{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":647,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":647,"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","author_layer_release":"2026-06-26"},"query_hash":"432751205d30","filters":{"venue":"BMC Bioinformatics"}},"results":[{"id":"W2136850043","doi":"10.1186/1471-2105-4-2","title":"An automated method for finding molecular complexes in large protein interaction networks","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6293,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Tree traversal; Cluster analysis; Protein Interaction Networks; Protein–protein interaction; Interaction network; Data mining; False positive paradox; Computational biology; Theoretical computer science; Algorithm; Artificial intelligence; Biology; Genetics","authors":[{"name":"Gary D. Bader","is_ca":true},{"name":"Christopher W.V. Hogue","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01704138690107336,"gpt":0.3135825610453267,"spread":0.2965411741442533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001050482,0.001919187,0.00101863,0.006494888,0.001551686,0.002266301,0.002293383,0.001503326,0.004975339],"category_scores_gemma":[0.006487999,0.0007598197,0.00128664,0.003499652,0.000834992,0.001900799,0.001691962,0.001262429,0.00247788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001514594,"about_ca_system_score_gemma":0.002233903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004420822,"about_ca_topic_score_gemma":0.005955643,"domain_scores_codex":[0.9983436,0.0002585274,0.00009439225,0.0004360038,0.0007879717,0.00007953751],"domain_scores_gemma":[0.9976225,0.001100762,0.000240015,0.0003175036,0.0006254859,0.00009374673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001985323,0.000165324,0.004114739,0.0005302659,0.0002294411,0.0004100268,0.0002642712,0.07854603,0.02660965,0.02761425,0.01774975,0.8435677],"study_design_scores_gemma":[0.0000641532,0.00004162094,0.001212066,0.00004109973,0.00005347069,0.0005785357,0.00007674003,0.9360606,0.01166092,0.02980494,0.02036384,0.00004201227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003390209,0.000163895,0.9921604,0.000086911,0.00002928253,0.0001438155,0.0003529775,0.003006275,0.0006662793],"genre_scores_gemma":[0.02403232,0.0001195532,0.9733098,0.00004343364,0.00002114662,0.0002410842,0.0009262831,0.000210204,0.001096257],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006494888,"threshold_uncertainty_score":0.01664418,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050345155","doi":"10.1186/1471-2105-12-35","title":"VennDiagram: a package for the generation of highly-customizable Venn and Euler diagrams in R","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":3262,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Venn diagram; Computer science; Visualization; Process (computing); Data mining; Engineering drawing; Theoretical computer science; Programming language; Mathematics","authors":[{"name":"Hanbo Chen","is_ca":true},{"name":"Paul C. Boutros","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07426646512308042,"gpt":0.2469729188522922,"spread":0.1727064537292118,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01122103,0.003464084,0.002904505,0.006970113,0.001434353,0.003416202,0.005243167,0.001344343,0.08476263],"category_scores_gemma":[0.04580577,0.00236365,0.003340425,0.004122194,0.00121245,0.003840954,0.004033357,0.005063618,0.02695123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008609319,"about_ca_system_score_gemma":0.003094797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001802806,"about_ca_topic_score_gemma":0.002376098,"domain_scores_codex":[0.9939023,0.002676071,0.0007728085,0.001257557,0.001142402,0.0002488069],"domain_scores_gemma":[0.9752855,0.01775907,0.001523814,0.002866133,0.002068957,0.0004965786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001138176,0.0001534464,0.004947765,0.008324218,0.001575737,0.001054428,0.001670644,0.0196947,0.01746877,0.03621138,0.6473024,0.2604584],"study_design_scores_gemma":[0.0007537932,0.000233704,0.005904801,0.001366485,0.0006237754,0.001842532,0.0002794941,0.1076371,0.03900562,0.1186189,0.7228094,0.0009244471],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001558522,0.000521216,0.7922303,0.0002676489,0.0004279497,0.0003712908,0.02351511,0.1787196,0.002388377],"genre_scores_gemma":[0.01425159,0.0004649534,0.8749583,0.0002959798,0.0001350203,0.002549579,0.02316324,0.08185899,0.002322382],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.08476263,"threshold_uncertainty_score":0.2835593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099753867","doi":"10.1186/1471-2105-12-491","title":"MAKER2: an annotation pipeline and genome-database management tool for second-generation genome projects","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2312,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Division of Integrative Organismal Systems; National Institute of General Medical Sciences; National Human Genome Research Institute; University of Utah; Agricultural Research Service; San Francisco State University; Michigan State University; College of Engineering, Michigan State University; U.S. Department of Agriculture; National Institutes of Health; National Science Foundation","keywords":"Annotation; Genome; Genome project; Gene Annotation; Computer science; DNA sequencing; Pipeline (software); Genome browser; Computational biology; Genomics; Database; Data mining; Biology; Gene; Genetics; Artificial intelligence","authors":[{"name":"Carson Holt","is_ca":true},{"name":"Mark Yandell","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04623520706017015,"gpt":0.2460322174434468,"spread":0.1997970103832766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009493947,0.005252019,0.00257325,0.007264455,0.003261194,0.006893245,0.008182982,0.003210953,0.02858165],"category_scores_gemma":[0.01963092,0.004022828,0.003421888,0.008139729,0.001165009,0.00572265,0.007175013,0.006050323,0.02254083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001860878,"about_ca_system_score_gemma":0.004140984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00176904,"about_ca_topic_score_gemma":0.001787698,"domain_scores_codex":[0.9952631,0.0007036352,0.0004977278,0.001448283,0.001729638,0.000357697],"domain_scores_gemma":[0.992574,0.002794777,0.001132449,0.001381677,0.001189764,0.0009272904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00307706,0.0003298643,0.004786778,0.003769115,0.0006788102,0.001574977,0.001446484,0.006630694,0.04446607,0.01229154,0.7771792,0.1437694],"study_design_scores_gemma":[0.001223398,0.0003216167,0.006387158,0.0004456725,0.0003929197,0.001425287,0.0004110525,0.049209,0.08549716,0.03102177,0.822902,0.0007630424],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.005469632,0.0007947944,0.4306002,0.001280804,0.0007997465,0.001102699,0.1048083,0.4494049,0.005738907],"genre_scores_gemma":[0.02731824,0.0008500857,0.6304623,0.001303529,0.0003326541,0.005132054,0.2519807,0.07469785,0.007922563],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.02858165,"threshold_uncertainty_score":0.09561515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132548846","doi":"10.1186/1471-2105-13-31","title":"PANDAseq: paired-end assembler for illumina sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":2221,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Amplicon; Computer science; Sequence (biology); Error detection and correction; k-mer; Amplicon sequencing; Sequence assembly; Computational biology; DNA sequencing; Biology; Genetics; Algorithm; DNA; 16S ribosomal RNA; Polymerase chain reaction; Gene","authors":[{"name":"Andre Masella","is_ca":true},{"name":"Andrea K. Bartram","is_ca":true},{"name":"Jakub Truszkowski","is_ca":true},{"name":"Daniel G. Brown","is_ca":true},{"name":"Josh D. Neufeld","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03929258653023519,"gpt":0.2637107171785696,"spread":0.2244181306483344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002247244,0.002989926,0.001653314,0.001627355,0.001542559,0.002216277,0.002871254,0.001073271,0.02465936],"category_scores_gemma":[0.003331048,0.001714269,0.001755492,0.001443101,0.0005490237,0.001093197,0.001923209,0.003002233,0.02538489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006892459,"about_ca_system_score_gemma":0.001164912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001210426,"about_ca_topic_score_gemma":0.002198391,"domain_scores_codex":[0.9980946,0.0004277926,0.0001924035,0.0006360273,0.0005045538,0.0001445809],"domain_scores_gemma":[0.9989331,0.0002184514,0.0001374361,0.0002656568,0.0003540107,0.00009127503],"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":[0.002826185,0.0002986467,0.00331902,0.004365745,0.001044066,0.0006557765,0.000609874,0.005994136,0.6363922,0.006072728,0.2039494,0.1344723],"study_design_scores_gemma":[0.0005004271,0.0009409166,0.006936243,0.0002537881,0.0004329438,0.001454803,0.0001201602,0.06717082,0.4222796,0.009365859,0.4901672,0.000377373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.02318856,0.001346413,0.7452071,0.0003185489,0.000528309,0.002001452,0.08074807,0.1309354,0.01572627],"genre_scores_gemma":[0.03325165,0.0006432718,0.7964174,0.0005432412,0.0000929447,0.003981707,0.1341715,0.01857856,0.01231974],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02465936,"threshold_uncertainty_score":0.08249378,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142056356","doi":"10.1186/1471-2105-3-2","title":"The Comparative RNA Web (CRW) Site: an online database of comparative sequence and structure information for ribosomal, intron, and other RNAs","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1643,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Dalhousie University","funders":"National Institute of General Medical Sciences; University of Texas at Austin; Welch Foundation; National Institutes of Health; National Science Foundation","keywords":"Intron; RNA; Biology; Phylogenetic tree; Nucleic acid structure; Computational biology; Ribosomal RNA; Genetics; Nucleic acid secondary structure; Sequence (biology); Database; Gene; Computer science","authors":[{"name":"Jamie J. Cannone","is_ca":false},{"name":"Sankar Subramanian","is_ca":false},{"name":"Murray N. Schnare","is_ca":true},{"name":"James R. Collett","is_ca":false},{"name":"Lisa M. D'Souza","is_ca":false},{"name":"Yushi Du","is_ca":false},{"name":"Brian Feng","is_ca":false},{"name":"Nan Lin","is_ca":false},{"name":"Lakshmi V Madabusi","is_ca":false},{"name":"Kirsten M. Müller","is_ca":true},{"name":"Nupur T. Pande","is_ca":false},{"name":"Zhidi Shang","is_ca":false},{"name":"Nan Yu","is_ca":false},{"name":"Robin R. Gutell","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06946269515937568,"gpt":0.2973266295758393,"spread":0.2278639344164636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00195745,0.001522367,0.001431883,0.006130077,0.001122229,0.002185442,0.002385321,0.001418113,0.07778636],"category_scores_gemma":[0.004268449,0.0007198783,0.0005131923,0.008343894,0.0005447284,0.002264224,0.001523338,0.001684478,0.04503168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008319225,"about_ca_system_score_gemma":0.002370536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001988228,"about_ca_topic_score_gemma":0.001931303,"domain_scores_codex":[0.998937,0.0002218131,0.0001219454,0.0002464753,0.0003741659,0.00009860557],"domain_scores_gemma":[0.9980891,0.0006261659,0.0003391258,0.0003041952,0.0002684687,0.0003730171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008338353,0.0002654805,0.002934099,0.003890899,0.0001861064,0.0005270135,0.0004061414,0.001107409,0.07102668,0.01996142,0.6361937,0.2626673],"study_design_scores_gemma":[0.0001826221,0.0002018605,0.00845998,0.0006111402,0.0001485923,0.0005979207,0.0001476117,0.002585536,0.02125021,0.01024192,0.9554652,0.0001075398],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.01535593,0.009564512,0.1106064,0.00173367,0.001119763,0.0007571627,0.7261166,0.06129524,0.07345076],"genre_scores_gemma":[0.02266951,0.004830377,0.1549748,0.0008532666,0.0004816907,0.001216206,0.7867006,0.006782338,0.02149129],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.07778636,"threshold_uncertainty_score":0.2602213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903125175","doi":"10.1186/s12859-018-2485-7","title":"Purge Haplotigs: allelic contig reassignment for third-gen diploid genome assemblies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1285,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Wine Australia; Australian Government; Alberta Water Research Institute; Bioplatforms Australia","keywords":"Contig; Genome; Ploidy; Biology; Haplotype; Genetics; Sequence assembly; Purge; Computational biology; Allele; Gene; Transcriptome","authors":[{"name":"Michael J. Roach","is_ca":false},{"name":"Simon A. Schmidt","is_ca":false},{"name":"Anthony