762,"score_spread":0.23455863285158446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164474166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47578645,0.016262528,0.5018755,0.000013550402,0.0006420428,0.00018519856,0.000027702372,0.000029225777,0.0051778094],"genre_scores_gemma":[0.8727823,0.0027096053,0.12262798,0.000071848066,0.00021245696,0.000009907246,0.00010067287,0.00002658332,0.0014586251],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991431,0.000049784623,0.0003026055,0.00016685335,0.000104139224,0.00023349505],"domain_scores_gemma":[0.99946994,0.000016125985,0.00013735745,0.00018426252,0.0001295334,0.000062814404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002320601,0.00014721442,0.00022391444,0.00005622491,0.00015803227,0.00008645453,0.00006889486,0.000114052586,0.0000063338553],"category_scores_gemma":[0.00023763202,0.00013988768,0.000060740585,0.0001392825,0.00005356697,0.000012375617,0.0002418593,0.00010502753,0.000004841479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001795378,0.00019731358,0.09928343,0.001819055,0.0011926796,0.000010167781,0.0009988532,0.026654633,0.82974696,0.033637747,0.0026022189,0.0036774045],"study_design_scores_gemma":[0.0013530316,0.00022282483,0.0038710271,0.00008913096,0.00027048387,0.00036166227,0.007946385,0.85647345,0.029143363,0.00019356595,0.099244565,0.0008305338],"about_ca_topic_score_codex":0.000012812794,"about_ca_topic_score_gemma":0.00000896534,"teacher_disagreement_score":0.8298188,"about_ca_system_score_codex":0.0000233328,"about_ca_system_score_gemma":0.00010802064,"threshold_uncertainty_score":0.5704454},"labels":[],"label_agreement":null},{"id":"W3165113039","doi":"10.1186/s12859-021-04042-6","title":"PIGNON: a protein–protein interaction-guided functional enrichment analysis for quantitative proteomics","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Ontario; Compute Canada","keywords":"Proteomics; Computational biology; Interaction network; Cluster analysis; Biology; DNA microarray; Annotation; Gene ontology; Quantitative proteomics; Bioinformatics; Computer science; Gene expression; Gene; Genetics; Artificial intelligence","score_opus":0.036280038192337966,"score_gpt":0.2814574738628821,"score_spread":0.24517743567054415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165113039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06108276,0.0001654301,0.93519115,0.00014206646,0.0002034378,0.0012182379,0.00012671472,0.00002532523,0.0018449009],"genre_scores_gemma":[0.1193143,0.000030300283,0.8730761,0.00057209755,0.0003168433,0.0007011785,0.0025949345,0.000036868318,0.0033574214],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983052,0.000041794676,0.00078649074,0.00026922132,0.00022650506,0.00037076743],"domain_scores_gemma":[0.99847203,0.00003399572,0.00039825318,0.0005103476,0.0004577549,0.0001276226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038196123,0.00027191403,0.0003167429,0.00013096142,0.00020476278,0.00013513853,0.00018179655,0.00023358576,0.00006664326],"category_scores_gemma":[0.00018407096,0.0002585508,0.00036216417,0.00041633626,0.000065612316,0.000028634186,0.0001612824,0.0001457135,0.00003683841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004261479,0.0021578844,0.0059070527,0.0049698567,0.017187933,0.000014983257,0.004354237,0.23367614,0.5449179,0.09453704,0.07231724,0.015698252],"study_design_scores_gemma":[0.0035069974,0.0010559881,0.00086972537,0.00012387219,0.00067566556,0.00005826132,0.0033396217,0.7902842,0.13431408,0.002229173,0.062220357,0.0013220609],"about_ca_topic_score_codex":0.000005455143,"about_ca_topic_score_gemma":0.00008336281,"teacher_disagreement_score":0.5566081,"about_ca_system_score_codex":0.00006002478,"about_ca_system_score_gemma":0.00036804506,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W3165409583","doi":"10.1186/s12859-021-04215-3","title":"Uncovering the roles of microRNAs/lncRNAs in characterising breast cancer subtypes and prognosis","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; National Natural Science Foundation of China; Cancer Research UK","keywords":"Subtyping; Breast cancer; microRNA; Oncology; Cancer; Computational biology; Bioinformatics; Biology; Medicine; Internal medicine; Gene; Computer science; Genetics","score_opus":0.010208272530979449,"score_gpt":0.2552147196282357,"score_spread":0.24500644709725627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165409583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99096,0.0024768056,0.0057552457,0.000247892,0.00007982604,0.00021292164,0.00007910083,0.000005828554,0.00018237613],"genre_scores_gemma":[0.9916143,0.002497607,0.005411037,0.00019766837,0.00007640494,0.000032918655,0.00005355235,0.000022940148,0.00009357358],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992269,0.000037568094,0.00026412675,0.0001275664,0.0001422515,0.00020157675],"domain_scores_gemma":[0.999509,0.000013797404,0.00010221895,0.00022497031,0.00011001513,0.000040020714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018257824,0.00010574974,0.00012901888,0.000044958568,0.000046740293,0.000043004213,0.00012543546,0.00010525262,0.000013566151],"category_scores_gemma":[0.000050021703,0.0000852758,0.000049661354,0.00016624916,0.000066535584,0.000009707636,0.00020783968,0.00011281362,0.0000014545437],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011076248,0.000049137616,0.010882116,0.00039267723,0.00007676238,0.0000041143085,0.0006483468,0.0008726404,0.9655915,0.000051423434,0.00010279767,0.021217758],"study_design_scores_gemma":[0.0006287653,0.000051137984,0.021728976,0.00019964106,0.000023827042,0.00011344842,0.0009879908,0.0054049357,0.96799517,0.000031086594,0.0026420257,0.00019297669],"about_ca_topic_score_codex":0.00004610069,"about_ca_topic_score_gemma":0.0008042112,"teacher_disagreement_score":0.02102478,"about_ca_system_score_codex":0.00002273889,"about_ca_system_score_gemma":0.00023210069,"threshold_uncertainty_score":0.3477446},"labels":[],"label_agreement":null},{"id":"W3173187119","doi":"10.1186/s12859-021-04267-5","title":"Pheniqs 2.0: accurate, high-performance Bayesian decoding and confidence estimation for combinatorial barcode indexing","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi; New York University","keywords":"Barcode; Computer science; Decoding methods; Probabilistic logic; Benchmark (surveying); Data mining; Algorithm; Artificial intelligence","score_opus":0.016237025944968002,"score_gpt":0.25120736955113604,"score_spread":0.23497034360616803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173187119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69573766,0.00044253175,0.30263945,0.00004149324,0.00044188165,0.00024340744,0.00003700721,0.0000071361796,0.00040943007],"genre_scores_gemma":[0.8373924,0.00033592444,0.16187778,0.000105290615,0.00011852399,0.000025807933,0.000084608946,0.000011780857,0.000047877125],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992296,0.0000142117915,0.00029950438,0.00015901233,0.000085344785,0.00021231906],"domain_scores_gemma":[0.99943745,0.000049020076,0.000119963275,0.00019840148,0.00013621461,0.000058966718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013958864,0.00014117574,0.0001531216,0.000020611202,0.00019406917,0.00007229337,0.00009691895,0.000105944324,0.0000027377998],"category_scores_gemma":[0.00016460502,0.00014192793,0.000037417805,0.00006111422,0.000055066666,0.000006645237,0.00012710705,0.00004868148,0.000001982134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011833104,0.00043362935,0.08475633,0.006821495,0.0011024103,0.000007862302,0.005755998,0.07101467,0.57576007,0.07622306,0.006666555,0.17027462],"study_design_scores_gemma":[0.0026965283,0.00037965542,0.009718436,0.00009607351,0.00007594144,0.000046100533,0.00071603386,0.7455002,0.23287325,0.002992205,0.0042784396,0.0006271375],"about_ca_topic_score_codex":0.000003165557,"about_ca_topic_score_gemma":0.000012044203,"teacher_disagreement_score":0.6744855,"about_ca_system_score_codex":0.0000109812945,"about_ca_system_score_gemma":0.0001199834,"threshold_uncertainty_score":0.57876533},"labels":[],"label_agreement":null},{"id":"W3176962018","doi":"10.1186/s12859-021-04230-4","title":"StrongestPath: a Cytoscape application for protein–protein interaction analysis","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Institute for Research in Fundamental Sciences","keywords":"Protein–protein interaction; Computer science; Computational biology; Network analysis; Interaction network; DNA microarray; Graphical user interface; Bioinformatics; Set (abstract data type); Biology; Database; Gene; Genetics; Gene expression; Engineering","score_opus":0.01255292378503829,"score_gpt":0.2511388889712844,"score_spread":0.2385859651862461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176962018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07365034,0.00015073258,0.9236761,0.000096639524,0.000076900826,0.0008132381,0.000086980086,0.00002568687,0.0014234233],"genre_scores_gemma":[0.5936303,0.00003603305,0.3996274,0.0004374203,0.0004060457,0.00058957096,0.0037278899,0.000038772843,0.0015066017],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988249,0.00002240763,0.00052796595,0.00020473739,0.00013708217,0.00028293394],"domain_scores_gemma":[0.99879706,0.0000114199365,0.00028935226,0.00056369684,0.00021956507,0.00011891454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023692458,0.00018130816,0.00022253707,0.00008716567,0.0001213761,0.000084961546,0.00017619514,0.00021508464,0.000015797683],"category_scores_gemma":[0.00010626089,0.00018632725,0.00027218592,0.00031129995,0.000034598874,0.00001955801,0.00010990096,0.0000991318,0.000027526663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011665348,0.0008985914,0.0032874953,0.0029207815,0.004407783,0.000002961001,0.0014239517,0.049811885,0.63944525,0.019046826,0.011314327,0.26627365],"study_design_scores_gemma":[0.0012390615,0.000296804,0.0004103958,0.00004346725,0.00041449358,0.000016921567,0.0011236798,0.81068707,0.096906945,0.00058718614,0.08765661,0.00061738165],"about_ca_topic_score_codex":0.0000046288815,"about_ca_topic_score_gemma":0.0001201727,"teacher_disagreement_score":0.76087517,"about_ca_system_score_codex":0.0000301008,"about_ca_system_score_gemma":0.00020235855,"threshold_uncertainty_score":0.75982046},"labels":[],"label_agreement":null},{"id":"W3191052428","doi":"10.1186/1471-2105-12-s9-s5","title":"Fractionation statistics","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Genome; Gene; Gene duplication; Genetics; Chromosome; Function (biology); Copy-number variation; Computational biology; Binomial distribution; Gene dosage; Statistics; Mathematics; Gene expression","score_opus":0.0331666259512709,"score_gpt":0.236926421764829,"score_spread":0.2037597958135581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191052428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011486044,0.000056371908,0.96234083,0.000006282182,0.00022925605,0.00017376879,0.000056641267,0.00002411412,0.02562667],"genre_scores_gemma":[0.032777306,0.00008091435,0.9650706,0.00015081631,0.00012279615,0.000015459023,0.00041558212,0.0000171781,0.0013493265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999465,0.000010590967,0.00019173304,0.00007727787,0.0001192603,0.00013616092],"domain_scores_gemma":[0.99957144,0.000004925366,0.00008855106,0.00020394854,0.00008289121,0.000048225775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001016951,0.000085548716,0.000057648052,0.000041153813,0.00004687176,0.000013757075,0.000105462976,0.000074810276,0.00013612057],"category_scores_gemma":[0.000049139384,0.00008281319,0.000029599165,0.000053316286,0.00003066147,0.0000071907693,0.00004782589,0.000040401374,0.00022480832],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082022545,0.0020707054,0.20149815,0.0020550117,0.0012463334,0.000017322662,0.01310492,0.0016901859,0.056379624,0.0496559,0.30721346,0.36424816],"study_design_scores_gemma":[0.00471749,0.001963699,0.19720802,0.000048277263,0.00021956803,0.00013423724,0.0037368732,0.18896995,0.09213482,0.00606456,0.5023964,0.0024061014],"about_ca_topic_score_codex":0.000005169946,"about_ca_topic_score_gemma":0.000012891379,"teacher_disagreement_score":0.36184207,"about_ca_system_score_codex":0.000010344993,"about_ca_system_score_gemma":0.00004569055,"threshold_uncertainty_score":0.33770236},"labels":[],"label_agreement":null},{"id":"W3197024050","doi":"10.1186/s12859-021-04337-8","title":"A globally diverse reference alignment and panel for imputation of mitochondrial DNA variants","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mitochondrial Function and Pathology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; JPB Foundation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Haplogroup; Imputation (statistics); 1000 Genomes Project; Mitochondrial DNA; Biology; Computational biology; Missing data; Genetics; Genome; Genotyping; DNA microarray; Reference genome; Hypervariable region; Single-nucleotide polymorphism; Genotype; Computer science; Haplotype; Gene","score_opus":0.03677071907624388,"score_gpt":0.26635807950817375,"score_spread":0.22958736043192987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197024050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13814543,0.00016790784,0.85623515,0.00009680056,0.001283937,0.0005597946,0.0004094934,0.000015978037,0.0030855257],"genre_scores_gemma":[0.05230629,0.00034446243,0.9422024,0.0011325536,0.0005243758,0.00005706521,0.0017754162,0.000023738947,0.0016337045],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934226,0.000028372791,0.00027557756,0.00013355374,0.00009359713,0.00012661492],"domain_scores_gemma":[0.9994646,0.000022741246,0.00012975559,0.00018217953,0.000146096,0.000054636435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080703285,0.00009279325,0.00012600413,0.000021150467,0.000046152585,0.000018400062,0.00006908952,0.0001419643,0.000020279165],"category_scores_gemma":[0.00019219985,0.00008802713,0.00005136238,0.00004801184,0.00004060295,0.0000068058216,0.000087135195,0.000028021956,0.000005333398],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093472004,0.0001650711,0.0012150182,0.00058478024,0.00013402544,0.0000034528423,0.00075608684,0.0003591727,0.9644271,0.007218012,0.014317669,0.009884897],"study_design_scores_gemma":[0.019893741,0.004229106,0.008145321,0.00019400562,0.0005152602,0.0005211253,0.0070654266,0.048321977,0.68491673,0.0038376753,0.22065447,0.0017051728],"about_ca_topic_score_codex":0.0000036189215,"about_ca_topic_score_gemma":0.000031057083,"teacher_disagreement_score":0.27951038,"about_ca_system_score_codex":0.000006997447,"about_ca_system_score_gemma":0.00012493416,"threshold_uncertainty_score":0.35896423},"labels":[],"label_agreement":null},{"id":"W3203875161","doi":"10.1186/s12859-021-04398-9","title":"On the robustness of generalization of drug–drug interaction models","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université Laval","funders":"Mitacs; Compute Canada; Nvidia","keywords":"Computer science; Machine learning; Robustness (evolution); Generalizability theory; Artificial intelligence; Benchmarking; Multi-task learning; Generalization; Task (project management); Data mining","score_opus":0.04704167203536014,"score_gpt":0.2900567858064442,"score_spread":0.24301511377108403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203875161","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05527677,0.00002378608,0.9423126,0.00024080239,0.00034415117,0.00009501219,0.000005666499,0.000019791445,0.0016814084],"genre_scores_gemma":[0.23489244,0.000013603847,0.76473707,0.00018052285,0.000028122793,0.000006043936,0.0000182938,0.0000060139887,0.00011786724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884355,0.00015797226,0.0004534508,0.000090524016,0.0003630196,0.00009147858],"domain_scores_gemma":[0.99828,0.0006686771,0.00031403755,0.0004158515,0.0002983298,0.000023119124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047956585,0.00008498758,0.00013502104,0.00008726657,0.00004590067,0.000052006446,0.00038448602,0.000022277343,0.000011445395],"category_scores_gemma":[0.00015374734,0.0000635753,0.000077791236,0.0004757206,0.000032422584,0.0007208403,0.00018189914,0.00007210249,0.0000041100025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035473,0.00003090635,0.000011155505,0.00006795945,0.0000071596237,1.04611836e-7,0.0010729294,0.7830136,0.000017021533,0.21352088,0.0005659524,0.0016887644],"study_design_scores_gemma":[0.00011127773,0.000008578664,0.00010498906,0.0000600252,0.0000055248297,0.0000052899163,0.00031307997,0.97785157,0.0071394946,0.014294873,0.000039809845,0.00006551251],"about_ca_topic_score_codex":0.0000065508225,"about_ca_topic_score_gemma":0.00000924965,"teacher_disagreement_score":0.19922602,"about_ca_system_score_codex":0.00002965773,"about_ca_system_score_gemma":0.00018133972,"threshold_uncertainty_score":0.25925258},"labels":[],"label_agreement":null},{"id":"W3208925084","doi":"10.1186/s12859-021-04451-7","title":"LongStitch: high-quality genome assembly correction and scaffolding using long reads","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Scaffold; Sequence assembly; Computational biology; DNA microarray; Genome; Computer science; Quality (philosophy); Biology; Genetics; Programming language; Gene; Transcriptome","score_opus":0.033476493123443814,"score_gpt":0.27870488512566594,"score_spread":0.24522839200222213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208925084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.951915,0.0011377662,0.045527592,0.000016832844,0.00046947307,0.00010113367,0.000020574143,0.0000069753955,0.00080461754],"genre_scores_gemma":[0.9367442,0.00048022546,0.062051658,0.00014834688,0.00019499072,0.0000041329904,0.00008426355,0.000016778784,0.00027536732],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99909955,0.00003718885,0.00033693018,0.00019107998,0.00011067968,0.00022454956],"domain_scores_gemma":[0.99934804,0.000024332612,0.00014187506,0.0002755602,0.00013593481,0.00007425374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022965015,0.00015521458,0.00018090877,0.000032866596,0.00017278196,0.000071838556,0.00007684654,0.00012741769,0.000005582352],"category_scores_gemma":[0.000112778245,0.0001575173,0.000060898903,0.00009754297,0.000056454784,0.000003726632,0.00022083845,0.000056129873,0.0000047880358],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006236371,0.000074202355,0.06330002,0.00036479495,0.00020608104,0.0000059489385,0.00051408197,0.005536918,0.9213388,0.00035591592,0.00030033287,0.007940524],"study_design_scores_gemma":[0.0028320788,0.00046392053,0.56820375,0.00013899976,0.00031021688,0.0009165321,0.003954703,0.056534257,0.35436296,0.00028314386,0.009997183,0.0020022816],"about_ca_topic_score_codex":0.000033567554,"about_ca_topic_score_gemma":0.000108479864,"teacher_disagreement_score":0.5669759,"about_ca_system_score_codex":0.000022442924,"about_ca_system_score_gemma":0.00010638231,"threshold_uncertainty_score":0.64233685},"labels":[],"label_agreement":null},{"id":"W3209044105","doi":"10.1186/s12859-021-04420-0","title":"Improve hot region prediction by analyzing different machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Wuhan University of Science and Technology; Wuhan University; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Naive Bayes classifier; Machine learning; Artificial intelligence; Random forest; Hot spot (computer programming); Support vector machine; Cluster analysis; Algorithm; Bayes' theorem; Precision and recall; Measure (data warehouse); Data mining; Pattern recognition (psychology); Bayesian probability","score_opus":0.023246946459827913,"score_gpt":0.26319112687879803,"score_spread":0.23994418041897012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209044105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052266303,0.00022884046,0.993042,0.00015408428,0.00047567117,0.000110098226,0.00002438613,0.00020504977,0.0005332326],"genre_scores_gemma":[0.031577352,0.00013753278,0.9666927,0.0002344293,0.00013258697,0.000016417463,0.00025393034,0.000019261772,0.00093579735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985104,0.0001277016,0.0004715391,0.00023480903,0.00039622458,0.0002592946],"domain_scores_gemma":[0.9987205,0.00043514904,0.00022236379,0.00038272145,0.00013320727,0.00010603331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003097255,0.00017686049,0.00019530406,0.000104320876,0.00018256885,0.00031701897,0.0003601475,0.00007187304,0.000006825189],"category_scores_gemma":[0.00032902468,0.00016167069,0.000108299864,0.0004402866,0.000025962589,0.00087234756,0.0003712623,0.00026124716,0.000020956497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035367306,0.00063371094,0.032895632,0.00078706193,0.00019011364,0.00003960427,0.006069009,0.16379239,0.0020500028,0.01211035,0.006239469,0.7751573],"study_design_scores_gemma":[0.00032800675,0.00006820937,0.0024998165,0.000029621107,0.000012334917,0.000043189757,0.000072994764,0.9916408,0.0026679798,0.0005826235,0.0018842513,0.00017018252],"about_ca_topic_score_codex":0.0000070280134,"about_ca_topic_score_gemma":0.000004233723,"teacher_disagreement_score":0.82784843,"about_ca_system_score_codex":0.000105985455,"about_ca_system_score_gemma":0.0001149703,"threshold_uncertainty_score":0.6592739},"labels":[],"label_agreement":null},{"id":"W3216980854","doi":"10.1186/s12859-021-04484-y","title":"A multitask transfer learning framework for the prediction of virus-human protein–protein interactions","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction; Gottfried Wilhelm Leibniz Universität Hannover; Niedersächsische Ministerium für Wissenschaft und Kultur","keywords":"Transfer of learning; Computer science; Computational biology; Protein–protein interaction; Multi-task learning; Artificial intelligence; Machine learning; Biology; Task (project management); Genetics; Engineering","score_opus":0.020319157096883683,"score_gpt":0.26183476274924095,"score_spread":0.24151560565235727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216980854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06701255,0.00020791026,0.9310109,0.0000776833,0.0001666381,0.0007500079,0.00014529565,0.00001932061,0.0006096641],"genre_scores_gemma":[0.78957593,0.00007605927,0.2074424,0.00018126934,0.0003973502,0.00027429865,0.0006032664,0.00003737359,0.0014120764],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989537,0.00002996783,0.0005473943,0.00011888086,0.00012800048,0.00022204184],"domain_scores_gemma":[0.99918866,0.00005380235,0.00014782655,0.00037501322,0.000181705,0.00005298033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023004813,0.0001543897,0.00015751764,0.000032496093,0.0002666294,0.000052162068,0.00017791259,0.00018968464,0.000034749373],"category_scores_gemma":[0.00016170375,0.00012158502,0.00019463293,0.00011090958,0.00008469256,0.000016338183,0.00007550803,0.00024362029,0.0000067580945],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049162953,0.0004845797,0.00083541445,0.0023441922,0.0009631323,9.933802e-7,0.0045291134,0.02517088,0.8744559,0.046893056,0.0035354726,0.040295586],"study_design_scores_gemma":[0.0023776004,0.0009498028,0.0005965878,0.00053760246,0.0002286435,0.000039966617,0.004794555,0.32866177,0.49710402,0.004594944,0.15945627,0.0006582447],"about_ca_topic_score_codex":0.0000067154883,"about_ca_topic_score_gemma":0.00005460943,"teacher_disagreement_score":0.72356856,"about_ca_system_score_codex":0.0000141984065,"about_ca_system_score_gemma":0.00010491133,"threshold_uncertainty_score":0.49580932},"labels":[],"label_agreement":null},{"id":"W3216989434","doi":"10.1186/s12859-021-04371-6","title":"Randomized quantile residuals for diagnosing zero-inflated generalized linear mixed models with applications to microbiome count data","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Public Health Ontario; University of Toronto; University of Saskatchewan","funders":"","keywords":"Count data; Statistics; Overdispersion; Nominal level; Generalized linear mixed model; Quantile; Type I and type II errors; Generalized linear model; Quasi-likelihood; Computer science; Mathematics; False discovery rate; Poisson distribution; Confidence interval; Biology","score_opus":0.05691195805946668,"score_gpt":0.3233291252895891,"score_spread":0.26641716723012243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216989434","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049059257,0.0006988855,0.94597065,0.0003253979,0.000097323005,0.0022814416,0.0013674743,0.000040466588,0.00015907417],"genre_scores_gemma":[0.012445905,0.0005061639,0.9707278,0.0017050764,0.00016456212,0.0003915076,0.0134460805,0.00005646431,0.0005564219],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983542,0.00007672782,0.0006813715,0.0003701072,0.00012231512,0.00039525333],"domain_scores_gemma":[0.99797183,0.00010719062,0.00023176764,0.001159893,0.00037010308,0.00015919187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061879656,0.00023877097,0.00047821974,0.00007259155,0.00020392722,0.00009148997,0.00040064155,0.00019231519,0.00000767101],"category_scores_gemma":[0.00014884931,0.00020023082,0.0001033309,0.0002329845,0.00008001903,0.000024058369,0.00028358033,0.000076541706,0.000023384386],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029588649,0.0006439282,0.0001737366,0.002725874,0.0009391781,0.0000047827407,0.0013456565,0.029459875,0.79119605,0.0070549943,0.13478503,0.002082249],"study_design_scores_gemma":[0.14594376,0.00035869182,0.000050133178,0.00028263376,0.0005020129,0.00013005725,0.0005985211,0.343588,0.22605051,0.00042249053,0.2806262,0.0014469933],"about_ca_topic_score_codex":0.000024831279,"about_ca_topic_score_gemma":0.00016516307,"teacher_disagreement_score":0.56514555,"about_ca_system_score_codex":0.000024178384,"about_ca_system_score_gemma":0.00054847926,"threshold_uncertainty_score":0.81651753},"labels":[],"label_agreement":null},{"id":"W37286963","doi":"10.1186/s12859-023-05340-x","title":"Una experiencia de adecuación al EEES desde el área de Educación Plástica-Visual en el C.E.S. Cardenal Spínola","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Technology in Education and