{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":160,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":160,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"6221cfeba50a","filters":{"venue":"Journal of Computational Biology"}},"results":[{"id":"W2033292629","doi":"10.1089/cmb.2009.0238","title":"Ray: Simultaneous Assembly of Reads from a Mix of High-Throughput Sequencing Technologies","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":559,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; Centre hospitalier universitaire de Québec","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Contig; Sequence assembly; Hybrid genome assembly; Computer science; Software; DNA sequencing; Reference genome; Genome; Throughput; Computational biology; Sequence (biology); Data mining; Biology; Genetics; Gene; Transcriptome; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.00983358367180499,"gpt":0.2552465525768091,"spread":0.2454129689050041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001718275,0.0001064584,0.0003111154,0.00007540192,0.00002848492,0.000003469389,0.0002287007,0.0001885844,0.000004700186],"category_scores_gemma":[0.0003683099,0.00008737017,0.0001074629,0.0000617427,0.0002314217,0.000001172662,0.0001005199,0.0001409718,6.720039e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000084152,"about_ca_system_score_gemma":0.0001736862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004963337,"about_ca_topic_score_gemma":0.00001904618,"domain_scores_codex":[0.9991298,0.00004041417,0.0004897154,0.0001366911,0.00009042978,0.0001129557],"domain_scores_gemma":[0.9985186,0.0002442722,0.0005820584,0.0001338415,0.0004977655,0.00002339341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009400059,0.00004704391,0.002729916,0.000007241368,0.0002072862,0.000004062967,0.00005322521,0.01524947,0.9771276,0.001071265,0.00007606234,0.003332874],"study_design_scores_gemma":[0.00144624,0.002394856,0.01292408,0.00003282262,0.0000911162,0.0001497367,0.0003693033,0.001032433,0.9044364,0.07334224,0.003513053,0.0002676934],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918332,0.001075239,0.00631946,0.0002455134,0.0003493507,0.00004801,0.00007604733,0.000002113847,0.00005110422],"genre_scores_gemma":[0.9553446,0.0001424407,0.04428633,0.00003965756,0.000149668,8.725578e-7,0.00002362964,0.00000747071,0.000005352012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07269112,"threshold_uncertainty_score":0.3562852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056251063","doi":"10.1089/cmb.2014.0156","title":"PASTA: Ultra-Large Multiple Sequence Alignment for Nucleotide and Amino-Acid Sequences","year":2014,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":463,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; Howard Hughes Medical Institute; National Science Foundation; National Institutes of Health; National Institute on Aging; University of Alberta; Pennsylvania Department of Health","keywords":"Scalability; Multiple sequence alignment; Parallelizable manifold; Computer science; Sequence (biology); Alignment-free sequence analysis; Sequence alignment; Tree (set theory); Algorithm; Computational biology; Data mining; Biology; Mathematics; Peptide sequence; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01704934772177304,"gpt":0.2699171632434254,"spread":0.2528678155216524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003036133,0.00009760691,0.0001704437,0.00003378486,0.00008277685,0.00001128228,0.0001029141,0.00006085774,0.00000220589],"category_scores_gemma":[0.0001412983,0.00007959605,0.00007048884,0.00002123458,0.0001035509,0.000001337978,0.00003177947,0.00004110746,6.619759e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000910698,"about_ca_system_score_gemma":0.0000498546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002515068,"about_ca_topic_score_gemma":0.000005863698,"domain_scores_codex":[0.9993164,0.00005603406,0.0002731483,0.0001459827,0.00005792625,0.0001504878],"domain_scores_gemma":[0.9993561,0.000121917,0.0002155054,0.00005676884,0.0001932114,0.00005648367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001044428,0.00003940631,0.02087729,0.00001472092,0.0001347668,8.019247e-7,0.00007263671,0.002291101,0.9698454,0.002300632,0.0004591098,0.003859752],"study_design_scores_gemma":[0.00955601,0.01054888,0.1419181,0.00007472892,0.0001874389,0.0007173788,0.0006427402,0.007781061,0.3497959,0.125366,0.3522577,0.001154015],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9421309,0.0009876231,0.05602004,0.0004339006,0.0002130999,0.00008685904,0.00006674301,0.000001014307,0.00005977207],"genre_scores_gemma":[0.9833122,0.0001906575,0.01569591,0.0004626843,0.0002849603,0.000004645793,0.00003084179,0.000006842943,0.00001118085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6200494,"threshold_uncertainty_score":0.3245833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061327015","doi":"10.1089/106652703322756104","title":"Mining the Biomedical Literature in the Genomic Era: An Overview","year":2003,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":264,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Data science; Computer science; Biomedical text mining; sort; Genomics; Genome; Data mining; Text mining; Information retrieval; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06706577458925418,"gpt":0.389611694130938,"spread":0.3225459195416839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001426002,0.0002442596,0.0007120127,0.0001470224,0.00007691691,0.00004626896,0.0007986201,0.0005671188,0.00001175183],"category_scores_gemma":[0.0002687662,0.0001097053,0.0003623672,0.0002834283,0.0003237441,0.000003334784,0.00006942468,0.0006703572,0.000003721412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002371557,"about_ca_system_score_gemma":0.0005418135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.840843e-7,"about_ca_topic_score_gemma":0.000002483229,"domain_scores_codex":[0.9973201,0.001258346,0.0007910141,0.000227912,0.0001825097,0.0002201259],"domain_scores_gemma":[0.9985688,0.0004294976,0.0006029246,0.0002134189,0.000120492,0.00006480545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001974639,0.0001150543,0.00001981734,0.0004106508,0.0002012468,0.00004912326,0.0001814558,0.00002490669,0.00001233383,0.000647363,0.005660611,0.9926577],"study_design_scores_gemma":[0.0002334719,0.0005605377,0.0001059204,0.000744984,0.00009163529,0.001932436,0.00005954106,0.000008368917,2.514211e-7,0.001188426,0.9949473,0.0001271049],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0007392652,0.9976203,0.000450597,0.0005019075,0.0004780787,0.0001285936,0.00003632154,0.000002143508,0.0000427331],"genre_scores_gemma":[0.0003697702,0.9937277,0.003411955,0.001023726,0.0008699475,0.000009702161,0.0005516114,0.00001525993,0.00002035639],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9925306,"threshold_uncertainty_score":0.4473653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074993099","doi":"10.1089/10665270152530818","title":"On Combinatorial DNA Word Design","year":2001,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":236,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Alphabet; Word (group theory); DNA computing; Combinatorics; Heuristic; Code (set theory); Discrete mathematics; Computer science; Coding (social sciences); Dynamic programming; Constraint (computer-aided design); Complement (music); Algorithm; Mathematics; Computation; Biology; Genetics; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.01447372318489215,"gpt":0.2974973618649308,"spread":0.2830236386800386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002860624,0.000100543,0.0001708849,0.0001011934,0.00004985054,0.000009489306,0.0001311745,0.0001205189,0.000004806879],"category_scores_gemma":[0.000152709,0.00007699816,0.0001202392,0.00009753362,0.00008012629,0.000002934582,0.00002354077,0.0001043163,0.000003275976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001662436,"about_ca_system_score_gemma":0.00007101839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.679748e-7,"about_ca_topic_score_gemma":3.047485e-7,"domain_scores_codex":[0.9992204,0.0001296319,0.0002928343,0.0001278369,0.0001084352,0.0001208966],"domain_scores_gemma":[0.9992324,0.00009581559,0.0002597437,0.00008381371,0.000275285,0.00005293373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004979385,0.0008854078,0.00235927,0.000007520174,0.0007504734,0.0001186535,0.00003356103,0.02382815,0.8624532,0.02117364,0.02563846,0.05777229],"study_design_scores_gemma":[0.004117083,0.009924923,0.003429186,0.00006862491,0.0001183721,0.001453583,0.0000392758,0.001061618,0.3746721,0.519545,0.08485576,0.0007144515],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7744188,0.000143756,0.2239875,0.0005699231,0.000431395,0.00006238052,0.000004167201,0.00001107981,0.0003709758],"genre_scores_gemma":[0.9802206,0.00007708887,0.01868882,0.0004686242,0.0004648953,6.206897e-7,0.00002752825,0.000007344492,0.00004446921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4983714,"threshold_uncertainty_score":0.3139893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054547415","doi":"10.1089/106652701300099119","title":"Perfect Phylogenetic Networks with Recombination","year":2001,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":216,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Phylogenetic tree; Phylogenetic network; Recombination; Phylogenetics; Tree (set theory); Time complexity; Mathematics; Evolutionary biology; Biology; Combinatorics; Computer science; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.007125730998609258,"gpt":0.2408557460107803,"spread":0.2337300150121711,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002184243,0.00009129107,0.000130274,0.00008235119,0.0000403404,0.0000106642,0.0001237713,0.00008013881,0.00003122006],"category_scores_gemma":[0.0000235292,0.00007083594,0.00006181233,0.00009773399,0.00005600998,0.000003297789,0.000023306,0.00008441081,0.000004203561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000158552,"about_ca_system_score_gemma":0.00006741132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.503108e-7,"about_ca_topic_score_gemma":0.000002029486,"domain_scores_codex":[0.9993395,0.0000848976,0.0002294191,0.0001188608,0.00009381634,0.0001334858],"domain_scores_gemma":[0.9993204,0.00002888897,0.0002226606,0.00006948215,0.0003076611,0.00005091873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0009656858,0.0003835708,0.1649445,0.0000135973,0.0007019946,0.00005367761,0.00006641448,0.6868437,0.07161407,0.0006916008,0.002051199,0.07167],"study_design_scores_gemma":[0.01644246,0.02896841,0.7017493,0.0001195874,0.0003440352,0.009834047,0.0002194703,0.04139257,0.008591129,0.02343426,0.167233,0.001671831],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8393068,0.0008592559,0.1589122,0.0003017659,0.0001792857,0.00006899359,0.000001357799,0.000002855345,0.0003675018],"genre_scores_gemma":[0.9909842,0.0002068789,0.008125323,0.0001553042,0.0003726073,0.000002057236,0.00006039335,0.00001042464,0.00008278765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6454511,"threshold_uncertainty_score":0.2888606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008288996","doi":"10.1089/10665270252935511","title":"A General Edit Distance between RNA Structures","year":2002,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":207,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Edit distance; RNA; Similarity (geometry); Set (abstract data type); Computer science; Computation; Nucleic acid secondary structure; Arc (geometry); Algorithm; Mathematics; Theoretical computer science; Artificial intelligence; Geometry; Biology; Genetics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01613724710562217,"gpt":0.2617552788092111,"spread":0.245618031703589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001523087,0.00009841676,0.0001755095,0.00005292619,0.00005168053,0.00001247874,0.0001910323,0.0001189035,0.0001235247],"category_scores_gemma":[0.0000725253,0.00007860011,0.0001099379,0.00004483948,0.00006097653,0.000004222469,0.00003012746,0.00008549081,0.00000794231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009495643,"about_ca_system_score_gemma":0.00002861987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.62396e-7,"about_ca_topic_score_gemma":4.318063e-7,"domain_scores_codex":[0.9992253,0.00009710846,0.0003095612,0.0001209821,0.0001127113,0.0001343381],"domain_scores_gemma":[0.9993859,0.00004715538,0.0002646839,0.00008008495,0.0001539232,0.00006824166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002527376,0.0001255349,0.01146952,0.00002575419,0.0006531682,0.00003134969,0.0001193465,0.00878844,0.7735405,0.02045006,0.02715587,0.1573877],"study_design_scores_gemma":[0.002742324,0.003241081,0.0228752,0.00004212967,0.0001109416,0.0004760105,0.00003675829,0.0008565926,0.250143,0.2820037,0.4366868,0.0007854372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8361024,0.002113985,0.1595052,0.0008158942,0.0005625212,0.00006907503,0.00003530249,0.000004470472,0.0007911636],"genre_scores_gemma":[0.9813065,0.00007082272,0.01624118,0.000254947,0.001919094,0.000001301587,0.00002828465,0.000008733124,0.0001691616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5233976,"threshold_uncertainty_score":0.320522,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2253609413","doi":"10.1089/cmb.2015.0189","title":"Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters","year":2016,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":207,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Artificial