R. Borneman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02474087615458948,"gpt":0.2563884776234654,"spread":0.2316476014688759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003932375,0.002122416,0.001402985,0.002128466,0.001480866,0.002335866,0.00193932,0.001181508,0.01071021],"category_scores_gemma":[0.006816694,0.001974668,0.002094789,0.001391844,0.0007924602,0.001550886,0.003081233,0.002860344,0.006654101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017942,"about_ca_system_score_gemma":0.001580959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00263769,"about_ca_topic_score_gemma":0.004696571,"domain_scores_codex":[0.9982916,0.0002599627,0.0001674025,0.0006704593,0.0004734338,0.0001371385],"domain_scores_gemma":[0.9971122,0.001101715,0.0004324789,0.0007414519,0.0004223151,0.0001899309],"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":[0.003218203,0.0003147244,0.01878117,0.00411464,0.0009795267,0.002133916,0.003377171,0.0242225,0.4352126,0.008585918,0.08436553,0.4146941],"study_design_scores_gemma":[0.0005040031,0.0006452704,0.02011411,0.0004288079,0.0004266484,0.002463349,0.0004991647,0.1355445,0.5295796,0.008767663,0.3005149,0.0005119283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06524167,0.001310703,0.7492672,0.0003213305,0.0004848719,0.0009372025,0.01435561,0.163041,0.005040406],"genre_scores_gemma":[0.09269521,0.0004998283,0.8423929,0.0003395935,0.00006524081,0.0008923107,0.04014789,0.01859182,0.004375278],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01071021,"threshold_uncertainty_score":0.03582925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594844287","doi":"10.1186/s12859-017-1559-2","title":"Reactome pathway analysis: a high-performance in-memory approach","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":927,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; European Bioinformatics Institute","keywords":"Computer science; DNA microarray; Computational biology; Biology; Genetics; Gene; Gene expression","authors":[{"name":"Antonio Fabregat","is_ca":false},{"name":"Konstantinos Sidiropoulos","is_ca":false},{"name":"Guilherme Viteri","is_ca":false},{"name":"Oscar Forner","is_ca":false},{"name":"Pablo Marín-García","is_ca":false},{"name":"Vicente Arnau","is_ca":false},{"name":"Peter D’Eustachio","is_ca":false},{"name":"Lincoln Stein","is_ca":true},{"name":"Henning Hermjakob","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01424369254937085,"gpt":0.2266288534852671,"spread":0.2123851609358962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002441495,0.003392981,0.001229356,0.003526809,0.000880386,0.00467971,0.004673027,0.001459937,0.01544874],"category_scores_gemma":[0.005297315,0.001390484,0.002966816,0.003112856,0.0007066746,0.004000768,0.003546591,0.002158851,0.008006428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00110936,"about_ca_system_score_gemma":0.001666052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002631674,"about_ca_topic_score_gemma":0.002403557,"domain_scores_codex":[0.9981384,0.0003760757,0.0001695764,0.0005006258,0.0006378749,0.0001774221],"domain_scores_gemma":[0.9980156,0.0007133873,0.0001431347,0.0006107968,0.000383197,0.0001338849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004515299,0.0007565035,0.008668948,0.003077587,0.00167341,0.001455285,0.001217246,0.1302629,0.09469573,0.09193262,0.06632474,0.5954196],"study_design_scores_gemma":[0.0003063541,0.0002281392,0.001518178,0.0001461536,0.0002946541,0.0005968427,0.0002004973,0.7462888,0.0720367,0.1005294,0.07765988,0.0001945278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005891032,0.0003643595,0.9278795,0.0002628238,0.00009639111,0.000144626,0.002484547,0.06067876,0.002197953],"genre_scores_gemma":[0.08499535,0.0008286462,0.8909723,0.0002678626,0.000101648,0.0008040512,0.01123172,0.005797583,0.005000864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01544874,"threshold_uncertainty_score":0.05168122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111607030","doi":"10.1186/1471-2105-10-202","title":"NLStradamus: a simple Hidden Markov Model for nuclear localization signal prediction","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":719,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Nuclear localization sequence; NLS; Hidden Markov model; Nuclear transport; Markov chain; Computational biology; Simple (philosophy); Computer science; Set (abstract data type); Markov model; Artificial intelligence; Biology; Machine learning; Genetics; Cell nucleus; Gene","authors":[{"name":"Alex N. Nguyen Ba","is_ca":true},{"name":"Anastassia K. Pogoutse","is_ca":true},{"name":"Nicholas J. Provart","is_ca":true},{"name":"Alan M Moses","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01034064885787714,"gpt":0.2196102180540038,"spread":0.2092695691961267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001240187,0.000740307,0.0008809349,0.0006782584,0.0005835521,0.0007821274,0.001763267,0.001310154,0.005223549],"category_scores_gemma":[0.003728669,0.000732502,0.001100273,0.0005958867,0.000362531,0.0008259699,0.0007842989,0.001530237,0.001650235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043235,"about_ca_system_score_gemma":0.001527908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01612737,"about_ca_topic_score_gemma":0.01863304,"domain_scores_codex":[0.9996421,0.0001653714,0.00002387939,0.00007355343,0.00006387819,0.00003122195],"domain_scores_gemma":[0.9986162,0.001122159,0.000057073,0.00005366751,0.00009166298,0.00005920668],"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":[0.000634713,0.0001177494,0.002507367,0.0002139954,0.0001800301,0.0001915671,0.00007826459,0.8941348,0.001853811,0.005627616,0.008078866,0.0863813],"study_design_scores_gemma":[0.00001733452,0.000008084204,0.00006196935,0.000003530387,0.000005259508,0.000008905992,0.000001918015,0.9976271,0.000214687,0.001690387,0.0003568146,0.00000392372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0322669,0.0006957483,0.9469694,0.0006440379,0.0001307801,0.0001521325,0.003048458,0.01487517,0.001217404],"genre_scores_gemma":[0.4192776,0.0006554696,0.5655959,0.0004897231,0.0001305849,0.0008295349,0.008260283,0.0009035837,0.003857311],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01612737,"threshold_uncertainty_score":0.032067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070040136","doi":"10.1186/1471-2105-12-436","title":"clusterMaker: a multi-algorithm clustering plugin for Cytoscape","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":669,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Cluster analysis; Computer science; Interactome; Plug-in; Hierarchical clustering; Computational biology; Visualization; Dendrogram; Data mining; Bioinformatics; Biology; Machine learning; Genetics","authors":[{"name":"John H. Morris","is_ca":false},{"name":"Leonard Apeltsin","is_ca":false},{"name":"Aaron M. Newman","is_ca":false},{"name":"Jan Baumbach","is_ca":false},{"name":"Tobias Wittkop","is_ca":false},{"name":"Gang Su","is_ca":false},{"name":"Gary D. Bader","is_ca":true},{"name":"Thomas E. Ferrin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03728483425002162,"gpt":0.2498073105875191,"spread":0.2125224763374975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002792338,0.0032162,0.001890031,0.004773441,0.001943694,0.002668996,0.007116656,0.002878002,0.06687146],"category_scores_gemma":[0.009217148,0.002318028,0.002175089,0.002658704,0.0007771382,0.003368896,0.003261485,0.005041406,0.02877718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001301908,"about_ca_system_score_gemma":0.00474129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007032656,"about_ca_topic_score_gemma":0.01030028,"domain_scores_codex":[0.9981692,0.0003166468,0.0001351283,0.00046368,0.0007585263,0.0001567127],"domain_scores_gemma":[0.9963129,0.002113836,0.0002207185,0.0004658231,0.0005908947,0.0002959235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001020228,0.0002512282,0.001717493,0.004435379,0.000994061,0.0006283902,0.000752757,0.01546015,0.01789149,0.01473614,0.7748127,0.1673],"study_design_scores_gemma":[0.0008561639,0.0001653116,0.003379519,0.0006956886,0.0002768142,0.0007202434,0.0001905834,0.1832321,0.05756226,0.07015693,0.6819919,0.0007724399],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002357919,0.0006602238,0.3182177,0.0005041914,0.0005105864,0.0005648569,0.03313565,0.6389078,0.00514101],"genre_scores_gemma":[0.03342263,0.001151766,0.7388601,0.001540603,0.0003013397,0.006376929,0.0588536,0.14718,0.01231309],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.06687146,"threshold_uncertainty_score":0.2237073,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150756255","doi":"10.1186/1471-2105-10-106","title":"flowCore: a Bioconductor package for high throughput flow cytometry","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":651,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Terry Fox Research Institute; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Data mining; Data management; Throughput; Automation; Data science; Data flow diagram; Software engineering; Database; Operating system; Engineering","authors":[{"name":"Florian Hahne","is_ca":false},{"name":"Nolwenn Le Meur","is_ca":false},{"name":"Ryan R. Brinkman","is_ca":true},{"name":"Byron Ellis","is_ca":false},{"name":"Perry Haaland","is_ca":false},{"name":"Deepayan Sarkar","is_ca":false},{"name":"Josef Špidlen","is_ca":true},{"name":"Errol Strain","is_ca":false},{"name":"Robert Gentleman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02186983869540404,"gpt":0.2510222181838827,"spread":0.2291523794884787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009944251,0.005066703,0.00469338,0.007108669,0.002088674,0.004143065,0.01181554,0.00324562,0.1129948],"category_scores_gemma":[0.02595481,0.003597338,0.004079209,0.006836625,0.001711126,0.004164215,0.00486376,0.007187481,0.09547021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001915733,"about_ca_system_score_gemma":0.008328781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005573346,"about_ca_topic_score_gemma":0.004751917,"domain_scores_codex":[0.9950896,0.001166452,0.0007637521,0.001119183,0.001368463,0.0004926536],"domain_scores_gemma":[0.9879708,0.005770591,0.001129517,0.001763621,0.00271995,0.0006456875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001470839,0.0002124852,0.002210775,0.005021544,0.001010836,0.0004782933,0.0005183999,0.00591849,0.007778729,0.02579062,0.8569188,0.09267022],"study_design_scores_gemma":[0.00166365,0.0002348678,0.00637974,0.001094172,0.0007707739,0.0009370553,0.0001361168,0.1075584,0.02407325,0.1065874,0.7500752,0.000489366],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001950392,0.001073497,0.4836633,0.001023771,0.001047541,0.001071147,0.09247484,0.4096153,0.008080252],"genre_scores_gemma":[0.01922664,0.001491583,0.7120162,0.002140105,0.000467953,0.01282523,0.108418,0.1290256,0.01438874],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1129948,"threshold_uncertainty_score":0.3780052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109327803","doi":"10.1186/1471-2105-3-35","title":"FunSpec: a web-based cluster interpreter for yeast","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":409,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Genome Canada","keywords":"Cluster analysis; Categorical variable; Interpreter; Gene; Computational biology; Computer science; Exposition (narrative); Interpretation (philosophy); DNA microarray; Biology; Genetics; Artificial intelligence; Gene expression; Machine learning","authors":[{"name":"Mark D. Robinson","is_ca":true},{"name":"Jörg Grigull","is_ca":true},{"name":"Naveed Mohammad","is_ca":true},{"name":"Timothy R. Hughes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01484499009857399,"gpt":0.2245644029157306,"spread":0.2097194128171566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001687805,0.001490701,0.0007903557,0.001954256,0.0009148137,0.001895417,0.002708918,0.0009362382,0.02395264],"category_scores_gemma":[0.004196754,0.001008717,0.001660164,0.001385935,0.0007326758,0.002278112,0.002107112,0.001322483,0.007646844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038847,"about_ca_system_score_gemma":0.001301039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003400894,"about_ca_topic_score_gemma":0.004218918,"domain_scores_codex":[0.999579,0.00005914982,0.00007600777,0.0001145005,0.0001286659,0.00004262283],"domain_scores_gemma":[0.9984725,0.0008035605,0.0001228368,0.0002354281,0.0002722396,0.00009339407],"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":[0.0048672,0.0003375323,0.01481949,0.004179082,0.0006267335,0.003023078,0.004022485,0.04932901,0.04486599,0.07786445,0.3469102,0.4491547],"study_design_scores_gemma":[0.000772538,0.0002143741,0.005669589,0.0006369581,0.000187549,0.001751748,0.0008207915,0.342535,0.08274246,0.1201557,0.4440616,0.0004516875],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0105017,0.0002734228,0.5753296,0.0001881445,0.0001152535,0.000207785,0.01788979,0.3901116,0.005382687],"genre_scores_gemma":[0.1257601,0.0006443444,0.7186713,0.0004885258,0.00009129226,0.001422611,0.04706454,0.09593019,0.00992703],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02395264,"threshold_uncertainty_score":0.08012956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139259976","doi":"10.1186/1471-2105-4-11","title":"PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":340,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; National Research Council Canada; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Directorate for Biological Sciences; Genome Canada","keywords":"Computer science; Support vector machine; Set (abstract data type); Task (project management); Interaction information; Precision and recall; Recall; Data curation; Interaction network; Artificial intelligence; Protein–protein interaction; Data mining; Machine learning; Database; Information retrieval; Biology","authors":[{"name":"Ian Donaldson","is_ca":true},{"name":"Joel Martin","is_ca":true},{"name":"Berry de Bruijn","is_ca":true},{"name":"Cheryl