Healthcare","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Humanities; Art","score_opus":0.017456639588664145,"score_gpt":0.39521756619012327,"score_spread":0.3777609266014591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37286963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94560474,0.0002430238,0.011804401,0.008596053,0.00087210897,0.00052094023,0.000036109053,0.000616557,0.031706087],"genre_scores_gemma":[0.93893045,0.00010923754,0.057723705,0.0016305245,0.0006724181,0.00007458045,0.00003338981,0.000021788926,0.0008039223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99779296,0.00015431571,0.0005447292,0.00017239695,0.0004477394,0.0008878311],"domain_scores_gemma":[0.9988634,0.00022534306,0.00019842733,0.00027636436,0.00015387437,0.00028256964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079277443,0.00020518574,0.00023806839,0.0001793167,0.0007014172,0.00011099092,0.00051211513,0.00046445796,0.00017594696],"category_scores_gemma":[0.0005900431,0.00020979656,0.00010558037,0.00039884637,0.0005095149,0.00030587622,0.00007306529,0.00037620077,0.00017869797],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050032566,0.0005713008,0.3101796,0.00031241064,0.000041752963,0.000009836238,0.23318431,0.00015420574,0.00018162587,0.36921942,0.07169003,0.014405478],"study_design_scores_gemma":[0.0012084589,0.00025886815,0.16840237,0.00020594453,0.00009129845,0.00010861394,0.47265786,0.012329651,0.0018137054,0.023188503,0.31842145,0.0013132951],"about_ca_topic_score_codex":0.0033515517,"about_ca_topic_score_gemma":0.0034155606,"teacher_disagreement_score":0.34603092,"about_ca_system_score_codex":0.0006563969,"about_ca_system_score_gemma":0.002526127,"threshold_uncertainty_score":0.85552555},"labels":[],"label_agreement":null},{"id":"W4205780876","doi":"10.1186/s12859-021-04521-w","title":"Aristotle: stratified causal discovery for omics data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Medical Research Council; Genome Canada; Alfred P. Sloan Foundation","keywords":"Omics; Causal inference; Data science; Computer science; Data mining; Bioinformatics; Computational biology; Medicine; Biology","score_opus":0.09495989527245134,"score_gpt":0.2949676792731858,"score_spread":0.20000778400073443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205780876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00058906287,0.000043290107,0.99671495,0.0002121253,0.0006029649,0.00024731917,0.0004305571,0.00014069285,0.0010190482],"genre_scores_gemma":[0.09943289,0.0000091608135,0.898833,0.000700175,0.000073136536,0.000057951205,0.00049772044,0.000013274965,0.00038270274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869925,0.000030549985,0.00041618216,0.00024254617,0.00031845891,0.00029303675],"domain_scores_gemma":[0.9981621,0.00014821695,0.00016861313,0.0014019355,0.00004450146,0.000074659925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000598477,0.00013696868,0.00015725347,0.00006884281,0.0003913218,0.0004123589,0.0023163655,0.00004212113,0.0000075581283],"category_scores_gemma":[0.00007000077,0.00013185486,0.000047997488,0.00022647729,0.000033412638,0.0014812561,0.0014623185,0.00019809305,0.000015453885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009199788,0.00036373123,0.00044945558,0.0004934936,0.00008242039,0.0000062742906,0.004080763,0.0415421,0.0001716592,0.8309569,0.061000362,0.060760874],"study_design_scores_gemma":[0.00027135946,0.000095775475,0.00004039923,0.0000044651197,0.000009142543,0.000017371354,0.00028398965,0.981916,0.00005233588,0.010901935,0.006209039,0.00019816856],"about_ca_topic_score_codex":0.000014870699,"about_ca_topic_score_gemma":0.000014019751,"teacher_disagreement_score":0.9403739,"about_ca_system_score_codex":0.000054523684,"about_ca_system_score_gemma":0.00043407615,"threshold_uncertainty_score":0.5376885},"labels":[],"label_agreement":null},{"id":"W4206795002","doi":"10.1186/s12859-022-04559-4","title":"Topology preserving stratification of tissue neoplasticity using Deep Neural Maps and microRNA signatures","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"Southeastern Ontario Academic Medical Organization; Natural Sciences and Engineering Research Council of Canada","keywords":"microRNA; Computational biology; Artificial intelligence; Cluster analysis; Cancer; DNA microarray; Deep learning; Biology; Artificial neural network; Machine learning; Computer science; Bioinformatics; Gene expression; Gene; Genetics","score_opus":0.02635764017547924,"score_gpt":0.257129791685578,"score_spread":0.23077215151009875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206795002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06656271,0.00022129554,0.9324841,0.00018011055,0.00012781788,0.00010916868,0.000042901687,0.000033632292,0.00023828326],"genre_scores_gemma":[0.662384,0.000004769462,0.33741468,0.000114353665,0.000017767203,0.00000382034,0.000029952997,0.0000021898204,0.000028503657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991122,0.000065010536,0.00033298414,0.00012802797,0.00020060113,0.00016119496],"domain_scores_gemma":[0.99920726,0.00018596686,0.0002208865,0.00029422616,0.00004250601,0.000049181148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021361407,0.00008344231,0.00015978534,0.00018932552,0.00019991444,0.00006185437,0.0005828461,0.000041154934,0.00006364014],"category_scores_gemma":[0.00010048719,0.00007084544,0.000031418,0.0007077995,0.00006819219,0.0003547054,0.00074377254,0.00012804226,0.000001722549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010366998,0.00065525423,0.020773172,0.0011529508,0.00024449022,0.00002539763,0.010433294,0.50093883,0.013691181,0.2070255,0.0033330477,0.24162324],"study_design_scores_gemma":[0.000106884974,0.00009753806,0.0031066805,0.0000013379887,0.000016798813,0.00002185588,0.00038240087,0.9934765,0.0004387172,0.0017555397,0.00050530635,0.000090424975],"about_ca_topic_score_codex":0.00007961667,"about_ca_topic_score_gemma":0.000020447062,"teacher_disagreement_score":0.59582126,"about_ca_system_score_codex":0.000017828323,"about_ca_system_score_gemma":0.000024781175,"threshold_uncertainty_score":0.2888993},"labels":[],"label_agreement":null},{"id":"W4207000820","doi":"10.1186/s12859-022-04571-8","title":"Epigenetic landscape of drug responses revealed through large-scale ChIP-seq data analyses","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Degradation and Inhibitors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Bioscience Database Center; Japan Science and Technology Agency; Japan Society for the Promotion of Science; Institute of Genetics; Precursory Research for Embryonic Science and Technology; Kyoto University; Japan Agency for Medical Research and Development","keywords":"Epigenetics; Drug discovery; Computational biology; Transcriptome; Biology; DNA microarray; Drug; Disease; Histone; Bioinformatics; Gene; Genetics; Gene expression; Pharmacology; Medicine","score_opus":0.05363702471057392,"score_gpt":0.3247655073235028,"score_spread":0.2711284826129289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207000820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9133467,0.0045954403,0.067953385,0.00034049992,0.0005993782,0.0009598786,0.0033475908,0.00007577605,0.008781329],"genre_scores_gemma":[0.831214,0.00057248055,0.15549718,0.0009940155,0.00025581982,0.0000714907,0.0067835664,0.00005032163,0.0045611113],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985823,0.00014636488,0.00052985706,0.00021152447,0.0002996836,0.00023023738],"domain_scores_gemma":[0.9984329,0.000032154854,0.00029478248,0.0011244835,0.000060836344,0.00005488663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055022124,0.00014932117,0.00020334833,0.000072591705,0.00019128076,0.000021556962,0.0006670698,0.000060509534,0.00021542907],"category_scores_gemma":[0.00018467513,0.0001378827,0.00009198349,0.00022991792,0.000059870144,0.000020766121,0.00091387046,0.00011175341,0.000014846139],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028608232,0.0019358353,0.10504308,0.0019129058,0.000838484,0.000010093926,0.009219987,0.00778278,0.20870575,0.0008740529,0.6548091,0.0060070856],"study_design_scores_gemma":[0.004230208,0.0009510899,0.009365176,0.00006792756,0.000233817,0.000063766805,0.014970426,0.09708653,0.2981887,0.00026337476,0.57333434,0.0012446364],"about_ca_topic_score_codex":0.00001195929,"about_ca_topic_score_gemma":0.00003744993,"teacher_disagreement_score":0.09567791,"about_ca_system_score_codex":0.00001036834,"about_ca_system_score_gemma":0.000185605,"threshold_uncertainty_score":0.5622694},"labels":[],"label_agreement":null},{"id":"W4207037095","doi":"10.1186/s12859-022-04568-3","title":"Iam hiQ—a novel pair of accuracy indices for imputed genotypes","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Princess Margaret Cancer Centre; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto","funders":"University of Texas MD Anderson Cancer Center; National Institutes of Health; Deutsches Zentrum für Lungenforschung; Clalit Health Services; Radboud Universitair Medisch Centrum; Universität Salzburg; Umeå Universitet; Markey Cancer Center, University of Kentucky; Georg-August-Universität Göttingen; Lunds Universitet; Skånes universitetssjukhus; Radboud Universiteit; Newcastle University; National Cancer Institute; Universität Heidelberg; University of Liverpool; Vanderbilt University Medical Center; Huntsman Cancer Institute; Universidad de Oviedo; BC Cancer Agency; Vanderbilt University; Moffitt Cancer Center; Dartmouth College; Washington State University; Fred Hutchinson Cancer Research Center; World Health Organization","keywords":"Imputation (statistics); Computer science; Data mining; Software; Computational biology; Machine learning; Biology; Missing data","score_opus":0.025590839880014423,"score_gpt":0.2752904179259309,"score_spread":0.24969957804591647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207037095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6608101,0.0003583349,0.33656552,0.00020973744,0.000323619,0.0005877377,0.000738722,0.000029238221,0.0003769589],"genre_scores_gemma":[0.694197,0.000042713884,0.3035648,0.000601347,0.00013134671,0.00013780691,0.0010214464,0.000024910825,0.00027862997],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908906,0.00003351428,0.000441991,0.00011411774,0.000104067854,0.00021725746],"domain_scores_gemma":[0.9991099,0.00011086707,0.00040200233,0.00024941677,0.000088628716,0.000039185365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046298135,0.000105685125,0.00017738668,0.000055406384,0.00016196688,0.0000071501386,0.00024480085,0.00009708221,0.00002079449],"category_scores_gemma":[0.00042296693,0.00010151804,0.00010356995,0.000101086516,0.000040752842,0.00000427129,0.00022518057,0.00006411554,0.0000030548126],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001120564,0.0019515017,0.26412207,0.0022254828,0.0017830576,8.9867376e-7,0.006311872,0.09867371,0.34181654,0.008550031,0.21311828,0.060325984],"study_design_scores_gemma":[0.006603157,0.0038398495,0.14744338,0.000024753286,0.00026752762,0.00006502129,0.007161838,0.2180711,0.051147573,0.0013251998,0.5626408,0.0014097736],"about_ca_topic_score_codex":0.000016102877,"about_ca_topic_score_gemma":0.000015937589,"teacher_disagreement_score":0.34952253,"about_ca_system_score_codex":0.000018392451,"about_ca_system_score_gemma":0.00015554592,"threshold_uncertainty_score":0.41397855},"labels":[],"label_agreement":null},{"id":"W4220730260","doi":"10.1186/s12859-022-04631-z","title":"LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Genomics; Genome Canada","keywords":"Selection (genetic algorithm); Computational biology; Throughput; Computer science; DNA microarray; Landmark; DNA sequencing; Biology; Machine learning; Artificial intelligence; Genetics; DNA; Gene","score_opus":0.039024028273366214,"score_gpt":0.25847034451258344,"score_spread":0.21944631623921723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220730260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8723413,0.0003286059,0.122230016,0.0001394906,0.0003484999,0.0008598693,0.0009091972,0.00001745316,0.0028255768],"genre_scores_gemma":[0.8929916,0.00007295542,0.10439897,0.0005083836,0.0000948709,0.00005008423,0.0018333393,0.000019201652,0.00003056577],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999099,0.000057273188,0.00031241396,0.00018428617,0.00015480864,0.00019222686],"domain_scores_gemma":[0.99910486,0.000025411777,0.00009571227,0.0006871375,0.000037146496,0.000049712344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005627439,0.00010269436,0.000120354314,0.000065586726,0.00011709327,0.000025549589,0.00053379947,0.000049298007,0.000008986725],"category_scores_gemma":[0.00008862974,0.000089113884,0.000028737226,0.00026931966,0.000025736374,0.000012442797,0.0005870257,0.00008396769,0.0000018680128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020055454,0.0013313941,0.07064497,0.0010715344,0.00057877967,0.000003770699,0.010665603,0.65838534,0.1275592,0.0042104307,0.084723905,0.03881952],"study_design_scores_gemma":[0.0015314373,0.000710577,0.0027135273,0.000012314025,0.000047797563,0.00004515342,0.006658688,0.9356032,0.01307564,0.000077645265,0.039085485,0.0004385435],"about_ca_topic_score_codex":0.00046232346,"about_ca_topic_score_gemma":0.00095044455,"teacher_disagreement_score":0.27721784,"about_ca_system_score_codex":0.00006595945,"about_ca_system_score_gemma":0.00027751017,"threshold_uncertainty_score":0.36339587},"labels":[],"label_agreement":null},{"id":"W4220798428","doi":"10.1186/s12859-022-04649-3","title":"LPMX: a pure rootless composable container system","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo","keywords":"Container (type theory); Computer science; Composability; Host (biology); Operating system; Distributed computing; Pipeline (software); Cache; Virtualization; File system; Cloud computing; Engineering","score_opus":0.011376411945248294,"score_gpt":0.20942865192418297,"score_spread":0.19805223997893467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220798428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95692456,0.0020645265,0.014235839,0.00011655341,0.00090993283,0.0006985657,0.00038820645,0.000035480905,0.024626322],"genre_scores_gemma":[0.988405,0.000026405552,0.010144707,0.00027923455,0.00012332719,0.00008491779,0.00014083079,0.00002026434,0.0007753455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991214,0.000038306254,0.00029128004,0.00013816998,0.00016313126,0.00024768172],"domain_scores_gemma":[0.99940896,0.000011787261,0.00012283248,0.00034054334,0.000054882756,0.000060982893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020546808,0.00015161405,0.00017174047,0.00003542495,0.00031128438,0.000028893835,0.00026262284,0.000052527652,0.000019512385],"category_scores_gemma":[0.000010345104,0.00013821729,0.00009595487,0.00008361521,0.00004014782,9.499539e-7,0.0004504511,0.000085951106,0.00002089988],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019577334,0.0011831854,0.18006937,0.0047279303,0.0023042536,0.000049118215,0.008179132,0.23562962,0.23426068,0.052435633,0.26718205,0.012021309],"study_design_scores_gemma":[0.003782016,0.0014036717,0.0074522574,0.000035177072,0.00014356819,0.00039609018,0.024631321,0.14631948,0.011081013,0.0001534222,0.80320275,0.0013992174],"about_ca_topic_score_codex":0.000010576489,"about_ca_topic_score_gemma":0.000016731998,"teacher_disagreement_score":0.5360207,"about_ca_system_score_codex":0.000037505957,"about_ca_system_score_gemma":0.000087874745,"threshold_uncertainty_score":0.56363374},"labels":[],"label_agreement":null},{"id":"W4221090405","doi":"10.1186/s12859-022-04636-8","title":"The Xenopus phenotype ontology: bridging model organism phenotype data to human health and development","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; National Human Genome Research Institute; National Institutes of Health","keywords":"Ontology; Open Biomedical Ontologies; Computer science; Ontology-based data integration; Interoperability; Process ontology; Phenotype; Computational biology; Biology; Suggested Upper Merged Ontology; Bioinformatics; Information retrieval; World Wide Web; Semantic Web; Genetics; Gene","score_opus":0.07694043601688808,"score_gpt":0.31537138656195013,"score_spread":0.23843095054506205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221090405","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23196705,0.007273046,0.7488456,0.006726517,0.0010406513,0.0014121553,0.00033107382,0.00025762516,0.002146272],"genre_scores_gemma":[0.28105345,0.0002270752,0.70529693,0.009501981,0.00024130999,0.00008921227,0.0018884817,0.00006426912,0.0016373114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877936,0.00005049747,0.00037095716,0.00023016229,0.00020914381,0.00035989349],"domain_scores_gemma":[0.9989993,0.000026087346,0.00013251221,0.00064573396,0.000029419045,0.00016694817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006324072,0.00014304853,0.00015564542,0.000035226738,0.0011083178,0.00005058821,0.0006731873,0.00006469349,0.0000065627637],"category_scores_gemma":[0.00016519736,0.000110792476,0.000015683961,0.00008878499,0.00011115288,0.0000053105796,0.0016506043,0.00015705393,0.000010422897],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002957413,0.00024465972,0.0020507413,0.0003821944,0.00024221929,0.0000033613244,0.013345221,0.0026171778,0.0039091688,0.0023780053,0.17086627,0.8036652],"study_design_scores_gemma":[0.0009478268,0.0009614283,0.00085562875,0.000020740832,0.000017947905,0.00003847969,0.0056842887,0.13112958,0.000515705,0.0002646616,0.8589898,0.0005739384],"about_ca_topic_score_codex":0.000017582874,"about_ca_topic_score_gemma":0.00022697105,"teacher_disagreement_score":0.8030913,"about_ca_system_score_codex":0.000041620806,"about_ca_system_score_gemma":0.00054962863,"threshold_uncertainty_score":0.85243964},"labels":[],"label_agreement":null},{"id":"W4223431254","doi":"10.1186/s12859-022-04669-z","title":"Identification of multimodal brain imaging association via a parameter decomposition based sparse multi-view canonical correlation analysis method","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Key Research and Development Projects of Shaanxi Province; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; H. Lundbeck A/S; Servier; National Institutes of Health; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; Eisai; Genentech; IXICO; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; China Postdoctoral Science Foundation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Canonical correlation; Computer science; Modality (human–computer interaction); Neuroimaging; Artificial intelligence; Identification (biology); Pattern recognition (psychology); Correlation; Feature (linguistics); Feature selection; Association (psychology); Machine learning; Data mining; Mathematics; Neuroscience","score_opus":0.03446274984406474,"score_gpt":0.32011182714199315,"score_spread":0.28564907729792843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223431254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014702827,0.000019297788,0.98306775,0.0011905467,0.0003163105,0.00042959544,0.00014674675,0.000076768345,0.00005017876],"genre_scores_gemma":[0.78623533,0.000003161101,0.2108404,0.002503051,0.00002323962,0.00013761593,0.00013514234,0.000016419477,0.00010566027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720037,0.0007072316,0.0008432779,0.00028166885,0.0007422481,0.00022520301],"domain_scores_gemma":[0.98975766,0.008728267,0.0010116404,0.00031038825,0.0001449284,0.000047142737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019420248,0.00015872416,0.00031352954,0.00045316256,0.00043991263,0.000058116893,0.00019055884,0.00005133953,0.00007197081],"category_scores_gemma":[0.007901692,0.00017260204,0.00025605655,0.0013605997,0.000044987453,0.00044499908,0.00013171781,0.00022649993,0.00002214713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013205809,0.0004938914,0.05080594,0.00013639692,0.00017180308,0.0000014837757,0.0015097312,0.9071102,0.029323718,0.00031004005,0.0011084505,0.008896264],"study_design_scores_gemma":[0.000648406,0.00003841452,0.022754788,0.0000060832713,0.00021177762,0.0000046275463,0.00015334769,0.9690845,0.0065702396,0.000083035346,0.0002767733,0.00016800192],"about_ca_topic_score_codex":0.00009304899,"about_ca_topic_score_gemma":0.00008692758,"teacher_disagreement_score":0.77222735,"about_ca_system_score_codex":0.00059738447,"about_ca_system_score_gemma":0.00011197451,"threshold_uncertainty_score":0.9459633},"labels":[],"label_agreement":null},{"id":"W4223988818","doi":"10.1186/s12859-022-04667-1","title":"Deep clustering of small molecules at large-scale via variational autoencoder embedding and K-means","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Autoencoder; Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Principal component analysis; Cluster (spacecraft); Embedding; Similarity (geometry); Biological system; Data mining; Deep learning; Biology","score_opus":0.011832895892648772,"score_gpt":0.2411205728047431,"score_spread":0.22928767691209434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223988818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014458757,0.000026552465,0.9838732,0.000049935436,0.00043194924,0.00017956932,0.000065886874,0.00007934407,0.00083484326],"genre_scores_gemma":[0.0015886821,0.00000246694,0.99801886,0.0001548611,0.000030238672,0.000024703897,0.000025357003,0.00001424804,0.00014055861],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832577,0.0001229699,0.00054629846,0.00019173285,0.00047808487,0.00033513052],"domain_scores_gemma":[0.9990855,0.00013259624,0.00037971436,0.0002726912,0.00005123141,0.00007830219],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012456543,0.00014936157,0.00021880699,0.00010619703,0.0005167563,0.000086421656,0.00039202935,0.000041462543,0.0014712688],"category_scores_gemma":[0.00011765312,0.0001441242,0.000042326814,0.00016528532,0.00009967728,0.00023557307,0.0011109104,0.00010758296,0.00004554351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002142123,0.000024585579,0.0015143277,0.0001773238,0.000002440896,7.5320946e-7,0.0036579182,0.98912084,0.005037673,0.00031634836,0.000038054015,0.0000882978],"study_design_scores_gemma":[0.00030684704,0.000064127926,0.0020662309,0.000013155204,0.000011212814,0.000059671664,0.00062694406,0.9958841,0.00024215154,0.00019460326,0.00036119166,0.00016974758],"about_ca_topic_score_codex":0.00003190697,"about_ca_topic_score_gemma":0.00010153419,"teacher_disagreement_score":0.014145721,"about_ca_system_score_codex":0.00008973251,"about_ca_system_score_gemma":0.000058392823,"threshold_uncertainty_score":0.9994415},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4225364091","doi":"10.1186/s12859-021-04536-3","title":"vCOMBAT: a novel tool to create and visualize a computational model of bacterial antibiotic target-binding","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Norges Forskningsråd; National Center for Advancing Translational Sciences; Universitetet i Tromsø; European Molecular Biology Organization; Bill and Melinda Gates Foundation","keywords":"Antibiotics; Dosing; Antibiotic resistance; Computer science; Rifampicin; Computational biology; Bacteria; Biochemical engineering; Biology; Microbiology; Pharmacology; Engineering","score_opus":0.01690757740222136,"score_gpt":0.24422808697473308,"score_spread":0.2273205095725117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225364091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91540927,0.000024129531,0.0834744,0.0000549519,0.00014912027,0.00025784067,0.00048623374,0.000013518745,0.00013053721],"genre_scores_gemma":[0.6459187,0.000012802576,0.35336792,0.00016938549,0.000037089554,0.000010027996,0.00037774027,0.000016180345,0.00009014149],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906707,0.000016268657,0.00038471635,0.00017078775,0.00015037076,0.0002107675],"domain_scores_gemma":[0.9995194,0.00000956807,0.00015514153,0.00020137825,0.000054219647,0.00006030028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018371649,0.00014432117,0.000191959,0.000101519,0.00012576046,0.000028538776,0.00019105183,0.000114942595,0.000023012799],"category_scores_gemma":[0.000042707165,0.0001465571,0.000056037657,0.00012257343,0.000068377376,0.000005368554,0.0005704907,0.00007761168,0.00000289274],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024141968,0.00012765826,0.0004691829,0.000111273985,0.000048787486,2.9513285e-7,0.00026015198,0.047906175,0.9483034,0.0011225705,0.0004886664,0.00092044065],"study_design_scores_gemma":[0.0022654159,0.0014957122,0.0009591675,0.000021928929,0.000044217086,0.00006758925,0.00042728038,0.85249734,0.13252795,0.00023909622,0.008860784,0.0005935222],"about_ca_topic_score_codex":0.000003627153,"about_ca_topic_score_gemma":0.0000020285668,"teacher_disagreement_score":0.81577545,"about_ca_system_score_codex":0.000015158544,"about_ca_system_score_gemma":0.00012249676,"threshold_uncertainty_score":0.5976425},"labels":[],"label_agreement":null},{"id":"W4225376695","doi":"10.1186/s12859-022-04673-3","title":"KnotAli: informed energy minimization through the use of evolutionary information","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudoknot; Multiple sequence alignment; Computer science; Structural alignment; Sequence alignment; Energy minimization; Nucleic acid structure; Sequence (biology); Nucleic acid secondary structure; Quality Score; Data mining; Computational biology; Bioinformatics; Artificial