intelligence; Deep learning; Computer science; Feature selection; Feature (linguistics); Artificial neural network; Machine learning; Nonlinear system; Selection (genetic algorithm); Linear model; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.002544613022489751,"gpt":0.2572304031433438,"spread":0.254685790120854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002150262,0.0000589705,0.00008101024,0.00004337801,0.00003780146,0.000009793502,0.0000553385,0.00007141355,0.000003481864],"category_scores_gemma":[0.00004395834,0.00004093491,0.00002324035,0.00003104534,0.00005310814,0.000003460879,0.00003324633,0.00003590111,0.0000011587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001294344,"about_ca_system_score_gemma":0.00003457066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.612443e-7,"about_ca_topic_score_gemma":0.000002879744,"domain_scores_codex":[0.9995993,0.00005177624,0.0001310632,0.0001115009,0.00003745073,0.00006895953],"domain_scores_gemma":[0.9996256,0.00004017277,0.0001197857,0.00003623113,0.0001245929,0.00005360281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001664513,0.00001540659,0.003215671,0.000007219781,0.00007439246,5.144842e-7,0.00005427656,0.001009844,0.9421837,0.00314684,0.0002689223,0.04985676],"study_design_scores_gemma":[0.005954228,0.006284633,0.4694147,0.0001335351,0.0001740819,0.003368231,0.000342042,0.006229639,0.1149062,0.3430422,0.0490091,0.001141412],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6209273,0.0002406964,0.3779938,0.0007273361,0.00004639478,0.00004378159,0.000002746853,0.00000109886,0.00001678562],"genre_scores_gemma":[0.9904981,0.00009616779,0.008964057,0.0002443142,0.000138828,0.000002460248,0.000008105324,0.000005065933,0.00004291604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8272775,"threshold_uncertainty_score":0.1669277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034206030","doi":"10.1089/10665270252935421","title":"Algorithms for Phylogenetic Footprinting","year":2002,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":177,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Substring; Phylogenetic tree; Footprinting; Computational biology; Biology; Dynamic programming; Set (abstract data type); Computer science; Phylogenetic network; Conserved sequence; Theoretical computer science; Genetics; Algorithm; DNA; Gene; Base sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.02977687371953442,"gpt":0.2799829105839355,"spread":0.2502060368644011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001618128,0.00008550773,0.0001500908,0.00005054628,0.00006133225,0.000007817403,0.000132332,0.00006712045,0.000008721637],"category_scores_gemma":[0.00008445146,0.00007425394,0.0001287252,0.00003526381,0.00005730081,4.227127e-7,0.00004047875,0.00004460201,0.000001877053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006170796,"about_ca_system_score_gemma":0.00002298604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.785542e-7,"about_ca_topic_score_gemma":4.201131e-7,"domain_scores_codex":[0.9993652,0.00003103197,0.0002963191,0.0001179794,0.0000524678,0.0001369875],"domain_scores_gemma":[0.9993213,0.00006633293,0.0002173909,0.00006177063,0.0002913799,0.00004183208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001617211,0.0002528752,0.03189886,0.00003296084,0.0008084011,0.000004188999,0.0001937793,0.03789654,0.7890774,0.002890664,0.005940073,0.1308425],"study_design_scores_gemma":[0.01041732,0.01195009,0.1508107,0.00005401689,0.0002738739,0.001286845,0.0002803145,0.01964068,0.08110693,0.1258628,0.5968769,0.001439545],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9407016,0.003948513,0.05410647,0.0004596284,0.0003960886,0.00009678944,0.00001243524,0.000001073349,0.000277382],"genre_scores_gemma":[0.9614193,0.000161959,0.03749155,0.000225316,0.0006240207,0.000004080321,0.000006460826,0.000009098382,0.00005819136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7079705,"threshold_uncertainty_score":0.3027988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2081112743","doi":"10.1089/106652703322756195","title":"A Transition Probability Model for Amino Acid Substitutions from Blocks","year":2003,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":140,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Ontario Institute for Cancer Research","funders":"","keywords":"Substitution (logic); Sequence (biology); Distance matrices in phylogeny; Sequence alignment; Function (biology); Stochastic matrix; Matrix (chemical analysis); Protein sequencing; Computer science; Protein evolution; Algorithm; Evolutionary algorithm; Mathematics; Peptide sequence; Combinatorics; Biology; Genetics; Artificial intelligence; Machine learning; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02387444716844759,"gpt":0.2631178745095681,"spread":0.2392434273411206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001749402,0.0000809535,0.0001423729,0.00002988004,0.00007285815,0.000005910734,0.00007447611,0.00008526872,0.000005054108],"category_scores_gemma":[0.00008820872,0.00007036974,0.0001265625,0.0000271568,0.00008085074,9.66229e-7,0.000009157527,0.00004787738,4.821324e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001277618,"about_ca_system_score_gemma":0.0001686557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001633106,"about_ca_topic_score_gemma":0.000006434841,"domain_scores_codex":[0.9994006,0.00004721863,0.0002748714,0.0001282532,0.00004615558,0.0001029537],"domain_scores_gemma":[0.9993997,0.00004390366,0.0001401593,0.00006388612,0.0003116253,0.00004070516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002330156,0.0001810276,0.002041142,0.000008077792,0.0002843257,6.466112e-7,0.0002205618,0.4617838,0.5257729,0.008078989,0.000544884,0.0008506212],"study_design_scores_gemma":[0.004102901,0.001657476,0.01088344,0.00001694975,0.0001899546,0.0001281993,0.0001015495,0.05253151,0.07271124,0.8422472,0.01497222,0.0004573175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6039755,0.0006059501,0.3949404,0.000167183,0.0001053118,0.00007416811,0.00008866302,6.050546e-7,0.00004212989],"genre_scores_gemma":[0.9435433,0.0000379635,0.05600346,0.0001902372,0.0001318553,0.000007751966,0.00007046649,0.000004561339,0.00001047983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8341683,"threshold_uncertainty_score":0.2869595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093225483","doi":"10.1089/cmb.2020.0252","title":"Diagnosis of Autism Spectrum Disorder Based on Functional Brain Networks with Deep Learning","year":2020,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Autoencoder; Autism spectrum disorder; Artificial intelligence; Computer science; Deep learning; Machine learning; Benchmark (surveying); Artificial neural network; Functional magnetic resonance imaging; Autism; Pattern recognition (psychology); Set (abstract data type); Neuroscience; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02267701052063384,"gpt":0.2459420574932694,"spread":0.2232650469726356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002252215,0.0001396573,0.0002960914,0.000149987,0.0001439945,0.00001260578,0.0001325873,0.00005929528,0.0001525105],"category_scores_gemma":[0.00323259,0.0001076361,0.0001155471,0.0003561001,0.000204719,0.00008879093,0.00003664032,0.0003819615,0.0000081946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003827043,"about_ca_system_score_gemma":0.0001051783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001932163,"about_ca_topic_score_gemma":0.000003140899,"domain_scores_codex":[0.9985877,0.0003155513,0.0003600776,0.0002385728,0.0003325528,0.000165493],"domain_scores_gemma":[0.9865798,0.01272781,0.0004640732,0.00004732763,0.000100552,0.00008041994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006571053,0.0001143141,0.03994744,0.000007874775,0.00004026972,0.0000149769,0.00005561978,0.949481,0.0003444166,0.006954124,0.00094466,0.001438271],"study_design_scores_gemma":[0.003947283,0.008566893,0.2650424,0.00008155583,0.00005126874,0.000164111,0.00009307577,0.6959857,0.001382353,0.01219687,0.01210876,0.0003797336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3339137,0.0001740265,0.4968075,0.1680901,0.0005016995,0.0001454566,0.00001242223,0.00003401053,0.0003211197],"genre_scores_gemma":[0.988323,0.00001149342,0.001112586,0.01028005,0.0002392945,0.00000509739,0.000006287104,0.00001269233,0.000009444306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6544093,"threshold_uncertainty_score":0.4389274,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035596374","doi":"10.1089/cmb.2009.0047","title":"Maximum Likelihood Genome Assembly","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Genome; De Bruijn graph; De Bruijn sequence; Contig; Hybrid genome assembly; Sequence assembly; Computational biology; Biology; Genetics; Computer science; Algorithm; Mathematics; Combinatorics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.009191157194856088,"gpt":0.2570611932085001,"spread":0.247870036013644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828972,0.00009468847,0.0001646772,0.00006049518,0.00004728962,0.000009622924,0.0001590212,0.00008021868,0.000007128162],"category_scores_gemma":[0.00003681147,0.0000794455,0.0001127675,0.00004634809,0.00003831219,7.936814e-7,0.00003121901,0.00007081771,0.000005571637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009566435,"about_ca_system_score_gemma":0.00009860095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.001427e-7,"about_ca_topic_score_gemma":6.636687e-7,"domain_scores_codex":[0.9993186,0.00004397172,0.0003000915,0.000114421,0.00007190598,0.0001510357],"domain_scores_gemma":[0.9993723,0.00002200888,0.0002102135,0.00007259597,0.0002604054,0.0000624519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001344093,0.0001129227,0.0018939,0.000002733304,0.0001778802,0.00000855561,0.00004730904,0.004880693,0.971918,0.001037099,0.001046814,0.01873965],"study_design_scores_gemma":[0.003189402,0.008753324,0.4911844,0.00001622067,0.00009406039,0.001175157,0.0001062343,0.0002095863,0.02409345,0.3013304,0.169205,0.0006427786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815794,0.002618534,0.01368954,0.001055723,0.0002335991,0.00004400371,0.00001064122,0.000001211579,0.0007673352],"genre_scores_gemma":[0.9893419,0.0001827809,0.008959622,0.0009442774,0.0005254711,4.910103e-7,0.0000215123,0.000005250808,0.00001875488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9478246,"threshold_uncertainty_score":0.3239693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983815263","doi":"10.1089/cmb.2006.13.267","title":"RNA–RNA Interaction Prediction and Antisense RNA Target Search","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Simon Fraser University","funders":"","keywords":"RNA; Non-coding RNA; Computational biology; Antisense RNA; Biology; Nucleic acid secondary structure; Gene; Nucleic acid structure; Algorithm; Sense (electronics); Genetics; Computer science; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01063543045560723,"gpt":0.267135800277262,"spread":0.2565003698216548,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003250316,0.00009114866,0.0001402788,0.00009788419,0.00006667505,0.00001943951,0.00007276082,0.0001219538,0.00002657395],"category_scores_gemma":[0.00004340995,0.0000782165,0.00007054514,0.00004547011,0.0000593667,0.0000102924,0.00003147464,0.0001040494,0.000003891726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001401754,"about_ca_system_score_gemma":0.00006314056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009796647,"about_ca_topic_score_gemma":0.000001066432,"domain_scores_codex":[0.9991693,0.0001448859,0.0003217807,0.0001355271,0.0001081091,0.0001204147],"domain_scores_gemma":[0.999411,0.00005404408,0.0002079845,0.00005672895,0.0002224538,0.00004778713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000198655,0.00004742823,0.00122506,0.000006582387,0.00005461361,0.000007004904,0.00001353517,0.004620896,0.9822676,0.0007702861,0.001447094,0.009341205],"study_design_scores_gemma":[0.00122203,0.001590748,0.01571576,0.00003726967,0.00003211452,0.0008528724,0.00005886985,0.002041449,0.9317905,0.02444805,0.02200463,0.0002057604],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9310924,0.0008320587,0.06668175,0.0004267985,0.0003960785,0.0000680805,0.00002051118,0.000004220487,0.0004781116],"genre_scores_gemma":[0.9881085,0.0001319293,0.01077101,0.0001036216,0.000719953,0.000001423532,0.00007391807,0.000008596531,0.00008105474],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05701611,"threshold_uncertainty_score":0.3189576,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2026888821","doi":"10.1089/cmb.2006.13.1630","title":"A