Wolting","is_ca":true},{"name":"Vicki Lay","is_ca":true},{"name":"Brigitte Tuekam","is_ca":true},{"name":"Shudong Zhang","is_ca":false},{"name":"Berivan Baskin","is_ca":true},{"name":"Gary D. Bader","is_ca":true},{"name":"Katerina Michalickova","is_ca":true},{"name":"Tony Pawson","is_ca":true},{"name":"Christopher W.V. Hogue","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02721208388926301,"gpt":0.2967162964898785,"spread":0.2695042126006155,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003664037,0.001115911,0.001130792,0.01690686,0.0006997165,0.002174788,0.00132593,0.000947494,0.008280493],"category_scores_gemma":[0.01239189,0.0003690659,0.001302856,0.007089309,0.0005402458,0.00217465,0.00143533,0.0008191144,0.004607525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008082588,"about_ca_system_score_gemma":0.003111933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002209707,"about_ca_topic_score_gemma":0.003747143,"domain_scores_codex":[0.9978281,0.0004170439,0.0005289041,0.0005328124,0.0005994194,0.00009379743],"domain_scores_gemma":[0.9913651,0.004296163,0.001220894,0.0006881528,0.002145953,0.0002838159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000945551,0.0003989681,0.02033173,0.00663502,0.0004595455,0.001075073,0.0006788184,0.005066533,0.03736115,0.002692855,0.0528539,0.871501],"study_design_scores_gemma":[0.000700597,0.002955172,0.09226254,0.002301746,0.001320389,0.007551084,0.002627303,0.317281,0.1706269,0.03345927,0.3684707,0.000443324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3048123,0.03055897,0.4491294,0.006488458,0.001080134,0.004479551,0.1394828,0.04922898,0.01473933],"genre_scores_gemma":[0.2728015,0.005532228,0.6024123,0.0007535659,0.0003976708,0.002010341,0.1073434,0.0005317177,0.00821724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01690686,"threshold_uncertainty_score":0.02770096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338215681","doi":"10.1186/s12859-016-1015-8","title":"BAGEL: a computational framework for identifying essential genes from pooled library screens","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":325,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Computational biology; DNA microarray; Gene; Computer science; Biology; Genetics; Bioinformatics; Gene expression","authors":[{"name":"Traver Hart","is_ca":false},{"name":"Jason Moffat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01657515414873308,"gpt":0.3018650987314888,"spread":0.2852899445827558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004141299,0.001946173,0.00186536,0.002525985,0.0007146152,0.00203475,0.003155348,0.001723625,0.007349461],"category_scores_gemma":[0.008983421,0.0009737205,0.002691912,0.001182465,0.0008631106,0.001536903,0.002099501,0.002891517,0.00235339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009588823,"about_ca_system_score_gemma":0.002143419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003623489,"about_ca_topic_score_gemma":0.009332381,"domain_scores_codex":[0.9988204,0.0005327587,0.00006330882,0.0002244197,0.000290223,0.00006887204],"domain_scores_gemma":[0.9950524,0.003945145,0.0002310128,0.0002801901,0.0003291409,0.0001620143],"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":[0.001089478,0.0003933844,0.005741546,0.001436434,0.001305906,0.0004318825,0.0001802725,0.7176157,0.009972141,0.03642218,0.02207171,0.2033393],"study_design_scores_gemma":[0.00005603109,0.00003813151,0.0002118665,0.00002424094,0.00004463606,0.00004165994,0.00001141332,0.9728118,0.001022378,0.02315763,0.002560021,0.00002005161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003234195,0.0001857235,0.981128,0.0001439393,0.00003224235,0.00007001687,0.00124813,0.01359992,0.0003579352],"genre_scores_gemma":[0.05326704,0.000310236,0.937247,0.0004277947,0.00006809212,0.0007774678,0.004627097,0.00225399,0.001021256],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007349461,"threshold_uncertainty_score":0.02458638,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125456570","doi":"10.1186/1471-2105-11-461","title":"Pan-genome sequence analysis using Panseq: an online tool for the rapid analysis of core and accessory genomic regions","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Escherichia coli research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":306,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge; Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada; Canadian Food Inspection Agency","keywords":"Genome; Biology; Genetics; Multilocus sequence typing; Locus (genetics); Population; Phylogenetic tree; Bacterial genome size; Reference genome; Whole genome sequencing; Computational biology; Gene; Genotype","authors":[{"name":"Chad Laing","is_ca":true},{"name":"Cody Buchanan","is_ca":true},{"name":"Eduardo N. Taboada","is_ca":true},{"name":"Yongxiang Zhang","is_ca":true},{"name":"Andrew M. Kropinski","is_ca":true},{"name":"André Villegas","is_ca":true},{"name":"James E. Thomas","is_ca":true},{"name":"Victor P. J. Gannon","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1134047475220261,"gpt":0.3565360867214132,"spread":0.2431313391993871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003016212,0.002313561,0.001650714,0.003313971,0.0007896436,0.001298799,0.001383155,0.0008730387,0.01537657],"category_scores_gemma":[0.003410103,0.001038079,0.00131068,0.0018127,0.0004325715,0.001604833,0.001389574,0.001842887,0.006255821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003838028,"about_ca_system_score_gemma":0.001036886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005950127,"about_ca_topic_score_gemma":0.001141262,"domain_scores_codex":[0.9987282,0.0003378737,0.000135575,0.0003654467,0.0003416032,0.00009132091],"domain_scores_gemma":[0.9982974,0.0006277573,0.0004092936,0.0002092218,0.0003023279,0.0001541007],"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":[0.004766714,0.0007135103,0.02379265,0.004684595,0.001393908,0.001739135,0.001556805,0.004438937,0.4730847,0.005074349,0.1399507,0.338804],"study_design_scores_gemma":[0.00136304,0.001817767,0.06949263,0.00087246,0.0008113653,0.003437075,0.0006531489,0.172116,0.3928668,0.01072537,0.34499,0.0008542142],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05578463,0.002149008,0.7127163,0.0004849054,0.0004538877,0.001136622,0.07007096,0.1514194,0.005784246],"genre_scores_gemma":[0.04882456,0.0008161161,0.8761697,0.0004369767,0.0001082443,0.001998707,0.05791342,0.01000412,0.003728077],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01537657,"threshold_uncertainty_score":0.05143976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162224067","doi":"10.1186/1471-2105-9-340","title":"RNA STRAND: The RNA Secondary Structure and Statistical Analysis Database","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":287,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"RNA; Nucleic acid secondary structure; Database; Protein secondary structure; Computer science; Nucleic acid structure; Computational biology; Biology; Genetics; Gene","authors":[{"name":"Mirela Andronescu","is_ca":true},{"name":"Vera Bereg","is_ca":true},{"name":"Holger H. Hoos","is_ca":true},{"name":"Anne Condon","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01374187862728997,"gpt":0.2343050137810196,"spread":0.2205631351537296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002992968,0.002134748,0.002509757,0.004597024,0.001046442,0.003197867,0.003571743,0.001824766,0.04641],"category_scores_gemma":[0.008541309,0.0009622249,0.001222568,0.005842542,0.0005717433,0.002065452,0.002385147,0.001982827,0.06596905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007376946,"about_ca_system_score_gemma":0.003763156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001580123,"about_ca_topic_score_gemma":0.001663526,"domain_scores_codex":[0.9977343,0.0004323342,0.0004502629,0.0005137619,0.0007225157,0.0001467675],"domain_scores_gemma":[0.9951177,0.001789379,0.0007300755,0.0008589168,0.001064774,0.0004391879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001429726,0.0001458613,0.003958255,0.008195748,0.0003556358,0.0006904356,0.0003673479,0.003905156,0.04050913,0.01696966,0.7614022,0.1620708],"study_design_scores_gemma":[0.0002513773,0.0001302512,0.003708395,0.0005412009,0.0001727297,0.0006729636,0.00007774496,0.003593369,0.01169325,0.01432699,0.9647086,0.0001232783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.003475828,0.005232446,0.09605861,0.0006894775,0.0003975295,0.0005545344,0.8195636,0.05750949,0.01651849],"genre_scores_gemma":[0.008659736,0.001938551,0.09143086,0.0005659505,0.000180107,0.001097389,0.8841836,0.007398628,0.004545168],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04641,"threshold_uncertainty_score":0.1552569,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129978006","doi":"10.1186/1471-2105-9-329","title":"Evaluation of genomic island predictors using a comparative genomics approach","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":284,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Genome Canada; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Genome; Identification (biology); Comparative genomics; Genomics; Computational biology; Precision and recall; Computer science; Sequence (biology); Data mining; Biology; Genetics; Artificial intelligence; Gene; Ecology","authors":[{"name":"Morgan G. I. Langille","is_ca":true},{"name":"William Hsiao","is_ca":true},{"name":"Fiona S. L. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1005527452698731,"gpt":0.2917008819532804,"spread":0.1911481366834074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004061918,0.001647651,0.001285349,0.008217617,0.0008646502,0.001370175,0.001652753,0.00123739,0.001370705],"category_scores_gemma":[0.008389838,0.0002884758,0.001549123,0.004666429,0.0006320661,0.001141125,0.001106536,0.0009564342,0.0007149166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499909,"about_ca_system_score_gemma":0.001364026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008481373,"about_ca_topic_score_gemma":0.008542989,"domain_scores_codex":[0.9970708,0.0006620733,0.000237309,0.001094773,0.0007389534,0.0001959789],"domain_scores_gemma":[0.9932696,0.00420435,0.0004086827,0.0004237937,0.001431328,0.0002621278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003917016,0.001381098,0.2529938,0.003007123,0.002968899,0.0009948784,0.0005008436,0.2418046,0.1171924,0.00299275,0.01265522,0.3595913],"study_design_scores_gemma":[0.0001092355,0.00121841,0.06775353,0.0001037016,0.0003992261,0.0007512395,0.0004301939,0.8779494,0.04390789,0.002129226,0.00516249,0.0000853983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8952181,0.002816512,0.07617,0.0002653895,0.00009512185,0.0003539,0.01676781,0.005530246,0.002783019],"genre_scores_gemma":[0.8021508,0.0004432451,0.1491155,0.0001333867,0.00005729689,0.0003201273,0.04691589,0.0002730598,0.0005906391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008481373,"threshold_uncertainty_score":0.02148175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080569293","doi":"10.1186/1471-2105-10-442","title":"G+C content dominates intrinsic nucleosome occupancy","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Genome Canada; Ontario Genomics; Ontario Genomics Institute; Canadian Institute for Advanced Research; Howard Hughes Medical Institute","keywords":"Nucleosome; Chromatin; Linker DNA; Biology; DNA; Genome; Genetics; Histone; DNA sequencing; GC-content; Computational biology; DNA microarray; Sequence (biology); Biophysics; Biological system; Gene","authors":[{"name":"Desiree Tillo","is_ca":true},{"name":"Timothy R. Hughes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01536453061776141,"gpt":0.225525571516338,"spread":0.2101610408985766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004121366,0.0005599673,0.0006499701,0.0003622657,0.0003134063,0.0005760204,0.0004866947,0.0005784803,0.001573361],"category_scores_gemma":[0.001755878,0.0002994821,0.00055121,0.0004722997,0.0003724255,0.0004675366,0.0002999316,0.000328176,0.0005106073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007631773,"about_ca_system_score_gemma":0.0005893096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007061298,"about_ca_topic_score_gemma":0.007089188,"domain_scores_codex":[0.9997033,0.00004639515,0.00001300222,0.0001423652,0.00005555978,0.00003934949],"domain_scores_gemma":[0.9991539,0.0004190983,0.0001881275,0.00008586883,0.00008283306,0.0000703753],"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":[0.001120612,0.0001068775,0.2729589,0.001378976,0.0005699426,0.0005848785,0.0002189071,0.2689188,0.4052002,0.00651293,0.002324195,0.0401048],"study_design_scores_gemma":[0.00005804139,0.0002431928,0.1405708,0.00005633795,0.0003838663,0.0007511957,0.00008693879,0.7782287,0.06348582,0.01286197,0.003187521,0.00008564597],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.950204,0.0008694571,0.04468101,0.0001475361,0.00002968322,0.00002250299,0.001101337,0.0008256837,0.002118718],"genre_scores_gemma":[0.9943586,0.0002037203,0.004322486,0.00006040396,0.00001058178,0.000009816248,0.0007050136,0.00007505711,0.0002543992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007061298,"threshold_uncertainty_score":0.01404041,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144847592","doi":"10.1186/1471-2105-15-35","title":"Inferring clonal evolution of tumors from single nucleotide somatic mutations","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sinai Health