intelligence; RNA; Biology; Genetics; Physics","score_opus":0.030252200067816076,"score_gpt":0.22977132947826795,"score_spread":0.19951912941045188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225376695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07049646,0.0012484367,0.9049678,0.0008981038,0.002196271,0.0025907091,0.0014826001,0.00016308155,0.015956579],"genre_scores_gemma":[0.41597477,0.00091293175,0.5651442,0.007063243,0.00029776938,0.0007183081,0.007167552,0.00006465777,0.002656612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989484,0.00007030613,0.0004783654,0.0000605051,0.00028837664,0.00015404486],"domain_scores_gemma":[0.99911904,0.00005076434,0.00034742392,0.00036097137,0.00009612636,0.000025652225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004885907,0.00011421937,0.00010124546,0.00005018911,0.00025184557,0.000031650812,0.00024167997,0.000074132964,0.000091314774],"category_scores_gemma":[0.00018414398,0.000089886664,0.00008879358,0.00017829183,0.000060252343,0.000083454695,0.00024406455,0.000052670486,0.0000066945513],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010225158,0.00026171556,0.0012917898,0.0005714385,0.00029048216,6.373862e-7,0.007025374,0.23348923,0.004178546,0.054983426,0.63906735,0.0578175],"study_design_scores_gemma":[0.0002684244,0.00017665328,0.0001375152,0.000006303726,0.000014847944,0.000018854073,0.0009940452,0.031881135,0.008705048,0.00022283714,0.95744157,0.00013274999],"about_ca_topic_score_codex":0.000036833884,"about_ca_topic_score_gemma":0.000008700945,"teacher_disagreement_score":0.3454783,"about_ca_system_score_codex":0.000026263851,"about_ca_system_score_gemma":0.0002026314,"threshold_uncertainty_score":0.36654717},"labels":[],"label_agreement":null},{"id":"W4225684933","doi":"10.1186/s12859-022-04647-5","title":"Supervised promoter recognition: a benchmark framework","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Benchmark (surveying); Benchmarking; Machine learning; Deep learning; Computer science; Artificial intelligence; Promoter; DNA microarray; Computational biology; Process (computing); Data mining; Biology; Gene; Genetics","score_opus":0.013961049832787028,"score_gpt":0.22111594216789052,"score_spread":0.20715489233510348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225684933","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92073494,0.00020609719,0.06885178,0.0001538094,0.0005614277,0.0005353702,0.00033733808,0.0000443344,0.008574921],"genre_scores_gemma":[0.38246834,0.00009207315,0.61090463,0.002063711,0.0003572657,0.00021624059,0.0029563021,0.000060328763,0.0008811328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990837,0.000037210506,0.00031051747,0.00015015302,0.00018096186,0.00023747304],"domain_scores_gemma":[0.99935895,0.000013544447,0.00011126115,0.00039725733,0.00004712937,0.00007186959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020760237,0.00014206371,0.000114630006,0.000043607135,0.00024490026,0.000043707772,0.0002758139,0.00009629872,0.00043947942],"category_scores_gemma":[0.000051143634,0.00014790692,0.000104159684,0.00012078658,0.000035442026,0.0000050545277,0.0003517993,0.00016515004,0.000050303886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029774779,0.0058576646,0.08492426,0.0062023103,0.0023206938,0.00009254423,0.031638317,0.055218335,0.104148746,0.0129380375,0.28555617,0.40812543],"study_design_scores_gemma":[0.0040332717,0.003121738,0.0045706253,0.000092999675,0.00016508729,0.0006086239,0.008730187,0.65421724,0.008309063,0.014111983,0.29921642,0.0028227412],"about_ca_topic_score_codex":0.0000022768575,"about_ca_topic_score_gemma":0.0000052416094,"teacher_disagreement_score":0.5989989,"about_ca_system_score_codex":0.000028395069,"about_ca_system_score_gemma":0.00011137337,"threshold_uncertainty_score":0.6031469},"labels":[],"label_agreement":null},{"id":"W4226144949","doi":"10.1186/s12859-022-04662-6","title":"Computationally repurposing drugs for breast cancer subtypes using a network-based approach","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Windsor Clinical Research; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Drug repositioning; Repurposing; Drug discovery; Computational biology; Drug; In silico; Disease; Drug development; DNA microarray; Interaction network; Bioinformatics; Computer science; Biology; Medicine; Pharmacology; Gene; Genetics","score_opus":0.04285852233238176,"score_gpt":0.30537347045572055,"score_spread":0.2625149481233388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226144949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024035384,0.00011019343,0.99559027,0.00019638083,0.0004816412,0.00057485484,0.00016528176,0.00014639749,0.00033146248],"genre_scores_gemma":[0.016779823,8.165187e-7,0.98178965,0.0010343435,0.00014385988,0.0001340776,0.00007517439,0.000018207418,0.000024041776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806607,0.00015909877,0.0005203994,0.00026012957,0.0006188801,0.00037542725],"domain_scores_gemma":[0.99839604,0.0006265284,0.0003595379,0.00034087483,0.00019481924,0.00008221424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011133001,0.00018357381,0.00022077518,0.00016223428,0.00070051925,0.00025385764,0.0007500492,0.00003517588,0.000015330454],"category_scores_gemma":[0.000028409955,0.00019367514,0.0001476855,0.00077979785,0.000043769756,0.0006031445,0.00043610123,0.00015464322,0.0000019105112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031343618,0.000050717732,0.00031304362,0.00011738404,0.000018807363,2.8840844e-7,0.0006696889,0.9666602,0.0000023023254,0.017496627,0.00050700596,0.0141326],"study_design_scores_gemma":[0.0005679374,0.00002913615,0.001060098,0.000020435446,0.000018051112,0.00004596504,0.00014094479,0.993279,0.000006283657,0.0035539304,0.0010237904,0.00025442845],"about_ca_topic_score_codex":0.000020791405,"about_ca_topic_score_gemma":0.0000020887085,"teacher_disagreement_score":0.026618809,"about_ca_system_score_codex":0.00030050246,"about_ca_system_score_gemma":0.0010653099,"threshold_uncertainty_score":0.78978425},"labels":[],"label_agreement":null},{"id":"W4237234846","doi":"10.1186/1471-2105-3-15","title":"Erratum to: The Comparative RNA Web (CRW) Site: an online database of comparative sequence and structure information for ribosomal, intron, and other RNAs: Correction","year":2002,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"National Science Foundation","keywords":"Intron; Computational biology; Biology; Ribosomal RNA; Web site; Sequence (biology); RNA; Genetics; Sequence database; Database; World Wide Web; Computer science; Gene; The Internet","score_opus":0.05235440435453029,"score_gpt":0.2973078417660093,"score_spread":0.24495343741147899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237234846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2917298,0.012707209,0.5071885,0.0008730427,0.03591048,0.022720484,0.11248603,0.00025507255,0.016129352],"genre_scores_gemma":[0.2699743,0.00613623,0.5846322,0.0076193623,0.0074315933,0.0009357457,0.09462114,0.00033581106,0.028313633],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998504,0.00009961871,0.00066273357,0.00023613308,0.00023737607,0.00026017104],"domain_scores_gemma":[0.9983101,0.000054380736,0.00070046296,0.00052477675,0.00028199484,0.00012828139],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021747588,0.00040503006,0.0004885569,0.0001192351,0.00019863812,0.00011859319,0.00029057567,0.0004675141,0.000016824626],"category_scores_gemma":[0.00010447987,0.0002979748,0.00006916377,0.00013011601,0.00017582686,0.00008199219,0.00015787956,0.00029886104,0.0000047104118],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005727588,0.00009761371,0.00006132087,0.0013651463,0.00023183187,2.1983394e-7,0.008467393,0.00059806544,0.045279626,0.00024023019,0.936594,0.0064918105],"study_design_scores_gemma":[0.0011679614,0.0018505711,0.00015333407,0.000508099,0.00020918633,0.0000612316,0.0057388297,0.25732124,0.030665232,0.00010804332,0.7013133,0.000902936],"about_ca_topic_score_codex":0.000027746793,"about_ca_topic_score_gemma":0.0008103509,"teacher_disagreement_score":0.25672317,"about_ca_system_score_codex":0.000022896691,"about_ca_system_score_gemma":0.00016646463,"threshold_uncertainty_score":0.99994725},"labels":[],"label_agreement":null},{"id":"W4281817583","doi":"10.1186/s12859-022-04751-6","title":"CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"Institute of Health Services and Policy Research; Canadian Institutes of Health Research","keywords":"Benchmarking; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Data science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Computational biology; Information retrieval; Biology; Virology; Medicine; Business","score_opus":0.12784802972864218,"score_gpt":0.3884872227123956,"score_spread":0.26063919298375343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281817583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094765314,0.00016463842,0.9963729,0.00041248876,0.00024828865,0.00034330488,0.00019694712,0.00017469197,0.0011390835],"genre_scores_gemma":[0.023499412,0.00001619151,0.97541213,0.0007105208,0.000051333423,0.000071485614,0.00020656426,0.000007199248,0.000025170139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974675,0.00062453223,0.00047199105,0.00025462953,0.0008273631,0.00035397953],"domain_scores_gemma":[0.99705666,0.0017679945,0.00020966929,0.0006774558,0.000087643646,0.0002005982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072070854,0.00011437854,0.00013552881,0.00022808496,0.0009978873,0.00034335826,0.0006804579,0.00003841246,0.000009018647],"category_scores_gemma":[0.0025385648,0.00012002493,0.000020486525,0.00043667195,0.000058172685,0.001386086,0.0014907174,0.0003774777,0.000016544602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001339506,0.00017320218,0.0019094828,0.0077743377,0.00007891807,0.00014119083,0.103951566,0.28535983,0.00008095319,0.45465162,0.055037513,0.090707436],"study_design_scores_gemma":[0.00021709659,0.00008589749,0.000017162325,0.000028716277,0.0000044899375,0.0002949362,0.014273823,0.91088,0.0000017722236,0.00016620176,0.07390195,0.0001278991],"about_ca_topic_score_codex":0.00037768474,"about_ca_topic_score_gemma":0.000025312944,"teacher_disagreement_score":0.6255202,"about_ca_system_score_codex":0.00038263277,"about_ca_system_score_gemma":0.00034708617,"threshold_uncertainty_score":0.7675044},"labels":[],"label_agreement":null},{"id":"W4283267624","doi":"10.1186/s12859-022-04790-z","title":"RResolver: efficient short-read repeat resolution within ABySS","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Computational biology; DNA microarray; Resolution (logic); Computer science; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.01872862315502454,"score_gpt":0.23430197223895327,"score_spread":0.21557334908392872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283267624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9513678,0.0021014337,0.02009027,0.00007295362,0.001146273,0.0006321692,0.00022315203,0.000028176079,0.024337798],"genre_scores_gemma":[0.9692816,0.000099697725,0.028575283,0.0004231149,0.00017791922,0.00009078041,0.00023428208,0.00002895273,0.0010883845],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988525,0.000043927725,0.00039809913,0.0001955021,0.0002395663,0.00027042395],"domain_scores_gemma":[0.99929374,0.000012637182,0.00011794124,0.0004562664,0.000052755397,0.00006665252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037486164,0.00016269411,0.00014474173,0.000054298373,0.00038209648,0.000026336993,0.0002497158,0.000063680134,0.000027707421],"category_scores_gemma":[0.0000466096,0.0001582582,0.000111359455,0.00011340209,0.00006679018,8.5230874e-7,0.00052611274,0.00011360183,0.000013027881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011271262,0.00079011306,0.03055543,0.00045070116,0.0005853889,0.000013218828,0.008199123,0.7770848,0.10841393,0.005699019,0.049685564,0.017395569],"study_design_scores_gemma":[0.0020989573,0.0017373905,0.011510448,0.000024923038,0.00014668208,0.00019918512,0.007732505,0.4855131,0.017267425,0.00020090371,0.47212702,0.0014414823],"about_ca_topic_score_codex":0.00000912857,"about_ca_topic_score_gemma":0.000014889006,"teacher_disagreement_score":0.42244145,"about_ca_system_score_codex":0.00004173572,"about_ca_system_score_gemma":0.000086897955,"threshold_uncertainty_score":0.6453582},"labels":[],"label_agreement":null},{"id":"W4283365300","doi":"10.1186/s12859-022-04804-w","title":"SAPFIR: A webserver for the identification of alternative protein features","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Alternative splicing; Biology; RNA splicing; Computational biology; Gene; Genetics; Human genome; DNA microarray; Gene isoform; Genome; Gene expression; RNA","score_opus":0.020927017190322375,"score_gpt":0.2846299926362194,"score_spread":0.26370297544589705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283365300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8614029,0.0011029724,0.13374771,0.00028395417,0.00020623491,0.0022463566,0.00027606863,0.000012673616,0.0007211236],"genre_scores_gemma":[0.96882015,0.000045916,0.0158032,0.0002482893,0.00012806398,0.00082068157,0.0002406442,0.000018569697,0.013874484],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993821,0.000026999403,0.00022932154,0.00006782093,0.00017542478,0.000118367636],"domain_scores_gemma":[0.9994677,0.000021876025,0.00015517468,0.00024883938,0.00008381649,0.000022620385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038843002,0.000057242916,0.00005905079,0.000028529199,0.00017352415,0.00002042274,0.00027879883,0.000024843031,0.000009223319],"category_scores_gemma":[0.00013848917,0.000041137835,0.000075670265,0.000068710906,0.00004039024,0.0000049797254,0.00015612469,0.00006424141,0.0000013724161],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083161314,0.00023192624,0.0010480967,0.0007058251,0.00023772636,3.1516527e-7,0.0008256843,0.009794243,0.9131452,0.006659698,0.030636277,0.035883438],"study_design_scores_gemma":[0.00132689,0.0008500395,0.0022477903,0.000022232185,0.00003385819,0.000016928992,0.0040804753,0.21994895,0.6742525,0.00060551555,0.09634039,0.00027441094],"about_ca_topic_score_codex":0.000019435194,"about_ca_topic_score_gemma":0.000016018912,"teacher_disagreement_score":0.23889263,"about_ca_system_score_codex":0.000012619579,"about_ca_system_score_gemma":0.00012544042,"threshold_uncertainty_score":0.16775522},"labels":[],"label_agreement":null},{"id":"W4287959313","doi":"10.1186/s12859-022-04840-6","title":"Pan-cancer integrative analysis of whole-genome De novo somatic point mutations reveals 17 cancer types","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Simon Fraser University","funders":"","keywords":"Cancer; Somatic cell; Genetics; Biology; Point mutation; DNA microarray; Genome; Computational biology; Mutation; Gene; Gene expression","score_opus":0.013698067476509522,"score_gpt":0.27714162343285337,"score_spread":0.26344355595634383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287959313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9390696,0.0033054305,0.047137294,0.00036431153,0.00027870497,0.0005728954,0.007043067,0.000022159817,0.002206508],"genre_scores_gemma":[0.97154367,0.0009956857,0.0224471,0.0011495901,0.00013241191,0.00042963627,0.0018962771,0.000034022218,0.0013716046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988721,0.000044105826,0.0005057809,0.00015485533,0.00018170656,0.00024144203],"domain_scores_gemma":[0.99900204,0.00006647667,0.0003540067,0.00035655036,0.00014675071,0.00007418399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022342727,0.0001647232,0.00031054512,0.00019638425,0.00014955198,0.000027967211,0.0002627189,0.00006727811,0.00028468735],"category_scores_gemma":[0.000121051686,0.00015612388,0.00021707093,0.00055487413,0.000079528116,0.000008642748,0.00017189783,0.000110137,0.0000045459465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023577463,0.00041730553,0.055910513,0.00048155262,0.0045779184,0.000004152365,0.011431197,0.73248446,0.17989263,0.0008355906,0.008952223,0.0047766683],"study_design_scores_gemma":[0.006551899,0.0025174343,0.15418708,0.00028370676,0.013124277,0.0000715379,0.045260765,0.5537403,0.071830995,0.0028571733,0.14569156,0.0038832396],"about_ca_topic_score_codex":0.00017443013,"about_ca_topic_score_gemma":0.00094820233,"teacher_disagreement_score":0.17874415,"about_ca_system_score_codex":0.00014581483,"about_ca_system_score_gemma":0.0004656425,"threshold_uncertainty_score":0.6366547},"labels":[],"label_agreement":null},{"id":"W4292171780","doi":"10.1186/s12859-022-04878-6","title":"Semi-supervised COVID-19 CT image segmentation using deep generative models","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Deep learning; Autoencoder; Pattern recognition (psychology); Generative model; Image segmentation; Convolutional neural network; Ground truth; Scale-space segmentation; Segmentation-based object categorization; Generative grammar","score_opus":0.08687116947554052,"score_gpt":0.34736270832576854,"score_spread":0.260491538850228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292171780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07721895,0.00016209988,0.9163527,0.0036308623,0.0003163194,0.0013591828,0.00014217016,0.00028481107,0.00053294085],"genre_scores_gemma":[0.04155819,0.000053018928,0.86647403,0.090506405,0.00018277833,0.00021921248,0.0007120097,0.00008069458,0.00021367201],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979503,0.00011838561,0.000641523,0.00022342248,0.00070745416,0.00035889892],"domain_scores_gemma":[0.9985847,0.00026624603,0.00025833232,0.00046313275,0.00011099274,0.00031658178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005214711,0.00024768192,0.00034249475,0.0003069682,0.00058803783,0.0000870228,0.00018041943,0.000043708675,0.0005718765],"category_scores_gemma":[0.00029059974,0.00025119318,0.0001506951,0.0005365912,0.00008399653,0.00054631266,0.00025929735,0.00028153267,0.00004018765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020575455,0.00038055624,0.0024148386,0.0016378646,0.00013197059,0.00007920802,0.021260124,0.9451956,0.0048250523,0.0003641469,0.02117229,0.0023325898],"study_design_scores_gemma":[0.00238301,0.00014981578,0.000051924817,0.000029435942,0.00017050505,0.00019166568,0.006183383,0.9842201,0.0012440705,0.00025456492,0.0048508337,0.0002706752],"about_ca_topic_score_codex":0.00016967152,"about_ca_topic_score_gemma":0.000025802094,"teacher_disagreement_score":0.08687554,"about_ca_system_score_codex":0.0016072823,"about_ca_system_score_gemma":0.0011885009,"threshold_uncertainty_score":0.99999404},"labels":[],"label_agreement":null},{"id":"W4292729083","doi":"10.1186/s12859-022-04882-w","title":"Learning to detect boundary information for brain image segmentation","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Segmentation; Computer science; Boundary (topology); Artificial intelligence; Image segmentation; Pattern recognition (psychology); Sørensen–Dice coefficient; Computer vision; Context (archaeology); Scale-space segmentation; Mathematics; Biology","score_opus":0.015227836235929859,"score_gpt":0.2715470974248548,"score_spread":0.2563192611889249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292729083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014555304,0.0000052702762,0.9957124,0.0008840747,0.00016251346,0.00093908876,0.000020422458,0.00027204776,0.0005486582],"genre_scores_gemma":[0.0033512039,0.0000016786571,0.9932149,0.0024480713,0.000029061548,0.0006944419,0.00011093905,0.00000788162,0.00014179891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989393,0.00003507764,0.00039220235,0.00010537656,0.00028070377,0.00024737348],"domain_scores_gemma":[0.9990944,0.00022671619,0.00021753785,0.00030712222,0.00007606555,0.000078114186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003692134,0.00010719987,0.00009379906,0.00016432621,0.00079630857,0.0002358507,0.00053592294,0.000020365505,0.000011180926],"category_scores_gemma":[0.00010757584,0.000117686235,0.000052900472,0.0006213326,0.000016334872,0.0021349979,0.0004136829,0.00014858274,0.00010398563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000471825,0.000023838327,0.000082218925,0.00016727697,0.000012642083,3.2102113e-7,0.011852304,0.24215129,0.0012790029,0.0133314505,0.03156627,0.6994862],"study_design_scores_gemma":[0.0003156307,0.00022022166,0.000099342105,0.0000029803857,0.0000028566371,0.000009358081,0.00080698065,0.8563496,0.00060407765,0.0020170915,0.1394102,0.00016165593],"about_ca_topic_score_codex":0.0000014021757,"about_ca_topic_score_gemma":0.0000023513214,"teacher_disagreement_score":0.69932455,"about_ca_system_score_codex":0.00014751905,"about_ca_system_score_gemma":0.000085749874,"threshold_uncertainty_score":0.61246425},"labels":[],"label_agreement":null},{"id":"W4297475198","doi":"10.1186/s12859-022-04933-2","title":"Identifying health related occupations of Twitter users through word embedding and deep neural networks","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Lakehead University","keywords":"Computer science; Word embedding; Artificial neural network; Embedding; Artificial intelligence; Word (group theory); Encoder; Recurrent neural network; Transformer; Deep learning; Recall; Social media; Construct (python library); Machine learning; Precision and recall; F1 score; Natural language processing; Information retrieval; World Wide Web","score_opus":0.1478485987947585,"score_gpt":0.41606809107234716,"score_spread":0.2682194922775887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297475198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.865327,0.0018490738,0.104679376,0.006123438,0.015104187,0.0040590907,0.000029661338,0.00031977377,0.0025083877],"genre_scores_gemma":[0.9058616,0.0002714257,0.09218086,0.0010270082,0.00025595678,0.0002788592,0.00007204514,0.000020331912,0.000031911208],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826455,0.00027497511,0.00063885294,0.00008980713,0.00039222842,0.00033958233],"domain_scores_gemma":[0.9982088,0.0009426047,0.00053835294,0.00013668183,0.00006127619,0.00011224812],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0011119146,0.000080131606,0.00017636323,0.0000935969,0.0013682735,0.000050363687,0.00016317383,0.00006391985,0.000121010744],"category_scores_gemma":[0.00081133196,0.00009183985,0.00004178671,0.0007041752,0.00013423059,0.00045228325,0.000086832915,0.00025827868,0.0000035841363],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017612321,0.00004892658,0.10891656,0.00028365827,0.000018208448,2.9995985e-7,0.8450479,0.016226314,3.1997894e-7,0.004938613,0.0014269534,0.02307467],"study_design_scores_gemma":[0.0003321706,0.000068174166,0.029033955,0.00004507146,0.000022876882,0.0000038167964,0.27357447,0.6915546,6.506815e-7,0.001002418,0.004159241,0.0002025414],"about_ca_topic_score_codex":0.002177997,"about_ca_topic_score_gemma":0.00056152715,"teacher_disagreement_score":0.6753283,"about_ca_system_score_codex":0.00029663867,"about_ca_system_score_gemma":0.00031307258,"threshold_uncertainty_score":0.9999318},"labels":[],"label_agreement":null},{"id":"W4297997542","doi":"10.1186/s12859-022-04946-x","title":"Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; Directorate for Computer and Information Science and Engineering; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Artificial intelligence; Neuroimaging; Discriminative model; Cluster analysis; Computer science; Canonical correlation; Feature learning; Imaging genetics; Pattern recognition (psychology); Modality (human–computer interaction); Unsupervised learning; Dimensionality reduction; Deep learning; Machine learning; Psychology; Neuroscience","score_opus":0.02594478998113494,"score_gpt":0.34339418836680774,"score_spread":0.3174493983856728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297997542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9679977,0.0003786759,0.020405874,0.000613281,0.00018673037,0.0027828116,0.000027905107,0.00013333141,0.007473661],"genre_scores_gemma":[0.98902065,0.000049100974,0.008057652,0.0013007045,0.000038674243,0.0003942077,0.00016379211,0.000027912081,0.00094728323],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977705,0.00015580255,0.0005136481,0.00021395492,0.000790591,0.00055549736],"domain_scores_gemma":[0.999176,0.00015322077,0.00011501353,0.00016832206,0.000159556,0.00022789132],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00078280194,0.00019432412,0.00030164298,0.0005115998,0.00024288437,0.00006431654,0.00015951098,0.000029196339,0.0010120983],"category_scores_gemma":[0.00023855842,0.0001869178,0.00012335135,0.00067123724,0.00005543919,0.00020397294,0.00047129724,0.0005145407,0.00046268158],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047686137,0.0005287486,0.9717012,0.00047585557,0.000060396458,0.00007696092,0.0060634105,0.0008197644,0.00007441188,0.000019901552,0.0006663705,0.019036142],"study_design_scores_gemma":[0.004129565,0.00093047804,0.75150824,0.00028396546,0.00008935427,0.000075147465,0.025525898,0.2140045,0.00025038785,0.00002029111,0.00290007,0.00028208905],"about_ca_topic_score_codex":0.000044562024,"about_ca_topic_score_gemma":0.000042458007,"teacher_disagreement_score":0.22019292,"about_ca_system_score_codex":0.00026412643,"about_ca_system_score_gemma":0.00019284869,"threshold_uncertainty_score":0.9999011},"labels":[],"label_agreement":null},{"id":"W4303423564","doi":"10.1186/s12859-022-04972-9","title":"Comparative transcriptomics analysis pipeline for the meta-analysis of phylogenetically divergent datasets (CoRMAP)","year":2022,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada; Morris Animal Foundation","keywords":"Computational biology; Biology; RNA-Seq; Pipeline (software); De novo transcriptome assembly; DNA microarray; Metadata; Transcriptome; Gene; Gene expression; Computer science; Genetics; World Wide Web","score_opus":0.23312561210069377,"score_gpt":0.3716177139744434,"score_spread":0.1384921018737496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303423564","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009303055,0.88344234,0.085303955,0.000008175756,0.00012200219,0.001211577,0.029801426,0.0000029421183,0.000098249766],"genre_scores_gemma":[0.0000884954,0.9696752,0.01441639,0.00010272541,0.000057790043,0.0004819463,0.01504039,0.000028005708,0.00010905904],"study_design_codex":"meta_analysis","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970945,0.0001638293,0.0016328408,0.000418489,0.00033266706,0.00035767653],"domain_scores_gemma":[0.9969109,0.00042397925,0.0010737915,0.0013580441,0.00014057306,0.00009268703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071423355,0.0005917738,0.0039777323,0.00039567996,0.00026130976,0.000039454502,0.0010687673,0.00021726276,0.00017452722],"category_scores_gemma":[0.00006736172,0.00037308031,0.00716551,0.0013402881,0.00019158398,0.0000015989444,0.00047757308,0.00016598147,0.0000028119216],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005781158,0.00016503048,0.00001741379,0.003092459,0.9485298,2.584006e-7,0.0004110866,0.02112767,0.000013076626,0.00012008644,0.0032086724,0.023256673],"study_design_scores_gemma":[0.00009343472,0.00006652247,0.00000804863,0.000003518079,0.44689098,8.428836e-7,0.00013443461,0.016073518,0.0000099570025,0.0000027154624,0.5364804,0.00023558279],"about_ca_topic_score_codex":0.000017631974,"about_ca_topic_score_gemma":0.00025762996,"teacher_disagreement_score":0.5332718,"about_ca_system_score_codex":0.000026350624,"about_ca_system_score_gemma":0.00022899483,"threshold_uncertainty_score":0.9998721},"labels":[],"label_agreement":null},{"id":"W4308436127","doi":"10.1186/s12859-022-04812-w","title":"A