General Modeling Strategy for Gene Regulatory Networks with Stochastic Dynamics","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada; Government of Alberta","keywords":"Gene; Gene regulatory network; Genetic network; Stochastic modelling; Computer science; Computational biology; Translation (biology); Genetics; Transcription (linguistics); Regulation of gene expression; Stochastic process; Activator (genetics); Biology; Gene expression; Mathematics; Messenger RNA","retraction":null,"screen_n_in":null,"score":{"opus":0.008581990317334634,"gpt":0.2416487419311768,"spread":0.2330667516138422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002489635,0.0001552175,0.0002600973,0.0001006397,0.00007916208,0.00001674784,0.0001550168,0.000153368,0.00000312779],"category_scores_gemma":[0.00001063398,0.0001282924,0.0001757738,0.00009689973,0.00007801631,0.000005016901,0.00002570551,0.00009110387,3.230909e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004223203,"about_ca_system_score_gemma":0.0001878008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005753833,"about_ca_topic_score_gemma":0.0000287343,"domain_scores_codex":[0.9989405,0.00006251858,0.0004534223,0.0002009849,0.0001184788,0.0002240618],"domain_scores_gemma":[0.9988934,0.0000340258,0.0003517477,0.0001183286,0.0005379393,0.00006456411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002343082,0.00003869008,0.0003771752,0.000002801972,0.0001832535,0.000002023567,0.000001647635,0.9920452,0.004240029,0.001560633,0.0002428926,0.001071374],"study_design_scores_gemma":[0.0008796507,0.0006138278,0.000948129,0.00000774219,0.00009213832,0.0001989164,0.000009432859,0.9898643,0.0002724205,0.006894493,0.00006126077,0.0001576861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4606334,0.0006580679,0.5385266,0.00004286422,0.00006118115,0.00005508926,0.000007981071,0.00000240422,0.00001241388],"genre_scores_gemma":[0.9678469,0.000008720351,0.03033001,0.00007156722,0.001223839,0.000005169462,0.0004270846,0.00002204529,0.00006464494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5081966,"threshold_uncertainty_score":0.5231615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161936690","doi":"10.1089/cmb.2008.0221","title":"Parallel GPU Implementation of Iterative PCA Algorithms","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Principal component analysis; Orthogonalization; Graphics processing unit; Computer science; Algorithm; Orthogonality; CUDA; Graphics; Parallel computing; Artificial intelligence; Mathematics; Computer graphics (images)","retraction":null,"screen_n_in":null,"score":{"opus":0.01947093356858705,"gpt":0.3585168678255983,"spread":0.3390459342570113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001035115,0.0000793576,0.0002469571,0.0001617231,0.00003113173,0.000008005964,0.0001182997,0.00005783846,0.0008164624],"category_scores_gemma":[0.00003041857,0.00006460363,0.0001114562,0.0001790085,0.00004333176,0.00007684717,0.000008686764,0.0001150965,0.000002773797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000409628,"about_ca_system_score_gemma":0.00008908499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005244944,"about_ca_topic_score_gemma":6.219826e-7,"domain_scores_codex":[0.9991837,0.0000215236,0.0004820605,0.00007771717,0.0001336115,0.0001014231],"domain_scores_gemma":[0.9988952,0.0001577144,0.0005500951,0.00004230464,0.0003142166,0.00004052382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001164885,0.001887127,0.1011241,0.0001332466,0.003489712,0.00009710388,0.003858141,0.04645386,0.539969,0.07457342,0.01166817,0.2155813],"study_design_scores_gemma":[0.007872748,0.00337534,0.1148016,0.00006098616,0.0005861723,0.0006392327,0.003120392,0.003642353,0.5018932,0.3591904,0.004161334,0.0006562129],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8794249,0.001082961,0.11545,0.001624411,0.00009978726,0.00003538394,0.00004140264,0.00001087763,0.002230291],"genre_scores_gemma":[0.9793962,0.00003388813,0.02012875,0.0001907491,0.0001669678,4.135741e-7,0.0000380256,0.000002748651,0.00004225244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.284617,"threshold_uncertainty_score":0.8939691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1966241066","doi":"10.1089/cmb.2007.r002","title":"Bayesian Inference of MicroRNA Targets from Sequence and Expression Data","year":2007,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"microRNA; Biology; Computational biology; Robustness (evolution); Inference; Gene; DNA microarray; Gene expression profiling; Gene expression; Bayesian probability; Regulation of gene expression; Bioinformatics; Artificial intelligence; Computer science; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.07661162696924576,"gpt":0.3947066090749922,"spread":0.3180949821057464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003513941,0.0002056087,0.0006922063,0.0001446856,0.0000271395,0.00001023309,0.0005067166,0.0003513429,0.00002604132],"category_scores_gemma":[0.0002255543,0.0001633195,0.0001388215,0.00007426477,0.0001392266,0.000009568065,0.0003084226,0.0001776546,0.000001465335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002565051,"about_ca_system_score_gemma":0.0004978353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005388028,"about_ca_topic_score_gemma":0.00000183034,"domain_scores_codex":[0.9983902,0.0002023067,0.0008596272,0.0002976815,0.0001248473,0.0001253477],"domain_scores_gemma":[0.9977422,0.0002339571,0.001390361,0.0002973562,0.0002463367,0.0000898259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001253317,0.0001158034,0.0002625226,0.001594202,0.0005702675,0.00002082859,0.00002448351,0.0002500688,0.05943929,0.00008415421,0.00137245,0.9361406],"study_design_scores_gemma":[0.0005282583,0.0002843482,0.0002598783,0.003240175,0.0003507015,0.0002708636,0.000006289839,0.0001720541,0.00186554,0.003252193,0.9894094,0.0003602561],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001490831,0.9411433,0.05640703,0.00001654943,0.0001665058,0.0001187074,0.0006420411,0.00000165885,0.00001340723],"genre_scores_gemma":[0.01088714,0.9585935,0.02578972,0.00003552769,0.0004266739,0.000001135539,0.004239687,0.00001970287,0.000006906569],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.988037,"threshold_uncertainty_score":0.6659978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205330988","doi":"10.1089/cmb.2021.0290","title":"MONI: A Pangenomic Index for Finding Maximal Exact Matches","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Parsing; Computer science; Index (typography); Trie; Prefix; Matching (statistics); Pattern matching; Algorithm; Sequence (biology); Tree (set theory); Theoretical computer science; Mathematics; Data structure; Artificial intelligence; Combinatorics; Statistics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02062048482590375,"gpt":0.2744811594893764,"spread":0.2538606746634727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002728638,0.00008583799,0.0001620964,0.00007505392,0.0001530109,0.000007970131,0.0001722317,0.00004184416,0.00002134159],"category_scores_gemma":[0.00003297276,0.00008059421,0.0001156951,0.00004027074,0.00004217674,6.578352e-7,0.0001260484,0.00008159991,7.625384e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002739405,"about_ca_system_score_gemma":0.0001254818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000027784,"about_ca_topic_score_gemma":0.000001535473,"domain_scores_codex":[0.99933,0.00005769556,0.0002775431,0.0001248533,0.00006996346,0.0001399394],"domain_scores_gemma":[0.9994621,0.00007047633,0.0002582169,0.00005756468,0.0001165929,0.00003500482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001363909,0.0002078304,0.09036966,0.00002354625,0.0008787185,0.000008896614,0.0002838831,0.2105164,0.6780713,0.001764284,0.00558836,0.0109232],"study_design_scores_gemma":[0.009073903,0.01369172,0.3221289,0.00001630732,0.000210603,0.001793607,0.002000483,0.004742431,0.01834266,0.1302861,0.4965356,0.001177731],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845384,0.001549769,0.01298414,0.0003159387,0.0003616952,0.00009631785,0.00008621658,9.197191e-7,0.00006655473],"genre_scores_gemma":[0.9942918,0.00004203095,0.004939253,0.0002761429,0.0003292895,0.00001526328,0.0000468256,0.00001071061,0.00004871823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6597286,"threshold_uncertainty_score":0.3286537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978802080","doi":"10.1089/cmb.2007.0229","title":"Computing Knock-Out Strategies in Metabolic Networks","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Computation; Computer science; Block (permutation group theory); Computational complexity theory; Metabolic network; Algorithm; Theoretical computer science; Mathematics; Computational biology; Biology; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01034546835111357,"gpt":0.2563395280575266,"spread":0.245994059706413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002471764,0.00009356246,0.0001981815,0.0001106923,0.0000392842,0.000007315482,0.0001097909,0.00009980823,0.000004829809],"category_scores_gemma":[0.00005185306,0.00008022163,0.00007626345,0.00009631311,0.00006698864,0.000006260671,0.00002798371,0.0001450317,0.000001979674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006956314,"about_ca_system_score_gemma":0.0001097567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006252876,"about_ca_topic_score_gemma":0.000004087186,"domain_scores_codex":[0.9992515,0.00007332698,0.0003564917,0.0001206682,0.00005755672,0.0001404157],"domain_scores_gemma":[0.9995508,0.00001348864,0.0001800579,0.00006092448,0.0001580667,0.00003672848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00008613853,0.000073571,0.00579327,0.000005542693,0.00007880182,0.00001102979,0.00009720788,0.7529543,0.2351161,0.001190596,0.0007371737,0.003856288],"study_design_scores_gemma":[0.009719159,0.003297688,0.6168624,0.000184589,0.0001434649,0.01094918,0.0006961875,0.04115953,0.09225098,0.009364303,0.2133861,0.001986435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8735946,0.002936103,0.1226351,0.00009662945,0.000612178,0.00003485059,0.000001646276,0.000004055781,0.00008482472],"genre_scores_gemma":[0.9920356,0.0003649795,0.006391904,0.00008707012,0.001059619,3.866457e-7,0.00002667689,0.000007128303,0.00002659171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7117947,"threshold_uncertainty_score":0.3271343,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007492229","doi":"10.1089/106652704773416966","title":"From a Phylogenetic Tree to a Reticulated Network","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Reticulate; Reticulate evolution; Phylogenetic tree; Phylogenetic network; Biology; Phylogenetics; Evolutionary biology; Tree (set theory); Most recent common ancestor; Ancestor; Paleontology; Genetics; Gene; Combinatorics; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.009135419365097668,"gpt":0.2517320367021659,"spread":0.2425966173370682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001317868,0.0001170188,0.0002060279,0.00004915597,0.00005109148,0.00000937019,0.0001768693,0.00009380401,0.000008560215],"category_scores_gemma":[0.00006127752,0.0001000662,0.0001102848,0.00009621347,0.00005614043,4.87224e-7,0.00007861703,0.00006803266,0.00001031976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001809487,"about_ca_system_score_gemma":0.000130918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001340186,"about_ca_topic_score_gemma":0.00001402018,"domain_scores_codex":[0.9991722,0.00005109745,0.0003508422,0.000166874,0.00008307948,0.0001759014],"domain_scores_gemma":[0.9993365,0.0000366541,0.000183251,0.000101117,0.0002451765,0.00009727849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002682744,0.00007269174,0.00647812,0.000002084892,0.0003667359,0.00001059314,0.00015693,0.5446119,0.4420863,0.000684763,0.001479066,0.003782553],"study_design_scores_gemma":[0.006542938,0.00692771,0.4726969,0.00009023278,0.0001906681,0.0004233232,0.0001436078,0.0002712599,0.0393135,0.3976735,0.07483838,0.0008880064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9741224,0.001650645,0.02263905,0.0009857918,0.0003754696,0.00007727392,0.00001921995,0.000001354886,0.0001287958],"genre_scores_gemma":[0.9625935,0.00005634651,0.03533367,0.0008514296,0.001110787,0.000002390143,0.0000308858,0.00001053802,0.00001042834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5443406,"threshold_uncertainty_score":0.4080581,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058730888","doi":"10.1089/cmb.2010.0184","title":"Gene Prediction Based on DNA Spectral Analysis: A Literature Review","year":2011,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"ENCODE; Digital signal processing; Genetic code; Computational biology; Computer science; DNA; Coding (social