System; University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genetics; Biology; Somatic cell; DNA microarray; Somatic evolution in cancer; Computational biology; Mutation; Nucleotide; Gene; Gene expression","authors":[{"name":"Wei Jiao","is_ca":true},{"name":"Shankar Vembu","is_ca":true},{"name":"Amit G. Deshwar","is_ca":true},{"name":"Lincoln Stein","is_ca":true},{"name":"Quaid Morris","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01003790526440334,"gpt":0.2169162751917296,"spread":0.2068783699273262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001077079,0.0002585008,0.0003186101,0.001416756,0.0003017888,0.0006483757,0.000426278,0.0004536372,0.0005077394],"category_scores_gemma":[0.004116395,0.0002232809,0.0005045364,0.0006814877,0.000385704,0.0004651033,0.0005096632,0.0005317012,0.0001509458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006746215,"about_ca_system_score_gemma":0.0005053715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003119547,"about_ca_topic_score_gemma":0.005293585,"domain_scores_codex":[0.999711,0.00006296161,0.00001912638,0.0001078917,0.00007209345,0.0000269503],"domain_scores_gemma":[0.9976605,0.001525666,0.0004136481,0.0001630288,0.0001499777,0.00008712385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000342306,0.00008807056,0.4940109,0.0002528106,0.0002661734,0.0004113145,0.0003452811,0.3363302,0.04489721,0.006319818,0.001648086,0.1150877],"study_design_scores_gemma":[0.00002063229,0.00003690814,0.05849195,0.00003509638,0.00005709955,0.0004536647,0.00008727625,0.9072059,0.01406811,0.01791109,0.001614356,0.00001787503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8076327,0.0005846326,0.1887283,0.0001827017,0.000008592117,0.00003335611,0.00159059,0.0005146735,0.0007244554],"genre_scores_gemma":[0.9658281,0.0001955241,0.03184812,0.00006046395,0.00001390899,0.0000234835,0.00181364,0.00005185796,0.0001648467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003119547,"threshold_uncertainty_score":0.006202817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159835316","doi":"10.1186/1471-2105-8-242","title":"Improving gene set analysis of microarray data by SAM-GS","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":263,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Astellas Pharma; Genome Alberta; Canada Research Chairs; Muttart Foundation; University of Alberta; Fondation pour la Recherche Médicale; Roche Organ Transplant Research Foundation; Kidney Foundation of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Gene; Microarray analysis techniques; DNA microarray; Biology; Computational biology; Microarray; Genetics; Gene expression; Gene expression profiling; Significance analysis of microarrays; Phenotype; Microarray databases; Biological pathway","authors":[{"name":"Irina Dinu","is_ca":true},{"name":"John D. Potter","is_ca":false},{"name":"Thomas Mueller","is_ca":true},{"name":"Qi Liu","is_ca":true},{"name":"Adeniyi J. Adewale","is_ca":true},{"name":"Gian S. Jhangri","is_ca":true},{"name":"Gunilla Einecke","is_ca":true},{"name":"Konrad S. Famulski","is_ca":true},{"name":"Philip F. Halloran","is_ca":true},{"name":"Yutaka Yasui","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01877831092716567,"gpt":0.2585670723938918,"spread":0.2397887614667261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01708156,0.003980894,0.003350056,0.006214662,0.001380206,0.002338545,0.002926614,0.001136842,0.004613153],"category_scores_gemma":[0.03137808,0.001187424,0.006790022,0.007483272,0.001331908,0.001797505,0.002439108,0.004224862,0.002639306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101022,"about_ca_system_score_gemma":0.001778272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002453656,"about_ca_topic_score_gemma":0.003559337,"domain_scores_codex":[0.9894847,0.005769706,0.0008777771,0.001939236,0.001649145,0.0002793783],"domain_scores_gemma":[0.975998,0.01672082,0.001079472,0.004020438,0.001950394,0.0002309152],"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":[0.002228318,0.0005278631,0.02910244,0.003336031,0.006225902,0.0005797299,0.001049467,0.1205233,0.09624361,0.01421127,0.0234656,0.7025066],"study_design_scores_gemma":[0.0003385258,0.000625739,0.02221272,0.0001406078,0.001401022,0.0006697028,0.0003461981,0.8368705,0.06306286,0.03968748,0.03432081,0.0003239313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01595916,0.0006264781,0.9675663,0.0002171864,0.0001582863,0.0001648773,0.00158589,0.01323947,0.0004824625],"genre_scores_gemma":[0.05137588,0.0002450083,0.9423526,0.000159322,0.000083198,0.0006734487,0.003377809,0.001428437,0.0003043495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01708156,"threshold_uncertainty_score":0.09033698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1640378004","doi":"10.1186/1471-2105-6-30","title":"An ant colony optimisation algorithm for the 2D and 3D hydrophobic polar protein folding problem","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":261,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein folding; Polar; Protein structure prediction; Computer science; Folding (DSP implementation); Ant colony optimization algorithms; Ant colony; Computational biology; DNA microarray; Algorithm; Chemistry; Artificial intelligence; Protein structure; Biology; Engineering; Biochemistry; Physics; Gene","authors":[{"name":"Alena Shmygelska","is_ca":true},{"name":"Holger H. Hoos","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007372782569299728,"gpt":0.2365800328822989,"spread":0.2292072503129991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006671686,0.0008712802,0.0009103531,0.0005327114,0.0005203558,0.0006180616,0.001274562,0.001326696,0.00250361],"category_scores_gemma":[0.001977514,0.0003425893,0.0006564332,0.0006663672,0.000680771,0.0005818421,0.001038211,0.000986574,0.0004110975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006533007,"about_ca_system_score_gemma":0.001193159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006316463,"about_ca_topic_score_gemma":0.004868736,"domain_scores_codex":[0.9996192,0.0001339463,0.00002096768,0.00008115336,0.00009841834,0.0000461681],"domain_scores_gemma":[0.9989861,0.0006631585,0.00009319959,0.00004906868,0.0001484416,0.00006002664],"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":[0.0000359468,0.00002947769,0.0004340916,0.00004829703,0.00001890917,0.00006425773,0.0000394361,0.9701936,0.0007288823,0.003406435,0.001044046,0.02395654],"study_design_scores_gemma":[0.00001051712,0.000009776551,0.00003692142,0.000002291905,0.000002681173,0.00001245553,0.000004312257,0.9985341,0.00008704251,0.0009799356,0.0003180784,0.00000185705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04055007,0.0004527789,0.9502529,0.000469533,0.00008284332,0.0001522325,0.0001116881,0.0005009517,0.00742705],"genre_scores_gemma":[0.4038884,0.0002693013,0.5897312,0.0002729792,0.0000541308,0.0004752822,0.0003129033,0.0001476722,0.004848193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006316463,"threshold_uncertainty_score":0.01255935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030006812","doi":"10.1186/1471-2105-10-99","title":"Markov clustering versus affinity propagation for the partitioning of protein interaction graphs","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":234,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Cluster analysis; Computer science; Markov chain; Affinity propagation; Partition (number theory); Theoretical computer science; Data mining; Machine learning; Correlation clustering; Mathematics; Canopy clustering algorithm; Combinatorics","authors":[{"name":"James Vlasblom","is_ca":true},{"name":"Shoshana J. Wodak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02334492071945516,"gpt":0.2621829235474462,"spread":0.238838002827991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002642145,0.000994583,0.0007449154,0.002456684,0.0009041055,0.001192381,0.002070885,0.001888188,0.001673291],"category_scores_gemma":[0.01198185,0.0005376514,0.001053126,0.001608149,0.001102349,0.001938919,0.001297512,0.001617312,0.0006323393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002016742,"about_ca_system_score_gemma":0.001465359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056082,"about_ca_topic_score_gemma":0.01063489,"domain_scores_codex":[0.9986553,0.0004715779,0.00006837954,0.0003321601,0.0003548175,0.000117861],"domain_scores_gemma":[0.9883147,0.008483449,0.0009325517,0.0007916291,0.00115696,0.0003206863],"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":[0.0002359054,0.0001014301,0.003530002,0.000166447,0.0001003559,0.00006396484,0.0001614548,0.9007372,0.003952,0.01345774,0.001396125,0.07609734],"study_design_scores_gemma":[0.000009498036,0.00002350423,0.0004119472,0.000007061727,0.000009090832,0.00002865449,0.00001471134,0.9891304,0.001303051,0.008809067,0.0002440805,0.000008954452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07637575,0.0005996625,0.9192938,0.0003979995,0.00004511953,0.0001711776,0.0003370711,0.001121869,0.001657569],"genre_scores_gemma":[0.480282,0.0005090138,0.5152599,0.0002130833,0.00006921514,0.000284064,0.001368175,0.000221731,0.001792826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01056082,"threshold_uncertainty_score":0.02099866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087937056","doi":"10.1186/1471-2105-10-287","title":"Epitopia: a web-server for predicting B-cell epitopes","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":232,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Tel Aviv University; Killam Trusts","keywords":"Epitope; Computer science; Web server; Web application; Interface (matter); Sequence (biology); Computational biology; Graphical user interface; Data mining; Bioinformatics; Antigen; Biology; The Internet; Operating system; Immunology; Genetics","authors":[{"name":"Nimrod D. Rubinstein","is_ca":false},{"name":"Itay Mayrose","is_ca":true},{"name":"Eric Martz","is_ca":false},{"name":"Tal Pupko","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01522111856171145,"gpt":0.2332089179338898,"spread":0.2179877993721783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007680455,0.001451948,0.0009198183,0.001358345,0.0005341666,0.000967026,0.002013798,0.001081928,0.03162585],"category_scores_gemma":[0.002708504,0.0006411271,0.0006786961,0.001099907,0.0002674336,0.001893226,0.001081241,0.001100423,0.01898587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004885852,"about_ca_system_score_gemma":0.001063125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002837897,"about_ca_topic_score_gemma":0.002494576,"domain_scores_codex":[0.9997129,0.00005193856,0.00003113609,0.00005988831,0.0001055698,0.00003860129],"domain_scores_gemma":[0.9993061,0.0002788995,0.00006650505,0.00007652984,0.0001574822,0.0001144768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00648655,0.0004299248,0.007788912,0.002918826,0.0003657747,0.001928761,0.0003043015,0.01829922,0.07846796,0.007403496,0.5919305,0.2836758],"study_design_scores_gemma":[0.002290851,0.0008185997,0.02578714,0.0006441979,0.0003378753,0.003892043,0.0002702353,0.3863706,0.1068563,0.01915636,0.4530917,0.0004840117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.07762764,0.005805463,0.3053122,0.001181471,0.0005716087,0.001112919,0.1702604,0.4052571,0.0328711],"genre_scores_gemma":[0.1869921,0.002664834,0.378392,0.0006146423,0.0002586309,0.001401507,0.3794779,0.01770668,0.03249175],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03162585,"threshold_uncertainty_score":0.105799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295126179","doi":"10.1186/s12859-016-0943-7","title":"Improving cell mixture deconvolution by identifying optimal DNA methylation libraries (IDOL)","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":230,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institutes of Health; National Cancer Institute; University of California, San Francisco; National Institute of General Medical Sciences; Kansas IDeA Network of Biomedical Research Excellence; Child and Family Research Institute","keywords":"DNA methylation; Deconvolution; Methylation; Flow cytometry; Computational biology; Biology; DNA; Computer science; Molecular biology; Algorithm; Genetics; Gene; Gene expression","authors":[{"name":"Devin C. Koestler","is_ca":false},{"name":"Meaghan J. Jones","is_ca":true},{"name":"Joseph Usset","is_ca":false},{"name":"Brock C. Christensen","is_ca":false},{"name":"Rondi A. Butler","is_ca":false},{"name":"Michael S. Kobor","is_ca":true},{"name":"John K. Wiencke","is_ca":false},{"name":"Karl T. Kelsey","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01219439740062806,"gpt":0.2305355039585823,"spread":0.2183411065579542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003581669,0.001524632,0.0011389,0.001598721,0.0005176332,0.001702889,0.001231785,0.001049168,0.001196272],"category_scores_gemma":[0.006347553,0.0006144114,0.001217365,0.001031896,0.0006778655,0.001094244,0.001823691,0.00148389,0.001167437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016586,"about_ca_system_score_gemma":0.001442593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001979754,"about_ca_topic_score_gemma":0.003330508,"domain_scores_codex":[0.9990942,0.0002135103,0.00004998374,0.0003226795,0.0002355154,0.00008412798],"domain_scores_gemma":[0.9982337,0.0009802553,0.0002170952,0.0001753049,0.0003118476,0.0000817789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001300387,0.0005188857,0.02763854,0.0005579241,0.0004963643,0.0001499569,0.0003971087,0.1859579,0.275643,0.005026243,0.002550011,0.4997637],"study_design_scores_gemma":[0.00006860377,0.000244104,0.003876736,0.00002645418,0.0001242029,0.000130105,0.00006364689,0.801,0.1871849,0.003998277,0.003209193,0.00007377243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09090001,0.0007858922,0.9041508,0.0001852101,0.00003447534,0.0001023572,0.0003023413,0.002787729,0.0007511867],"genre_scores_gemma":[0.200824,0.0004107202,0.7956171,0.0002603337,0.00002724099,0.0002240043,0.001029969,0.0003538199,0.001252743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003581669,"threshold_uncertainty_score":0.01894194,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077350268","doi":"10.1186/1471-2105-15-s6-i1","title":"Knowledge