novel method for drug-target interaction prediction based on graph transformers model","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital","funders":"","keywords":"Drug target; Drug; Computer science; Graph; Transformer; Interaction network; Artificial intelligence; Theoretical computer science; Pharmacology; Engineering; Medicine; Biology; Voltage","score_opus":0.04043657864088868,"score_gpt":0.3149732236917865,"score_spread":0.2745366450508978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308436127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015723435,0.0000037881573,0.9960994,0.00043620743,0.00073853036,0.0006569419,0.00028489783,0.00018406745,0.0014388943],"genre_scores_gemma":[0.006333598,7.2940935e-7,0.99206406,0.0010788537,0.00002886487,0.00028777076,0.00012913451,0.000014499863,0.00006250745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830854,0.00010567202,0.0004969347,0.00023746146,0.0005897085,0.00026171026],"domain_scores_gemma":[0.9985662,0.000750529,0.00020489725,0.00031096122,0.00008735331,0.00008004241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014086276,0.00017890718,0.00017526292,0.00040907416,0.00037185635,0.00011274768,0.0005099485,0.00003532322,0.000010705345],"category_scores_gemma":[0.00007404373,0.00018264624,0.00021697275,0.0005566772,0.000017402699,0.0009168556,0.00010193396,0.000219593,0.0000039701354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007693236,0.00012390995,0.000008083681,0.000075274715,0.0000112670305,8.2175994e-8,0.0011047511,0.9714355,0.000052631254,0.010858166,0.0009424468,0.0153109925],"study_design_scores_gemma":[0.00094723067,0.00021669744,0.000039420876,0.00001235723,0.000013673662,0.000012532333,0.00031805685,0.98951095,0.00030665332,0.0067830686,0.0016514976,0.00018785556],"about_ca_topic_score_codex":0.000006910851,"about_ca_topic_score_gemma":0.000003000152,"teacher_disagreement_score":0.018075494,"about_ca_system_score_codex":0.00022132207,"about_ca_system_score_gemma":0.00033095872,"threshold_uncertainty_score":0.74480975},"labels":[],"label_agreement":null},{"id":"W4311134061","doi":"10.1186/s12859-022-04582-5","title":"Boosting tissue-specific prediction of active cis-regulatory regions through deep learning and Bayesian optimization techniques","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Charité – Universitätsmedizin Berlin; Berlin Institute of Health; Università degli Studi di Milano","keywords":"Artificial intelligence; Machine learning; Bayesian optimization; Deep learning; Computer science; Enhancer; Computational biology; Convolutional neural network; Epigenomics; Artificial neural network; Biology; DNA methylation; Transcription factor; Genetics","score_opus":0.009196831369433146,"score_gpt":0.2200819021844075,"score_spread":0.21088507081497437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311134061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06163679,0.00037898638,0.93484503,0.00001621882,0.0000798437,0.00029905277,0.000062683794,0.000041266114,0.0026401577],"genre_scores_gemma":[0.5494185,0.0007494989,0.44870242,0.00004414479,0.00007768924,0.000045109802,0.00075370894,0.00003298038,0.00017592881],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992599,0.000039456478,0.00031247787,0.00012623101,0.00012921334,0.00013272511],"domain_scores_gemma":[0.9994506,0.000013719876,0.00026929824,0.00017686118,0.00005829996,0.000031184125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001451596,0.00011083587,0.00011618845,0.000048718186,0.00026609786,0.000018391685,0.00009900405,0.00008461051,0.000017221297],"category_scores_gemma":[0.000027336986,0.00012321073,0.000037940616,0.000095527634,0.00006581387,0.000014294167,0.00019927259,0.000117652104,3.0881782e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039206937,0.0003256633,0.0073933396,0.00093074294,0.00025384632,0.0000027345059,0.011309432,0.72058153,0.1452117,0.0050009415,0.002055784,0.10654225],"study_design_scores_gemma":[0.00055953924,0.0008489119,0.0010113277,0.000033187192,0.000041061245,0.00007838103,0.007934986,0.9317311,0.030612966,0.00027943696,0.026535101,0.00033398083],"about_ca_topic_score_codex":0.0000034088935,"about_ca_topic_score_gemma":0.000003270536,"teacher_disagreement_score":0.4877817,"about_ca_system_score_codex":0.000034425415,"about_ca_system_score_gemma":0.00003831736,"threshold_uncertainty_score":0.5024388},"labels":[],"label_agreement":null},{"id":"W4311481079","doi":"10.1186/s12859-022-05059-1","title":"Development of an image classification pipeline for atherosclerotic plaques assessment using supervised machine learning","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Carleton University","keywords":"Artificial intelligence; Thresholding; Segmentation; Computer science; Pattern recognition (psychology); Feature selection; Pipeline (software); Support vector machine; Image segmentation; Preprocessor; Image processing; Classifier (UML); Image (mathematics)","score_opus":0.05393710765054982,"score_gpt":0.3645234978491708,"score_spread":0.310586390198621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311481079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35348782,0.000033405246,0.64558697,0.000018620054,0.000032503453,0.0003534219,0.0000523696,0.000027754,0.00040714245],"genre_scores_gemma":[0.114217184,0.00001748263,0.8842586,0.000052626758,0.000040184088,0.00010893178,0.0011632608,0.000018289178,0.00012339947],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988405,0.000043166117,0.00043185984,0.00014671878,0.000318969,0.00021879791],"domain_scores_gemma":[0.99944586,0.000023195587,0.00014706471,0.00021440009,0.00008952496,0.0000799784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005780381,0.000111930596,0.00013502053,0.000057168298,0.00021912366,0.000018506416,0.00027821906,0.00007168152,0.0000624792],"category_scores_gemma":[0.00009557379,0.00010291268,0.000060182916,0.000108109474,0.00007966688,0.000009273852,0.00024583872,0.00015461276,5.485595e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094683215,0.00016458343,0.00036025702,0.00016748112,0.000013675597,8.6876824e-8,0.0001411509,0.00006212986,0.9933414,0.00008544067,0.00014984971,0.0054192645],"study_design_scores_gemma":[0.0004644942,0.00028866503,0.00013783427,0.000010088345,0.000008757259,0.0000032374226,0.00053452345,0.66361874,0.32209542,0.00004966431,0.012656963,0.00013160775],"about_ca_topic_score_codex":0.000003886598,"about_ca_topic_score_gemma":0.000003102153,"teacher_disagreement_score":0.671246,"about_ca_system_score_codex":0.000084849285,"about_ca_system_score_gemma":0.00024804525,"threshold_uncertainty_score":0.41966572},"labels":[],"label_agreement":null},{"id":"W4319748040","doi":"10.1186/s12859-023-05141-2","title":"Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data","year":2023,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Institute of General Medical Sciences; Intellectual and Developmental Disabilities Research Center; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of Pennsylvania","keywords":"Interpretability; Leverage (statistics); Computer science; Machine learning; Artificial intelligence; Annotation; Labeled data; Data mining","score_opus":0.06189355387424046,"score_gpt":0.30034539051275455,"score_spread":0.2384518366385141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319748040","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006812425,0.8182771,0.16339491,0.000006417074,0.00041745434,0.0034511397,0.0073117777,0.000055544504,0.00027321282],"genre_scores_gemma":[0.00090585375,0.9651815,0.028542336,0.000049288792,0.00017902393,0.00006426354,0.004917692,0.00006415954,0.00009584951],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819005,0.000063011525,0.0008112905,0.0004473059,0.00018137177,0.0003069559],"domain_scores_gemma":[0.9980062,0.000042064326,0.0003669679,0.001276164,0.000118738004,0.00018983765],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003509016,0.00042153988,0.0009001091,0.00008709655,0.00007701117,0.000043133976,0.00073569926,0.00034490039,0.000003161639],"category_scores_gemma":[0.00010835957,0.00030960143,0.00014060838,0.00020901115,0.000108810375,0.000019220928,0.0011272298,0.00016478261,0.0000058593555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018478445,0.0005552405,0.00090676465,0.11843865,0.005191758,0.000012120154,0.0013830487,0.13164936,0.000087437234,0.000066510045,0.009959547,0.72990173],"study_design_scores_gemma":[0.0005890686,0.00038819946,0.00002096787,0.0021125318,0.0008422632,0.000023089575,0.00006833555,0.9748746,0.00000779739,0.0000026242542,0.020580262,0.0004902489],"about_ca_topic_score_codex":0.000005365136,"about_ca_topic_score_gemma":0.000035630947,"teacher_disagreement_score":0.84322524,"about_ca_system_score_codex":0.000027669847,"about_ca_system_score_gemma":0.0009234112,"threshold_uncertainty_score":0.9999356},"labels":[],"label_agreement":null},{"id":"W4321002108","doi":"10.1186/s12859-023-05168-5","title":"petiteFinder: an automated computer vision tool to compute Petite colony frequencies in baker’s yeast","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Simons Foundation","keywords":"Biology; Yeast; Computer science; Artificial intelligence; Object detection; Object (grammar); Computational biology; Pattern recognition (psychology); Genetics","score_opus":0.012276469586557724,"score_gpt":0.2896800436631122,"score_spread":0.27740357407655447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321002108","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9042778,0.000023997427,0.09280435,0.00013468467,0.00008809648,0.0005531074,0.00003446183,0.00076301035,0.0013204622],"genre_scores_gemma":[0.28849715,0.00016429221,0.70483035,0.0025327934,0.00035731908,0.00008167093,0.0022997586,0.00008640497,0.0011502348],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861985,0.000050882903,0.00049515365,0.0002575103,0.00022561857,0.00035096967],"domain_scores_gemma":[0.9990637,0.000016901426,0.000108129425,0.0005873018,0.00011519901,0.000108820685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040171176,0.0002089512,0.00023219669,0.00030197445,0.000070000126,0.00012648238,0.0003483664,0.00016813075,0.0000151379345],"category_scores_gemma":[0.000056281893,0.00020503052,0.00009556437,0.0005879481,0.000056566947,0.000030900504,0.00034079092,0.00009855212,0.00029619562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003241111,0.0006878583,0.02791055,0.00086400495,0.00021576256,0.00012102868,0.0028641003,0.052271202,0.31248733,0.00048042665,0.55394804,0.047825564],"study_design_scores_gemma":[0.0004695974,0.0005833579,0.024416741,0.0000732715,0.000016017935,0.000024444755,0.00017338645,0.9237451,0.012788265,0.000020892849,0.037233,0.0004559094],"about_ca_topic_score_codex":0.000035366742,"about_ca_topic_score_gemma":0.0003662347,"teacher_disagreement_score":0.8714739,"about_ca_system_score_codex":0.000036499845,"about_ca_system_score_gemma":0.00008162877,"threshold_uncertainty_score":0.83609015},"labels":[],"label_agreement":null},{"id":"W4353020774","doi":"10.1186/s12859-023-05227-x","title":"PWN: enhanced random walk on a warped network for disease target prioritization","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Prioritization; Computer science; Random walk; Computational biology; Biology; Mathematics; Statistics; Engineering; Process management","score_opus":0.012019183507147879,"score_gpt":0.24452672842898954,"score_spread":0.23250754492184167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353020774","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0097036,0.00018470296,0.98533577,0.00015135788,0.0007636479,0.0013240499,0.00020537035,0.000119541844,0.0022119859],"genre_scores_gemma":[0.30041188,0.001601736,0.6566636,0.0060369866,0.005537741,0.0011593185,0.020720067,0.00027289827,0.0075958157],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998497,0.000020803534,0.0005617888,0.0001965785,0.00018980107,0.0005340201],"domain_scores_gemma":[0.9989383,0.00007304337,0.00021672477,0.0004666531,0.00010670622,0.00019854377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044089704,0.00024978528,0.000234513,0.00007077713,0.00022527129,0.0000759251,0.00023957607,0.00019632898,0.000010614194],"category_scores_gemma":[0.00014869879,0.00022595092,0.00020005529,0.00025171274,0.000052238724,0.000014513372,0.00010733748,0.00009095485,0.00012973776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00487741,0.00019003847,0.0010876347,0.0017514717,0.00026229394,0.000002705238,0.001028941,0.43451464,0.0017547203,0.006399634,0.50942975,0.038700774],"study_design_scores_gemma":[0.0036014563,0.000324764,0.000548227,0.000082458464,0.000045553796,0.000001651059,0.00015486668,0.90208286,0.0014345889,0.0029817296,0.0882425,0.0004993279],"about_ca_topic_score_codex":7.837186e-7,"about_ca_topic_score_gemma":0.000004718528,"teacher_disagreement_score":0.46756822,"about_ca_system_score_codex":0.000020417085,"about_ca_system_score_gemma":0.00015002489,"threshold_uncertainty_score":0.9214011},"labels":[],"label_agreement":null},{"id":"W4360826396","doi":"10.1186/s12859-023-05226-y","title":"Complete sequence verification of plasmid DNA using the Oxford Nanopore Technologies’ MinION device","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nanopore and Nanochannel Transport Studies","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Minion; Plasmid; Nanopore sequencing; Sanger sequencing; Biology; DNA sequencing; Computational biology; Consensus sequence; Genetics; Sequence (biology); Computer science; DNA; Base sequence","score_opus":0.08525135470605225,"score_gpt":0.2667828808131616,"score_spread":0.18153152610710935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360826396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8572824,0.0014209326,0.12842008,0.00046948376,0.0015650712,0.0014888284,0.00064301037,0.004356469,0.004353705],"genre_scores_gemma":[0.96275026,0.00148165,0.035470515,0.000029968744,0.000029964964,0.00003077195,0.00013961524,0.000032912798,0.000034374265],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909383,0.00000538599,0.00042644638,0.00006873639,0.00018335623,0.00022226782],"domain_scores_gemma":[0.99945086,0.000071671566,0.00010523311,0.00030127034,0.00005426438,0.000016698927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015822132,0.00014294838,0.00018189593,0.00013673313,0.00012777485,0.000012289395,0.00025255885,0.00009468255,0.0000036086005],"category_scores_gemma":[0.00002691794,0.000106213534,0.000057469053,0.0007442242,0.00012808041,0.00015686855,0.000043102566,0.00009589883,0.00002877208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013443736,0.00019071646,0.023312168,0.022490192,0.001133021,0.000029148812,0.04465036,0.55193347,0.24649061,0.01441087,0.02860447,0.066620514],"study_design_scores_gemma":[0.00019040766,0.000027320348,0.00042054587,0.000115035116,0.00003434586,0.000006792611,0.0045191734,0.9622691,0.020245964,0.0001802057,0.011792088,0.00019898254],"about_ca_topic_score_codex":0.0000037203679,"about_ca_topic_score_gemma":0.000014078653,"teacher_disagreement_score":0.41033566,"about_ca_system_score_codex":0.00003164105,"about_ca_system_score_gemma":0.000016637201,"threshold_uncertainty_score":0.4331262},"labels":[],"label_agreement":null},{"id":"W4366742336","doi":"10.1186/s12859-023-05264-6","title":"In-vitro validated methods for encoding digital data in deoxyribonucleic acid (DNA)","year":2023,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"Division of Electrical, Communications and Cyber Systems; Semiconductor Research Corporation; National Science Foundation","keywords":"DNA microarray; DNA; Computational biology; In vitro; Encoding (memory); Computer science; Digital polymerase chain reaction; Biology; Genetics; Gene; Polymerase chain reaction; Gene expression; Artificial intelligence","score_opus":0.2006860204091278,"score_gpt":0.43959385722058486,"score_spread":0.23890783681145705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366742336","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008552389,0.88356066,0.11147262,0.00001352196,0.000625546,0.0019523756,0.0013498925,0.000080508085,0.0008593319],"genre_scores_gemma":[0.000016067976,0.7263886,0.2592679,0.00008002659,0.00026801325,0.00007102644,0.013673585,0.00006466097,0.00017014137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997659,0.00012099066,0.0011471127,0.00045512817,0.00010001912,0.0005177157],"domain_scores_gemma":[0.99833846,0.00028820732,0.00040509936,0.00085290836,0.000036184716,0.0000791439],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012783861,0.00040800648,0.0010157301,0.00020542252,0.000050121867,0.00014415526,0.0011431508,0.0006403484,0.0000023238338],"category_scores_gemma":[0.0014697404,0.00031263725,0.000274016,0.00045345858,0.000055231132,0.000026689484,0.0013796267,0.00026221178,0.000037649526],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026813646,0.00004197008,0.000009898096,0.01061184,0.000067982626,0.0000032273022,0.000020733192,0.000004506391,0.00046141318,0.000019454628,0.00055038993,0.98818177],"study_design_scores_gemma":[0.00035465072,0.000092080496,0.0000018583297,0.00155634,0.000082697334,0.000022088161,0.00005596589,0.010226026,0.0005574826,0.00006631156,0.9864337,0.0005508091],"about_ca_topic_score_codex":0.000001940726,"about_ca_topic_score_gemma":0.0000066809853,"teacher_disagreement_score":0.98763096,"about_ca_system_score_codex":0.00004157584,"about_ca_system_score_gemma":0.00021867912,"threshold_uncertainty_score":0.9999326},"labels":[],"label_agreement":null},{"id":"W4376872947","doi":"10.1186/s12859-023-05327-8","title":"CysPresso: a classification model utilizing deep learning protein representations to predict recombinant expression of cysteine-dense peptides","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biochemical and Structural Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Critical Systems Labs; Sunnybrook Health Science Centre","funders":"H2020 Marie Skłodowska-Curie Actions; Medical Research Council; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; University of Cambridge; UK Research and Innovation","keywords":"Artificial intelligence; Deep learning; Computer science; Computational biology; Machine learning; Concatenation (mathematics); Convolutional neural network; Chemical space; Support vector machine; Drug discovery; Chemistry; Biology; Biochemistry; Mathematics","score_opus":0.030178129362653336,"score_gpt":0.2728277365811366,"score_spread":0.24264960721848328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376872947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9324856,0.000018238201,0.06639515,0.000062385305,0.000060134906,0.00044152452,0.00002393594,0.000066740555,0.00044629964],"genre_scores_gemma":[0.96476454,0.00003645456,0.033568036,0.000025591522,0.000045749483,0.000073405274,0.0007725509,0.000016943468,0.0006967229],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989193,0.00003829945,0.00045918158,0.00019019097,0.00019173372,0.00020127455],"domain_scores_gemma":[0.9992429,0.000015702763,0.00022257671,0.00029194652,0.00013851192,0.00008834096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015713967,0.00013547605,0.00014019462,0.00009060181,0.00010758144,0.000028453438,0.00016298545,0.00015263034,0.000003039272],"category_scores_gemma":[0.00036906937,0.00011737647,0.000072057366,0.0002546639,0.000040328367,0.000022495822,0.00015979387,0.00009292533,0.000016465943],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007290941,0.000013059599,0.0008572009,0.000175108,0.0000066141874,1.5741651e-7,0.00041249083,0.005726896,0.9909638,0.00008025978,0.00026786423,0.0014236068],"study_design_scores_gemma":[0.00024825527,0.00012562226,0.0031885474,0.000093626615,0.0000092395485,0.000002892723,0.00063749164,0.48598403,0.5092061,0.000094501185,0.00026742977,0.00014227077],"about_ca_topic_score_codex":0.0000034897243,"about_ca_topic_score_gemma":0.0000033728127,"teacher_disagreement_score":0.48175773,"about_ca_system_score_codex":0.000012292101,"about_ca_system_score_gemma":0.000036367175,"threshold_uncertainty_score":0.47864735},"labels":[],"label_agreement":null},{"id":"W4378903236","doi":"10.1186/s12859-023-05357-2","title":"Correction: Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data","year":2023,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Interpretability; Generative grammar; Computer science; Artificial intelligence; Machine learning; DNA microarray; Generative adversarial network; Computational biology; Adversarial system; Data mining; Deep learning; Biology; Genetics; Gene","score_opus":0.0189577919662543,"score_gpt":0.2449546566504362,"score_spread":0.2259968646841819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378903236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029275205,0.0013743591,0.92464757,0.000076705386,0.0277115,0.0026898591,0.007242177,0.000099436,0.0068831905],"genre_scores_gemma":[0.20040976,0.05750127,0.46292025,0.0040306076,0.021462638,0.00084573403,0.13785438,0.0013133755,0.113662],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981329,0.000036603615,0.00069263286,0.00051539944,0.00026840248,0.0003541061],"domain_scores_gemma":[0.9977498,0.00006921445,0.00036043784,0.001383172,0.00025304855,0.00018432231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036317974,0.00041111177,0.00052747125,0.000094596806,0.00010773246,0.00006436936,0.00064683554,0.00057642104,0.0000065955965],"category_scores_gemma":[0.0003151077,0.00036891742,0.00007337593,0.00022654593,0.00014704048,0.000024008383,0.0011320128,0.00038952878,0.000004947339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008745662,0.000064258325,0.0011078897,0.0006390903,0.00033396613,9.840966e-7,0.00043605876,0.19150124,0.00012846304,0.0000050170056,0.8018407,0.003067752],"study_design_scores_gemma":[0.0008723031,0.0007387689,0.00037689076,0.00026897623,0.00020628302,0.000011948443,0.00013415606,0.9865358,0.00019246183,0.0000036906592,0.010235046,0.00042366495],"about_ca_topic_score_codex":0.00003902732,"about_ca_topic_score_gemma":0.0005656072,"teacher_disagreement_score":0.7950346,"about_ca_system_score_codex":0.00006349067,"about_ca_system_score_gemma":0.0012573053,"threshold_uncertainty_score":0.99987626},"labels":[],"label_agreement":null},{"id":"W4379197269","doi":"10.1186/s12859-023-05350-9","title":"An analysis of entity normalization evaluation biases in specialized domains","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Computer science; Data science; Task (project management); Natural language processing; Field (mathematics); Information retrieval; Artificial intelligence; Mathematics","score_opus":0.08364742459170624,"score_gpt":0.3394736568482408,"score_spread":0.25582623225653456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379197269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32882363,0.000003613194,0.6704948,0.000010688624,0.00009216817,0.00012688141,0.000004487136,0.00006283563,0.00038087243],"genre_scores_gemma":[0.76751244,0.000016692455,0.23223361,0.000038391325,0.000024690946,0.000010550831,0.00014866376,0.0000033458932,0.000011619694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869126,0.000080637845,0.00049652247,0.00010524925,0.00047321734,0.00015310162],"domain_scores_gemma":[0.9990909,0.00008147532,0.00018572672,0.0004819432,0.00012187069,0.000038070706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013431681,0.00006681481,0.00016908276,0.0008837858,0.000037526723,0.00007107916,0.0003668019,0.000045780067,0.00002414729],"category_scores_gemma":[0.0002453123,0.00006555396,0.00006223541,0.0029773964,0.000015127781,0.0009311667,0.000081912454,0.00003287282,0.000018288523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027924334,0.00003358802,0.04669656,0.000036304813,0.000027140253,3.205768e-7,0.0035542632,0.93188745,0.00002967858,0.008390349,0.000025982046,0.009315601],"study_design_scores_gemma":[0.0002545407,0.000012583623,0.08200925,0.000010911086,0.000056250537,1.8131428e-7,0.000214045,0.91685534,0.00010588567,0.00039711312,0.00001785332,0.000066035944],"about_ca_topic_score_codex":0.00008450645,"about_ca_topic_score_gemma":0.0008904817,"teacher_disagreement_score":0.43868878,"about_ca_system_score_codex":0.00006379598,"about_ca_system_score_gemma":0.00010601251,"threshold_uncertainty_score":0.2673213},"labels":[],"label_agreement":null},{"id":"W4379768536","doi":"10.1186/s12859-023-05340-x","title":"Rescuing biologically relevant consensus regions across replicated samples","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Computer science; Bioconductor; Computational biology; Scripting language; R package; Data