sciences); Biology; Gene; Genetics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01866156464907689,"gpt":0.3082749050703346,"spread":0.2896133404212577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004322315,0.0003161364,0.001373671,0.0005592524,0.0000441107,0.00001900389,0.0003299527,0.0003897397,0.00007539892],"category_scores_gemma":[0.0001138396,0.0002154595,0.001818587,0.0007526547,0.0000694335,0.000006330838,0.00003142753,0.0003591226,0.00001434552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000409858,"about_ca_system_score_gemma":0.000381143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001232616,"about_ca_topic_score_gemma":0.000001251336,"domain_scores_codex":[0.9979939,0.0003594107,0.0009758726,0.0003251429,0.00016789,0.0001777798],"domain_scores_gemma":[0.9979848,0.00006292302,0.00119898,0.0002372339,0.0004082729,0.0001077697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003892312,0.0009473118,0.0002421995,0.01677076,0.0226486,0.0002895648,0.00003065804,0.008947495,0.0003094331,0.0005838961,0.01294603,0.9358948],"study_design_scores_gemma":[0.0002687382,0.001357892,0.0000703086,0.01023667,0.008264245,0.0004214344,0.000001037256,0.0001932797,0.00003629606,0.0005689408,0.9782403,0.000340846],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00004484217,0.9960496,0.003129218,0.00007349181,0.0001834672,0.0001422719,0.00020083,0.000004149115,0.000172169],"genre_scores_gemma":[0.0003748711,0.9931255,0.001574669,0.0007153692,0.0006650759,0.000009089942,0.003454354,0.00001692506,0.00006414246],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9652943,"threshold_uncertainty_score":0.8786184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122316710","doi":"10.1089/cmb.2014.0160","title":"On the Representation of De Bruijn Graphs","year":2015,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; Canada's Michael Smith Genome Sciences Centre","funders":"Division of Biological Infrastructure","keywords":"De Bruijn sequence; De Bruijn graph; Bottleneck; Computer science; Theoretical computer science; Data structure; Graph; Representation (politics); Mathematics; Discrete mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03073178202377309,"gpt":0.3002495380754645,"spread":0.2695177560516914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002536328,0.00004470941,0.00009256535,0.00003424347,0.00002110221,0.000003179725,0.0001049116,0.0000385058,0.000002899381],"category_scores_gemma":[0.0001921375,0.00002899678,0.00006745093,0.00004620765,0.00007534106,3.888929e-7,0.00002622243,0.00004255166,9.22296e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006124632,"about_ca_system_score_gemma":0.00009994447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002753407,"about_ca_topic_score_gemma":0.000001193732,"domain_scores_codex":[0.9995324,0.00009198418,0.0001942409,0.0000552635,0.00006547954,0.00006064449],"domain_scores_gemma":[0.9992883,0.0001079898,0.0002070706,0.00005928662,0.0003070006,0.00003039235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00100626,0.0002298335,0.1037343,0.000008965401,0.0006416693,0.000004899282,0.0006321575,0.1457475,0.6291919,0.08881437,0.02500542,0.004982728],"study_design_scores_gemma":[0.001978778,0.004099,0.1279503,0.00001803561,0.00005545357,0.0001923441,0.0004860173,0.0006617213,0.08241938,0.7738668,0.00807913,0.0001930371],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949365,0.0004844232,0.003267989,0.0007625095,0.000140015,0.00003315616,0.00000563727,2.936088e-7,0.0003694226],"genre_scores_gemma":[0.9978682,0.00004200962,0.001650568,0.0003192645,0.00009827398,9.268081e-7,0.000005942554,0.000003046392,0.00001177931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6850525,"threshold_uncertainty_score":0.1182454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022846158","doi":"10.1089/10665270360688129","title":"Tests for Gene Clustering","year":2003,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"National Human Genome Research Institute","keywords":"Genome; Biology; Gene; Gene duplication; Comparative genomics; Horizontal gene transfer; Gene cluster; Genetics; Genomics; Evolutionary biology; Gene family; Computational biology; Genome evolution","retraction":null,"screen_n_in":null,"score":{"opus":0.0198886956447467,"gpt":0.2979448129065418,"spread":0.2780561172617951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000256245,0.00006663587,0.0001102026,0.00005544101,0.00003294445,0.000006967548,0.00008896737,0.00006314879,0.00001145337],"category_scores_gemma":[0.0001303417,0.00005855094,0.00008763651,0.00003485303,0.00002891638,0.00000206583,0.00001634772,0.00003931405,0.000002485147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001087766,"about_ca_system_score_gemma":0.00008585517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.280142e-7,"about_ca_topic_score_gemma":7.05149e-7,"domain_scores_codex":[0.9994662,0.00004472851,0.0002312062,0.00009018776,0.00005328492,0.00011441],"domain_scores_gemma":[0.9994487,0.00004142995,0.0001658038,0.00005233834,0.0002492057,0.00004253494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000192085,0.0001527977,0.007137284,0.00002682711,0.0003792837,0.000005935929,0.00005063255,0.05767652,0.9196212,0.002238329,0.003101883,0.009417227],"study_design_scores_gemma":[0.01121305,0.007830634,0.02546885,0.00003916196,0.0001530552,0.002642298,0.0001406498,0.004604133,0.1902722,0.0902853,0.6663705,0.0009801615],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5062876,0.0009252855,0.4918031,0.0001820679,0.0004105582,0.0001054366,0.00001143166,0.000002180526,0.0002723591],"genre_scores_gemma":[0.8828136,0.00003101401,0.1165715,0.0001769031,0.0002818019,0.000003235677,0.00003922759,0.000008774494,0.00007388606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.729349,"threshold_uncertainty_score":0.2387638,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068396445","doi":"10.1089/cmb.2006.13.567","title":"On Sorting by Translocations","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Sorting; Chromosomal translocation; Sorting algorithm; Genome; Chromosome; Computer science; Algorithm; Computational biology; Biology; Mathematics; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.005620043957935987,"gpt":0.250474535487991,"spread":0.244854491530055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001426249,0.00006529177,0.00009150634,0.00005722681,0.00003967055,0.000007267327,0.00009574612,0.00005892758,0.00002019708],"category_scores_gemma":[0.00002663336,0.00005696198,0.00007155283,0.00004864954,0.00003914852,0.000001991367,0.000008529249,0.00006280567,0.000007396128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001038829,"about_ca_system_score_gemma":0.00005134437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002698818,"about_ca_topic_score_gemma":0.000001284104,"domain_scores_codex":[0.9994162,0.00004293184,0.0002759691,0.00008649193,0.00008115253,0.0000973027],"domain_scores_gemma":[0.9995526,0.00003598839,0.0001862053,0.00004733671,0.0001506302,0.00002720799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001459891,0.0004265773,0.004991642,0.00001027839,0.0001986626,0.000005071773,0.00002974025,0.1067526,0.8171862,0.01400387,0.04533903,0.0109103],"study_design_scores_gemma":[0.01007514,0.008499281,0.05249779,0.00007361763,0.0001750808,0.0007201644,0.0001374691,0.004551077,0.1546614,0.4955339,0.271749,0.001326001],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8617514,0.0007365888,0.1350561,0.0009111433,0.0001729231,0.00005661314,0.00001800573,0.000003459958,0.00129374],"genre_scores_gemma":[0.9941571,0.00001248719,0.005065402,0.0002021869,0.0002673261,0.000001320109,0.0001586531,0.000006696358,0.0001287628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6625248,"threshold_uncertainty_score":0.2322842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034206612","doi":"10.1089/cmb.2008.0054","title":"Gene Family Evolution by Duplication, Speciation, and Loss","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Simon Fraser University; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Gene duplication; Genetic algorithm; Gene family; Biology; Tree rearrangement; Gene; Heuristic; Tree (set theory); Evolutionary biology; Phylogenetics; Computational biology; Genetics; Computer science; Mathematics; Genome; Combinatorics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.008717990535582093,"gpt":0.2306207468131898,"spread":0.2219027562776077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001139784,0.0000720547,0.0001165214,0.00004107844,0.00008952752,0.000004001379,0.00007469138,0.00006580543,0.00000223988],"category_scores_gemma":[0.00003847468,0.00006450281,0.00004198205,0.00004281421,0.0001173436,0.000001231553,0.00003240409,0.00004325335,0.000002041347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001408727,"about_ca_system_score_gemma":0.00008302218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000367685,"about_ca_topic_score_gemma":6.296301e-7,"domain_scores_codex":[0.9994416,0.00003768758,0.0002601303,0.0001123677,0.00006410165,0.00008407445],"domain_scores_gemma":[0.9993314,0.00002673179,0.0002101758,0.00005416264,0.0003346962,0.00004280616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00008734458,0.00007026512,0.127522,0.000003590786,0.0001603429,0.000002413806,0.00006829528,0.002560701,0.8568807,0.001260622,0.01034419,0.001039581],"study_design_scores_gemma":[0.001253549,0.0007601983,0.9156926,0.000003869118,0.00002513919,0.000757715,0.00003532663,0.0001634787,0.01499586,0.01943143,0.04666987,0.0002109597],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9694392,0.005786136,0.0240845,0.000416248,0.0001250096,0.00004079409,0.0000231438,8.506643e-7,0.00008412822],"genre_scores_gemma":[0.9940524,0.00105426,0.004240787,0.0002446013,0.0003118351,0.000001438617,0.00004488598,0.0000052493,0.00004454551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8418848,"threshold_uncertainty_score":0.2630348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045430208","doi":"10.1089/106652701752236232","title":"Unfolding of Microarray Data","year":2001,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Microarray databases; DNA microarray; Microarray analysis techniques; Microarray; Robustness (evolution); Outlier; Computer science; Data mining; Gene chip analysis; Inference; Computational biology; Biology; Artificial intelligence; Genetics; Gene expression; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03968641451553621,"gpt":0.3339513396237907,"spread":0.2942649251082545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002188087,0.00004988622,0.0001058259,0.00005555154,0.00001972231,0.000003879766,0.0002838864,0.00006187482,0.00002811538],"category_scores_gemma":[0.00007050267,0.0000410183,0.00004280184,0.00007145948,0.00004991695,0.000004543125,0.00006493431,0.00004819341,0.000001595924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005522678,"about_ca_system_score_gemma":0.0001180345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001004737,"about_ca_topic_score_gemma":6.920631e-7,"domain_scores_codex":[0.9994117,0.00005294034,0.0002953897,0.0001042325,0.00007034979,0.0000653696],"domain_scores_gemma":[0.9992564,0.00002311511,0.0003279042,0.0001570095,0.0002018344,0.00003378921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001275397,0.0000480123,0.007320471,0.000004128057,0.00005197967,0.000001208036,0.00001585995,0.002059545,0.9752134,0.0004143316,0.006544082,0.008199427],"study_design_scores_gemma":[0.002665739,0.001205268,0.03399995,0.00006478459,0.00005949762,0.0007945787,0.0002583881,0.001394363,0.2320604,0.01022275,0.7169592,0.0003150896],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9147108,0.001621942,0.08218098,0.0006440842,0.0003167625,0.00003394822,0.00001702764,0.000001601462,0.0004728973],"genre_scores_gemma":[0.9933891,0.0002205724,0.005810211,0.0001579697,0.0002335678,3.422115e-7,0.0001257721,0.000004093209,0.00005831176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.743153,"threshold_uncertainty_score":0.1672678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003921372","doi":"10.1089/cmb.2005.12.812","title":"Chromosomal Breakpoint Reuse in Genome Sequence Rearrangement","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Breakpoint; Genome; Biology; Computational biology; Sequence (biology); Genetics; Identification (biology); Gene; Reuse; Computer