Discovery and interactive Data Mining in Bioinformatics - State-of-the-Art, future challenges and research directions","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Discovery Centre; University Health Network","funders":"","keywords":"Data science; State (computer science); Computer science; World Wide Web; Bioinformatics; Biology","authors":[{"name":"Andreas Holzinger","is_ca":false},{"name":"Matthias Dehmer","is_ca":false},{"name":"Igor Jurišica","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06287523198941182,"gpt":0.3455186186540535,"spread":0.2826433866646417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04148045,0.001397238,0.002925267,0.00372203,0.002042677,0.01177641,0.00712097,0.007434176,0.004766567],"category_scores_gemma":[0.03216751,0.001361823,0.001639861,0.009374736,0.009313778,0.02978408,0.005089097,0.007534922,0.002313749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002647214,"about_ca_system_score_gemma":0.006611762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003310578,"about_ca_topic_score_gemma":0.002709518,"domain_scores_codex":[0.9834785,0.009558967,0.001168665,0.001474862,0.003621529,0.0006974039],"domain_scores_gemma":[0.9071623,0.08071096,0.001528696,0.003119414,0.005022509,0.002456072],"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":[0.0006199392,0.0005533911,0.003133539,0.008073018,0.0001966161,0.0002149733,0.00101824,0.006887729,0.002067341,0.1013424,0.04732186,0.828571],"study_design_scores_gemma":[0.0001341334,0.0004194904,0.002142064,0.005754825,0.0002193122,0.0006818001,0.001676759,0.06670327,0.003837511,0.6695781,0.2485574,0.0002953735],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006498812,0.6616751,0.1902281,0.1334896,0.002123911,0.0001859343,0.0004766155,0.001341443,0.003980405],"genre_scores_gemma":[0.06103795,0.6039002,0.308495,0.01000621,0.01148421,0.0004108324,0.00124197,0.0003533857,0.003070208],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.04148045,"threshold_uncertainty_score":0.2193722,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161701113","doi":"10.1186/1471-2105-7-365","title":"PIPE: a protein-protein interaction prediction engine based on the re-occurring short polypeptide sequences between known interacting protein pairs","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":219,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem affinity purification; Saccharomyces cerevisiae; Protein–protein interaction; Yeast; Computational biology; Interaction network; Biology; Gene; Genetics; Bioinformatics; Biochemistry","authors":[{"name":"Sylvain Pitre","is_ca":true},{"name":"Frank Dehne","is_ca":true},{"name":"Albert Chan","is_ca":false},{"name":"Jim Cheetham","is_ca":true},{"name":"Alex Duong","is_ca":true},{"name":"Andrew Emili","is_ca":true},{"name":"Marinella Gebbia","is_ca":true},{"name":"Jack Greenblatt","is_ca":true},{"name":"Mathew Jessulat","is_ca":true},{"name":"Nevan J. Krogan","is_ca":true},{"name":"Xuemei Luo","is_ca":true},{"name":"Ashkan Golshani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01760215492765312,"gpt":0.2389834037510581,"spread":0.221381248823405,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008511827,0.001973407,0.0009177497,0.001453369,0.000389882,0.0008465125,0.001567287,0.0008470567,0.005659737],"category_scores_gemma":[0.001898943,0.000680964,0.001323467,0.0008116668,0.000324255,0.00158611,0.0009522756,0.0009591738,0.003740133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003528143,"about_ca_system_score_gemma":0.0006010257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007640724,"about_ca_topic_score_gemma":0.00102623,"domain_scores_codex":[0.9996225,0.00004151377,0.00003255727,0.0001351358,0.0001405631,0.00002773001],"domain_scores_gemma":[0.9993463,0.0003320969,0.0001298736,0.00006204371,0.0000832798,0.00004636837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00616169,0.0007205209,0.03287801,0.005639948,0.001269603,0.003908232,0.0006729617,0.07235546,0.2612729,0.01051636,0.1407928,0.4638115],"study_design_scores_gemma":[0.0003275525,0.0007387395,0.01356287,0.0001852991,0.0003462031,0.002519122,0.0001225898,0.7497336,0.1449449,0.01244148,0.07482881,0.0002487878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05558652,0.0009455743,0.6943454,0.0002373996,0.0001401248,0.0004022402,0.01892616,0.2267901,0.002626435],"genre_scores_gemma":[0.2404221,0.001372475,0.6823657,0.0004020802,0.0001011501,0.0008490807,0.06304176,0.00651156,0.004934218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005659737,"threshold_uncertainty_score":0.01893365,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102858485","doi":"10.1186/1471-2105-10-357","title":"AIR: A batch-oriented web program package for construction of supermatrices ready for phylogenomic analyses","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":211,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Norges Forskningsråd; Universitetet i Oslo","keywords":"Phylogenetic tree; Sequence (biology); Biology; Computational biology; Tree (set theory); Phylogenomics; DNA microarray; Evolutionary biology; Phylogenetics; R package; Computer science; Gene; Data mining; Bioinformatics; Genetics; Clade; Programming language","authors":[{"name":"Surendra Kumar","is_ca":false},{"name":"Åsmund Skjæveland","is_ca":false},{"name":"Russell JS Orr","is_ca":false},{"name":"Pål Enger","is_ca":false},{"name":"Torgeir A. Ruden","is_ca":false},{"name":"Bjørn‐Helge Mevik","is_ca":false},{"name":"Fabien Burki","is_ca":true},{"name":"Andreas Botnen","is_ca":false},{"name":"Kamran Shalchian‐Tabrizi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0384095315106722,"gpt":0.3222790566447174,"spread":0.2838695251340452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003140196,0.003691311,0.001839815,0.002262415,0.001124365,0.001988824,0.003734691,0.001252599,0.06338245],"category_scores_gemma":[0.004832723,0.002137525,0.003534509,0.00170974,0.0008332561,0.00219492,0.003011367,0.003929869,0.04156023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005302949,"about_ca_system_score_gemma":0.001692809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001548821,"about_ca_topic_score_gemma":0.001735449,"domain_scores_codex":[0.9987778,0.0002663798,0.0001289525,0.0003661719,0.0003118679,0.0001489188],"domain_scores_gemma":[0.9975109,0.00141913,0.0002282719,0.0003617204,0.0003096641,0.0001702741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004208551,0.0005947413,0.006411169,0.005406051,0.001496726,0.001428218,0.001331896,0.01391712,0.104262,0.01364699,0.5198617,0.3274348],"study_design_scores_gemma":[0.001483918,0.0005507822,0.01091076,0.0005320566,0.0006273446,0.001473842,0.0002197303,0.1764457,0.1305541,0.03000637,0.6466478,0.0005477541],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.003502022,0.0002365755,0.6323768,0.0001093145,0.0001921124,0.00037424,0.02148332,0.3395008,0.002224761],"genre_scores_gemma":[0.01561399,0.0003566499,0.7829149,0.0002969699,0.0001292799,0.002747587,0.06116423,0.1317613,0.005015045],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.06338245,"threshold_uncertainty_score":0.2120354,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159348493","doi":"10.1186/1471-2105-9-327","title":"Gene Ontology term overlap as a measure of gene functional similarity","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":205,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Michael Smith Health Research BC","funders":"National Institute of General Medical Sciences; National Institutes of Health; Michael Smith Health Research BC","keywords":"Semantic similarity; Computer science; Similarity (geometry); Term (time); Measure (data warehouse); Data mining; Similarity measure; Ontology; Gene ontology; Information retrieval; Artificial intelligence; Machine learning; Gene; Biology; Genetics","authors":[{"name":"Meeta Mistry","is_ca":true},{"name":"Paul Pavlidis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02404013247122475,"gpt":0.2268267298727449,"spread":0.2027865974015202,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00330077,0.0005544442,0.000674932,0.007592582,0.0004681252,0.001143621,0.000767144,0.0006711867,0.001404199],"category_scores_gemma":[0.01606927,0.0001273319,0.0007722678,0.006925846,0.0008487486,0.001479112,0.001238548,0.0006267175,0.0002629223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009226803,"about_ca_system_score_gemma":0.0004969887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001196783,"about_ca_topic_score_gemma":0.001489976,"domain_scores_codex":[0.9964477,0.0009636542,0.0003829655,0.0005152923,0.001512549,0.0001778251],"domain_scores_gemma":[0.9866235,0.008871399,0.001882485,0.0008247301,0.001466287,0.0003315379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003720855,0.0007928048,0.4447158,0.002089173,0.002205801,0.0005746863,0.001966636,0.07717814,0.09659623,0.03365775,0.006834792,0.3296673],"study_design_scores_gemma":[0.000161529,0.00189381,0.4565187,0.0002066918,0.0007577008,0.002756566,0.001312749,0.3895998,0.06184439,0.06903464,0.01554726,0.0003661885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.819299,0.00161311,0.1688904,0.0001716378,0.00009788878,0.0001937859,0.003078171,0.0009582613,0.005697675],"genre_scores_gemma":[0.9343256,0.0001690687,0.06295078,0.0000277165,0.00003794246,0.0001689823,0.001833896,0.00007840723,0.0004074942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007592582,"threshold_uncertainty_score":0.01745635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134591904","doi":"10.1186/1471-2105-5-170","title":"PhyME: A probabilistic algorithm for finding motifs in sets of orthologous sequences","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Human Genome Research Institute; W. M. Keck Foundation; National Institutes of Health; National Science Foundation","keywords":"Probabilistic logic; Phylogenetic tree; Motif (music); Expectation–maximization algorithm; Computer science; Computational biology; Biology; Data mining; Algorithm; Gene; Genetics; Artificial intelligence; Maximum likelihood; Mathematics","authors":[{"name":"Saurabh Sinha","is_ca":false},{"name":"Mathieu Blanchette","is_ca":true},{"name":"Martin Tompa","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0151012122346998,"gpt":0.2562718729200442,"spread":0.2411706606853444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00302872,0.00117215,0.001341971,0.002684317,0.000975778,0.001403847,0.002527353,0.001970823,0.005966541],"category_scores_gemma":[0.01269768,0.001133341,0.00175656,0.001891267,0.001017833,0.00325401,0.003369625,0.002034212,0.001864662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004983762,"about_ca_system_score_gemma":0.001487809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001175618,"about_ca_topic_score_gemma":0.00221797,"domain_scores_codex":[0.9985662,0.0004696471,0.0001061098,0.0003342518,0.0004486604,0.00007516381],"domain_scores_gemma":[0.9970779,0.002132814,0.0001725168,0.0002780599,0.0002555249,0.00008318749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001248614,0.0003638163,0.01315205,0.001209249,0.0006534145,0.0005473914,0.0005286014,0.1678378,0.02106977,0.04212556,0.01752749,0.7337362],"study_design_scores_gemma":[0.0002705897,0.0001585195,0.001923987,0.00007931134,0.00007816614,0.000723755,0.00008228157,0.895408,0.007975809,0.0803318,0.01289644,0.00007140951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0072295,0.0001688822,0.9879243,0.0001040233,0.00002635931,0.00008428625,0.0004544161,0.00360434,0.0004037584],"genre_scores_gemma":[0.04721661,0.0001225298,0.9497302,0.0001101448,0.00002810764,0.0003569594,0.001250456,0.0004349786,0.0007499171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005966541,"threshold_uncertainty_score":0.01996011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009474665","doi":"10.1186/1471-2105-10-145","title":"flowClust: a Bioconductor package for automated gating of flow cytometry data","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Cluster analysis; Data mining; Data transformation; Throughput; Outlier; Workflow; Artificial intelligence; Database; Data warehouse","authors":[{"name":"Kenneth Lo","is_ca":true},{"name":"Florian Hahne","is_ca":false},{"name":"Ryan R. Brinkman","is_ca":true},{"name":"Raphaël