mining; Biology; Genetics; Gene","score_opus":0.037743523144960406,"score_gpt":0.28342205504383733,"score_spread":0.24567853189887692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379768536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98179364,0.0000920219,0.015122497,0.0002656668,0.00016964025,0.00029285438,0.0002431146,0.00017751215,0.0018430587],"genre_scores_gemma":[0.81431085,0.0010587282,0.17890641,0.0007158546,0.00024248073,0.0000618885,0.0026063945,0.00007377548,0.0020236142],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986109,0.00003321489,0.00051347225,0.00024996046,0.0001222216,0.00047022075],"domain_scores_gemma":[0.9988288,0.000060587896,0.00019682985,0.00070189015,0.00010341652,0.000108457214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004241726,0.0001921034,0.00019359225,0.00004690472,0.00023030366,0.00006406805,0.00031225517,0.00024558365,0.0000054677334],"category_scores_gemma":[0.00039862155,0.00016405772,0.00012740219,0.00026541742,0.00015943983,0.000002919536,0.00033968623,0.00010990378,0.00013958456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006951103,0.0003959664,0.040053394,0.001415964,0.00071668683,0.00005854287,0.004127769,0.026672147,0.6966326,0.026241649,0.1797572,0.023232972],"study_design_scores_gemma":[0.0036307003,0.0012922504,0.056393683,0.00019731284,0.00009803267,0.0004605796,0.010084532,0.589908,0.025430925,0.0062269336,0.30372757,0.0025494595],"about_ca_topic_score_codex":0.000009550349,"about_ca_topic_score_gemma":0.000062290244,"teacher_disagreement_score":0.6712017,"about_ca_system_score_codex":0.000018716557,"about_ca_system_score_gemma":0.00008814299,"threshold_uncertainty_score":0.669008},"labels":[],"label_agreement":null},{"id":"W4381094396","doi":"10.1186/s12859-023-05377-y","title":"Covariance regression with random forests","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; HEC Montréal; Fondation HEC","keywords":"Random forest; Covariance; Regression; Statistics; Regression analysis; Analysis of covariance; Computer science; Computational biology; Biology; Mathematics; Artificial intelligence","score_opus":0.10617106040966945,"score_gpt":0.3688357029765211,"score_spread":0.2626646425668516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381094396","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002974835,0.000015536207,0.9918347,0.000037341237,0.00021601464,0.0002923257,0.000025728335,0.00027696337,0.004326567],"genre_scores_gemma":[0.0027319973,0.00002611815,0.9965886,0.000050872342,0.00007634155,0.000033878998,0.000013108276,0.000020592675,0.00045849604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988289,0.00005106267,0.0003926037,0.00010478761,0.0003238021,0.00029884468],"domain_scores_gemma":[0.99745625,0.0017651534,0.00017495481,0.00035730356,0.0001443644,0.00010195682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059419754,0.00015784396,0.00026760323,0.000084275795,0.00011209762,0.00005346573,0.00017613017,0.0000676651,0.00006579261],"category_scores_gemma":[0.0037191145,0.000095124706,0.000043858687,0.00044887885,0.00008332678,0.00013258828,0.000068379755,0.00014400612,0.00020405398],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007206938,0.00012789955,0.012045971,0.0033515855,0.00006431949,0.000020909047,0.002202718,0.0004825502,0.000015396481,0.7560563,0.10708601,0.11782564],"study_design_scores_gemma":[0.002120585,0.00013139768,0.004442678,0.00050914806,0.00003987614,0.00001106322,0.00026139218,0.68545866,0.00012932853,0.3024434,0.004142847,0.00030965975],"about_ca_topic_score_codex":0.0000020140337,"about_ca_topic_score_gemma":0.000016269341,"teacher_disagreement_score":0.6849761,"about_ca_system_score_codex":0.00001699741,"about_ca_system_score_gemma":0.000078092846,"threshold_uncertainty_score":0.4452396},"labels":[],"label_agreement":null},{"id":"W4382316216","doi":"10.1186/1471-2105-16-s19-s6","title":"Evolution of genes neighborhood within reconciled phylogenies: an ensemble approach","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"Simon Fraser University; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Evolutionary biology; Computer science; Gene; Computational biology; Biology; Genetics","score_opus":0.0365057201472548,"score_gpt":0.2460932431510488,"score_spread":0.20958752300379402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382316216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52983415,0.0012382679,0.45510438,0.000007037355,0.00030516754,0.00053597754,0.00004538417,0.00003943773,0.012890183],"genre_scores_gemma":[0.69260556,0.0000318598,0.306597,0.000029745199,0.00017853596,0.00002219915,0.0002696235,0.000022411627,0.00024306962],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998921,0.0000462892,0.00043132337,0.00015795015,0.00022692361,0.00021654913],"domain_scores_gemma":[0.99891144,0.0000048556462,0.0002479558,0.00047520746,0.00021932044,0.00014123989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042774325,0.0001625996,0.00018397252,0.00007052039,0.000036937843,0.000021263111,0.00024292042,0.00016623396,0.000004244687],"category_scores_gemma":[0.00007977587,0.00014841714,0.00007279173,0.00013538353,0.00006932314,0.00001838458,0.00009503544,0.000054875938,0.000019545425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014381589,0.0025221007,0.15251374,0.0031756745,0.0011094493,0.0000032428404,0.023005677,0.09328416,0.65989554,0.006952097,0.009560427,0.04653972],"study_design_scores_gemma":[0.0050214804,0.0027791413,0.002715197,0.00003862822,0.0001656122,0.00009379724,0.021951267,0.8177098,0.14162906,0.0011687435,0.005523955,0.0012033231],"about_ca_topic_score_codex":0.000014282668,"about_ca_topic_score_gemma":0.000022366714,"teacher_disagreement_score":0.7244256,"about_ca_system_score_codex":0.000041985735,"about_ca_system_score_gemma":0.00027975146,"threshold_uncertainty_score":0.60522753},"labels":[],"label_agreement":null},{"id":"W4382777287","doi":"10.1186/s12859-023-05394-x","title":"Neuroimaging feature extraction using a neural network classifier for imaging genetics","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Natural Sciences and Engineering Research Council of Canada; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer Society; Bristol-Myers Squibb; National Institute on Aging; Alzheimer Society Research Program; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Neuroimaging; Artificial intelligence; Computer science; Imaging genetics; Machine learning; Artificial neural network; Classifier (UML); Feature selection; Pattern recognition (psychology); Bayesian probability; Pipeline (software); Biology; Neuroscience","score_opus":0.043862887520467526,"score_gpt":0.3193616961983528,"score_spread":0.2754988086778853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382777287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43854627,0.0006294586,0.55711144,0.00069412653,0.0014759281,0.0006770304,0.00006596953,0.000098703604,0.00070104713],"genre_scores_gemma":[0.30109736,0.0003488022,0.69016165,0.002446696,0.0025339955,0.00009476314,0.0013161687,0.000121762634,0.0018787782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998747,0.000053114854,0.00036005452,0.00020874513,0.00010337115,0.0005277195],"domain_scores_gemma":[0.9992009,0.00007573014,0.00023342225,0.00030027516,0.0001108111,0.00007888111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043766358,0.00018066808,0.0001780695,0.00007166012,0.00026700107,0.00005288732,0.00015549584,0.00016163001,0.0000030962],"category_scores_gemma":[0.00020227478,0.00017915815,0.00014825368,0.00023246575,0.00004973592,0.000011513152,0.00011638982,0.00011699278,0.000014358066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007979529,0.000032115895,0.239875,0.00019438833,0.00008628288,0.0000023442421,0.00018986592,0.55516243,0.01828492,0.00009408491,0.16860542,0.017393379],"study_design_scores_gemma":[0.00035344588,0.00004181502,0.029948646,0.000008892186,0.000036420235,0.00003266835,0.0002302873,0.93234915,0.00018618956,0.00014887631,0.036461595,0.00020204077],"about_ca_topic_score_codex":0.0000030134963,"about_ca_topic_score_gemma":0.000015538291,"teacher_disagreement_score":0.37718672,"about_ca_system_score_codex":0.000023870703,"about_ca_system_score_gemma":0.00008392912,"threshold_uncertainty_score":0.7305857},"labels":[],"label_agreement":null},{"id":"W4384663316","doi":"10.1186/s12859-023-05390-1","title":"IS-Seq: a bioinformatics pipeline for integration sites analysis with comprehensive abundance quantification methods","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Virus-based gene therapy research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"University of Pennsylvania","keywords":"Pipeline (software); Computer science; Workflow; Data mining; Computational biology; Fragment (logic); Identifier; Process (computing); Pipeline transport; Biology; Database; Engineering; Algorithm","score_opus":0.08634068336102907,"score_gpt":0.39989763439967674,"score_spread":0.31355695103864767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384663316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08045192,0.00014248527,0.9179813,0.00017409069,0.000053216645,0.00075242436,0.00020249363,0.00007976309,0.00016229607],"genre_scores_gemma":[0.039531313,0.00043736404,0.95046866,0.0007959342,0.00014277392,0.00024185416,0.006985638,0.000059750066,0.0013367363],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832624,0.000082731705,0.00064076117,0.00024137573,0.00030693057,0.0004019475],"domain_scores_gemma":[0.9980801,0.00014178037,0.00032573112,0.0007417461,0.0006026024,0.000108080305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007696669,0.00025906376,0.000320632,0.00043060395,0.00019891336,0.00012285302,0.00033125977,0.0001788551,0.000017801844],"category_scores_gemma":[0.00017584777,0.00020932741,0.00022485718,0.001501587,0.00013352258,0.000033491724,0.000082241444,0.00011311771,0.000085249274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010855991,0.00041876733,0.007290193,0.002882398,0.0040431004,0.0000018941771,0.008913212,0.08846424,0.58424485,0.0007869698,0.054517347,0.23758106],"study_design_scores_gemma":[0.000684855,0.0007781977,0.0005004343,0.00001627914,0.00016088848,0.0000027906042,0.0012305168,0.8196583,0.17240843,0.00006224945,0.0042303153,0.00026673177],"about_ca_topic_score_codex":0.0000055103396,"about_ca_topic_score_gemma":0.00021915366,"teacher_disagreement_score":0.7311941,"about_ca_system_score_codex":0.00003108742,"about_ca_system_score_gemma":0.00016708227,"threshold_uncertainty_score":0.8536124},"labels":[],"label_agreement":null},{"id":"W4386031784","doi":"10.1186/s12859-023-05436-4","title":"BioLegato: a programmable, object-oriented graphic user interface","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Genome Prairie; Genome Canada","keywords":"Computer science; Copying; Graphical user interface; Programming language; Software; Pipeline (software); Process (computing); User interface; Set (abstract data type); Simple (philosophy); Interface (matter); Usability; Software engineering; Field (mathematics); Source code; Debugger; Java; Human–computer interaction; Debugging; Operating system","score_opus":0.020662865741215973,"score_gpt":0.29314173950236094,"score_spread":0.272478873761145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386031784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7223692,0.00088982383,0.24722342,0.00082898035,0.0026349772,0.0035474547,0.000427149,0.0009774566,0.021101527],"genre_scores_gemma":[0.7082315,0.0062473416,0.24765812,0.0020845896,0.0015362864,0.00054969906,0.0055281147,0.00030759402,0.027856752],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972999,0.000054230964,0.00077447266,0.00029147428,0.00063694053,0.00094295945],"domain_scores_gemma":[0.99837,0.000042553103,0.00018844618,0.000750084,0.00025673982,0.0003921917],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007457756,0.00033462886,0.0002760074,0.0003398769,0.00019434033,0.00014200111,0.00059377926,0.0003692714,0.00003448965],"category_scores_gemma":[0.00054730603,0.00027698203,0.0002200033,0.0010547494,0.00037507244,0.000023785698,0.0005905599,0.00025140087,0.0009382043],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001687695,0.0014298372,0.06997695,0.0076442845,0.0015555266,0.00004421703,0.0066843405,0.0020798196,0.068397336,0.0028754617,0.6156406,0.22198395],"study_design_scores_gemma":[0.0024683247,0.0014451531,0.0041065053,0.0001510221,0.000052050753,0.000047228612,0.0044164527,0.10825824,0.043097775,0.00017047187,0.83471847,0.0010683277],"about_ca_topic_score_codex":0.000013403458,"about_ca_topic_score_gemma":0.000067060835,"teacher_disagreement_score":0.22091562,"about_ca_system_score_codex":0.00002487289,"about_ca_system_score_gemma":0.00027588473,"threshold_uncertainty_score":0.99996823},"labels":[],"label_agreement":null},{"id":"W4386890558","doi":"10.1186/s12859-023-05484-w","title":"Correspondence on NanoVar’s performance outlined by Jiang T. et al. in “Long-read sequencing settings for efficient structural variation detection based on comprehensive evaluation”","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canada Research Chairs; National Research Foundation Singapore; Alliance de recherche numérique du Canada; National Research Foundation","keywords":"Benchmarking; Concordance; Recall; Variation (astronomy); Computer science; Structural variation; Computational biology; Statistics; Artificial intelligence; Bioinformatics; Biology; Psychology; Genetics; Mathematics; Cognitive psychology; Genome; Gene","score_opus":0.027046479786477628,"score_gpt":0.28870790108067085,"score_spread":0.26166142129419323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386890558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98188204,0.000036133035,0.016543996,0.00018602067,0.00034795195,0.00079688313,0.00009387302,0.000014466223,0.00009861426],"genre_scores_gemma":[0.99315083,0.000020767297,0.0044360887,0.0017840955,0.000032107928,0.000109455395,0.0003935323,0.00001705171,0.000056091398],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888057,0.000055633394,0.00034267874,0.00021452362,0.000263026,0.00024356056],"domain_scores_gemma":[0.9992355,0.00011714507,0.00018564911,0.00022647723,0.00020064764,0.000034540724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006094957,0.00017441635,0.00013738162,0.00013118067,0.00015071963,0.000033600078,0.00011052973,0.000090851536,0.0000035323474],"category_scores_gemma":[0.00024048855,0.00016203149,0.00005724705,0.0002040612,0.000028456596,0.0000034794018,0.000043274984,0.000079815094,0.000014797505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043591406,0.000022608428,0.0016962431,0.00014687485,0.000023368144,2.1312378e-7,0.00070056936,0.8737687,0.11521533,0.000014652989,0.0015153742,0.006460177],"study_design_scores_gemma":[0.0011546706,0.00045066024,0.03696905,0.000051206065,0.000012966079,0.000001461952,0.00023269647,0.9406483,0.019267537,0.000009962197,0.0010152335,0.00018623346],"about_ca_topic_score_codex":0.00000880845,"about_ca_topic_score_gemma":0.000027643036,"teacher_disagreement_score":0.095947795,"about_ca_system_score_codex":0.00010194311,"about_ca_system_score_gemma":0.00014348407,"threshold_uncertainty_score":0.66074526},"labels":[],"label_agreement":null},{"id":"W4387495851","doi":"10.1186/s12859-023-05507-6","title":"Network-based prediction approach for cancer-specific driver missense mutations using a graph neural network","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Missense mutation; Artificial neural network; Computer science; Graph; Computational biology; DNA microarray; Artificial intelligence; Mutation; Biology; Gene; Machine learning; Genetics; Theoretical computer science","score_opus":0.03745443612303352,"score_gpt":0.2630600823418652,"score_spread":0.22560564621883167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387495851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14732821,0.0008418504,0.8488481,0.000055134915,0.0010104564,0.0009655256,0.0006183607,0.00009257376,0.0002397507],"genre_scores_gemma":[0.2102657,0.00094283966,0.77274483,0.001373775,0.0045959004,0.0005163254,0.00918303,0.00014036884,0.00023722123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988497,0.000019449368,0.00036875665,0.00020070445,0.00012272445,0.00043869167],"domain_scores_gemma":[0.9992471,0.0000645093,0.00016370168,0.00029833222,0.00012610992,0.00010030202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019319802,0.00018149943,0.00016020247,0.00006432471,0.0002788739,0.00006948784,0.00013550726,0.00015807162,0.000004257036],"category_scores_gemma":[0.00004029718,0.00018792914,0.00014840234,0.00038067787,0.0000747127,0.00000893722,0.000059862527,0.000072539195,0.0000037186348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007755045,0.000019315054,0.002320027,0.0000742935,0.000027849954,4.6503717e-7,0.000058170484,0.96344644,0.00059616816,0.00012362354,0.03226469,0.000991415],"study_design_scores_gemma":[0.000798765,0.000111263995,0.0011366373,0.00001963031,0.00005415476,0.0000057126904,0.00011656886,0.9757181,0.00030376524,0.00013857792,0.021373767,0.00022304784],"about_ca_topic_score_codex":0.0000147576875,"about_ca_topic_score_gemma":0.000042737833,"teacher_disagreement_score":0.07610329,"about_ca_system_score_codex":0.000036807236,"about_ca_system_score_gemma":0.00019443344,"threshold_uncertainty_score":0.7663528},"labels":[],"label_agreement":null},{"id":"W4387733089","doi":"10.1186/s12859-023-05502-x","title":"Artificial Intelligence based wrapper for high dimensional feature selection","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada","keywords":"Feature selection; Computer science; Feature (linguistics); Categorical variable; Data mining; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Machine learning; Data set; Pattern recognition (psychology)","score_opus":0.03285917897682682,"score_gpt":0.28588844081041753,"score_spread":0.2530292618335907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387733089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03445533,0.000037446003,0.96317357,0.0009067966,0.0005507914,0.0004593591,0.00005816655,0.00009031305,0.0002682091],"genre_scores_gemma":[0.8285808,0.000027790984,0.16524199,0.0010301184,0.00057517877,0.00023041913,0.0021342153,0.000036892274,0.0021425735],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933684,0.000014354762,0.00019974,0.00014207652,0.00013188382,0.00017512302],"domain_scores_gemma":[0.99956834,0.000017631814,0.000083903054,0.00017444338,0.00010423462,0.000051422212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015904242,0.000102360034,0.00007379382,0.000083418396,0.00011973375,0.000028969887,0.000101010395,0.00015094639,0.000018577733],"category_scores_gemma":[0.00007733602,0.00009023729,0.00006695036,0.00024489328,0.000028651688,0.0000058957303,0.000030156978,0.00005245378,0.00006018643],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079481024,0.00016249019,0.0011383403,0.00042322974,0.00006210857,3.198393e-7,0.00018307073,0.05406976,0.52044374,0.00819233,0.3137602,0.10076957],"study_design_scores_gemma":[0.00016704858,0.00019355248,0.0011182898,0.000018746216,0.000014319482,0.0000021299063,0.00013334608,0.5626987,0.3964549,0.0009428029,0.038034167,0.00022197995],"about_ca_topic_score_codex":0.0000014012032,"about_ca_topic_score_gemma":0.00001116899,"teacher_disagreement_score":0.7979316,"about_ca_system_score_codex":0.000013054446,"about_ca_system_score_gemma":0.00012397756,"threshold_uncertainty_score":0.367977},"labels":[],"label_agreement":null},{"id":"W4388501528","doi":"10.1186/s12859-023-05556-x","title":"A model-based clustering via mixture of hierarchical models with covariate adjustment for detecting differentially expressed genes from paired design","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Sanofi","keywords":"Covariate; Cluster analysis; Confounding; False positive paradox; Hierarchical clustering; Computational biology; DNA microarray; Biology; Computer science; Gene; Data mining; Genetics; Machine learning; Gene expression; Statistics; Mathematics","score_opus":0.0628024944333424,"score_gpt":0.26320892573570503,"score_spread":0.20040643130236263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388501528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038302578,0.00007337083,0.96084744,0.00002989575,0.00007699324,0.0005140698,0.00008453023,0.000043046857,0.000028065713],"genre_scores_gemma":[0.54198676,0.000031412575,0.45728332,0.00007020381,0.000057297566,0.00017111046,0.00033767446,0.000024038784,0.000038210266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989899,0.000043305365,0.00035979983,0.00020361498,0.00018223103,0.00022114563],"domain_scores_gemma":[0.9991916,0.000047845457,0.00021636269,0.0003658046,0.000103497594,0.00007488238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015224674,0.00017071047,0.00018428982,0.00007740547,0.00008255873,0.000023627214,0.00019133053,0.00015871263,0.000002443906],"category_scores_gemma":[0.000026909433,0.00013958791,0.00008990564,0.000116058975,0.000038103233,0.0000104472865,0.00007203631,0.000055937187,0.0000010958598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005763088,0.000027939264,0.000019688612,0.00015090579,0.000034630637,8.670597e-8,0.00020884883,0.5407759,0.4513271,0.00001452129,0.00017697261,0.0066871243],"study_design_scores_gemma":[0.0011080384,0.00015673491,0.00007663853,0.000050123246,0.000032421274,3.8055674e-7,0.00008251301,0.76731604,0.23055792,0.00042760375,0.000049597562,0.00014199053],"about_ca_topic_score_codex":0.000004647375,"about_ca_topic_score_gemma":0.000017350238,"teacher_disagreement_score":0.50368416,"about_ca_system_score_codex":0.000014439751,"about_ca_system_score_gemma":0.0001727141,"threshold_uncertainty_score":0.569223},"labels":[],"label_agreement":null},{"id":"W4388866605","doi":"10.1186/s12859-023-05570-z","title":"Image-centric compression of protein structures improves space savings","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Computer science; Compression (physics); Image compression; Computational biology; Artificial intelligence; Computer graphics (images); Image (mathematics); Computer vision; Image processing; Biology; Genetics; Gene; Materials science; Gene expression; Composite material","score_opus":0.015107522464248383,"score_gpt":0.24591595228719174,"score_spread":0.23080842982294336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388866605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020964047,0.00007400072,0.9768392,0.000119046745,0.00030497336,0.00052184134,0.000032580134,0.00038094388,0.00076338224],"genre_scores_gemma":[0.014208965,0.00001983997,0.9854193,0.000040420746,0.000045187255,0.000013868205,0.000034036766,0.0000101500455,0.00020823751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986589,0.000027426971,0.00042292298,0.00016265518,0.00042864302,0.00029943776],"domain_scores_gemma":[0.9987474,0.00007751514,0.00030676436,0.00067097915,0.00010211845,0.00009519357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002151771,0.00015571907,0.00020229461,0.00021511108,0.00012934579,0.00015373566,0.00092160935,0.00007826348,0.0000109981975],"category_scores_gemma":[0.000096052274,0.00011538899,0.000067088375,0.00075624074,0.00006044046,0.0010638572,0.00095329277,0.000120756216,0.00009169982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014509253,0.0004139843,0.0015501265,0.0065448475,0.00010708913,0.00003635749,0.0118724955,0.0022329052,0.14290206,0.109378025,0.112367086,0.61244994],"study_design_scores_gemma":[0.0003837482,0.00006478786,0.0042302636,0.00010272943,0.000003997217,0.0000050996987,0.00014775283,0.9805561,0.009286007,0.0020695247,0.0029788732,0.00017117064],"about_ca_topic_score_codex":0.00002129829,"about_ca_topic_score_gemma":0.0000011400917,"teacher_disagreement_score":0.97832316,"about_ca_system_score_codex":0.000018769075,"about_ca_system_score_gemma":0.00008881646,"threshold_uncertainty_score":0.47054264},"labels":[],"label_agreement":null},{"id":"W4389734944","doi":"10.1186/s12859-023-05596-3","title":"Performance analysis of conventional and AI-based variant callers using short and long reads","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Government of Canada; Université Laval; Grain Farmers of Ontario; Génome Québec; Canadian Field Crop Research Alliance; Genome Canada","keywords":"DNA microarray; Computational biology; Computer science; Genetics; Biology; Bioinformatics; Gene; Gene expression","score_opus":0.021544958236113118,"score_gpt":0.2658458750186123,"score_spread":0.24430091678249916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389734944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98773205,0.00011137116,0.011896181,0.000010748182,0.00002873148,0.00006966347,0.00008481867,0.000005879479,0.00006053181],"genre_scores_gemma":[0.9941126,0.00014321202,0.0051669134,0.00008865768,0.000013941731,0.0000022907004,0.00044030673,0.0000057464445,0.00002631335],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994915,0.000008704742,0.00021160678,0.000091031245,0.000083695064,0.00011346141],"domain_scores_gemma":[0.99968594,0.000010018555,0.000057235033,0.00013397234,0.00005356764,0.000059283368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000128985,0.00007940959,0.00012700619,0.00013592433,0.000057447494,0.000017351855,0.000050440125,0.000062394734,0.000006867551],"category_scores_gemma":[0.000017344346,0.00007200758,0.000065725275,0.0002045016,0.00007894173,0.0000055761357,0.000062710205,0.000024364455,7.816767e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021598229,0.000096888485,0.87366384,0.00120153,0.0014306034,0.000010876231,0.00023479701,0.10740454,0.011737671,0.00019514794,0.0005170592,0.0032910646],"study_design_scores_gemma":[0.00019971986,0.000047693145,0.15190876,0.000012487096,0.00024359344,0.0000067491624,0.000088808054,0.84644175,0.0007789786,0.0000026538057,0.00017238759,0.000096407726],"about_ca_topic_score_codex":0.000004595178,"about_ca_topic_score_gemma":0.000014482858,"teacher_disagreement_score":0.7390372,"about_ca_system_score_codex":0.000004657622,"about_ca_system_score_gemma":0.000080710575,"threshold_uncertainty_score":0.29363835},"labels":[],"label_agreement":null},{"id":"W4391228942","doi":"10.1186/s12859-024-05659-z","title":"Anchor Clustering for million-scale immune repertoire sequencing data","year":2024,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Artificial Immune Systems Applications","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Repertoire; Cluster analysis; Computational biology; DNA microarray; Biology; Scale (ratio); Immune system; Data science; Computer science; Genetics; Bioinformatics; Gene; Geography; Artificial intelligence; Cartography; Gene