science; Chromosome","retraction":null,"screen_n_in":null,"score":{"opus":0.01606047862208839,"gpt":0.2841884439062238,"spread":0.2681279652841354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003881768,0.0001131454,0.0001828041,0.0001484906,0.00002590251,0.00001061017,0.0003190193,0.00009488298,0.00006107488],"category_scores_gemma":[0.00007371444,0.0001022578,0.00008930333,0.00009542904,0.00007024338,0.00000801391,0.0001065932,0.0001233711,0.00002262037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007023803,"about_ca_system_score_gemma":0.0001353856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000407545,"about_ca_topic_score_gemma":0.00001006682,"domain_scores_codex":[0.998946,0.00009314562,0.0004659198,0.0001662381,0.0001352311,0.000193531],"domain_scores_gemma":[0.9993089,0.00002272528,0.0002456901,0.0001563602,0.0001972484,0.00006911594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001610849,0.0001974242,0.005282579,0.00001054766,0.0001245722,0.00002998872,0.0001456166,0.04762824,0.9365019,0.0002972392,0.0007970422,0.008823771],"study_design_scores_gemma":[0.01164157,0.006157984,0.2575446,0.0001129868,0.00009496191,0.003005149,0.0002220705,0.004573222,0.03579548,0.01986405,0.659637,0.001350906],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930198,0.0009922354,0.003449901,0.001944291,0.0001818171,0.0001008307,0.0000181453,0.000003314719,0.0002896459],"genre_scores_gemma":[0.9742996,0.0001583763,0.02436478,0.0003665425,0.0006155935,0.000003431303,0.00009132839,0.00001077662,0.0000895772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9007064,"threshold_uncertainty_score":0.4169953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127421473","doi":"10.1089/cmb.2013.0042","title":"IDBA-MT: <i>De Novo</i> Assembler for Metatranscriptomic Data Generated from Next-Generation Sequencing Technology","year":2013,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Amgen (Canada); University of Toronto","funders":"","keywords":"Contig; Sequence assembly; Computational biology; DNA sequencing; Genome; Biology; Computer science; Transcriptome; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.08796824590738316,"gpt":0.2947364766319145,"spread":0.2067682307245314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002643581,0.0001414365,0.000250131,0.00009777119,0.00009061445,0.00003553256,0.0003849684,0.0001827323,0.00001872956],"category_scores_gemma":[0.0001086203,0.0001234376,0.00008242494,0.00007871722,0.00007505492,0.000006928836,0.00008965214,0.00009875307,0.000004529545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003048583,"about_ca_system_score_gemma":0.0002820511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002344631,"about_ca_topic_score_gemma":0.00001647384,"domain_scores_codex":[0.9989439,0.00006996791,0.0004534715,0.0002606901,0.00006609767,0.0002058274],"domain_scores_gemma":[0.9988579,0.00006395537,0.0002841387,0.0002067693,0.0005310711,0.00005622246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003158457,0.00002373715,0.001144425,0.000003450305,0.0002945779,9.207056e-7,0.00002272131,0.007173711,0.9852586,0.0002348681,0.003234501,0.002576949],"study_design_scores_gemma":[0.006070449,0.002935473,0.006924969,0.00003679629,0.000442102,0.0005768694,0.0004234078,0.1311147,0.6716205,0.1011006,0.07765321,0.001100909],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8637601,0.003451307,0.1308909,0.001156741,0.0004161662,0.0001548464,0.0001429334,0.000002844482,0.00002421222],"genre_scores_gemma":[0.9236363,0.000226613,0.07401019,0.000639288,0.0008508406,0.00001402712,0.0005894372,0.00001559434,0.00001773783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.313638,"threshold_uncertainty_score":0.503364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021281986","doi":"10.1089/cmb.2006.13.1419","title":"Approximating Subtree Distances Between Phylogenies","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of British Columbia; Graduate Center; National Science Foundation","keywords":"Tree (set theory); Approximation algorithm; Algorithm; Type (biology); Scheme (mathematics); Computer science; Mathematics; Combinatorics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0120957413160893,"gpt":0.2592623049771438,"spread":0.2471665636610545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003070595,0.00008452703,0.0002090899,0.0001119539,0.00009814579,0.0000605986,0.0005271449,0.00004437326,0.000005209485],"category_scores_gemma":[0.00002941971,0.00006194835,0.00007326629,0.0001510034,0.00006128626,0.000320223,0.0001141072,0.0001166428,0.000005491712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002033079,"about_ca_system_score_gemma":0.00006673235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009597935,"about_ca_topic_score_gemma":0.000001097633,"domain_scores_codex":[0.9989878,0.00007713501,0.0004891494,0.0001242585,0.0001844224,0.0001372228],"domain_scores_gemma":[0.9988025,0.0003660349,0.0004889303,0.0000952545,0.0002079358,0.00003929764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004121084,0.000257684,0.1120654,0.0000373988,0.0001623568,0.00006063074,0.0002931974,0.04945323,0.002745362,0.5344478,0.007321823,0.2931139],"study_design_scores_gemma":[0.0006756993,0.0002909983,0.125325,0.00003619592,0.00001210679,0.000147965,0.00001873467,0.05142065,0.0005264406,0.8105293,0.01080969,0.0002071855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09686499,0.0004770801,0.9015054,0.0005128332,0.0002401234,0.00002660189,0.00001096087,0.00001673952,0.0003453046],"genre_scores_gemma":[0.7190417,0.000002782086,0.2804661,0.00004441807,0.0004151789,4.820577e-7,0.00001739437,0.000002366784,0.000009576146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6221767,"threshold_uncertainty_score":0.2526181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2977115588","doi":"10.1089/cmb.2019.0237","title":"Analysis of Gene Expression in Bladder Cancer: Possible Involvement of Mitosis and Complement and Coagulation Cascades Signaling Pathway","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ministry of Agriculture","funders":"","keywords":"microRNA; Biology; Microarray analysis techniques; Gene; Cell cycle; Transcription factor; Gene regulatory network; Downregulation and upregulation; Cancer research; Cell biology; Gene expression; Computational biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02944806252690458,"gpt":0.3143439019859041,"spread":0.2848958394589995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002660817,0.00006771101,0.0004451212,0.0003981135,0.00001402611,0.000003501581,0.00003122817,0.0000401466,0.00008498091],"category_scores_gemma":[0.000009574,0.00005130873,0.00007184144,0.0002238805,0.00004816407,0.00004097638,0.00002069296,0.00006320258,6.694582e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003701738,"about_ca_system_score_gemma":0.00008161236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007470412,"about_ca_topic_score_gemma":0.00001874259,"domain_scores_codex":[0.9990492,0.00006147718,0.0005520718,0.000101311,0.0001628909,0.00007298647],"domain_scores_gemma":[0.9990536,0.0001341504,0.0004733831,0.00004065919,0.0002572291,0.00004098015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001727638,0.00008758807,0.7477779,0.00006026255,0.0004894194,7.840035e-7,0.0003354545,0.02324272,0.2247073,0.00007380878,0.000009487394,0.003042554],"study_design_scores_gemma":[0.001906853,0.0008172259,0.865436,0.0002223551,0.0004116192,0.000008431764,0.0003556023,0.01183705,0.1184961,0.0004041074,0.00003898843,0.00006567031],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959717,0.002352067,0.00119365,0.000286504,0.000044147,0.0001159027,0.00002523678,9.902539e-7,0.000009794171],"genre_scores_gemma":[0.9935673,0.0002372192,0.006048664,0.0000844735,0.00002634925,0.000002750487,0.00002768958,0.000003377297,0.000002116644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1176581,"threshold_uncertainty_score":0.2092309,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992306462","doi":"10.1089/cmb.2008.21tt","title":"How to Synchronize Biological Clocks","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Genetics; European Commission","keywords":"Biological clock; Construct (python library); Computer science; Biological network; Synchronization (alternating current); Set (abstract data type); Distributed computing; Theoretical computer science; Computer network; Biology; Computational biology; Programming language; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.01107651730193498,"gpt":0.2620000061672376,"spread":0.2509234888653026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002412648,0.000118909,0.000235171,0.0001106557,0.00004647966,0.00002153567,0.0002277043,0.0001467829,0.00001459895],"category_scores_gemma":[0.0001303255,0.00009176267,0.0001878592,0.000140818,0.0000518706,0.000003308814,0.00003912904,0.00009179422,0.000006104042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000213203,"about_ca_system_score_gemma":0.0000935352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.360399e-7,"about_ca_topic_score_gemma":6.608795e-7,"domain_scores_codex":[0.9991299,0.0001101108,0.0002936114,0.0001763843,0.0001069968,0.0001830105],"domain_scores_gemma":[0.9991841,0.00003262989,0.00021676,0.000111809,0.0003220854,0.0001326265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005608269,0.0003336181,0.01890388,0.000005373292,0.0006640048,0.00004168895,0.00005415261,0.169276,0.6862335,0.004389753,0.03170341,0.0878338],"study_design_scores_gemma":[0.004333333,0.02053048,0.2710251,0.00005763143,0.0002305407,0.002255845,0.0001761654,0.0027011,0.05753814,0.08058719,0.5590666,0.001497837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8918534,0.001001917,0.1021245,0.004678157,0.000166132,0.00005589094,0.000004343385,0.00000442644,0.0001112215],"genre_scores_gemma":[0.9840327,0.00004491163,0.01361677,0.001353353,0.000823672,7.559965e-7,0.0000374653,0.000005083322,0.0000852931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6286954,"threshold_uncertainty_score":0.3741973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051551591","doi":"10.1089/cmb.2006.13.1340","title":"On the Similarity of Sets of Permutations and Its Applications to Genome Comparison","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Genome; Chaining; Similarity (geometry); Generalization; Key (lock); Feature (linguistics); Computer science; Combinatorics; Mathematics; Computational biology; Theoretical computer science; Biology; Gene; Genetics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01775467834541102,"gpt":0.3016380343992673,"spread":0.2838833560538563,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195618,0.00006233054,0.0001466078,0.00007686241,0.00003899713,0.000003555011,0.0001211091,0.00004947882,0.00001129736],"category_scores_gemma":[0.00005114616,0.00004635369,0.00005274508,0.00008545511,0.00006087818,0.000001925239,0.00003532901,0.00005820471,0.000001736196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006233918,"about_ca_system_score_gemma":0.00005129375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002527581,"about_ca_topic_score_gemma":0.000002635558,"domain_scores_codex":[0.9993432,0.00006141484,0.0003493196,0.00008395379,0.00009241202,0.00006973503],"domain_scores_gemma":[0.9991332,0.0001298686,0.0002898675,0.00006715939,0.000350849,0.00002907273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001614136,0.000505545,0.009614994,0.00004397031,0.0002597053,8.18556e-7,0.0001785131,0.1897452,0.7445208,0.05178453,0.001418964,0.001765483],"study_design_scores_gemma":[0.003130956,0.005330883,0.6939421,0.00005092832,0.0002163908,0.0001696528,0.0004241987,0.007104199,0.09669778,0.1525014,0.03983404,0.0005973901],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9580363,0.0005953928,0.03994491,0.0009441396,0.00002829286,0.0001674006,0.00006217216,9.897753e-7,0.0002203828],"genre_scores_gemma":[0.9966179,0.00001626547,0.003108792,0.000103531,0.00006680335,0.000005424617,0.00006263322,0.000004270581,0.0000143834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6843271,"threshold_uncertainty_score":0.1890249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050243856","doi":"10.1089/cmb.2009.0095","title":"Space of Gene/Species Trees Reconciliations and Parsimonious Models","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Tree (set theory); Space (punctuation); Computer science; Mutation; Gene duplication; Family tree; Mathematics; Gene; Combinatorics; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01963970999811997,"gpt":0.2529601758186593,"spread":0.2333204658205393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001125307,0.00006776232,0.0001599529,0.000049947,0.00003540498,0.000004518425,0.00007347205,0.00005634906,0.000002086809],"category_scores_gemma":[0.00003568167,0.00005718331,0.00006165726,0.00003324757,0.00007707111,0.000001214806,0.0000172377,0.00003802034,1.924869e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005291444,"about_ca_system_score_gemma":0.00006380822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001629425,"about_ca_topic_score_gemma":0.000003064918,"domain_scores_codex":[0.9994982,0.0000337718,0.0002570029,0.0000840521,0.00005093116,0.00007601111],"domain_scores_gemma":[0.9994118,0.0000331396,0.0002210715,0.0000512133,0.0002494424,0.00003328946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001145444,0.0001016334,0.007334913,0.000004832943,0.0002280354,0.000001903588,0.000249763,0.09397534,0.8801405,0.01098514,0.0009903669,0.005873063],"study_design_scores_gemma":[0.003222328,0.006082016,0.5379928,0.00003037359,0.0001349135,0.0004016238,0.0004952616,0.00397685,0.0902146,0.3414917,0.01544781,0.0005097098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9835552,0.00379889,0.01127577,0.0008184742,0.00008368522,0.0000355334,0.00002407982,5.700323e-7,0.0004078129],"genre_scores_gemma":[0.9867758,0.0007009997,0.01220847,0.0001359532,0.0001272106,3.926804e-7,0.00001057651,0.000002777718,0.00003777789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7899259,"threshold_uncertainty_score":0.2331868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2083479074","doi":"10.1089/cmb.2008.0219","title":"An <i>O</i> ( <i>n</i> <sup>5</sup> ) Algorithm for MFE Prediction of Kissing Hairpins and 4-Chains in Nucleic Acids","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Nucleic acid; Algorithm; Function (biology); Computer science; Nucleic acid secondary structure; Nucleic acid structure; Class (philosophy); Protein secondary structure; RNA; Computational biology; Mathematics; Biology; Artificial intelligence; Genetics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01055262268037657,"gpt":0.261910987315347,"spread":0.2513583646349705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003999315,0.00009583426,0.0002082879,0.0001091396,0.00004268782,0.00001019142,0.0001058534,0.0001473756,0.000002747371],"category_scores_gemma":[0.00004951465,0.00008586106,0.00007421069,0.00005458838,0.00005530318,0.0000125481,0.00001201197,0.00006680974,1.529036e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013834,"about_ca_system_score_gemma":0.00008136927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001715235,"about_ca_topic_score_gemma":6.512685e-7,"domain_scores_codex":[0.9991556,0.0000969821,0.0004022294,0.0001423819,0.00007741476,0.0001254355],"domain_scores_gemma":[0.9993979,0.00004763714,0.0002475694,0.00007022824,0.0001755766,0.00006102551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002622374,0.0002037251,0.00160791,0.00001283135,0.00005467112,0.000002958315,0.0001517868,0.01273263,0.7589083,0.001242523,0.0001332596,0.2246872],"study_design_scores_gemma":[0.01085289,0.02951708,0.05047286,0.0003013274,0.0001499588,0.00113404,0.0006316635,0.2436944,0.5083095,0.1373354,0.01675258,0.0008482396],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.649579,0.0004846969,0.3493846,0.0002906979,0.00006905234,0.0001102086,0.00005138676,0.00000266356,0.00002769798],"genre_scores_gemma":[0.9186904,0.0000806869,0.08061036,0.000300435,0.0002447569,0.000002117478,0.00005757326,0.000007047257,0.000006656718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2691113,"threshold_uncertainty_score":0.3501312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024827079","doi":"10.1089/cmb.2009.0067","title":"Two Lower Bounds for Self-Assemblies at Temperature 1","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Tile; Square (algebra); Combinatorics; Upper and lower bounds; Domain (mathematical analysis); Mathematics; Discrete mathematics; Computer science; Geometry; Materials science; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.005450051418784046,"gpt":0.2983602811779114,"spread":0.2929102297591273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002497289,0.0001141561,0.0001839705,0.00008242589,0.0001028015,0.00001813498,0.00013887,0.0001746751,0.000003592673],"category_scores_gemma":[0.000098173,0.0000848694,0.0001915029,0.00006390861,0.00008557999,0.000004748365,0.00004530159,0.0001486218,0.000001022276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001446702,"about_ca_system_score_gemma":0.0001002504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.349843e-7,"about_ca_topic_score_gemma":0.00001368935,"domain_scores_codex":[0.9993044,0.000034121,0.0002916984,0.0001518719,0.00008017718,0.0001377715],"domain_scores_gemma":[0.9989474,0.00006490486,0.0002720042,0.0001016209,0.0005574588,0.00005655797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00018353,0.00006768544,0.001047934,0.000003835122,0.000121918,0.000002125989,0.000006619555,0.00011462,0.9929253,0.0007807474,0.003968901,0.0007767702],"study_design_scores_gemma":[0.001639017,0.001897748,0.002118557,0.00001257844,0.00009965954,0.0007738978,0.00002122156,0.0002774287,0.7619781,0.01756212,0.2132681,0.0003514976],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941865,0.0001474907,0.004383767,0.0006204763,0.0004375333,0.00006472749,0.00002397841,0.00001240214,0.0001231932],"genre_scores_gemma":[0.9083548,0.00003032579,0.0902236,0.0004348521,0.0007362445,0.000001919775,0.00009965933,0.000009556492,0.0001090038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2309472,"threshold_uncertainty_score":0.3460873,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035522779","doi":"10.1089/cmb.2006.13.1289","title":"Wavelet Analysis of DNA Walks","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Computational biology; Wavelet; Intron; Biology; Genome; DNA sequencing; Genetics; genomic DNA; Sequence analysis; DNA; Computer science; Gene; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.005689296584836071,"gpt":0.2539969995628238,"spread":0.2483077029779877,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001830385,0.00007425145,0.000273972,0.0002708332,0.00002267806,0.000004882475,0.000131615,0.00008627494,0.00005003263],"category_scores_gemma":[0.00004311852,0.00005846216,0.0003292309,0.0003272337,0.00009359392,0.000003974363,0.00002507351,0.00005377824,0.00000200967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008917892,"about_ca_system_score_gemma":0.00007189573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003232269,"about_ca_topic_score_gemma":0.00001948289,"domain_scores_codex":[0.9991881,0.00005660109,0.0004499222,0.0001016393,0.0001082491,0.00009546117],"domain_scores_gemma":[0.999058,0.00004431457,0.000421477,0.00007755663,0.0003669478,0.00003168391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001995227,0.0002454163,0.05222008,0.000008778123,0.003110368,0.00001285791,0.00002005732,0.1465638,0.7870789,0.004044595,0.002110842,0.004384751],"study_design_scores_gemma":[0.002536882,0.002896501,0.6777787,0.0000267684,0.003734059,0.0002434132,0.0001292199,0.01569482,0.1883449,0.07317596,0.03469624,0.0007426604],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9781105,0.0004503667,0.02059312,0.0002423169,0.00005922657,0.00001635626,0.00002365861,0.00000123525,0.0005032073],"genre_scores_gemma":[0.9961001,0.00002721928,0.003227892,0.0001458085,0.00017317,3.959437e-7,0.0002512356,0.000003526103,0.00007060149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6255586,"threshold_uncertainty_score":0.2384018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2081163014","doi":"10.1089/cmb.2008.0003","title":"Linear Time Probabilistic Algorithms for the Singular Haplotype Reconstruction Problem from SNP Fragments","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Probabilistic logic; Haplotype; Algorithm; SNP; Probabilistic analysis of algorithms; Computer science; Computational biology; Mathematics; Biology; Genetics; Artificial intelligence; Single-nucleotide polymorphism; Gene; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.03132108430340452,"gpt":0.2924202296880671,"spread":0.2610991453846626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001602759,0.00008100803,0.0001204725,0.00004036207,0.0001257008,0.00000703284,0.0001408408,0.00009800568,0.00002848057],"category_scores_gemma":[0.00009764102,0.00005542101,0.00009328294,0.00005256787,0.0001088384,0.000005073371,0.0000171701,0.0000757337,0.000006468111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001954737,"about_ca_system_score_gemma":0.0001813315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003575903,"about_ca_topic_score_gemma":6.653576e-7,"domain_scores_codex":[0.9992954,0.00006449575,0.0003114202,0.0001444731,0.00009185495,0.00009232284],"domain_scores_gemma":[0.9990798,0.00009171203,0.0003131983,0.00009311303,0.0003828992,0.00003924604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001242527,0.0003302342,0.005300247,0.00002191782,0.0006887057,0.000004194905,0.0002245467,0.06907159,0.8038374,0.0006045661,0.02010194,0.09857217],"study_design_scores_gemma":[0.0116435,0.006442933,0.06311524,0.0002072591,0.0004096817,0.002210909,0.0002743555,0.1622232,0.1119835,0.1389725,0.5012627,0.00125415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6109942,0.001308609,0.3853019,0.001179966,0.0007351749,0.0003183347,0.00004224522,0.00000753368,0.0001120779],"genre_scores_gemma":[0.9132071,0.0001326649,0.08460007,0.0003521829,0.001195779,0.00002123388,0.0002274148,0.00001613112,0.0002474932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6918538,"threshold_uncertainty_score":0.2260003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2369729543","doi":"10.1089/cmb.2010.0092","title":"Yeast Ancestral Genome Reconstructions: The Possibilities of Computational Methods II","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Genome; Yeast; Biology; Computational biology; Evolutionary biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.0171202863078199,"gpt":0.3258122984228377,"spread":0.3086920121150178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006667657,0.0001028977,0.0001897214,0.00009531112,0.0001083276,0.00001111147,0.0002573186,0.0001031957,0.00008317684],"category_scores_gemma":[0.0001274834,0.00007420869,0.0001476469,0.00009451482,0.0004006017,0.00000811241,0.00007139796,0.0002050732,0.000002437064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009520005,"about_ca_system_score_gemma":0.0002464128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003482874,"about_ca_topic_score_gemma":0.000003123155,"domain_scores_codex":[0.9989531,0.0001607021,0.0005013099,0.0001322751,0.0001223109,0.0001303018],"domain_scores_gemma":[0.9987287,0.0001112273,0.0004602667,0.0001133717,0.0005375447,0.00004891071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001780364,0.0002006346,0.005301461,0.00002410574,0.0005609993,0.000001709815,0.00035593,0.05903865,0.897699,0.008680503,0.0004794748,0.02747952],"study_design_scores_gemma":[0.005239018,0.005342685,0.2899276,0.00004737085,0.0002290143,0.004209063,0.00148087,0.004848118,0.05094313,0.5505681,0.08618023,0.000984806],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9531656,0.0004526774,0.04483038,0.0005229912,0.0006832316,0.00008747362,0.00005838923,0.000002737759,0.0001965377],"genre_scores_gemma":[0.7790822,0.00002295665,0.220258,0.00007770301,0.0004180592,0.000002260345,0.0000725726,0.000006851925,0.00005936595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8467559,"threshold_uncertainty_score":0.3026143,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978273076","doi":"10.1089/cmb.2007.r003","title":"A Parameterized Algorithm for Protein Structure Alignment","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Parameterized complexity; Algorithm; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.006747070707571181,"gpt":0.2753649814743295,"spread":0.2686179107667583,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002928903,0.0001011826,0.0001667231,0.00006305714,0.00004082287,0.000008832722,0.0001347273,0.0001474631,0.000007048202],"category_scores_gemma":[0.00006639237,0.00007976041,0.0001177137,0.0000423228,0.00005855714,0.000002987051,0.0000286944,0.00007730468,3.581631e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001729665,"about_ca_system_score_gemma":0.00009782866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.965432e-7,"about_ca_topic_score_gemma":0.00000155091,"domain_scores_codex":[0.9992359,0.00003397775,0.0003562666,0.0001215575,0.00008955343,0.0001627215],"domain_scores_gemma":[0.9992663,0.00003506567,0.0002991473,0.00006930362,0.0002669813,0.00006321895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004881802,0.00004043767,0.0001640063,0.00001036805,0.0001926089,0.000006362788,0.00002048386,0.001276473,0.8872156,0.002142097,0.0003773892,0.108066],"study_design_scores_gemma":[0.008184443,0.007128899,0.003782833,0.00004419874,0.00009644309,0.001240088,0.00008090065,0.005918882,0.4709522,0.3926088,0.1092535,0.0007087991],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3770796,0.0001525411,0.6222828,0.00009219218,0.0001674235,0.0001562811,0.00004559866,0.000001750208,0.00002175889],"genre_scores_gemma":[0.6818668,0.000003257646,0.3173233,0.0002582372,0.0004021081,0.000002615221,0.0001108433,0.000007207928,0.00002561089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4162633,"threshold_uncertainty_score":0.3252535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2607286649","doi":"10.1089/cmb.2017.0021","title":"Zseq: An Approach for Preprocessing Next-Generation Sequencing Data","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preprocessor; Sequence (biology); DNA sequencing; Sequence assembly; Computer science; Computational biology; Genome; Biology; Discriminative model; Genomics; Algorithm; Genetics; Artificial