Gottardo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05296027501363074,"gpt":0.3019501064415164,"spread":0.2489898314278856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01732127,0.006798736,0.006943312,0.01027063,0.003277888,0.007311065,0.01292714,0.005268631,0.1029584],"category_scores_gemma":[0.05295657,0.003646545,0.006403581,0.009136859,0.002245585,0.004668036,0.006071255,0.009132141,0.07241656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001894822,"about_ca_system_score_gemma":0.01089998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00500457,"about_ca_topic_score_gemma":0.005896514,"domain_scores_codex":[0.9881945,0.003946931,0.001493006,0.002947912,0.002711013,0.00070672],"domain_scores_gemma":[0.9738019,0.01584841,0.002237724,0.003267422,0.004054995,0.0007895686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009062961,0.0001657498,0.003435963,0.007054965,0.001972791,0.0005905367,0.0008664688,0.007585214,0.006707011,0.02146478,0.8815827,0.06766748],"study_design_scores_gemma":[0.001115673,0.0002142869,0.006298349,0.00143654,0.0009218445,0.0009719891,0.0002444064,0.09053008,0.01632095,0.08760641,0.7937486,0.0005908504],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.003086679,0.00226555,0.4465082,0.001744951,0.001517524,0.001205004,0.1377801,0.3992808,0.006611321],"genre_scores_gemma":[0.02150815,0.001741515,0.6861557,0.002202435,0.0005465917,0.01352198,0.1256202,0.1396884,0.009015011],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1029584,"threshold_uncertainty_score":0.34443,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135842485","doi":"10.1186/1471-2105-9-507","title":"MetaboMiner – semi-automated identification of metabolites from 2D NMR spectra of complex biofluids","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":199,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Genome Alberta; Ministry of Advanced Education, Government of Alberta","keywords":"Metabolomics; Heteronuclear single quantum coherence spectroscopy; NMR spectra database; Proton NMR; Two-dimensional nuclear magnetic resonance spectroscopy; Nuclear magnetic resonance spectroscopy; Chemistry; Heteronuclear molecule; Nuclear magnetic resonance; Spectral line; Biological system; Analytical Chemistry (journal); Chromatography; Stereochemistry; Biology; Physics","authors":[{"name":"Jianguo Xia","is_ca":true},{"name":"Trent C. Bjorndahl","is_ca":true},{"name":"Peter Tang","is_ca":true},{"name":"David S. Wishart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02520741091627525,"gpt":0.2568409985779328,"spread":0.2316335876616576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002155606,0.003314043,0.001854274,0.003967599,0.0005468031,0.001556638,0.001660436,0.00119254,0.01324397],"category_scores_gemma":[0.003031917,0.001089727,0.00193076,0.001455954,0.0004335418,0.001711928,0.001459903,0.001138387,0.004662303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004767262,"about_ca_system_score_gemma":0.00124594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001140192,"about_ca_topic_score_gemma":0.001679988,"domain_scores_codex":[0.9991972,0.0001216529,0.0000830085,0.0003268779,0.0002174073,0.0000538828],"domain_scores_gemma":[0.9985822,0.0006358312,0.0002876628,0.0001417328,0.0002575786,0.00009491497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003617048,0.0003808361,0.008109656,0.004238835,0.0009420527,0.001406804,0.000622606,0.01135306,0.4201349,0.002608014,0.06357124,0.4830149],"study_design_scores_gemma":[0.0006393873,0.0007483936,0.02145658,0.0004104345,0.0003862812,0.002980513,0.0002625062,0.3472596,0.5038238,0.007242338,0.1140869,0.0007032251],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03171709,0.001128859,0.6931795,0.0002770605,0.0001903519,0.0004648647,0.01838159,0.2525654,0.002095327],"genre_scores_gemma":[0.03431121,0.0005471243,0.9371342,0.0002050061,0.00005457118,0.0009571072,0.0159735,0.008902395,0.001914924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01324397,"threshold_uncertainty_score":0.0443055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149954962","doi":"10.1186/1471-2105-7-228","title":"A stable gene selection in microarray data analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene selection; Selection (genetic algorithm); Microarray analysis techniques; DNA microarray; Support vector machine; Computer science; Gene; Data mining; Significance analysis of microarrays; Microarray; Sample (material); Computational biology; Biology; Artificial intelligence; Genetics; Gene expression","authors":[{"name":"Kun Yang","is_ca":false},{"name":"Zhipeng Cai","is_ca":true},{"name":"Jianzhong Li","is_ca":false},{"name":"Guohui Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02232773026539993,"gpt":0.2640294807481557,"spread":0.2417017504827558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007050524,0.0009185729,0.001282332,0.002014989,0.0008004248,0.0008120408,0.001276723,0.0009581276,0.001187556],"category_scores_gemma":[0.009047967,0.0003965794,0.001229334,0.003709777,0.001360564,0.0007279796,0.0009667414,0.0008242402,0.001010387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007373635,"about_ca_system_score_gemma":0.001146383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006772691,"about_ca_topic_score_gemma":0.0007189894,"domain_scores_codex":[0.9940743,0.002616057,0.0003015479,0.001240212,0.001555556,0.000212234],"domain_scores_gemma":[0.9950408,0.002971614,0.000386931,0.0005785874,0.0009124081,0.0001096878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001437601,0.000243322,0.01702281,0.0009097118,0.0004948355,0.0005546516,0.0002988377,0.09596805,0.1226732,0.01143412,0.006468324,0.7424945],"study_design_scores_gemma":[0.0001472651,0.0008179385,0.01504679,0.00007108572,0.0002223978,0.0007213898,0.00009187322,0.8793719,0.06886196,0.02238142,0.01218695,0.0000789865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02532264,0.0009359634,0.9716108,0.0002282032,0.00007869198,0.0001431011,0.0003470904,0.00106826,0.0002651264],"genre_scores_gemma":[0.301036,0.0009847891,0.6928438,0.0003096264,0.0002801498,0.001027477,0.001781314,0.0002863547,0.001450556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007050524,"threshold_uncertainty_score":0.03728724,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042301222","doi":"10.1186/1471-2105-11-562","title":"An improved method for scoring protein-protein interactions using semantic similarity within the gene ontology","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Semantic similarity; Gene ontology; Computer science; Similarity (geometry); Graph; Protein function prediction; Cluster analysis; Ontology; Gene Annotation; Representation (politics); Computational biology; Data mining; Protein function; Information retrieval; Artificial intelligence; Gene; Theoretical computer science; Biology; Genetics; Genome; Gene expression","authors":[{"name":"Shobhit Jain","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02424040538563358,"gpt":0.3072557650958416,"spread":0.283015359710208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001319148,0.001182316,0.001111148,0.007883264,0.0006881072,0.001046557,0.001628896,0.001240814,0.002540915],"category_scores_gemma":[0.004571275,0.0003129164,0.001599945,0.004861587,0.0006464247,0.00165454,0.0009806345,0.001017449,0.001430675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001241942,"about_ca_system_score_gemma":0.001867071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008066691,"about_ca_topic_score_gemma":0.01090322,"domain_scores_codex":[0.9979094,0.0002071073,0.0001629521,0.0004194947,0.001165044,0.0001358832],"domain_scores_gemma":[0.9975426,0.0006968582,0.0002481932,0.0002769247,0.001157819,0.00007767727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006580637,0.0004802648,0.01658496,0.0006095848,0.0005747594,0.0003488979,0.0002505078,0.04214435,0.07439905,0.008208628,0.01467072,0.8410703],"study_design_scores_gemma":[0.0001335209,0.0002617879,0.01341195,0.00003540047,0.0001889584,0.0008808891,0.0001849452,0.9148925,0.0438811,0.01130288,0.0147383,0.00008769314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0727702,0.0005920045,0.9132202,0.0002131432,0.0001121295,0.0003674072,0.001840015,0.008821721,0.00206312],"genre_scores_gemma":[0.2266758,0.0002136606,0.7651625,0.0001009743,0.00006528784,0.0003310481,0.004971209,0.0003401164,0.002139488],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008066691,"threshold_uncertainty_score":0.01603949,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106017862","doi":"10.1186/1471-2105-9-375","title":"Critical assessment of alignment procedures for LC-MS proteomics and metabolomics measurements","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":191,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Cancer Research UK","keywords":"Proteomics; Metabolomics; Computational biology; DNA microarray; Computer science; Bioinformatics; Data science; Biology; Genetics","authors":[{"name":"Eva Lange","is_ca":false},{"name":"Ralf Tautenhahn","is_ca":true},{"name":"Steffen Neumann","is_ca":true},{"name":"Clemens Gröpl","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04279125193340434,"gpt":0.310214925530109,"spread":0.2674236735967047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04408759,0.002257845,0.001194217,0.005203695,0.001988688,0.003656951,0.002388692,0.001799952,0.002809723],"category_scores_gemma":[0.1447676,0.0008102464,0.001899808,0.004618898,0.001588801,0.003323076,0.002534003,0.001819261,0.0015773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001596664,"about_ca_system_score_gemma":0.003099896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001390304,"about_ca_topic_score_gemma":0.001013732,"domain_scores_codex":[0.9686067,0.01110141,0.003915503,0.003010876,0.01271472,0.0006506936],"domain_scores_gemma":[0.8487254,0.0756449,0.01350966,0.01172675,0.04908594,0.001307328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004249907,0.0008181108,0.0333777,0.005377897,0.0009630288,0.0006211478,0.002346646,0.04344959,0.1882564,0.01145928,0.01109465,0.6979855],"study_design_scores_gemma":[0.0002696725,0.002622573,0.05167102,0.001120307,0.0008549292,0.001710502,0.00153343,0.3124014,0.572257,0.01625365,0.03861954,0.0006859585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1144603,0.003876749,0.870358,0.0005780495,0.0005473371,0.001198694,0.001438539,0.00561491,0.001927342],"genre_scores_gemma":[0.1539935,0.0008853994,0.8394327,0.0001387589,0.00009076585,0.0009358017,0.002765442,0.001427199,0.0003303877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04408759,"threshold_uncertainty_score":0.2331603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146389940","doi":"10.1186/1471-2105-6-151","title":"AutoFACT: An Auto matic F unctional A nnotation and C lassification T ool","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University; Université de Montréal","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Perl; Annotation; Computer science; Software; Unix; Genomics; Functional genomics; Bioconductor; Computational biology; Information retrieval; Data mining; Programming language; Biology; Artificial intelligence; Genetics; Genome; Gene","authors":[{"name":"Liisa B. Koski","is_ca":true},{"name":"Michael W. Gray","is_ca":true},{"name":"B. Franz Lang","is_ca":true},{"name":"Gertraud Burger","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01476743885683266,"gpt":0.2402007987037153,"spread":0.2254333598468827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002820853,0.002847771,0.001375717,0.006012814,0.001567684,0.00387409,0.00286585,0.001410509,0.06290022],"category_scores_gemma":[0.0102623,0.001335335,0.002884255,0.003198066,0.001294929,0.003276425,0.003186364,0.001707052,0.03495541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009866101,"about_ca_system_score_gemma":0.001923661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002074206,"about_ca_topic_score_gemma":0.002098049,"domain_scores_codex":[0.9973092,0.0004696176,0.0002969044,0.0006897227,0.001050338,0.0001841947],"domain_scores_gemma":[0.9949425,0.001854939,0.0006249482,0.0013279,0.0009798231,0.0002698608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001069145,0.0001719278,0.003294607,0.001656046,0.0002075533,0.001215038,0.0008354113,0.004590131,0.02130234,0.02303544,0.5052717,0.4373507],"study_design_scores_gemma":[0.0001526657,0.0001605531,0.002655117,0.0004256036,0.0001055097,0.001497887,0.0002390325,0.05768335,0.0409612,0.03254368,0.86328,0.0002954782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.004177786,0.0005477158,0.6469788,0.0005350795,0.0008426263,0.0003769328,0.02541506,0.3068232,0.01430283],"genre_scores_gemma":[0.03533145,0.0008690723,0.7965491,0.0006527787,0.0004559529,0.0007780978,0.07539988,0.06362967,0.02633401],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.06290022,"threshold_uncertainty_score":0.2104222,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2511892808","doi":"10.1186/s12859-016-1228-x","title":"The parameter sensitivity of random forests","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Occupational Cancer Research Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Canadian Institutes of Health Research; Government of Ontario; Movember Foundation","keywords":"Sensitivity (control systems); Random forest; DNA microarray; Computational biology; Computer science; Biology; Artificial intelligence; Genetics; Engineering; Gene","authors":[{"name":"Barbara Huang","is_ca":true},{"name":"Paul