expression","score_opus":0.14455506523277642,"score_gpt":0.3438470522205079,"score_spread":0.19929198698773146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391228942","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3931832e-7,0.71065354,0.2843212,0.0000030109898,0.0009964642,0.0015786856,0.00086017814,0.0005672352,0.0010195706],"genre_scores_gemma":[8.3965165e-7,0.8834001,0.112780645,0.000005026046,0.00037509098,0.000589946,0.0022101123,0.00018677273,0.00045151485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99723357,0.000017332135,0.0018618007,0.00028578631,0.00018183494,0.00041964962],"domain_scores_gemma":[0.99719626,0.00014817227,0.00025747798,0.0022667872,0.000050526654,0.00008078341],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049675844,0.00051537907,0.0012300992,0.00024994113,0.00016270188,0.00022286127,0.0010817357,0.0003782196,0.000007729422],"category_scores_gemma":[0.0000616397,0.0004402142,0.00035870125,0.00046424274,0.000039213992,0.00040643127,0.00050741807,0.0003812892,0.0006560623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.447839e-7,0.000004839362,5.9556676e-8,0.17913367,0.0001894795,7.2816476e-7,0.00043452324,0.0010452985,0.0000037715333,0.000080580314,0.012368254,0.80673814],"study_design_scores_gemma":[0.000026177744,0.000004468391,2.112231e-8,0.007198006,0.00039408,0.00003250164,0.00015282173,0.42084408,0.0000019773715,0.000008313091,0.57105213,0.0002853893],"about_ca_topic_score_codex":0.000015651985,"about_ca_topic_score_gemma":0.00007010718,"teacher_disagreement_score":0.80645275,"about_ca_system_score_codex":0.00040953033,"about_ca_system_score_gemma":0.00023535737,"threshold_uncertainty_score":0.999805},"labels":[],"label_agreement":null},{"id":"W4391361452","doi":"10.1186/s12859-024-05643-7","title":"Learning self-supervised molecular representations for drug–drug interaction prediction","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; Université Laval","funders":"Alliance de recherche numérique du Canada; Canadian Institute for Advanced Research; Nvidia","keywords":"Computer science; Machine learning; Artificial intelligence; Feature (linguistics); Chemical space; Feature vector; Feature learning; Labeled data; Process (computing); Drug discovery; Bioinformatics; Biology","score_opus":0.022251661039304493,"score_gpt":0.31483372901423423,"score_spread":0.29258206797492975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391361452","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009159598,0.00008639915,0.98566973,0.00044049858,0.0011865774,0.00043676406,0.0000146877865,0.000815228,0.0021905173],"genre_scores_gemma":[0.04150081,0.000013739497,0.9577335,0.00011239974,0.00011179755,0.000094923555,0.00009123964,0.000016912329,0.0003246575],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864787,0.00011502716,0.00046303892,0.00023713322,0.00033270492,0.0002042479],"domain_scores_gemma":[0.99858207,0.00081597845,0.000095012816,0.0002957896,0.00013959639,0.00007154505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000666693,0.00014325594,0.000122019264,0.00027516508,0.00017079499,0.0006185801,0.00034381697,0.00003905427,0.000007684218],"category_scores_gemma":[0.000197058,0.00014191293,0.00015365185,0.0005522178,0.000017409951,0.002049779,0.00015789861,0.00019692651,0.00008118204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014421852,0.000068358,0.0002457866,0.00084514363,0.000107719185,0.0000039461743,0.01564674,0.8284192,0.0001610649,0.07712763,0.006421701,0.070938304],"study_design_scores_gemma":[0.00019642813,0.000034027253,0.00017905656,0.00007083999,0.000026249172,0.000023908522,0.00065237837,0.9862568,0.0006614945,0.0046792175,0.007079208,0.00014040417],"about_ca_topic_score_codex":0.000007277805,"about_ca_topic_score_gemma":0.0000027831788,"teacher_disagreement_score":0.1578376,"about_ca_system_score_codex":0.00011708468,"about_ca_system_score_gemma":0.00020313461,"threshold_uncertainty_score":0.5964982},"labels":[],"label_agreement":null},{"id":"W4391385457","doi":"10.1186/s12859-024-05660-6","title":"Multivariate pattern analysis: a method and software to reveal, quantify, and visualize predictive association patterns in multicollinear data","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institutes of Health; Universitetet i Bergen; National Center for Complementary and Integrative Health; Høgskulen på Vestlandet","keywords":"Covariate; Multivariate statistics; Statistics; Computer science; Regression analysis; Linear model; Partial least squares regression; Data mining; Multivariate analysis; Resampling; Linear regression; Variance (accounting); Contrast (vision); Ranking (information retrieval); Mathematics; Artificial intelligence","score_opus":0.031290639131473334,"score_gpt":0.34613156979160575,"score_spread":0.3148409306601324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391385457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14005683,0.00080893066,0.85757434,0.000121109275,0.00009786063,0.00030712746,0.0009896011,0.00002217006,0.000022032911],"genre_scores_gemma":[0.60322267,0.0020065955,0.39242437,0.00047876436,0.000181576,0.000060718332,0.0012286656,0.00003826395,0.00035838355],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882203,0.00007563314,0.00038574883,0.0003413453,0.00014895717,0.00022630212],"domain_scores_gemma":[0.9992897,0.00012672333,0.00010203492,0.00034851892,0.000053634212,0.00007939144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081777707,0.00016828768,0.00029407963,0.00023966623,0.0000525076,0.00012687787,0.00014877116,0.00013204047,0.0000047458734],"category_scores_gemma":[0.00060236175,0.00014679284,0.000046793903,0.00035821376,0.000014623205,0.000022398717,0.00053255574,0.00010265228,0.0000046657083],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019300774,0.00020221603,0.9238898,0.0018139879,0.004510412,0.000011295819,0.005280603,0.0012357316,0.009015039,0.00014149895,0.0045725317,0.04913388],"study_design_scores_gemma":[0.00075865304,0.00021695397,0.17256899,0.00009405085,0.0006621245,0.0000052888627,0.00083284883,0.81665355,0.0012194419,0.000040742245,0.0065587526,0.00038857898],"about_ca_topic_score_codex":0.00018009877,"about_ca_topic_score_gemma":0.000696597,"teacher_disagreement_score":0.8154178,"about_ca_system_score_codex":0.000028308636,"about_ca_system_score_gemma":0.00003685886,"threshold_uncertainty_score":0.5986038},"labels":[],"label_agreement":null},{"id":"W4392190584","doi":"10.1186/s12859-024-05693-x","title":"GPAD: a natural language processing-based application to extract the gene-disease association discovery information from OMIM","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Computational biology; Disease; DNA microarray; Association (psychology); Gene; Natural (archaeology); Computer science; Biology; Data science; Bioinformatics; Genetics; Medicine; Gene expression; Psychology; Pathology","score_opus":0.006096063725336593,"score_gpt":0.25596481010590466,"score_spread":0.24986874638056808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392190584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09988863,0.003182592,0.89384633,0.0014468402,0.00041714648,0.00048801745,0.0003096212,0.00015496869,0.00026585002],"genre_scores_gemma":[0.9608902,0.000022136504,0.034172453,0.0021779335,0.00034880737,0.000112475005,0.00196074,0.000013975819,0.00030130026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991087,0.000026220821,0.00029574678,0.00012286776,0.00025579374,0.00019067909],"domain_scores_gemma":[0.99941355,0.00006670631,0.00011918798,0.00026500277,0.00005708868,0.000078461715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002573444,0.0001336579,0.00009093276,0.00005512611,0.000099126395,0.0003214734,0.0002138186,0.00013707283,0.0000039437596],"category_scores_gemma":[0.0003898451,0.00008954011,0.000082007224,0.00017319762,0.000037317233,0.00005041894,0.00006217775,0.00012630528,0.00010415507],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030164502,0.00007480371,0.0028116535,0.0006342694,0.00010520395,0.0000022460904,0.0031031321,0.0020239202,0.010438448,0.00006292678,0.029918201,0.95052356],"study_design_scores_gemma":[0.00041130884,0.0000823073,0.0074930233,0.00010189842,0.000077779005,0.0000022668846,0.0011437135,0.8265734,0.008339094,0.000060405946,0.15537451,0.00034031074],"about_ca_topic_score_codex":0.000023281775,"about_ca_topic_score_gemma":0.00003308382,"teacher_disagreement_score":0.9501832,"about_ca_system_score_codex":0.00006159592,"about_ca_system_score_gemma":0.00024103162,"threshold_uncertainty_score":0.36513397},"labels":[],"label_agreement":null},{"id":"W4392517673","doi":"10.1186/s12859-024-05709-6","title":"DVA: predicting the functional impact of single nucleotide missense variants","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Key Technologies Research and Development Program; National Key Research and Development Program of China; Key Research and Development Program of Heilongjiang","keywords":"Missense mutation; Computational biology; Single-nucleotide polymorphism; Robustness (evolution); DNA microarray; Biology; Genetics; Computer science; Mutation; Gene; Genotype","score_opus":0.017016408345376297,"score_gpt":0.2458707352147775,"score_spread":0.22885432686940121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392517673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985396,0.001179355,0.009866126,0.000043126165,0.00042671454,0.00014756266,0.00019440766,0.000022274962,0.002724427],"genre_scores_gemma":[0.99681956,0.000054363303,0.0024252234,0.00006682015,0.0002552905,0.000003318508,0.00014016447,0.000014439295,0.00022083645],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994067,0.000014173146,0.00024227874,0.00008985484,0.00010146275,0.00014553122],"domain_scores_gemma":[0.9995714,0.000031803625,0.00006632146,0.00022087738,0.000056055127,0.00005358582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012759835,0.00010327334,0.000078407575,0.000032224052,0.00006598118,0.000054215212,0.000104752005,0.00006285889,0.000031635518],"category_scores_gemma":[0.0000729109,0.00006456315,0.0001812689,0.000081314734,0.00005669298,0.0000069438884,0.00007096031,0.000050587027,0.000020637877],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008549352,0.0008266954,0.03364333,0.002649577,0.0024891722,0.000055803466,0.0036310584,0.037577428,0.74440336,0.0021219563,0.14928617,0.022460513],"study_design_scores_gemma":[0.0021410906,0.0025002519,0.17957379,0.0005298559,0.00062754727,0.0012849316,0.004574647,0.7172337,0.036510374,0.001061742,0.052481145,0.0014808903],"about_ca_topic_score_codex":0.000011933814,"about_ca_topic_score_gemma":0.0000052347473,"teacher_disagreement_score":0.707893,"about_ca_system_score_codex":0.000014767609,"about_ca_system_score_gemma":0.00020442087,"threshold_uncertainty_score":0.2632809},"labels":[],"label_agreement":null},{"id":"W4392783992","doi":"10.1186/s12859-024-05661-5","title":"123VCF: an intuitive and efficient tool for filtering VCF files","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Computer science; Filter (signal processing); Annotation; Process (computing); Data mining; Flexibility (engineering); A priori and a posteriori; Identification (biology); Information retrieval; Artificial intelligence; Computer vision; Programming language","score_opus":0.012004658380433651,"score_gpt":0.25558263212881005,"score_spread":0.2435779737483764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392783992","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8276656,0.0010841714,0.16958894,0.00002380308,0.00025358683,0.0003564436,0.0005210291,0.00003398558,0.00047241652],"genre_scores_gemma":[0.9119441,0.00016296026,0.08625455,0.000227606,0.0002835505,0.00006605819,0.00073582097,0.000030414392,0.00029493618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949074,0.000006387842,0.00016684901,0.00013232764,0.000049989238,0.00015373286],"domain_scores_gemma":[0.9997042,0.000019483026,0.00002707275,0.00015137444,0.000034907727,0.00006300952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009160878,0.000105945124,0.00007679789,0.000037906982,0.0000679253,0.00011352265,0.000075354794,0.00006697902,0.0000075455864],"category_scores_gemma":[0.000042381835,0.000089257934,0.000060244696,0.000032150223,0.00004033496,0.0000063132456,0.00008036735,0.000029134577,0.000006969083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013789064,0.0009221098,0.0030140432,0.016823053,0.0009569745,0.000050118295,0.014440668,0.032859612,0.32800987,0.030653508,0.052793812,0.51809734],"study_design_scores_gemma":[0.000697721,0.00074014533,0.0020167357,0.00013893982,0.00008407101,0.00007624701,0.0014513446,0.88801587,0.024253206,0.00030811888,0.081587024,0.0006305913],"about_ca_topic_score_codex":0.0000014314526,"about_ca_topic_score_gemma":0.0000042029496,"teacher_disagreement_score":0.85515624,"about_ca_system_score_codex":0.0000071383865,"about_ca_system_score_gemma":0.00006583279,"threshold_uncertainty_score":0.36398327},"labels":[],"label_agreement":null},{"id":"W4393044540","doi":"10.1186/s12859-024-05739-0","title":"Cell4D: a general purpose spatial stochastic simulator for cellular pathways","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of Toronto","keywords":"Computer science; Flexibility (engineering); Visualization; Biological data; Cluster analysis; Graphics; Variety (cybernetics); Human–computer interaction; Data mining; Machine learning; Bioinformatics; Artificial intelligence; Biology","score_opus":0.04667898820955073,"score_gpt":0.3110424190695676,"score_spread":0.26436343086001685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393044540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17049192,0.001515282,0.8206836,0.0005082276,0.001005469,0.0019881937,0.0004638661,0.00028920564,0.003054229],"genre_scores_gemma":[0.78937566,0.0000893657,0.18262903,0.0010739339,0.0034430276,0.00023298674,0.0010586226,0.00013716615,0.021960221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840957,0.0000137429615,0.0004688897,0.00017867127,0.0004555774,0.00047357153],"domain_scores_gemma":[0.9990601,0.000249982,0.000045498375,0.00025246188,0.000113016875,0.00027892986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024053831,0.00021940209,0.00030607477,0.00018270101,0.00011703833,0.00010803088,0.00013326232,0.00013196586,0.00016026794],"category_scores_gemma":[0.000102902086,0.00016130414,0.00027396707,0.00017526234,0.000087149754,0.0001245478,0.00008796727,0.00023398551,0.00049966865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0097728865,0.0021573568,0.0046126707,0.08681244,0.0022982503,0.00092805095,0.019459993,0.039698817,0.07738443,0.10641455,0.15488183,0.4955787],"study_design_scores_gemma":[0.00074586546,0.00045599532,0.00011396978,0.00016483798,0.000086315136,0.000048577116,0.0000955145,0.9335866,0.0026451051,0.0004964351,0.061362877,0.00019793324],"about_ca_topic_score_codex":0.00004208138,"about_ca_topic_score_gemma":0.0000108845,"teacher_disagreement_score":0.89388776,"about_ca_system_score_codex":0.00006411646,"about_ca_system_score_gemma":0.00037946372,"threshold_uncertainty_score":0.6577792},"labels":[],"label_agreement":null},{"id":"W4393315502","doi":"10.1186/s12859-024-05759-w","title":"Feature-specific quantile normalization and feature-specific mean–variance normalization deliver robust bi-directional classification and feature selection performance between microarray and RNAseq data","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Feature selection; Computer science; Artificial intelligence; Data mining; Pattern recognition (psychology); Feature (linguistics); Model selection; Machine learning","score_opus":0.043403125535713044,"score_gpt":0.261369201763679,"score_spread":0.21796607622796596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393315502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27070916,0.022910863,0.7007514,0.0014197042,0.0012567504,0.0012011159,0.0006243935,0.00026448249,0.00086209556],"genre_scores_gemma":[0.83950394,0.036536265,0.10686107,0.0002763662,0.0014415592,0.00007814352,0.012330412,0.00011079168,0.0028614595],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842083,0.00007151647,0.00033085753,0.0006203249,0.00028409585,0.00027234934],"domain_scores_gemma":[0.9989346,0.000028171004,0.00021449,0.0004915423,0.00019452273,0.000136661],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039039142,0.00031553462,0.00020634208,0.00021506041,0.00039189798,0.00041345027,0.00021147369,0.00043280676,0.000010226506],"category_scores_gemma":[0.000029408757,0.00029378434,0.000037197497,0.00046479207,0.00014110994,0.00022142229,0.00016956785,0.00026819235,0.000009008919],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007702188,0.00013626974,0.087887,0.0027717974,0.0002866872,0.00000154325,0.0019522957,0.0019658029,0.3239106,0.0024644395,0.45592746,0.121925876],"study_design_scores_gemma":[0.0007810142,0.00014348367,0.14914253,0.00022656209,0.00008926764,0.00011601347,0.00038256546,0.28677654,0.015562435,0.000017398232,0.54613686,0.00062529725],"about_ca_topic_score_codex":0.0000036678402,"about_ca_topic_score_gemma":0.000032148575,"teacher_disagreement_score":0.59389037,"about_ca_system_score_codex":0.000053787586,"about_ca_system_score_gemma":0.000099840225,"threshold_uncertainty_score":0.9999514},"labels":[],"label_agreement":null},{"id":"W4395047680","doi":"10.1186/s12859-024-05768-9","title":"Mora: abundance aware metagenomic read re-assignment for disentangling similar strains","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Metagenomics; Computer science; Genome; Computational biology; Workflow; Genomics; Biology; Data mining; Genetics; Gene","score_opus":0.03176217315068975,"score_gpt":0.2793249900307563,"score_spread":0.24756281688006654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395047680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31609046,0.016693424,0.6552036,0.0005927079,0.002227526,0.0020727601,0.0018782323,0.00008494741,0.0051563485],"genre_scores_gemma":[0.8892006,0.001286711,0.10674642,0.00040581115,0.00060387,0.0001494225,0.00036001034,0.00007007753,0.0011770609],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998934,0.000012928158,0.00038093948,0.00024139797,0.00011613673,0.00031461893],"domain_scores_gemma":[0.99942243,0.000030529223,0.000080018,0.00033641557,0.000051306975,0.00007929701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020804792,0.00021990483,0.00019142321,0.00004592611,0.00014320623,0.00009808516,0.0001968435,0.00010909892,0.000012284677],"category_scores_gemma":[0.000035540026,0.00019460448,0.00018993083,0.00006966395,0.00006463078,0.0000031760871,0.00012429731,0.00006387235,0.000018090537],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000788913,0.0007436483,0.009965368,0.014404545,0.006291654,0.00004573441,0.017258877,0.07950685,0.50051826,0.013975986,0.14894556,0.20755464],"study_design_scores_gemma":[0.0016138599,0.00093855755,0.0015187223,0.0002147706,0.00044864204,0.000030339239,0.005314825,0.3644351,0.043063592,0.0019533196,0.5789896,0.0014786609],"about_ca_topic_score_codex":0.0000025560478,"about_ca_topic_score_gemma":0.000035916237,"teacher_disagreement_score":0.57311016,"about_ca_system_score_codex":0.000037255104,"about_ca_system_score_gemma":0.00012237334,"threshold_uncertainty_score":0.79357404},"labels":[],"label_agreement":null},{"id":"W4399465136","doi":"10.1186/s12859-024-05822-6","title":"Integrating transformers and many-objective optimization for drug design","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Thunder Bay Regional Research Institute; Brock University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; DNA microarray; Computational biology; Drug; Biology; Pharmacology; Genetics","score_opus":0.029820889704763705,"score_gpt":0.2946029113881443,"score_spread":0.2647820216833806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399465136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014316513,0.00014216534,0.99758154,0.00018499189,0.00032969206,0.0005049727,0.000009878198,0.0001875873,0.0009160219],"genre_scores_gemma":[0.0036619452,0.000017051256,0.9960655,0.000100956044,0.000031954536,0.000043148728,0.000010226462,0.000009708652,0.000059516122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991461,0.000056881006,0.00029843402,0.00016058561,0.00016701916,0.0001710046],"domain_scores_gemma":[0.998657,0.0010595636,0.000050119786,0.000109836496,0.000070801325,0.000052693485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007913869,0.00012798217,0.00011703497,0.00016878729,0.0001131538,0.00048099202,0.00020318241,0.000038071837,0.0000028921909],"category_scores_gemma":[0.000112618734,0.00010910697,0.000061156585,0.0003387778,0.000034024444,0.0014586463,0.00005442645,0.000085477055,0.0000056523486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009779947,0.000009897184,0.000005814732,0.0003802717,0.000022132726,5.193351e-7,0.007952604,0.720214,0.0000042315455,0.11484385,0.0004476091,0.15610926],"study_design_scores_gemma":[0.0001607661,0.000045697227,0.00001949482,0.00007424147,0.000011568922,0.000014369008,0.00053908577,0.99045026,0.00021735902,0.008013539,0.00031284642,0.00014076108],"about_ca_topic_score_codex":0.0000028941895,"about_ca_topic_score_gemma":0.000001974336,"teacher_disagreement_score":0.27023625,"about_ca_system_score_codex":0.000059075206,"about_ca_system_score_gemma":0.00019632898,"threshold_uncertainty_score":0.4638217},"labels":[],"label_agreement":null},{"id":"W4400046055","doi":"10.1186/s12859-024-05847-x","title":"Can large language models understand molecules?","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Computer science; Embedding; Representation (politics); Artificial intelligence; Natural language processing; Field (mathematics); Property (philosophy); Machine learning; Bioinformatics; Biology; Mathematics","score_opus":0.01972382980271739,"score_gpt":0.27239039583762137,"score_spread":0.252666566034904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400046055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0819326,0.0003122465,0.8984905,0.00029580272,0.0011643328,0.00023835195,0.00020294217,0.00070937857,0.016653892],"genre_scores_gemma":[0.5838595,0.00002236448,0.41360122,0.0006400747,0.00017782974,0.000015267675,0.000046179557,0.000047551224,0.0015899893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841934,0.000060106133,0.00038584793,0.0002151494,0.0004457496,0.0004738164],"domain_scores_gemma":[0.9992787,0.00009352875,0.000081987484,0.00039716085,0.000031206837,0.00011740069],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00092103187,0.00018303396,0.00017774817,0.00012225957,0.00015575443,0.00069306925,0.0004398023,0.00007953495,0.00077454513],"category_scores_gemma":[0.00009742816,0.00014571706,0.000059557973,0.00026258462,0.000101670295,0.0006004175,0.00018768785,0.00013634842,0.0011082332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006707508,0.0001547262,0.00028255937,0.005407206,0.00003698348,0.00015851561,0.08022007,0.28308722,0.15297543,0.45409092,0.02120752,0.0023117692],"study_design_scores_gemma":[0.0001367465,0.00003093956,0.000024361509,0.000087500375,0.000011407349,0.000029720573,0.0018491647,0.9890571,0.004157804,0.0035015976,0.0008986175,0.00021504324],"about_ca_topic_score_codex":0.00006029824,"about_ca_topic_score_gemma":0.00008884422,"teacher_disagreement_score":0.70596987,"about_ca_system_score_codex":0.000086100175,"about_ca_system_score_gemma":0.00017111324,"threshold_uncertainty_score":0.9996695},"labels":[],"label_agreement":null},{"id":"W4400560580","doi":"10.1186/s12859-024-05853-z","title":"SimSpliceEvol2: alternative splicing-aware simulation of biological sequence evolution and transcript phylogenies","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Biology; Tree (set theory); Computational biology; Web server; Phylogenetic tree; Documentation; Gene; Inference; DNA microarray; Computer science; Source code; Software; Sequence (biology); Phylogenetics; Genetics; The Internet; Gene expression; Programming language; World Wide Web; Artificial intelligence","score_opus":0.04176224017873746,"score_gpt":0.2843509021788098,"score_spread":0.24258866200007234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400560580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83303326,0.0029229794,0.16329691,0.000018498597,0.00014759257,0.00019101918,0.00012111767,0.000009682125,0.00025894443],"genre_scores_gemma":[0.99373025,0.00040245734,0.005650231,0.000035101257,0.00008911766,0.0000085004585,0.000037559308,0.000008948759,0.000037858114],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993082,0.000019434,0.00028069652,0.00016098628,0.00008496678,0.00014566889],"domain_scores_gemma":[0.999636,0.00004193943,0.000067429,0.00014190274,0.000074870804,0.000037848193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012328704,0.00013759997,0.0001408212,0.00005171422,0.000055886037,0.000023465549,0.00009048888,0.000107537126,0.000002745638],"category_scores_gemma":[0.000038248854,0.00011148958,0.00006915951,0.00008457065,0.00014461688,0.0000035699827,0.000065116306,0.00005105053,0.0000034939533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017165588,0.00006791837,0.017979989,0.0011467169,0.00038184322,0.000002024152,0.0033780457,0.08566245,0.873083,0.0045309393,0.00024606645,0.0133493785],"study_design_scores_gemma":[0.00039254868,0.00058552454,0.009146812,0.000081518214,0.00006064916,0.000017591638,0.0010743825,0.94562465,0.037787005,0.0014211213,0.003465493,0.00034268788],"about_ca_topic_score_codex":0.000016604594,"about_ca_topic_score_gemma":0.000015981142,"teacher_disagreement_score":0.8599622,"about_ca_system_score_codex":0.000014259924,"about_ca_system_score_gemma":0.00004548705,"threshold_uncertainty_score":0.45464128},"labels":[],"label_agreement":null},{"id":"W4400687503","doi":"10.1186/s12859-024-05858-8","title":"PyChelator: a Python-based Colab and web application for metal chelator calculations","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Trace Elements in Health","field":"Nursing","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Python (programming language); Computer science; World Wide Web; Web application; Computational biology; Bioinformatics; Operating