intelligence; DNA; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.2161899380631361,"gpt":0.3635272799106088,"spread":0.1473373418474727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004377244,0.00007944232,0.000137161,0.00002795036,0.0002870215,0.00007501696,0.0004802916,0.00007342998,8.8893e-7],"category_scores_gemma":[0.0001959856,0.00006767909,0.00004531659,0.000009673025,0.00008153819,0.00000859781,0.0001396019,0.00004597666,1.697312e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001036375,"about_ca_system_score_gemma":0.0001856096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003475833,"about_ca_topic_score_gemma":0.000004005243,"domain_scores_codex":[0.9993445,0.00003705652,0.0002525205,0.0002073042,0.00005439104,0.0001042592],"domain_scores_gemma":[0.9989068,0.00001908113,0.0004362109,0.0003034096,0.000292918,0.00004161437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008736584,0.00005006231,0.004672243,0.0000162516,0.0001447029,6.125277e-7,0.0000777539,0.03011579,0.9482689,0.0004769875,0.0003114759,0.01577787],"study_design_scores_gemma":[0.006679763,0.004795254,0.06429416,0.00005131509,0.0003486506,0.0008508901,0.0008331009,0.7630144,0.08147056,0.04351434,0.03281662,0.001330929],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7640704,0.0007919825,0.2345251,0.000135485,0.0002265663,0.0000755108,0.00003631591,7.778366e-7,0.0001378055],"genre_scores_gemma":[0.8851529,0.00004642932,0.1132214,0.0000960544,0.001119181,0.000002479814,0.0003407367,0.000007438046,0.00001342632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8667983,"threshold_uncertainty_score":0.2759873,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065400176","doi":"10.1089/cmb.2007.a006","title":"Exact and Heuristic Algorithms for the Indel Maximum Likelihood Problem","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Indel; Algorithm; Heuristic; Tree (set theory); Markov chain; Viterbi algorithm; Hidden Markov model; Phylogenetic tree; Computer science; Mathematics; Biology; Artificial intelligence; Genetics; Combinatorics; Machine learning; Gene; Decoding methods","retraction":null,"screen_n_in":null,"score":{"opus":0.01390614159782581,"gpt":0.2793256302335371,"spread":0.2654194886357112,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005157561,0.00007857393,0.0001183964,0.00003578605,0.00008918912,0.000009642632,0.0001025531,0.00006525596,0.000001503116],"category_scores_gemma":[0.00005852903,0.00005137808,0.0000661829,0.00002927589,0.00009079563,5.936626e-7,0.0000467214,0.00006162398,3.936702e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005966167,"about_ca_system_score_gemma":0.00006415708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002172637,"about_ca_topic_score_gemma":0.00000425337,"domain_scores_codex":[0.999418,0.00002090644,0.0002675275,0.00009934858,0.00005177861,0.00014239],"domain_scores_gemma":[0.9992539,0.0002224471,0.0001846403,0.00004995495,0.0002455287,0.00004357348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001786273,0.0003796261,0.04599976,0.00009495461,0.002362551,0.00001602352,0.000630888,0.01201635,0.3309372,0.007023279,0.008136205,0.5906169],"study_design_scores_gemma":[0.005543706,0.006187238,0.3044051,0.00003083835,0.000249395,0.001235017,0.0004947062,0.002473034,0.01017689,0.4286989,0.2398908,0.0006143303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6030943,0.006846786,0.3883921,0.001013577,0.0003342694,0.0001776056,0.0000261515,9.579558e-7,0.0001143303],"genre_scores_gemma":[0.9714349,0.0002697338,0.02745093,0.0003324682,0.0004784903,0.000002749409,0.00001051669,0.000006966793,0.00001323264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5900025,"threshold_uncertainty_score":0.2095137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969595164","doi":"10.1089/cmb.2007.a005","title":"Common Intervals and Symmetric Difference in a Model-Free Phylogenomics, with an Application to Streptophyte Evolution","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Phylogenomics; Biology; Evolutionary biology; Botany; Phylogenetics; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.009398791714588465,"gpt":0.264439563613116,"spread":0.2550407718985275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003121427,0.0000800196,0.0001461986,0.0002362436,0.00001929966,0.000007542561,0.0001271982,0.00006756377,5.382695e-7],"category_scores_gemma":[0.00002521559,0.00006827416,0.00002516834,0.0001345756,0.00004007296,0.000004605668,0.00005521477,0.00007301179,5.672806e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004658232,"about_ca_system_score_gemma":0.00006004491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006828384,"about_ca_topic_score_gemma":0.00004528077,"domain_scores_codex":[0.9993535,0.00003346886,0.000270069,0.000146402,0.00007505384,0.0001215591],"domain_scores_gemma":[0.9994755,0.00002217418,0.0001570806,0.0001042458,0.0001595438,0.00008139753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001510869,0.0004222785,0.3321772,0.00003000792,0.00014648,0.000009286768,0.0001603907,0.1447694,0.4498997,0.003987265,0.00002574435,0.06686143],"study_design_scores_gemma":[0.00173319,0.003433606,0.936772,0.00002068072,0.00002216668,0.0001545529,0.00006392464,0.03313861,0.003573624,0.02080481,0.00009826529,0.0001845507],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.65316,0.0001891424,0.3464387,0.00007672085,0.00001763486,0.00008671315,0.000005355294,0.00000116197,0.00002452879],"genre_scores_gemma":[0.9661236,0.00001813008,0.03361306,0.0001126283,0.00008516489,0.000002533023,0.0000324392,0.000006405345,0.000006011462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6045948,"threshold_uncertainty_score":0.278414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3177371828","doi":"10.1089/cmb.2020.0543","title":"Essential Protein Prediction Based on node2vec and XGBoost","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Biological network; Identification (biology); Computational biology; Construct (python library); Boosting (machine learning); Artificial intelligence; Machine learning; Data mining; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01235493312477577,"gpt":0.2912001665630558,"spread":0.27884523343828,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005402212,0.0001078437,0.0002011452,0.0002088799,0.00008141115,0.00008082638,0.0002344058,0.00006403271,0.00001934295],"category_scores_gemma":[0.0002612087,0.0000966353,0.00008823202,0.0002638458,0.00006802866,0.0002461999,0.00009209306,0.0001955702,0.000005443684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000465887,"about_ca_system_score_gemma":0.0005533905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001044189,"about_ca_topic_score_gemma":4.607289e-7,"domain_scores_codex":[0.9984979,0.000419013,0.0004226963,0.0002226444,0.0003082367,0.0001294772],"domain_scores_gemma":[0.9981917,0.0007553207,0.0002868208,0.0001169752,0.0005642333,0.00008492787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009337953,0.000235742,0.0009299306,0.00001856125,0.00006110728,0.00009573602,0.00008551763,0.8181748,0.004693452,0.1524421,0.0003087679,0.02286082],"study_design_scores_gemma":[0.00103887,0.0004196605,0.02120776,0.0000527359,0.00000984106,0.0003772093,0.000007275517,0.808861,0.00274042,0.1639166,0.001250714,0.0001179628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1714332,0.0001067264,0.8242116,0.003435726,0.0004622116,0.00005954487,0.00001052166,0.00001600911,0.0002645013],"genre_scores_gemma":[0.7733492,0.000002486986,0.2258418,0.0005824572,0.0001854413,0.000002010708,0.00001483053,0.000004699842,0.00001701458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6019161,"threshold_uncertainty_score":0.3940673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4233853535","doi":"10.1089/106652700750050925","title":"Early Eukaryote Evolution Based on Mitochondrial Gene Order Breakpoints","year":2000,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Genome; Breakpoint; Phylogenetic tree; Eukaryote; Biology; Phylogenetics; Evolutionary biology; Gene; Genetics; Computational biology; Synteny; Phylogenetic network","retraction":null,"screen_n_in":null,"score":{"opus":0.005654480235721184,"gpt":0.236491253388888,"spread":0.2308367731531668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001546156,0.0001235753,0.0001617065,0.0001147837,0.00005260652,0.0000127634,0.0001663088,0.0001320325,0.000255832],"category_scores_gemma":[0.00004528992,0.0001079931,0.0001203316,0.0001082173,0.00006107796,0.000004965706,0.00001533659,0.0001155971,0.0000650955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003488493,"about_ca_system_score_gemma":0.0001730333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004714375,"about_ca_topic_score_gemma":8.753473e-7,"domain_scores_codex":[0.9990246,0.0001232649,0.0003379013,0.0001729112,0.000172835,0.000168486],"domain_scores_gemma":[0.9992909,0.00003498361,0.0001808228,0.0001101639,0.0003077088,0.00007544098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00364578,0.0007569966,0.009322753,0.00001439169,0.0005100394,0.00004388668,0.00006920593,0.5111493,0.4190677,0.0004779952,0.005876057,0.04906593],"study_design_scores_gemma":[0.03137746,0.02588877,0.6374041,0.0001470487,0.0003132022,0.001321289,0.00003832409,0.04969707,0.04000667,0.03890184,0.1727591,0.002145129],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415115,0.0001984127,0.05647129,0.0005600732,0.0004497578,0.0001058454,0.00002432064,0.0000051798,0.0006736736],"genre_scores_gemma":[0.9745153,0.00001975933,0.02370906,0.0004109011,0.0009946378,0.000002493255,0.0001251291,0.00001426373,0.0002085027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6280814,"threshold_uncertainty_score":0.4403831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054028885","doi":"10.1089/cmb.2006.0108","title":"Parsing Nucleic Acid Pseudoknotted Secondary Structure: Algorithm and Applications","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Algorithm; Parsing; Nucleic acid secondary structure; Pseudoknot; Protein secondary structure; Computer science; Generality; Dynamic programming; Nucleic acid structure; Energy (signal processing); Artificial intelligence; Mathematics; RNA; Biology; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.006073057763412786,"gpt":0.2527020174113226,"spread":0.2466289596479098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000313129,0.0000888608,0.0001365903,0.00008023525,0.00007711927,0.00001247138,0.0001062494,0.0001299751,0.00002963917],"category_scores_gemma":[0.00002762388,0.00007712255,0.00005377458,0.0000586287,0.00007813482,0.000005103054,0.00003316501,0.0001031145,0.000001674871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009247809,"about_ca_system_score_gemma":0.00007824065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.43876e-7,"about_ca_topic_score_gemma":9.36452e-7,"domain_scores_codex":[0.9993104,0.00005259017,0.0003051956,0.0001271148,0.00007495689,0.0001297463],"domain_scores_gemma":[0.9993984,0.00005375592,0.0002339646,0.00006778499,0.0001700038,0.00007615898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005495308,0.00001976719,0.0002494809,0.000005020033,0.00006450257,0.000003330961,0.00001581704,0.0001002348,0.7124978,0.001067874,0.0001140223,0.2858072],"study_design_scores_gemma":[0.001948843,0.001326143,0.01869836,0.00002833622,0.00007105102,0.002497192,0.0001342338,0.0003534733,0.7403225,0.1485099,0.08564648,0.0004635343],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3544403,0.001696198,0.6432995,0.0001713887,0.0001474644,0.00008872624,0.00002515423,0.000003554481,0.0001277555],"genre_scores_gemma":[0.9058195,0.00004679128,0.09316606,0.0003763142,0.0005198448,0.000001210342,0.0000495576,0.000009005613,0.00001167364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5513793,"threshold_uncertainty_score":0.3144966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973255639","doi":"10.1089/cmb.2012.0089","title":"Determining Protein Structures from NOESY Distance Constraints by Semidefinite Programming","year":2012,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Peroxisome Proliferator-Activated Receptors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Semidefinite programming; Mathematical optimization; Euclidean distance; Computer science; Algorithm; Euclidean geometry; Simulated annealing; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.00952262510956205,"gpt":0.2651261782244295,"spread":0.2556035531148675,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001974374,0.0001496066,0.0002093353,0.00005324111,0.00006424153,0.0000207986,0.000167278,0.0001727905,0.00004321265],"category_scores_gemma":[0.000163793,0.0001246931,0.00008683882,0.00006118671,0.0001953845,0.00001544128,0.00004713378,0.0001914137,0.0000036017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002560896,"about_ca_system_score_gemma":0.0001087201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000180484,"about_ca_topic_score_gemma":5.154899e-7,"domain_scores_codex":[0.998937,0.0001313542,0.0003990562,0.0001476912,0.0001261446,0.0002588267],"domain_scores_gemma":[0.9991232,0.00006290959,0.0004297332,0.00007681658,0.0001725463,0.0001348577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001184097,0.00007361324,0.0452836,0.00000659438,0.000179706,0.000002141981,0.00007738057,0.0002163922,0.9313174,0.0002738795,0.0005453528,0.0219055],"study_design_scores_gemma":[0.001900108,0.0008508323,0.007613617,0.00007186932,0.00004369608,0.0003114188,0.0001631439,0.0000955459,0.9105678,0.004984905,0.07286476,0.0005322895],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590855,0.001375905,0.03892154,0.00008657482,0.0003026739,0.00009613144,0.00007609636,0.000006159584,0.00004936859],"genre_scores_gemma":[0.9733735,0.00001340718,0.02567079,0.0001793474,0.0005227963,0.000005660438,0.0002093007,0.00001456137,0.00001063019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0723194,"threshold_uncertainty_score":0.5084839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1606551583","doi":"10.1089/cmb.2006.13.1355","title":"Optimizing