C. Boutros","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0154773277249372,"gpt":0.2505137324377511,"spread":0.2350364047128139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03029907,0.001562936,0.001392929,0.002392061,0.00103161,0.002129454,0.001730431,0.001852787,0.001270458],"category_scores_gemma":[0.1072673,0.0006268235,0.001525733,0.001633256,0.001950301,0.002842746,0.001634839,0.002394933,0.0005883407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137792,"about_ca_system_score_gemma":0.0008099816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002194073,"about_ca_topic_score_gemma":0.001152794,"domain_scores_codex":[0.9806362,0.01134849,0.001044665,0.00342839,0.002880496,0.0006619366],"domain_scores_gemma":[0.8557652,0.1224165,0.00679744,0.00963131,0.004780155,0.0006094305],"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":[0.0006790805,0.0001377857,0.05082238,0.0005284802,0.0007876751,0.0002213378,0.0003853518,0.8437834,0.005788077,0.01141792,0.003011824,0.08243676],"study_design_scores_gemma":[0.0000425274,0.0002790552,0.01232046,0.0001917975,0.0001873502,0.0005456897,0.000146136,0.9132951,0.0100173,0.05952349,0.003310967,0.0001400505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4672245,0.007761553,0.5131292,0.001755072,0.0003319641,0.0002670451,0.001318645,0.002233237,0.005978758],"genre_scores_gemma":[0.9591705,0.00071266,0.0377745,0.0003377162,0.00014475,0.0001614432,0.001047389,0.0003449424,0.0003061271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03029907,"threshold_uncertainty_score":0.1602387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082852695","doi":"10.1186/1471-2105-12-414","title":"Three-dimensional modeling of chromatin structure from interaction frequency data using Markov chain Monte Carlo sampling","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research","keywords":"Chromatin; Markov chain Monte Carlo; Chromosome conformation capture; Computational biology; Chromosome; Computer science; Monte Carlo method; Biology; Algorithm; Enhancer; Genetics; Artificial intelligence; DNA; Bayesian probability; Transcription factor; Gene; Mathematics; Statistics","authors":[{"name":"Mathieu Rousseau","is_ca":true},{"name":"James A. Fraser","is_ca":true},{"name":"Maria Ferraiuolo","is_ca":true},{"name":"Josée Dostie","is_ca":true},{"name":"Mathieu Blanchette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06652223994272753,"gpt":0.265972490078861,"spread":0.1994502501361335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001790568,0.0006897348,0.000851971,0.00124127,0.0009337029,0.001212652,0.001970775,0.00179157,0.002451409],"category_scores_gemma":[0.006125968,0.0009832652,0.001597653,0.001020412,0.001403805,0.0008440486,0.0008204135,0.00164783,0.0004941148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002285633,"about_ca_system_score_gemma":0.001941665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03258531,"about_ca_topic_score_gemma":0.03041166,"domain_scores_codex":[0.9995492,0.0001939238,0.00002059451,0.00008837442,0.0000965217,0.00005136359],"domain_scores_gemma":[0.9947298,0.004297158,0.0002779065,0.000218661,0.0003051574,0.0001713037],"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":[0.00002486399,0.00001475192,0.001227573,0.00001741331,0.00002169135,0.00003296316,0.00002524174,0.9934232,0.0003300454,0.003074588,0.0001786278,0.001629085],"study_design_scores_gemma":[0.000003905696,0.000001779015,0.00009374753,0.000001898319,0.000001406931,0.000003944209,0.000001642163,0.9984505,0.00005511958,0.001324141,0.00005945735,0.000002352074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1818381,0.0003923479,0.8115792,0.000586634,0.00005300765,0.0002113718,0.00116988,0.001252847,0.002916652],"genre_scores_gemma":[0.7778251,0.0003469102,0.2154914,0.0002452012,0.00008272074,0.0007664274,0.002687507,0.0003159792,0.002238791],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03258531,"threshold_uncertainty_score":0.06479132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2501117253","doi":"10.1186/s12859-016-1097-3","title":"Evaluating the necessity of PCR duplicate removal from next-generation sequencing data and a comparison of approaches","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Servier; Brigham Young University; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Transversion; Computational biology; Reference genome; Biology; DNA sequencing; Concordance; Genetics; Exome; Population; Data mining; Computer science; Bioinformatics; Exome sequencing; Gene; Mutation; Medicine","authors":[{"name":"Mark Ebbert","is_ca":false},{"name":"Mark E. Wadsworth","is_ca":false},{"name":"Lyndsay A. Staley","is_ca":false},{"name":"Kaitlyn L. Hoyt","is_ca":false},{"name":"Brandon D. Pickett","is_ca":false},{"name":"Justin Miller","is_ca":false},{"name":"John Duce","is_ca":false},{"name":"John Kauwe","is_ca":false},{"name":"Perry G. Ridge","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3861978566480501,"gpt":0.3493385526642588,"spread":0.03685930398379128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08482776,0.001217886,0.001195987,0.003674785,0.002157393,0.003355269,0.002108899,0.001964098,0.001803868],"category_scores_gemma":[0.1639374,0.0006294568,0.003534363,0.002726663,0.001706549,0.002700476,0.002356919,0.001948399,0.0006324131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003080441,"about_ca_system_score_gemma":0.002909061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003319571,"about_ca_topic_score_gemma":0.005211914,"domain_scores_codex":[0.937059,0.02559928,0.007450223,0.01050463,0.01799452,0.001392391],"domain_scores_gemma":[0.737797,0.2127131,0.01258821,0.009506389,0.0258533,0.001542025],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02005261,0.001986943,0.3419904,0.01563008,0.01222701,0.001154966,0.005753607,0.03651098,0.07890572,0.007124733,0.008911291,0.4697517],"study_design_scores_gemma":[0.001413653,0.01598918,0.4049174,0.003630675,0.01268267,0.006247301,0.007333085,0.1882327,0.2758172,0.02436572,0.05810984,0.001260431],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7417684,0.02006547,0.2204788,0.001323596,0.00110095,0.002818519,0.003174371,0.001660847,0.007609065],"genre_scores_gemma":[0.6673804,0.002580829,0.3213092,0.0009171935,0.0001704267,0.001644573,0.004309527,0.0006499085,0.001037899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9151722,"threshold_uncertainty_score":0.4486174,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154003902","doi":"10.1186/s12859-015-0788-5","title":"Evaluation of shotgun metagenomics sequence classification methods using in silico and in vitro simulated communities","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"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; Public Health Agency; Michael Smith Health Research BC; Public Health Agency of Canada; Canadian Institutes of Health Research; University of Connecticut; Genome Canada; Genome British Columbia","keywords":"In silico; Metagenomics; Shotgun; Computational biology; Shotgun sequencing; Biology; DNA microarray; Bioinformatics; Sequence (biology); Computer science; Data mining; Genetics; DNA sequencing; Gene","authors":[{"name":"Michael A. Peabody","is_ca":true},{"name":"Thea Van Rossum","is_ca":true},{"name":"Raymond Lo","is_ca":true},{"name":"Fiona S. L. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2892683905235093,"gpt":0.4055330252369845,"spread":0.1162646347134753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01101505,0.001766288,0.001102229,0.002248995,0.000746768,0.001603803,0.001657224,0.00141343,0.00055798],"category_scores_gemma":[0.01812492,0.0003971783,0.001349415,0.001417107,0.0006379943,0.001134656,0.0009860651,0.001164787,0.0004771997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001455414,"about_ca_system_score_gemma":0.001209355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004235831,"about_ca_topic_score_gemma":0.003217218,"domain_scores_codex":[0.9931764,0.002121278,0.0007849036,0.00115145,0.00246151,0.0003044573],"domain_scores_gemma":[0.9843693,0.00911909,0.001091212,0.0008014756,0.00414853,0.0004704329],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006227355,0.002578136,0.1152829,0.004112264,0.001785424,0.0003661322,0.001225797,0.4007469,0.2230978,0.00173751,0.003210661,0.2396291],"study_design_scores_gemma":[0.00006716493,0.001624787,0.02303182,0.0001542301,0.0002156207,0.0001913848,0.0003612205,0.7965674,0.1747757,0.0008556839,0.002039524,0.0001154253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9031841,0.001575052,0.08886703,0.0002985504,0.0001532428,0.000296553,0.001638376,0.002296247,0.001690771],"genre_scores_gemma":[0.8432105,0.0008891026,0.1496794,0.0001501738,0.00003831172,0.0003510297,0.004896768,0.0002641767,0.0005206256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9889849,"threshold_uncertainty_score":0.05825382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1819658147","doi":"10.1186/1471-2105-6-68","title":"Feature selection and nearest centroid classification for protein mass spectrometry","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Feature selection; Computer science; Dimensionality reduction; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Linear discriminant analysis; Data mining; k-nearest neighbors algorithm; Curse of dimensionality; Centroid; Machine learning; Classifier (UML); Boosting (machine learning); Support vector machine","authors":[{"name":"Ilya Levner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01365895679510542,"gpt":0.2436644381373854,"spread":0.23000548134228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00278554,0.0009525084,0.001364877,0.002563887,0.0007108962,0.0008117898,0.001122159,0.000909389,0.001410529],"category_scores_gemma":[0.00668798,0.0002134756,0.001067186,0.002503031,0.0005072847,0.0009115583,0.000749459,0.0007691269,0.0008722653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000806447,"about_ca_system_score_gemma":0.0008209195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002150842,"about_ca_topic_score_gemma":0.001204261,"domain_scores_codex":[0.9980807,0.0004547854,0.0001188671,0.0003862053,0.0008244867,0.0001349323],"domain_scores_gemma":[0.9973711,0.00112444,0.0003014198,0.0002084411,0.000919109,0.00007553059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006482264,0.0003353794,0.007027515,0.0002842795,0.0002031054,0.0001992504,0.0001410363,0.13255,0.02202221,0.003159726,0.004931185,0.828498],"study_design_scores_gemma":[0.00004139667,0.0002941201,0.006360077,0.00002847863,0.00004957421,0.0002663735,0.00003875647,0.9688985,0.01573904,0.005861995,0.002379643,0.00004209427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09430326,0.001846324,0.8993361,0.0002656831,0.0001635466,0.0001674908,0.0003972306,0.002513251,0.00100705],"genre_scores_gemma":[0.5571774,0.0004504643,0.439712,0.00008101269,0.0001196143,0.0002716002,0.0009629304,0.0001010219,0.001123933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00278554,"threshold_uncertainty_score":0.01473147,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1775447850","doi":"10.1186/1471-2105-7-471","title":"The accuracy of several multiple sequence alignment programs for proteins","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Multiple sequence alignment; Alignment-free sequence analysis; Indel; Sequence alignment; Computer science; Benchmark (surveying); Inference; Software; Data mining; Range (aeronautics); Sequence (biology); Machine learning; Artificial intelligence; Biology; Genetics; Gene; Peptide sequence","authors":[{"name":"Paulo Nuin","is_ca":true},{"name":"Zhouzhi Wang","is_ca":true},{"name":"Elisabeth R.M. Tillier","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01566479295557471,"gpt":0.2533747827090948,"spread":0.2377099897535201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008068946,0.001050287,0.0007453315,0.002425285,0.0009954006,0.001617116,0.001645785,0.001339236,0.001222923],"category_scores_gemma":[0.02814474,0.0004034337,0.001006903,0.002756576,0.000664504,0.001733897,0.001020628,0.001296252,0.0005502924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001289614,"about_ca_system_score_gemma":0.001222286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002176198,"about_ca_topic_score_gemma":0.002890304,"domain_scores_codex":[0.9937648,0.002398947,0.0007657771,0.001053279,0.001784112,0.0002330818],"domain_scores_gemma":[0.9733055,0.01920902,0.002363741,0.001654495,0.003223068,0.0002441377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003350476,0.0008298916,0.1769878,0.002915339,0.00183499,0.0004970546,0.001161307,0.3616884,0.06198223,0.00785287,0.005108362,0.3757912],"study_design_scores_gemma":[0.0001331641,0.0008764409,0.02806854,0.0002561057,0.0003523637,0.0009404094,0.0002360885,0.878216,0.07854539,0.005777977,0.006486869,0.0001106396],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7928572,0.00367012,0.1908573,0.0004447255,0.0001177977,0.0001717498,0.001832012,0.006717565,0.003331587],"genre_scores_gemma":[0.7695832,0.0008348064,0.2248936,0.00009384767,0.00002006773,0.0001605816,0.003326261,0.0006995185,0.0003880525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008068946,"threshold_uncertainty_score":0.04267317,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009153021","doi":"10.1186/1471-2105-10-243","title":"Core Hunter: an algorithm for sampling genetic resources based on multiple genetic measures","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; International Fund for Agricultural Development; European Commission","keywords":"Core (optical fiber); Genetic diversity; Representativeness heuristic; Computer science; Genetic algorithm; Sampling (signal processing); Preference; Data mining; Machine learning; Statistics; Mathematics; Population","authors":[{"name":"Chris Thachuk","is_ca":true},{"name":"José Crossa","is_ca":false},{"name":"Jorge Franco","is_ca":false},{"name":"Susanne Dreisigacker","is_ca":false},{"name":"Marilyn