system; Biology","score_opus":0.02432804058987388,"score_gpt":0.3225738479674255,"score_spread":0.29824580737755163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400687503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074797414,0.0015206063,0.90898,0.0023640746,0.0024460307,0.005370016,0.0008631573,0.0013474227,0.0023112549],"genre_scores_gemma":[0.5656315,0.0000052317055,0.43268517,0.0006347937,0.00021797426,0.00042318713,0.00021648269,0.00006278559,0.00012284331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988049,0.000018311357,0.0005133313,0.00016402466,0.00022664515,0.0002727748],"domain_scores_gemma":[0.9990731,0.000366464,0.00011022591,0.00027252795,0.000061249804,0.00011645163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044170278,0.00015669093,0.00016733544,0.00016226499,0.00019494897,0.0001252466,0.000103518345,0.00013199975,0.00001228648],"category_scores_gemma":[0.00010661609,0.00014836188,0.00007761133,0.00026927426,0.00005922486,0.00030561813,0.00003102323,0.00014438912,0.00007529647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009138524,0.0008255786,0.042177137,0.041241404,0.00053637556,0.0000017779897,0.012059595,0.009380728,0.005150436,0.24309394,0.046489365,0.5981298],"study_design_scores_gemma":[0.00059145124,0.00010025014,0.0012370376,0.000073431314,0.00010117295,0.0000042536853,0.0001926608,0.9074345,0.00058566895,0.00041187071,0.089102544,0.0001651539],"about_ca_topic_score_codex":0.0000094441775,"about_ca_topic_score_gemma":0.000059099253,"teacher_disagreement_score":0.89805377,"about_ca_system_score_codex":0.00018288332,"about_ca_system_score_gemma":0.00021967852,"threshold_uncertainty_score":0.6050022},"labels":[],"label_agreement":null},{"id":"W4400788779","doi":"10.1186/s12859-024-05865-9","title":"HEROIC: a platform for remote collection of electroencephalographic data using consumer-grade brain wearables","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; McGill University; University Health Network","funders":"","keywords":"Computer science; Wearable computer; Neurocognitive; Scalability; Electroencephalography; Software; Human–computer interaction; Data collection; Data science; Inertial measurement unit; Technician; Protocol (science); Artificial intelligence; Embedded system; Database; Medicine; Cognition; Psychology; Neuroscience; Engineering","score_opus":0.11734397845058817,"score_gpt":0.334388231964429,"score_spread":0.21704425351384085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400788779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22187594,0.00068811735,0.7737186,0.000309261,0.0009922807,0.0010131802,0.0003713973,0.00031913558,0.00071208033],"genre_scores_gemma":[0.58062404,0.00037242475,0.41726667,0.0007127082,0.00018741097,0.000011930804,0.00009559062,0.000066204004,0.0006630423],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985861,0.000031836356,0.00052540656,0.00026203968,0.0002503665,0.00034423743],"domain_scores_gemma":[0.9983879,0.0008926318,0.00015583062,0.00046540223,0.000039480507,0.000058807513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043487723,0.00017037794,0.00022059592,0.0003162178,0.0001659578,0.00019518983,0.00056027883,0.000091516726,0.0000074914806],"category_scores_gemma":[0.00039603608,0.00014325822,0.00009163123,0.000785445,0.00016711625,0.0008232952,0.00015416679,0.00015781692,0.0000082014385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082915067,0.0005921616,0.0013081079,0.020000054,0.0004546904,0.00003129833,0.01426471,0.0068637375,0.6547051,0.02228676,0.12005516,0.15860908],"study_design_scores_gemma":[0.00028329255,0.00017004195,0.000014554801,0.00026558724,0.000027872395,0.00011837165,0.00015955232,0.9343677,0.05537037,0.0015985759,0.0074720727,0.00015199195],"about_ca_topic_score_codex":0.000042329848,"about_ca_topic_score_gemma":0.00007574305,"teacher_disagreement_score":0.927504,"about_ca_system_score_codex":0.000035822337,"about_ca_system_score_gemma":0.00019997271,"threshold_uncertainty_score":0.5841901},"labels":[],"label_agreement":null},{"id":"W4401214408","doi":"10.1186/s12859-024-05861-z","title":"Hybrid fragment-SMILES tokenization for ADMET prediction in drug discovery","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Brock University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Lexical analysis; Computer science; In silico; Drug discovery; Computational biology; Transformer; Artificial intelligence; Machine learning; Bioinformatics; Biology; Genetics","score_opus":0.01916693910531592,"score_gpt":0.2797357114306657,"score_spread":0.2605687723253498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401214408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0147378445,0.00016837502,0.9819909,0.00020136625,0.001259444,0.00047393967,0.00011834225,0.00023986462,0.0008099413],"genre_scores_gemma":[0.09328656,0.000029539488,0.90542316,0.00020793875,0.00016661496,0.00010167433,0.00021314422,0.00001815178,0.0005531905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986577,0.000056859553,0.0005219011,0.00021709988,0.00031547862,0.00023097455],"domain_scores_gemma":[0.99883306,0.0007011216,0.000078942685,0.00028044014,0.000056715588,0.000049734856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007032029,0.00014823746,0.0001444208,0.00033542854,0.00006829795,0.00068110146,0.00039857085,0.000036678746,0.0000050582585],"category_scores_gemma":[0.00017517385,0.00013757737,0.00009196932,0.00048249695,0.000024875277,0.0034795231,0.00017537223,0.00010431425,0.00004532875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002842056,0.00011086196,0.0009028364,0.0014638694,0.000041138268,0.0000055290975,0.004480536,0.559893,0.000028818702,0.31907246,0.021624638,0.0923479],"study_design_scores_gemma":[0.0002376419,0.000030789175,0.0011424468,0.00012251409,0.000007771047,0.000011817338,0.000101971,0.9741427,0.0004150148,0.018570175,0.005071352,0.00014581735],"about_ca_topic_score_codex":0.000008708838,"about_ca_topic_score_gemma":0.000010523255,"teacher_disagreement_score":0.4142497,"about_ca_system_score_codex":0.00014000204,"about_ca_system_score_gemma":0.0002563888,"threshold_uncertainty_score":0.6567877},"labels":[],"label_agreement":null},{"id":"W4401728618","doi":"10.1186/s12859-024-05816-4","title":"Modeling relaxation experiments with a mechanistic model of gene expression","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Laboratoire d'Excellence Ecofect; Agence Nationale de la Recherche; Université de Lyon; U.S. Department of Veterans Affairs","keywords":"DNA microarray; Computational biology; Relaxation (psychology); Population; Gene expression; Expression (computer science); Gene; Biology; Biological system; Computer science; Bioinformatics; Genetics; Neuroscience; Medicine","score_opus":0.021187813006774928,"score_gpt":0.24732616860079504,"score_spread":0.22613835559402012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401728618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15760368,0.0007277521,0.84129596,0.0000023175337,0.000031778272,0.00012720963,0.000007832474,0.000019086536,0.00018439423],"genre_scores_gemma":[0.731025,0.00005165738,0.26862475,0.000014116193,0.000030790656,0.00001694819,0.00008661032,0.000016847129,0.00013326727],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921286,0.0000150122205,0.00030702996,0.00013954706,0.00019044976,0.00013510897],"domain_scores_gemma":[0.9994901,0.0000045722522,0.00007671274,0.0003119481,0.00006917451,0.000047535083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012486153,0.00012624357,0.000141179,0.00007135255,0.000040393803,0.000024828189,0.00011073711,0.000100387704,0.0000034459454],"category_scores_gemma":[0.000016013222,0.00009721708,0.000078593745,0.000112433154,0.000021163884,0.000010653511,0.000050789236,0.00004230122,0.000005255283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026766837,0.000012770868,0.000015421478,0.0006600219,0.00004716487,2.1033544e-7,0.00020914078,0.73817706,0.2606256,0.00011170279,0.00004632238,0.000067789755],"study_design_scores_gemma":[0.00010366875,0.00005280848,4.922981e-7,0.00018416073,0.00005780737,0.0000034726127,0.00014220628,0.753179,0.24611123,0.00006576442,0.0000057229286,0.00009364317],"about_ca_topic_score_codex":0.0000014489563,"about_ca_topic_score_gemma":0.0000034393802,"teacher_disagreement_score":0.5734213,"about_ca_system_score_codex":0.000015529191,"about_ca_system_score_gemma":0.00010092697,"threshold_uncertainty_score":0.39643976},"labels":[],"label_agreement":null},{"id":"W4401914768","doi":"10.1186/s12859-024-05885-5","title":"HerpesDRG: a comprehensive resource for human herpesvirus antiviral drug resistance genotyping","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Herpesvirus Infections and Treatments","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"University College London Hospitals Biomedical Research Centre; Medical Research Council; University College London Hospitals NHS Foundation Trust; National Institute for Health and Care Research; UK Research and Innovation; Wellcome Trust","keywords":"Drug resistance; Genotyping; Sanger sequencing; Biology; Human herpesvirus 6; Annotation; Mutation; Computational biology; Genotype; Bioinformatics; Database; Genetics; Gene; Virus; Computer science; Viral disease; Herpesviridae","score_opus":0.0364832533639407,"score_gpt":0.3212147654646737,"score_spread":0.284731512100733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401914768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42187428,0.011313788,0.3259496,0.0018586308,0.0021367504,0.007967092,0.000645444,0.003224819,0.22502959],"genre_scores_gemma":[0.5300189,0.00015657314,0.4199493,0.0019609474,0.0009098602,0.00039240418,0.0005612367,0.00022413676,0.045826636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986188,0.000025448404,0.0005242077,0.00022308924,0.0002234244,0.00038503492],"domain_scores_gemma":[0.99911904,0.00017596425,0.00008897394,0.00039139204,0.00010391283,0.00012070188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017580649,0.0002533042,0.00034903066,0.00020261502,0.00032843495,0.00013963443,0.00008963047,0.000118929674,0.00003983924],"category_scores_gemma":[0.000034671753,0.00021231001,0.0002470791,0.0003303385,0.00009693504,0.00022004955,0.00004757291,0.00021713274,0.0002666967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017264049,0.0016005076,0.00463149,0.032980688,0.0035379236,0.0003595852,0.021744912,0.00022949187,0.0011166191,0.08810029,0.29091412,0.55305797],"study_design_scores_gemma":[0.0013560416,0.00009319065,0.00047190092,0.0007340972,0.00023015415,0.00003325085,0.00051528483,0.016559307,0.0007047355,0.0006748713,0.978367,0.00026018446],"about_ca_topic_score_codex":0.000024266166,"about_ca_topic_score_gemma":0.000107768734,"teacher_disagreement_score":0.68745285,"about_ca_system_score_codex":0.00017075856,"about_ca_system_score_gemma":0.00014944264,"threshold_uncertainty_score":0.8657751},"labels":[],"label_agreement":null},{"id":"W4401918821","doi":"10.1186/s12859-024-05776-9","title":"HBeeID: a molecular tool that identifies honey bee subspecies from different geographic populations","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Insect and Arachnid Ecology and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Animal and Plant Health Inspection Service; University of Illinois at Urbana-Champaign; Orta Doğu Teknik Üniversitesi; Office of International Science and Engineering; U.S. Department of Agriculture; Florida International University; Uppsala Universitet; National Science Foundation","keywords":"Subspecies; Honey bee; Biology; Pollinator; Linear discriminant analysis; Hierarchical clustering; Ecology; Cluster analysis; Artificial intelligence; Computer science; Pollen; Pollination","score_opus":0.02408205857244013,"score_gpt":0.2578502723451636,"score_spread":0.23376821377272347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401918821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832475,0.0011851416,0.01412179,0.000065791864,0.00070053816,0.00020530267,0.00015248393,0.00007385642,0.00024757086],"genre_scores_gemma":[0.99367255,0.00015656951,0.004094396,0.00018737494,0.0001612906,0.000042991098,0.001011795,0.00001951749,0.000653541],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906343,0.000026146789,0.0003023013,0.00019438012,0.00014912688,0.00026462486],"domain_scores_gemma":[0.9995632,0.00001776641,0.00006111347,0.0002708054,0.000031290412,0.0000557954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008297629,0.00020755408,0.00016090949,0.00010886007,0.00016900743,0.00016625828,0.00018384506,0.00023455096,0.00013520182],"category_scores_gemma":[0.000021254933,0.00017216355,0.00021394802,0.00009169205,0.00010474476,0.000023410492,0.00012142483,0.00013844077,0.0000984777],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120070516,0.00035003028,0.22652978,0.00044105315,0.00042914788,0.000054461023,0.0014881209,0.00022584882,0.7440256,0.008906276,0.012771345,0.0046582734],"study_design_scores_gemma":[0.0011990118,0.00042950496,0.32647172,0.00021394153,0.000629301,0.00008184598,0.0016518774,0.013695187,0.63670045,0.0032929482,0.013964309,0.0016699363],"about_ca_topic_score_codex":0.0000215386,"about_ca_topic_score_gemma":0.0002422937,"teacher_disagreement_score":0.107325174,"about_ca_system_score_codex":0.000011030379,"about_ca_system_score_gemma":0.00003885742,"threshold_uncertainty_score":0.7020626},"labels":[],"label_agreement":null},{"id":"W4401921714","doi":"10.1186/s12859-024-05882-8","title":"ARGV: 3D genome structure exploration using augmented reality","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Génome Québec; Genome Canada","keywords":"Genome; Visualization; Augmented reality; Computer science; Computational biology; Data visualization; Human–computer interaction; Biology; Genetics; Data mining; Gene","score_opus":0.02454012686021208,"score_gpt":0.26303558830816215,"score_spread":0.23849546144795006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401921714","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54219717,0.00047553662,0.45555544,0.00003828538,0.00037999245,0.0002525798,0.00025906536,0.000050641072,0.00079128164],"genre_scores_gemma":[0.7993306,0.00018775584,0.19734102,0.00018111638,0.00039948663,0.000008583595,0.0022244782,0.000047497615,0.0002794735],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913925,0.000018961187,0.0003453527,0.00016452336,0.00012666386,0.0002052256],"domain_scores_gemma":[0.99946433,0.00000598591,0.00008260054,0.00033087697,0.000052576685,0.00006361912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012860133,0.0001633082,0.000114358576,0.00005517093,0.00008593294,0.0001319221,0.00014523858,0.00016336888,0.000024269766],"category_scores_gemma":[0.000020644573,0.00014941081,0.0000727955,0.00011612764,0.000038414026,0.000019467605,0.00010589912,0.00008977709,0.000018697709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016347118,0.0001613361,0.0013320133,0.004058837,0.0005895739,0.000016401049,0.00419975,0.17772041,0.78197205,0.003902977,0.0045339256,0.02134924],"study_design_scores_gemma":[0.00021898976,0.00006911951,0.00033791352,0.00003623516,0.000039433464,0.000044499902,0.0003962161,0.9815617,0.0042171073,0.00035623432,0.012448256,0.0002742868],"about_ca_topic_score_codex":0.000007671173,"about_ca_topic_score_gemma":0.00004273267,"teacher_disagreement_score":0.8038413,"about_ca_system_score_codex":0.0000473802,"about_ca_system_score_gemma":0.0001398214,"threshold_uncertainty_score":0.60927963},"labels":[],"label_agreement":null},{"id":"W4402226771","doi":"10.1186/s12859-024-05912-5","title":"Answering open questions in biology using spatial genomics and structured methods","year":2024,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; National Cancer Institute; Center for Biomedical Informatics and Information Technology, National Cancer Institute; National Human Genome Research Institute; Canadian Institute for Advanced Research; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Data science; Context (archaeology); Computer science; Genomics; Biological data; Variety (cybernetics); Big data; Biology; Artificial intelligence; Bioinformatics; Data mining; Genome","score_opus":0.09727525832936341,"score_gpt":0.4270427508370241,"score_spread":0.3297674925076607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402226771","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015532268,0.8448935,0.1531054,0.0000025363724,0.0006501246,0.0007599699,0.00019372579,0.000016208594,0.00022318072],"genre_scores_gemma":[0.000012058415,0.683148,0.31616879,0.000026415371,0.0001573565,0.000020920648,0.00038467965,0.000048037662,0.00003371283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982377,0.00016624805,0.00086864474,0.00035716512,0.000052960473,0.0003172366],"domain_scores_gemma":[0.9991935,0.00003699713,0.00023597188,0.00040882354,0.000031433614,0.00009330517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004527465,0.00043771273,0.0009472333,0.00020685236,0.000077780925,0.00020207273,0.00050110935,0.00070317654,0.000005096708],"category_scores_gemma":[0.00008167317,0.00036562193,0.00019632299,0.00018463924,0.000112531634,0.000011857747,0.0005879133,0.00035017487,0.000004922619],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016103319,0.000023385523,0.000047809393,0.010974361,0.00015615825,0.0000021300666,0.00016620895,0.00008346783,0.0007464442,0.00024736783,0.000040620987,0.98749596],"study_design_scores_gemma":[0.00038491393,0.00011953479,0.0000060775806,0.0023531085,0.0006351494,0.00013633528,0.0000595014,0.02729068,0.00012361244,0.00027428273,0.9678676,0.00074921147],"about_ca_topic_score_codex":0.00022486117,"about_ca_topic_score_gemma":0.00053634704,"teacher_disagreement_score":0.9867467,"about_ca_system_score_codex":0.00008668261,"about_ca_system_score_gemma":0.00055806746,"threshold_uncertainty_score":0.9998796},"labels":[],"label_agreement":null},{"id":"W4403039748","doi":"10.1186/s12859-024-05935-y","title":"ScRNAbox: empowering single-cell RNA sequencing on high performance computing systems","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"Montreal Neurological Institute and Hospital; Fondation Brain Canada; McGill University; Canadian Institutes of Health Research; Québec Consortium for Drug Discovery; Michael J. Fox Foundation for Parkinson's Research","keywords":"Computer science; Scalability; Workstation; Pipeline (software); Workload; Distributed computing; Cluster analysis; Database; Operating system","score_opus":0.023389787648923927,"score_gpt":0.23039982112806542,"score_spread":0.2070100334791415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403039748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90219283,0.0008002321,0.084677145,0.000015909498,0.0018552382,0.00024225481,0.000023261236,0.00014064946,0.010052468],"genre_scores_gemma":[0.98572606,0.000095244446,0.012794014,0.0001767007,0.00048507602,0.000005054843,0.000098649085,0.000049126073,0.00057005085],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855304,0.000025736119,0.0005150831,0.00025678417,0.0002463806,0.0004029948],"domain_scores_gemma":[0.99933755,0.00003592238,0.00010341281,0.00035542026,0.000064987056,0.00010270485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002812932,0.00027542183,0.00020895767,0.00010846373,0.00016324445,0.0002721746,0.00025134953,0.00020005643,0.0000053943863],"category_scores_gemma":[0.000026178817,0.00024976977,0.00010526589,0.00016724496,0.000056762703,0.00002365632,0.000079544254,0.00021972717,0.00009973783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017412915,0.00018988735,0.00180567,0.006779585,0.00015823549,0.00002223514,0.0022810902,0.16096681,0.80300343,0.00091359817,0.0031150538,0.020590264],"study_design_scores_gemma":[0.0005072502,0.00060149573,0.00010945873,0.00064056285,0.000033534758,0.000049651364,0.00052431616,0.77753717,0.20898859,0.0000053960894,0.010470097,0.0005324954],"about_ca_topic_score_codex":0.00002653997,"about_ca_topic_score_gemma":0.0000046799914,"teacher_disagreement_score":0.61657035,"about_ca_system_score_codex":0.000111361886,"about_ca_system_score_gemma":0.00015351022,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W4404722864","doi":"10.1186/s12859-024-05941-0","title":"Plaseval: a framework for comparing and evaluating plasmid detection tools","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Agriculture and Agri-Food Canada; University of Saskatchewan; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"DNA microarray; Plasmid; Computational biology; Computer science; Biology; Genetics; Gene; Gene expression","score_opus":0.06687434104668352,"score_gpt":0.3231134474966735,"score_spread":0.25623910644998993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404722864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6169585,0.0015402962,0.38042533,0.000022014301,0.0003402606,0.00029570708,0.00003479524,0.000013953131,0.00036915415],"genre_scores_gemma":[0.7770757,0.00014395422,0.22236432,0.000076469,0.00020362239,0.00005340403,0.000025926975,0.000016323987,0.000040265197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993899,0.000009964822,0.00022072675,0.00013923467,0.00007318814,0.00016698109],"domain_scores_gemma":[0.99962825,0.000114325696,0.0000460065,0.0001309073,0.000039953804,0.00004053826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022945077,0.00011617253,0.00011266124,0.0000346034,0.00011648997,0.00012487906,0.000063051506,0.00010191355,0.0000013420296],"category_scores_gemma":[0.00022569805,0.000105714105,0.000059685484,0.000048756287,0.000036584126,0.000002637341,0.00008895155,0.00006101058,0.000005331048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076210237,0.000096476244,0.00968255,0.006405302,0.0010698395,0.0000018942891,0.0054867757,0.013471011,0.38432544,0.014907669,0.002900879,0.5608901],"study_design_scores_gemma":[0.00055803783,0.00064138795,0.0021781588,0.0001407571,0.00009763607,0.000036925492,0.0007962392,0.9279359,0.040625628,0.0030383302,0.023569515,0.00038149313],"about_ca_topic_score_codex":0.0000014429078,"about_ca_topic_score_gemma":0.00001629965,"teacher_disagreement_score":0.9144649,"about_ca_system_score_codex":0.000009852481,"about_ca_system_score_gemma":0.000042174917,"threshold_uncertainty_score":0.4310896},"labels":[],"label_agreement":null},{"id":"W4404976894","doi":"10.1186/s12859-024-05952-x","title":"Managing false positives during detection of pathogen sequences in shotgun metagenomics datasets","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency; Carleton University","funders":"Alliance de recherche numérique du Canada; Ontario Ministry of Agriculture, Food and Rural Affairs; Canadian Food Inspection Agency","keywords":"False positive paradox; Metagenomics; Shotgun; Computational biology; Shotgun sequencing; DNA microarray; Biology; True positive rate; Computer science; Bioinformatics; Genetics; DNA sequencing; Gene; Artificial intelligence; Gene expression","score_opus":0.02605075273000819,"score_gpt":0.24427652744555386,"score_spread":0.21822577471554566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404976894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979067,0.0006903392,0.00047486174,0.000060563623,0.00016684014,0.00012655839,0.0002872436,0.00004907457,0.00023782528],"genre_scores_gemma":[0.99774635,0.00025088503,0.0016767671,0.00004492907,0.000056141533,0.0000065001673,0.00020143368,8.6457754e-7,0.000016160173],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991059,0.000063091626,0.0004129096,0.00013088371,0.00008645236,0.00020082117],"domain_scores_gemma":[0.9995916,0.00021359636,0.00008552001,0.000057274596,0.000012424765,0.000039580817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038230294,0.000108336135,0.0001831179,0.00004192161,0.00005175127,0.000043055083,0.00016424675,0.00007714211,0.000023632125],"category_scores_gemma":[0.000033863656,0.000045599398,0.00007049718,0.0002920574,0.00004942106,0.00027626942,0.00007468729,0.00009116685,0.000024656985],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006799736,0.000046546003,0.035417035,0.000591495,0.000055676916,0.000026777108,0.0012739227,0.00047342022,0.83879554,0.00056619797,0.000040046965,0.122645356],"study_design_scores_gemma":[0.00028384363,0.00031772885,0.79444146,0.00036457973,0.00008915659,0.00016602408,0.006458648,0.1393742,0.051479552,0.0034262738,0.0028926248,0.00070593535],"about_ca_topic_score_codex":0.00008046547,"about_ca_topic_score_gemma":0.00038078075,"teacher_disagreement_score":0.78731596,"about_ca_system_score_codex":0.000028981009,"about_ca_system_score_gemma":0.000007897713,"threshold_uncertainty_score":0.18594895},"labels":[],"label_agreement":null},{"id":"W4406136011","doi":"10.1186/s12859-024-06030-y","title":"DFAST_QC: quality assessment and taxonomic identification tool for prokaryotic Genomes","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Bioscience Database Center; Japan Society for the Promotion of Science; Ohsumi Frontier Science Foundation; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Identification (biology); Computer science; Scalability; Genome; Biological classification; Data mining; Taxonomic rank; Data science; Biology; Database; Ecology","score_opus":0.030973555754661288,"score_gpt":0.31303070283876494,"score_spread":0.2820571470841037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406136011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7115092,0.0011048245,0.2843259,0.00014140017,0.00029860216,0.0010148506,0.00010394414,0.000007807118,0.0014934372],"genre_scores_gemma":[0.8558947,0.0004112456,0.14208908,0.00025893623,0.000073996256,0.00019791986,0.00012008161,0.000009903211,0.0009441402],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992264,0.000018289165,0.00039430856,0.0001562585,0.000049962815,0.00015479476],"domain_scores_gemma":[0.99945533,0.00003346431,0.00013361007,0.00027346617,0.00007811965,0.000026004564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033823942,0.00011845247,0.00014187292,0.000041180305,0.00012872188,0.000057230376,0.000110432884,0.00007543641,0.0000012106563],"category_scores_gemma":[0.000051781848,0.00011184194,0.00006236828,0.00004177199,0.00005823,0.0000021755807,0.000119874094,0.000030633855,0.000002176046],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003954118,0.00038293633,0.44816825,0.004967391,0.0010586045,2.0964143e-7,0.000875522,0.0018855567,0.31358275,0.048388917,0.015586183,0.16470827],"study_design_scores_gemma":[0.0025154501,0.0003264839,0.8532566,0.000040753333,0.00017333274,0.0000047827457,0.0013656223,0.035700794,0.019961836,0.0026832102,0.08324877,0.0007223496],"about_ca_topic_score_codex":0.000002455553,"about_ca_topic_score_gemma":0.000015356558,"teacher_disagreement_score":0.40508837,"about_ca_system_score_codex":0.000021655287,"about_ca_system_score_gemma":0.00013364627,"threshold_uncertainty_score":0.4560782},"labels":[],"label_agreement":null},{"id":"W4406677956","doi":"10.1186/s12859-024-06015-x","title":"A