Multiple Spaced Seeds for Homology Search","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Sensitivity (control systems); Greedy algorithm; Homology (biology); Algorithm; Set (abstract data type); Local search (optimization); Linear programming; Mathematical optimization; Computer science; Mathematics; Search algorithm; Biology; Engineering; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0242074479757779,"gpt":0.325914702964207,"spread":0.3017072549884292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004172585,0.00009253318,0.0002273235,0.0002349263,0.00008564658,0.00003247198,0.0004198639,0.00007686068,0.00000354826],"category_scores_gemma":[0.0001109787,0.00007732155,0.000121711,0.0001957449,0.00007652138,0.0002791674,0.00008202915,0.0001488556,0.000002928373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004469529,"about_ca_system_score_gemma":0.0001259484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006017357,"about_ca_topic_score_gemma":0.000001047577,"domain_scores_codex":[0.9990571,0.00007979202,0.0003892147,0.0001451669,0.0001184541,0.0002103318],"domain_scores_gemma":[0.9981361,0.0008624181,0.0002550301,0.00009395355,0.000606908,0.00004558653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004699041,0.0005096506,0.009162922,0.00005709617,0.0001924388,0.0001179627,0.0004254682,0.2473093,0.05814374,0.5295416,0.007920188,0.1461498],"study_design_scores_gemma":[0.002573815,0.002192372,0.007978787,0.0000325355,0.00001639356,0.0008862617,0.00002749364,0.1567843,0.04784093,0.7584323,0.0228862,0.0003485758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01461056,0.0003848345,0.983179,0.001334988,0.0002149948,0.0001081885,0.000004431883,0.00003839157,0.0001246201],"genre_scores_gemma":[0.4685757,0.000008267168,0.5310678,0.0001537266,0.0001545285,0.000001945722,0.000005752173,0.000004014826,0.00002822889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4539652,"threshold_uncertainty_score":0.3153082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999060916","doi":"10.1089/cmb.2007.0198","title":"Novel and Efficient RNA Secondary Structure Prediction Using Hierarchical Folding","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Pseudoknot; Nucleic acid secondary structure; Protein secondary structure; RNA; Nucleic acid structure; Computer science; Computational biology; Energy minimization; Algorithm; Base pair; Folding (DSP implementation); Bioinformatics; Theoretical computer science; Biology; Genetics; DNA; Physics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01579393709075526,"gpt":0.2522987994211601,"spread":0.2365048623304049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001458859,0.00008135477,0.0001331091,0.00007277091,0.0001049397,0.000007015462,0.00007118972,0.0001210303,0.00001512718],"category_scores_gemma":[0.00005622974,0.00006717277,0.00005714776,0.00003755634,0.00008979037,0.000003874004,0.00003783689,0.0001253707,2.390159e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001100337,"about_ca_system_score_gemma":0.0001409376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001417763,"about_ca_topic_score_gemma":2.336505e-7,"domain_scores_codex":[0.9993759,0.00005938835,0.0002535193,0.0001195018,0.00009066155,0.0001009998],"domain_scores_gemma":[0.9995508,0.00004041869,0.0001811564,0.00004579447,0.0001215778,0.00006023693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009153617,0.00002283997,0.0005871601,0.000004527525,0.00005091265,0.000004259197,0.00003762605,0.02013176,0.9760352,0.0003876633,0.00003805048,0.002608481],"study_design_scores_gemma":[0.005871013,0.003654061,0.06262321,0.0001167117,0.0001257849,0.02443299,0.0001153521,0.03780624,0.8265669,0.03029072,0.007650875,0.0007461011],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.82178,0.0005028569,0.1773183,0.00008818314,0.0002138874,0.00003999237,0.00002927922,0.000001851655,0.00002558788],"genre_scores_gemma":[0.9605942,0.00003224027,0.03884812,0.0001241231,0.0003684633,3.632969e-7,0.00002054299,0.000006692571,0.000005248446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1494682,"threshold_uncertainty_score":0.2739226,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1976245710","doi":"10.1089/cmb.2005.12.1083","title":"The Statistical Analysis of Spatially Clustered Genes under the Maximum Gap Criterion","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Alfred P. Sloan Foundation","keywords":"Pairwise comparison; Genome; Comparative genomics; Computational biology; Identification (biology); Genomics; Biology; Set (abstract data type); Statistical model; Cluster (spacecraft); Statistical analysis; Gene; Genetics; Computer science; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02096222089491316,"gpt":0.319773445089963,"spread":0.2988112241950499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003459573,0.00006725915,0.0001378917,0.00007684717,0.00009073144,0.00001589455,0.0002063517,0.00006489211,0.0000347148],"category_scores_gemma":[0.00005103058,0.0000365031,0.0001209457,0.0001335086,0.0001484895,0.000003218186,0.00003897088,0.00006888269,0.000001448658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001335314,"about_ca_system_score_gemma":0.0001224693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002914534,"about_ca_topic_score_gemma":0.00002705567,"domain_scores_codex":[0.9990785,0.0001966612,0.0004055528,0.00009552956,0.0001326671,0.0000910755],"domain_scores_gemma":[0.9990022,0.0001533447,0.0003611483,0.0001213219,0.0003274017,0.00003453622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001095263,0.0001760452,0.004447415,0.000008417168,0.001952686,0.000001089027,0.0001329229,0.3612638,0.4539171,0.01308654,0.006383328,0.1575354],"study_design_scores_gemma":[0.002926456,0.001945678,0.4788299,0.00002685486,0.001308268,0.0001509736,0.0007380675,0.06069857,0.04371827,0.0352324,0.3739228,0.0005017953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5492321,0.002001076,0.4424839,0.005768789,0.000264013,0.00007005336,0.00003041906,0.000001804908,0.0001478529],"genre_scores_gemma":[0.9958064,0.0002268436,0.003096083,0.0004988461,0.0002473527,0.000002109883,0.00006936116,0.000004167922,0.0000488435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4743824,"threshold_uncertainty_score":0.1488553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2943381976","doi":"10.1089/cmb.2018.0239","title":"Toward an Alignment-Free Method for Feature Extraction and Accurate Classification of Viral Sequences","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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":"Biology; Virus; Subsequence; Computational biology; Genetics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03237791519115444,"gpt":0.3414660170478026,"spread":0.3090881018566481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002651295,0.000065058,0.0001454023,0.00003927369,0.00002413796,0.000006590721,0.0001055651,0.00008405052,0.000002108742],"category_scores_gemma":[0.00004571467,0.00005246927,0.00005402097,0.0000202846,0.00004000555,0.000002943696,0.000027719,0.00003997389,1.867031e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006576535,"about_ca_system_score_gemma":0.00005733893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000274823,"about_ca_topic_score_gemma":0.000001745652,"domain_scores_codex":[0.9994879,0.00006560122,0.0002157295,0.0001126516,0.00005049898,0.00006757264],"domain_scores_gemma":[0.9992582,0.00007090579,0.000336288,0.00006951607,0.0002380435,0.0000270356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001858641,0.00002646106,0.004442015,0.00001345036,0.0001016013,1.510079e-7,0.00005847965,0.002774404,0.9853149,0.002388369,0.0001993107,0.004495007],"study_design_scores_gemma":[0.005425564,0.01033986,0.5206914,0.00003358839,0.0001912568,0.000434788,0.001001201,0.01318471,0.2337242,0.1899433,0.02449601,0.0005342096],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415073,0.0007327094,0.05673032,0.000618484,0.0002112435,0.0001021344,0.00005413385,5.112204e-7,0.00004318752],"genre_scores_gemma":[0.922117,0.00009484579,0.07749008,0.00008280027,0.0001410138,0.000002067208,0.00005134132,0.00000405798,0.00001681751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7515907,"threshold_uncertainty_score":0.2139635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2570688054","doi":"10.1089/cmb.2016.0148","title":"Clonality Inference from Single Tumor Samples Using Low-Coverage Sequence Data","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Deep sequencing; Tumor heterogeneity; Inference; DNA sequencing; Biology; Computational biology; Solid tumor; Sample (material); Sequence (biology); Single cell sequencing; Genetics; Cancer; Computer science; Artificial intelligence; Mutation; Exome sequencing; Genome; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1186770205578936,"gpt":0.3722387631576175,"spread":0.2535617425997239,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002248519,0.00009942661,0.000183933,0.00002728787,0.0001460064,0.00007895477,0.0007153351,0.00007085136,0.00002048979],"category_scores_gemma":[0.0009660353,0.00009167508,0.00005859903,0.00001545713,0.0001704045,0.00001676475,0.0003881209,0.0000972546,0.000001874016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002891566,"about_ca_system_score_gemma":0.0004095066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001753481,"about_ca_topic_score_gemma":0.00004534174,"domain_scores_codex":[0.9991859,0.00005154337,0.000331181,0.0002099879,0.00009465342,0.0001267949],"domain_scores_gemma":[0.998446,0.0001808432,0.0006322929,0.0004244308,0.000248129,0.00006824161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003579317,0.0002283018,0.1406822,0.00001643901,0.0002759003,0.00005270217,0.00003851081,0.03293004,0.811312,0.001251213,0.0009089651,0.01194586],"study_design_scores_gemma":[0.007093742,0.002208445,0.5076411,0.0003449359,0.0003262239,0.0008448052,0.00008184306,0.04602441,0.08925454,0.2461779,0.09825259,0.001749405],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9024057,0.0004719665,0.09556079,0.000216366,0.0004272382,0.0000347769,0.0008307224,0.000001344963,0.00005107956],"genre_scores_gemma":[0.9758993,0.0001013028,0.02232357,0.0004345331,0.0007472415,3.151617e-7,0.0004835847,0.000007239183,0.000002909825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7220574,"threshold_uncertainty_score":0.3738401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092120709","doi":"10.1089/cmb.2007.a007","title":"Duplication and Inversion History of a Tandemly Repeated Genes Family","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Phylogenetic tree; Biology; Gene duplication; Phylogenetics; Gene; Chromosomal inversion; Gene family; Genetics; Breakpoint; Chromosome; Segmental duplication; Inference; Maximum parsimony; Evolutionary biology; Genome; Karyotype; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01476863121669693,"gpt":0.2472926858771418,"spread":0.2325240546604449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002860979,0.00005535317,0.000118228,0.00006535868,0.00001694557,0.000001165735,0.0000580571,0.00006790327,0.000002307983],"category_scores_gemma":[0.00003563904,0.0000478291,0.00004470817,0.00002677198,0.0001019752,7.180456e-7,0.00003398748,0.00003542668,3.713945e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002309475,"about_ca_system_score_gemma":0.0000953296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005034768,"about_ca_topic_score_gemma":0.000001996472,"domain_scores_codex":[0.9994891,0.0000270638,0.0002835191,0.00008351985,0.00005063616,0.00006616233],"domain_scores_gemma":[0.9993188,0.00004092447,0.0002829295,0.00004681663,0.0002767213,0.00003383526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001467158,0.00002542441,0.01929357,0.000006237216,0.00007495969,0.000001013843,0.0000695008,0.0004873276,0.9703006,0.0003301536,0.0008762926,0.008388182],"study_design_scores_gemma":[0.002390778,0.002549906,0.7036268,0.00002551152,0.00008209974,0.0002396654,0.000259843,0.0005286967,0.05295944,0.009052107,0.2279884,0.0002966881],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9823915,0.008276839,0.008791814,0.00007060437,0.0001853865,0.00003350135,0.000003540909,5.404693e-7,0.0002462183],"genre_scores_gemma":[0.9944227,0.0005952457,0.004656383,0.0001620693,0.0001066121,2.883862e-7,0.00001229496,0.000003688819,0.00004070865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9173412,"threshold_uncertainty_score":0.1950414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}