graph neural network approach for hierarchical mapping of breast cancer protein communities","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breast cancer; Computational biology; Cluster analysis; Computer science; Hierarchical clustering; Machine learning; Artificial intelligence; Bioinformatics; Biology; Data mining; Cancer; Genetics","score_opus":0.01749997163686651,"score_gpt":0.24307157258260165,"score_spread":0.22557160094573514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406677956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042916737,0.0007197451,0.9504655,0.00012810837,0.0002044622,0.001194346,0.00027348858,0.000025106609,0.004072496],"genre_scores_gemma":[0.4813616,0.00015840188,0.51520145,0.00097634934,0.00036699593,0.00042203694,0.00080644316,0.000031894226,0.0006748102],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988051,0.000033378816,0.0006028416,0.00009393211,0.00010215999,0.0003626052],"domain_scores_gemma":[0.9991391,0.000029699575,0.00022770323,0.00041765717,0.00012749228,0.000058364683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032174974,0.00019671238,0.00026910394,0.00008474831,0.00017179217,0.000040949122,0.0003660547,0.00020945202,0.0000047872177],"category_scores_gemma":[0.000012045319,0.00017385898,0.00018255258,0.00021398532,0.0001892451,0.00001082352,0.00022623285,0.00015762715,4.7864125e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003770515,0.0010780365,0.038495764,0.02458015,0.002738626,6.0071903e-7,0.007408659,0.53025705,0.009654195,0.072235696,0.116484076,0.19329666],"study_design_scores_gemma":[0.0013785559,0.00013559831,0.0018345322,0.00021964184,0.000052985924,0.000011553298,0.0018750189,0.9853201,0.0005073692,0.0015472354,0.0067447126,0.0003727195],"about_ca_topic_score_codex":0.0000261946,"about_ca_topic_score_gemma":0.00004005703,"teacher_disagreement_score":0.45506305,"about_ca_system_score_codex":0.000013275017,"about_ca_system_score_gemma":0.00015625416,"threshold_uncertainty_score":0.7089763},"labels":[],"label_agreement":null},{"id":"W4407114045","doi":"10.1186/s12859-025-06050-2","title":"BioLake: an RNA expression analysis framework for prostate cancer biomarker powered by data lakehouse","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prostate Cancer Canada; University of Calgary","funders":"","keywords":"Upload; Computer science; Raw data; Scalability; Flexibility (engineering); Data science; Data pre-processing; Pipeline (software); Data mining; Workflow; Data warehouse; Database; World Wide Web","score_opus":0.04424208771644974,"score_gpt":0.352946851264794,"score_spread":0.3087047635483443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407114045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026374098,0.001725782,0.96801823,0.00028369413,0.00039479675,0.00068717526,0.0018888323,0.00005636984,0.00057100976],"genre_scores_gemma":[0.5317146,0.0029324691,0.42812616,0.0026879187,0.00032908676,0.00074325607,0.027546912,0.0000906025,0.005828998],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873984,0.000043651497,0.00042595415,0.0003828363,0.00014728354,0.00026042422],"domain_scores_gemma":[0.9980821,0.000024786894,0.00023373013,0.0014268478,0.00012698006,0.000105572595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002594873,0.00019514398,0.00020135121,0.00015343002,0.00015462232,0.000099942066,0.0006184662,0.00025936283,0.000031163796],"category_scores_gemma":[0.00014077986,0.00016383984,0.00010350577,0.0005065009,0.000057142635,0.000031947548,0.00023831171,0.00007656501,0.0000033874999],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008239068,0.00030591563,0.01012975,0.00042662543,0.0007345519,1.589346e-7,0.0003777568,0.00047209288,0.5798833,0.00039632595,0.35028037,0.05616929],"study_design_scores_gemma":[0.0017250426,0.00016424283,0.0030930417,0.00016616065,0.00058771286,5.2399196e-7,0.00097327423,0.14570853,0.30264506,0.00049741607,0.54373074,0.00070828985],"about_ca_topic_score_codex":0.000013961314,"about_ca_topic_score_gemma":0.00008648564,"teacher_disagreement_score":0.5398921,"about_ca_system_score_codex":0.000020906396,"about_ca_system_score_gemma":0.00020397737,"threshold_uncertainty_score":0.6681195},"labels":[],"label_agreement":null},{"id":"W4407364035","doi":"10.1186/s12859-025-06051-1","title":"A hybrid machine learning framework for functional annotation of mitochondrial glutathione transport and metabolism proteins in cancers","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computational biology; Context (archaeology); Biology; Annotation; Function (biology); Proteomics; Mitochondrion; Bioinformatics; Biochemistry; Gene; Genetics","score_opus":0.018564024742322795,"score_gpt":0.2678267071041971,"score_spread":0.2492626823618743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407364035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21556903,0.0009953101,0.78058714,0.00042789127,0.0003582075,0.0015210962,0.00010331672,0.00003573764,0.0004022549],"genre_scores_gemma":[0.55095536,0.00024405454,0.44763377,0.00032008655,0.000114372,0.0003594685,0.00020076666,0.000014447609,0.0001576993],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914736,0.0000115503,0.00043879036,0.000098774864,0.00016538528,0.00013813263],"domain_scores_gemma":[0.99956703,0.00007277675,0.00013335147,0.00008983199,0.000096620635,0.000040366012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014402845,0.00010559928,0.0002841403,0.00017630676,0.000050881667,0.000008382626,0.00003250375,0.00007457823,0.000016497814],"category_scores_gemma":[0.00015517522,0.000092196795,0.00007530544,0.00020887255,0.00004911938,0.00010839631,0.000009676434,0.00017590808,5.1546226e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02009957,0.0012749095,0.5298186,0.030454857,0.001309854,0.0000071458285,0.020267973,0.022648567,0.0051714843,0.08767176,0.0024619962,0.2788133],"study_design_scores_gemma":[0.016407354,0.0008906176,0.21997249,0.002442502,0.00082220655,0.000016145703,0.0023304778,0.71927357,0.010362265,0.0039084647,0.023050565,0.0005233255],"about_ca_topic_score_codex":0.000087186476,"about_ca_topic_score_gemma":0.000066679895,"teacher_disagreement_score":0.696625,"about_ca_system_score_codex":0.000058766323,"about_ca_system_score_gemma":0.0002934168,"threshold_uncertainty_score":0.37596762},"labels":[],"label_agreement":null},{"id":"W4407911294","doi":"10.1186/s12859-025-06082-8","title":"Bacterial network for precise plant stress detection and enhanced crop resilience","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Molecular Communication and Nanonetworks","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Key Technologies Research and Development Program","keywords":"Resilience (materials science); Crop; Biology; Computer science; DNA microarray; Stress (linguistics); Computational biology; Biotechnology; Genetics; Agronomy; Gene; Gene expression; Materials science","score_opus":0.008203899709209869,"score_gpt":0.21601200935749648,"score_spread":0.2078081096482866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407911294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015670925,0.00026837416,0.9806121,0.0000059624053,0.00044325026,0.000324763,0.00002201664,0.00011540196,0.002537178],"genre_scores_gemma":[0.69717187,0.00078252616,0.3012051,0.00008862844,0.00016805303,0.00015431484,0.00013437116,0.000023716188,0.00027143135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995237,0.000011322384,0.00022583509,0.00004876097,0.00004621217,0.00014419972],"domain_scores_gemma":[0.99960035,0.00008284064,0.000034606972,0.00022869922,0.000022279432,0.000031223513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010020865,0.00008247432,0.00009610751,0.000039833805,0.00008871208,0.000054575088,0.00011441492,0.00007822584,0.000005020187],"category_scores_gemma":[0.000029057566,0.000081096696,0.000025201698,0.000118324606,0.000021009428,0.00008786421,0.000040527528,0.000067606794,0.0000026611065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005533473,0.000053919284,0.00045904474,0.0029250877,0.00014878543,4.1342935e-7,0.00151258,0.6641018,0.01161662,0.0036587866,0.013866102,0.30110356],"study_design_scores_gemma":[0.00036790658,0.000018593279,0.00033923722,0.00010484081,0.000012466469,8.355727e-7,0.000034883942,0.9750762,0.014939383,0.00009439776,0.008911584,0.00009970211],"about_ca_topic_score_codex":0.0000012461292,"about_ca_topic_score_gemma":0.00009405011,"teacher_disagreement_score":0.681501,"about_ca_system_score_codex":0.000018731764,"about_ca_system_score_gemma":0.000015000554,"threshold_uncertainty_score":0.33070272},"labels":[],"label_agreement":null},{"id":"W4408170149","doi":"10.1186/s12859-025-06091-7","title":"GoldPolish-target: targeted long-read genome assembly polishing","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research","keywords":"DNA microarray; Computational biology; Genome; Polishing; Sequence assembly; Biology; Computer science; Genetics; Engineering; Gene; Gene expression; Mechanical engineering","score_opus":0.011122698417002787,"score_gpt":0.24270969500747325,"score_spread":0.23158699659047047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408170149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76349455,0.0091269,0.12319258,0.0004153183,0.0014349172,0.0009191291,0.00028726776,0.000060407,0.10106895],"genre_scores_gemma":[0.8924849,0.0006596057,0.09810084,0.0022329544,0.00047619478,0.000051350715,0.00043284253,0.00004882774,0.005512492],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987087,0.000028092176,0.00046300626,0.0002250699,0.00013703902,0.00043808244],"domain_scores_gemma":[0.9991026,0.000023262694,0.00014448742,0.00050564186,0.00013022553,0.00009376393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021399805,0.000253101,0.00024206535,0.00010778368,0.00018399232,0.000103187565,0.00038869286,0.00020149782,0.00002020832],"category_scores_gemma":[0.00013637278,0.00024073027,0.00014810928,0.00019609969,0.000082797225,0.0000044243675,0.00034042558,0.00010843154,0.000038514074],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058706576,0.0007688929,0.20666334,0.0027274508,0.0028425092,0.000014153278,0.004101749,0.0173931,0.6491645,0.011680054,0.08246787,0.021589309],"study_design_scores_gemma":[0.0037435724,0.0005928762,0.2730081,0.0001356884,0.0002690539,0.000041814572,0.0023450106,0.0237612,0.10252349,0.0014787576,0.5899065,0.002193943],"about_ca_topic_score_codex":0.000029668252,"about_ca_topic_score_gemma":0.00007047603,"teacher_disagreement_score":0.546641,"about_ca_system_score_codex":0.000031208077,"about_ca_system_score_gemma":0.00020357402,"threshold_uncertainty_score":0.9816695},"labels":[],"label_agreement":null},{"id":"W4408209964","doi":"10.1186/s12859-025-06083-7","title":"Cross-validation for training and testing co-occurrence network inference algorithms","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Inference; Computer science; Microbiome; Data mining; Machine learning; Consistency (knowledge bases); Interpretability; Artificial intelligence; Bioinformatics; Biology","score_opus":0.06368248566846932,"score_gpt":0.3683402510661587,"score_spread":0.3046577653976894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408209964","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21693192,0.00034426848,0.77883786,0.000053768137,0.0003738362,0.000671457,0.00029342633,0.0000428803,0.0024505577],"genre_scores_gemma":[0.2721319,0.00013932743,0.7243735,0.0008542877,0.0002997214,0.0000636548,0.0016297054,0.000014358223,0.0004935402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925673,0.000012207702,0.00029850352,0.00013177378,0.000044638604,0.00025613102],"domain_scores_gemma":[0.99948597,0.00008960208,0.00011474027,0.00015091458,0.000109321,0.000049472077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003099664,0.000110095476,0.0001196088,0.000032026463,0.00020992968,0.00008911191,0.00010139516,0.00011993466,0.0000021100518],"category_scores_gemma":[0.00035970393,0.00010712896,0.000029244327,0.00010693795,0.00007087925,0.000011022261,0.00005816294,0.00006361265,0.0000022525226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028097283,0.0001645799,0.4229538,0.0060984846,0.00019152138,8.057632e-7,0.0032553526,0.01345602,0.047540117,0.004908082,0.029550927,0.4715993],"study_design_scores_gemma":[0.0062881303,0.0015170065,0.10847417,0.000952095,0.00014687121,0.000056651053,0.0018337077,0.61755174,0.03756201,0.0019633793,0.22187148,0.001782763],"about_ca_topic_score_codex":0.000003190011,"about_ca_topic_score_gemma":0.000005910293,"teacher_disagreement_score":0.6040957,"about_ca_system_score_codex":0.000009547132,"about_ca_system_score_gemma":0.0002614434,"threshold_uncertainty_score":0.43685922},"labels":[],"label_agreement":null},{"id":"W4408787684","doi":"10.1186/s12859-025-06103-6","title":"ChIPbinner: an R package for analyzing broad histone marks binned in uniform windows from ChIP-Seq or CUT&RUN/TAG data","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill Genome Centre","funders":"National Cancer Institute; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Computational biology; Chromatin; Chromatin immunoprecipitation; Histone; Biology; Computer science; Genome; DNA microarray; DNA sequencing; Epigenetics; Software; Principal component analysis; Genetics; DNA; Gene; Artificial intelligence; Gene expression","score_opus":0.025867122165030842,"score_gpt":0.2977455756890775,"score_spread":0.27187845352404666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408787684","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7930453,0.00035010398,0.20193097,0.00011333932,0.0003980088,0.0008313831,0.001949775,0.00004085182,0.0013402748],"genre_scores_gemma":[0.36637935,0.00089881965,0.57984674,0.0012606852,0.0004091397,0.0001126884,0.047756385,0.00011813327,0.0032180413],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807423,0.000039027207,0.00084506173,0.00042929835,0.00013884254,0.00047354994],"domain_scores_gemma":[0.9976322,0.000058985617,0.00029386237,0.0018134635,0.00007979983,0.000121691584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045737214,0.0003346035,0.0003856604,0.00019037542,0.00015458006,0.000121637524,0.001082389,0.00035003392,0.000023903845],"category_scores_gemma":[0.00023940865,0.00030008436,0.0001076327,0.0002856574,0.00008408433,0.00004342551,0.00060335005,0.00017738275,0.000012383562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010892449,0.0049706255,0.1914405,0.008900132,0.0034638864,0.000034963155,0.008715156,0.01998044,0.37368727,0.007007745,0.1102374,0.26066944],"study_design_scores_gemma":[0.008162331,0.0006039169,0.014666936,0.00033248373,0.00030660117,0.000016774342,0.002342712,0.8806441,0.009410491,0.0016306887,0.08008187,0.0018011212],"about_ca_topic_score_codex":0.00014541768,"about_ca_topic_score_gemma":0.0073808124,"teacher_disagreement_score":0.86066365,"about_ca_system_score_codex":0.000082679726,"about_ca_system_score_gemma":0.00040514107,"threshold_uncertainty_score":0.9999451},"labels":[],"label_agreement":null},{"id":"W4411136978","doi":"10.1186/s12859-025-06160-x","title":"SEQSIM: A novel bioinformatics tool for comparisons of promoter regions—a case study of calcium binding protein spermatid associated 1 (CABS1)","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spermatid; DNA microarray; Computational biology; Calcium-binding protein; Bioinformatics; Biology; Calcium; Genetics; Medicine; Gene; Gene expression; Internal medicine","score_opus":0.029866246856013905,"score_gpt":0.2836415420908401,"score_spread":0.25377529523482617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411136978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8255073,0.000015591993,0.17158422,0.000018316137,0.00008522483,0.0021105066,0.00039056424,0.000017352493,0.0002709498],"genre_scores_gemma":[0.842581,0.000004383434,0.15657927,0.00003717692,0.000018751598,0.00011125443,0.00027470302,0.000024762778,0.00036872894],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978257,0.000034725515,0.0014310158,0.0001682452,0.00020230739,0.00033804378],"domain_scores_gemma":[0.9980812,0.00005504343,0.0008966269,0.0005546975,0.00035151708,0.00006089417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004819195,0.0002851463,0.0005007511,0.00020662734,0.00015198285,0.00004396154,0.00033969502,0.00025872135,0.0000025198817],"category_scores_gemma":[0.0002643225,0.00026779127,0.00018827635,0.0003289157,0.0000944973,0.000020870475,0.0002645093,0.00012474337,0.0000016958807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017029323,0.022053272,0.07652386,0.033474024,0.007078619,0.000044928747,0.037024323,0.027310492,0.7547551,0.006573724,0.02762577,0.0058329464],"study_design_scores_gemma":[0.007114367,0.0019003187,0.0007178083,0.00041675975,0.0003583274,0.0001455159,0.025109101,0.919585,0.043013263,0.000052862702,0.0008609536,0.0007257328],"about_ca_topic_score_codex":0.000053904427,"about_ca_topic_score_gemma":0.00023067393,"teacher_disagreement_score":0.8922745,"about_ca_system_score_codex":0.00005288999,"about_ca_system_score_gemma":0.000309021,"threshold_uncertainty_score":0.9999774},"labels":[],"label_agreement":null},{"id":"W4412785840","doi":"10.1186/s12859-025-06229-7","title":"The BeeBiome data portal provides easy access to bee microbiome information","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Insect and Pesticide Research","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agriculture and Agri-Food Canada; Université de Lausanne","keywords":"Metagenomics; Data science; Microbiome; Biology; World Wide Web; Honey bee; Resource (disambiguation); Computer science; Computational biology; Ecology; Bioinformatics; Gene","score_opus":0.06361257686676958,"score_gpt":0.3188988684488425,"score_spread":0.25528629158207294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412785840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7994678,0.0007145428,0.0120666735,0.026065769,0.0024688265,0.007977933,0.0039352207,0.0008487583,0.14645447],"genre_scores_gemma":[0.941861,0.00046306575,0.027281107,0.013180102,0.0010708541,0.00029864573,0.008346657,0.0000065468275,0.0074920654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987717,0.000031242536,0.0004497593,0.00010331106,0.00026778373,0.000376181],"domain_scores_gemma":[0.99909085,0.00036555782,0.00010452335,0.00019914233,0.00014791188,0.00009203498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067115284,0.00012609328,0.00011849242,0.000049392864,0.0005565973,0.0010023131,0.0016866603,0.00008521514,0.00010268455],"category_scores_gemma":[0.00036258774,0.000041292744,0.00004354401,0.0008692626,0.00008735895,0.0015423637,0.00099537,0.00012405323,0.00028236816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001970672,0.00008662013,0.011362789,0.00040677463,0.00007028462,0.0000016237893,0.0005167389,0.000058655514,0.00648793,0.0057584327,0.19451627,0.78053683],"study_design_scores_gemma":[0.00024646855,0.00017311906,0.10729533,0.00009998487,0.00002375854,0.000012305749,0.0011502185,0.031252056,0.0012655249,0.0008165847,0.8573046,0.00036009864],"about_ca_topic_score_codex":0.00017579959,"about_ca_topic_score_gemma":0.0011824218,"teacher_disagreement_score":0.7801767,"about_ca_system_score_codex":0.000025239413,"about_ca_system_score_gemma":0.00008480049,"threshold_uncertainty_score":0.9665329},"labels":[],"label_agreement":null},{"id":"W4413112863","doi":"10.1186/s12859-025-06243-9","title":"Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"RNA-Seq; Transcriptome; Computational biology; Set (abstract data type); DNA microarray; Biology; Gene; Single-cell analysis; Gene expression; Genetics; Computer science; Cell","score_opus":0.01999084210850849,"score_gpt":0.21007172743887745,"score_spread":0.19008088533036896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413112863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25105155,0.00037630202,0.7403407,0.000092489536,0.00063902215,0.0004696637,0.00007877937,0.00006205518,0.006889404],"genre_scores_gemma":[0.83319163,0.0003626386,0.15959644,0.0020760428,0.00039381697,0.000054313627,0.0015950631,0.000090722584,0.0026393337],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983527,0.000046221423,0.00064231805,0.000327228,0.00020278658,0.00042871007],"domain_scores_gemma":[0.99880224,0.000029681181,0.00020303631,0.00060588546,0.00024566345,0.00011350233],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021141118,0.0003681309,0.00029878944,0.00015003506,0.00016467055,0.00013070619,0.00039043222,0.00036370504,0.000010574717],"category_scores_gemma":[0.000051144943,0.00033822222,0.00014880068,0.0003359595,0.00013260804,0.000025419453,0.00005708354,0.000192339,0.000024180488],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037353586,0.0013012984,0.0111071225,0.0028350432,0.0005172261,0.000007764685,0.0013640904,0.020867506,0.8858478,0.00060735905,0.007140791,0.06466865],"study_design_scores_gemma":[0.004878924,0.0015340919,0.0008464613,0.00022436622,0.00026947242,0.000030422638,0.0006724849,0.03577907,0.9048603,0.00013068876,0.049603485,0.0011702088],"about_ca_topic_score_codex":0.00011806038,"about_ca_topic_score_gemma":0.000766708,"teacher_disagreement_score":0.5821401,"about_ca_system_score_codex":0.00008709527,"about_ca_system_score_gemma":0.00047307464,"threshold_uncertainty_score":0.99990696},"labels":[],"label_agreement":null},{"id":"W4415995537","doi":"10.1186/s12859-025-06295-x","title":"Graph convolution network based on meta-paths and mutual information for drug-target interaction prediction","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Science Foundation of Tianjin City","keywords":"Mutual information; Baseline (sea); Graph; Convolution (computer science); Graph theory; Interaction information","score_opus":0.0263901864289195,"score_gpt":0.2844000139566388,"score_spread":0.2580098275277193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415995537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006539087,0.000044199835,0.99487734,0.00036690786,0.0012238534,0.0006727612,0.000052498755,0.00018117319,0.0019273376],"genre_scores_gemma":[0.031078368,0.000008093771,0.9669172,0.0014637692,0.00007456317,0.00016462996,0.00022908393,0.0000057344278,0.000058524463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986044,0.000109490575,0.0006139008,0.00015481796,0.0002885682,0.0002287957],"domain_scores_gemma":[0.9982144,0.0009344413,0.0002822775,0.00030939857,0.00020101952,0.0000584309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010516973,0.00018703022,0.00023057472,0.00038657943,0.00023968366,0.0002967039,0.00025079589,0.00008092194,0.0000038424596],"category_scores_gemma":[0.0002560147,0.00016836669,0.00014945927,0.0005616777,0.000041377923,0.0027006185,0.00010281552,0.00013047921,0.000013105985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008909871,0.000036295485,0.00033457443,0.0002605237,0.00010120713,5.992115e-8,0.0004802824,0.89088213,0.0000010193851,0.081196345,0.009011777,0.01760669],"study_design_scores_gemma":[0.0006396859,0.00009061389,0.0019422802,0.00004833273,0.00009922398,0.000002041004,0.00009490735,0.9731089,0.000081154176,0.013677846,0.010079523,0.00013549715],"about_ca_topic_score_codex":0.000005224417,"about_ca_topic_score_gemma":0.0000047646686,"teacher_disagreement_score":0.08222677,"about_ca_system_score_codex":0.00010165348,"about_ca_system_score_gemma":0.00019038901,"threshold_uncertainty_score":0.68657947},"labels":[],"label_agreement":null},{"id":"W4416612861","doi":"10.1186/s12859-025-06276-0","title":"CLEP-GAN: an innovative approach to subject-independent ECG reconstruction from PPG signals","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Fields Institute for Research in Mathematical Sciences; Canada Research Chairs","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normal Sinus Rhythm; Sinus rhythm; RR interval; Pattern recognition (psychology); Atrial fibrillation; Electrocardiography","score_opus":0.028459659907360397,"score_gpt":0.2914696153237213,"score_spread":0.2630099554163609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416612861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5345794,0.000055899414,0.40536594,0.00017799147,0.0005517976,0.0005201308,0.000043161406,0.00020533724,0.058500323],"genre_scores_gemma":[0.5824266,0.000014294603,0.4148625,0.00053457246,0.00028719226,0.000031740852,0.00019760134,0.000016006969,0.0016294465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986299,0.000036502537,0.0005960303,0.00019975717,0.0002992199,0.00023854643],"domain_scores_gemma":[0.99889034,0.00006559855,0.00015304892,0.00044736807,0.0002968132,0.0001468519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033903372,0.00018230717,0.0003736165,0.00041425423,0.00011601502,0.000076734585,0.00014028992,0.0001566874,0.000032911285],"category_scores_gemma":[0.00017001141,0.00015648978,0.00008833692,0.0011528679,0.000042378524,0.00024750852,0.000048813712,0.00024426938,0.00008724322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063789776,0.0010559029,0.35043195,0.0011773276,0.001345484,0.000007153594,0.012795313,0.003970355,0.0046122726,0.0010457501,0.0048640002,0.6180566],"study_design_scores_gemma":[0.003108915,0.00052077224,0.058999747,0.0008353655,0.0006654759,0.000042611107,0.03056123,0.86768854,0.03317839,0.0007790957,0.0028653373,0.0007545364],"about_ca_topic_score_codex":0.0001391158,"about_ca_topic_score_gemma":0.000020281754,"teacher_disagreement_score":0.86371815,"about_ca_system_score_codex":0.00013007307,"about_ca_system_score_gemma":0.00021638289,"threshold_uncertainty_score":0.6381468},"labels":[],"label_agreement":null}]}