L. Warburton","is_ca":false},{"name":"Guy Davenport","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06288921997742554,"gpt":0.3033216433372166,"spread":0.240432423359791,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00385091,0.001302759,0.00158628,0.003273648,0.001003733,0.00134866,0.002674377,0.001210097,0.004090812],"category_scores_gemma":[0.009907615,0.0009341866,0.001222513,0.002428846,0.001108937,0.001760766,0.002714167,0.001202971,0.001296968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009506498,"about_ca_system_score_gemma":0.002407658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003760819,"about_ca_topic_score_gemma":0.006910596,"domain_scores_codex":[0.9986675,0.0004274654,0.00008902174,0.0003448333,0.0003539243,0.0001172898],"domain_scores_gemma":[0.9960788,0.002312226,0.0002531476,0.0005531868,0.0006309204,0.0001717321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006995953,0.0003678028,0.01564639,0.0004697539,0.0004867357,0.0002781699,0.001016436,0.1949635,0.01065221,0.01360564,0.02287164,0.7389421],"study_design_scores_gemma":[0.0001891772,0.0001332295,0.001874678,0.00005358236,0.00007805443,0.0002296805,0.0001854946,0.9648682,0.004641665,0.02042553,0.00728635,0.00003434468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02373839,0.0001526771,0.9713377,0.00009585399,0.00002774777,0.000291009,0.0003768061,0.002900221,0.001079636],"genre_scores_gemma":[0.05964102,0.0000630644,0.9367296,0.0001314307,0.00002087162,0.0005897203,0.001218348,0.0004844998,0.001121367],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004090812,"threshold_uncertainty_score":0.02036577,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1480287196","doi":"10.1186/1471-2105-7-356","title":"New directions in biomedical text annotation: definitions, guidelines and corpus construction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Task (project management); Information retrieval; Natural language processing; Categorization; Set (abstract data type); Biomedical text mining; Executable; Focus (optics); Artificial intelligence; Unified Medical Language System; Text corpus; Text mining","authors":[{"name":"W. John Wilbur","is_ca":false},{"name":"Andrey Rzhetsky","is_ca":false},{"name":"Hagit Shatkay","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03638827609910656,"gpt":0.2788558833373014,"spread":0.2424676072381949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2149568,0.002429281,0.002809617,0.02342934,0.005309296,0.01766306,0.009875565,0.006894047,0.003502523],"category_scores_gemma":[0.293678,0.003035181,0.001845046,0.01776026,0.0293193,0.03766417,0.01180518,0.01263205,0.003598975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007318465,"about_ca_system_score_gemma":0.01711188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007317709,"about_ca_topic_score_gemma":0.009847852,"domain_scores_codex":[0.789187,0.1458358,0.03294713,0.01235798,0.01823666,0.001435553],"domain_scores_gemma":[0.5153903,0.2991873,0.0277429,0.06283832,0.08872668,0.006114454],"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":[0.0003403772,0.0004773401,0.007899763,0.01231334,0.0001241118,0.0009237124,0.0500807,0.003854539,0.01561026,0.3488904,0.06746679,0.4920187],"study_design_scores_gemma":[0.0001691856,0.0002729469,0.005266161,0.01128732,0.0001398065,0.00130597,0.01965222,0.02255514,0.01303216,0.5046791,0.4211498,0.0004901489],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006766012,0.009523025,0.9220136,0.04917865,0.001152536,0.002684607,0.001420469,0.001718175,0.005542841],"genre_scores_gemma":[0.01193568,0.002206436,0.9754847,0.001956212,0.0005332645,0.004617312,0.001822016,0.0004774419,0.0009670536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2149568,"threshold_uncertainty_score":0.968098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060064237","doi":"10.1186/1471-2105-12-139","title":"PeakRanger: A cloud-enabled peak caller for ChIP-seq data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Science Foundation","keywords":"Computer science; Cloud computing; Chromatin immunoprecipitation; Massively parallel; Software; Chip; Parallel computing; Multi-core processor; Data mining; Biology; Operating system","authors":[{"name":"Xin Feng","is_ca":true},{"name":"Robert L. Grossman","is_ca":false},{"name":"Lincoln Stein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05121050092748334,"gpt":0.2519177744359786,"spread":0.2007072735084953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005245787,0.002557824,0.001697603,0.00302675,0.001336204,0.002228234,0.005279466,0.001614477,0.02074265],"category_scores_gemma":[0.009493588,0.001509896,0.002006672,0.002666469,0.0008220103,0.001851513,0.002127761,0.002978721,0.01506317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001395949,"about_ca_system_score_gemma":0.002470748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004605203,"about_ca_topic_score_gemma":0.005925868,"domain_scores_codex":[0.9961133,0.0004167169,0.000277362,0.00117692,0.001707293,0.0003083659],"domain_scores_gemma":[0.9946576,0.002273386,0.0005946857,0.0008802428,0.001237865,0.0003562501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005484753,0.0005855516,0.01836376,0.003564708,0.001231947,0.000942956,0.0009219201,0.03627029,0.1325938,0.007650479,0.5410562,0.2513337],"study_design_scores_gemma":[0.001718452,0.0004904112,0.0181864,0.0003654238,0.000381819,0.00117622,0.0002276724,0.5184122,0.2366752,0.01824094,0.2030505,0.001074655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01375821,0.001059134,0.3303536,0.0004698564,0.0003919854,0.0007293682,0.05720231,0.5906298,0.005405756],"genre_scores_gemma":[0.07791672,0.0006241211,0.7509269,0.001815147,0.0002520653,0.002423921,0.09783971,0.0636522,0.004549214],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02074265,"threshold_uncertainty_score":0.06939107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087932775","doi":"10.1186/1471-2105-11-403","title":"Data reduction for spectral clustering to analyze high throughput flow cytometry data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":166,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; Mitacs; National Institutes of Health; Michael Smith Health Research BC","keywords":"Throughput; Computer science; Cluster analysis; Reduction (mathematics); Flow cytometry; Data reduction; Data mining; Computational biology; Biology; Mathematics; Artificial intelligence; Molecular biology; Telecommunications","authors":[{"name":"Habil Zare","is_ca":true},{"name":"Parisa Shooshtari","is_ca":true},{"name":"Arvind Gupta","is_ca":true},{"name":"Ryan R. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05461754201277463,"gpt":0.3018674232321299,"spread":0.2472498812193553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002898488,0.001586571,0.001107762,0.003621341,0.001512727,0.001512309,0.002078702,0.001120124,0.004738255],"category_scores_gemma":[0.01087012,0.0005593837,0.002938548,0.003581482,0.0007850493,0.001051905,0.001783385,0.002204062,0.004586887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001137013,"about_ca_system_score_gemma":0.002002741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003571647,"about_ca_topic_score_gemma":0.004137075,"domain_scores_codex":[0.9981368,0.0004710899,0.0001655323,0.0003460692,0.0007646879,0.0001157907],"domain_scores_gemma":[0.9960915,0.001426379,0.0002732068,0.0007776141,0.001300083,0.0001310373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005499668,0.0006024283,0.004400041,0.000751551,0.0005211311,0.0002676701,0.0006478852,0.07984522,0.09912996,0.01458756,0.02080766,0.7778888],"study_design_scores_gemma":[0.00005848616,0.0001105316,0.004930998,0.00003170901,0.00006377607,0.000305981,0.0001713112,0.9156349,0.04468847,0.01909427,0.0148124,0.00009723967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006138331,0.00005951972,0.9880089,0.0001217196,0.00004190739,0.0001607089,0.0003175952,0.004879339,0.0002719407],"genre_scores_gemma":[0.0233318,0.0000534518,0.9741027,0.00005083129,0.00002410746,0.0004719672,0.001115049,0.0004904791,0.0003597104],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004738255,"threshold_uncertainty_score":0.01585102,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125816119","doi":"10.1186/1471-2105-6-34","title":"Atlas – a data warehouse for integrative bioinformatics","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":163,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research","keywords":"Atlas (anatomy); Data warehouse; Bioinformatics; Computational biology; Data science; Computer science; Biology; Data mining","authors":[{"name":"Sohrab P. Shah","is_ca":true},{"name":"Yong Huang","is_ca":true},{"name":"Tao Xu","is_ca":true},{"name":"Macaire M. S. Yuen","is_ca":true},{"name":"John Ling","is_ca":true},{"name":"B. F. Francis Ouellette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03051586659518616,"gpt":0.2760682048145316,"spread":0.2455523382193455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093965,0.001885705,0.002065467,0.008953859,0.002078333,0.01080137,0.007324488,0.001749346,0.01180577],"category_scores_gemma":[0.01443542,0.001885782,0.003029377,0.01356264,0.001395226,0.01149845,0.008800458,0.004777734,0.01557862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001863074,"about_ca_system_score_gemma":0.005823236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003626701,"about_ca_topic_score_gemma":0.002946524,"domain_scores_codex":[0.9931191,0.001248709,0.001549285,0.001191473,0.002530326,0.0003611526],"domain_scores_gemma":[0.9771994,0.003238163,0.00174171,0.009734944,0.005397708,0.002688103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001342863,0.0003313869,0.009533424,0.002505423,0.00116788,0.001186093,0.001365968,0.01621482,0.01405172,0.1092465,0.6234757,0.2195783],"study_design_scores_gemma":[0.000240484,0.000136025,0.003175344,0.0004508588,0.0002870987,0.000850415,0.0003595352,0.0399497,0.01303058,0.09342738,0.8477952,0.0002973367],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.006984635,0.002138188,0.5951705,0.003564019,0.0008266193,0.001080742,0.1526168,0.219586,0.01803252],"genre_scores_gemma":[0.0354252,0.002104953,0.5364498,0.002149117,0.0006585456,0.001698251,0.4029065,0.01367035,0.004937225],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01180577,"threshold_uncertainty_score":0.049694,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029036185","doi":"10.1186/1471-2105-10-120","title":"Multichromosomal median and halving problems under different genomic distances","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Genome; Breakpoint; Context (archaeology); Generalization; Time complexity; Biology; Computer science; Computational biology; Genetics; Combinatorics; Mathematics; Chromosome; Gene","authors":[{"name":"Éric Tannier","is_ca":false},{"name":"Chunfang Zheng","is_ca":true},{"name":"David Sankoff","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01240274061496869,"gpt":0.2228328514029068,"spread":0.2104301107879381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002358584,0.0008184002,0.001427647,0.0008526068,0.001287187,0.002828836,0.003111818,0.002392774,0.008719805],"category_scores_gemma":[0.01303916,0.0004257815,0.001535808,0.001829099,0.001882601,0.005657102,0.003106978,0.003643466,0.0006589693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002238308,"about_ca_system_score_gemma":0.00140976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001406962,"about_ca_topic_score_gemma":0.001601973,"domain_scores_codex":[0.9983184,0.0004805817,0.0001018868,0.0005262338,0.0003245873,0.0002483302],"domain_scores_gemma":[0.983809,0.01338858,0.00081266,0.0008629047,0.0005172783,0.0006095163],"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":[0.0007630689,0.0003334971,0.003487989,0.001171655,0.0002030176,0.0003786075,0.0007240931,0.5284105,0.003127046,0.3427903,0.01215298,0.1064573],"study_design_scores_gemma":[0.0001432128,0.0001288822,0.00109844,0.00007152552,0.0000732117,0.0004862389,0.0003269353,0.4925035,0.003637204,0.495629,0.005857283,0.00004446218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2067832,0.002312536,0.7688207,0.004163487,0.000174777,0.0002122409,0.000889545,0.0006937685,0.01594983],"genre_scores_gemma":[0.6520101,0.001482044,0.3336347,0.0005916049,0.0003442756,0.0003813179,0.00199925,0.0003410243,0.0092157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008719805,"threshold_uncertainty_score":0.02917063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1793987388","doi":"10.1186/s12859-015-0663-4","title":"Sealer: a scalable gap-closing application for finishing draft genomes","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Closing (real estate); Scalability; DNA microarray; Computer science; Genome; Computational biology; Biology; Genetics; Database; Business; Gene","authors":[{"name":"Daniel Paulino","is_ca":true},{"name":"René L. Warren","is_ca":true},{"name":"Benjamin P. Vandervalk","is_ca":true},{"name":"Anthony Raymond","is_ca":true},{"name":"Shaun D. Jackman","is_ca":true},{"name":"İnanç Birol","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04185362854053402,"gpt":0.2695208117224522,"spread":0.2276671831819182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003584241,0.002385608,0.001471543,0.00225538,0.001159384,0.002003895,0.002747876,0.001572903,0.02901225],"category_scores_gemma":[0.0133605,0.001565886,0.002200559,0.001647082,0.0007637954,0.003174286,0.003482994,0.002237842,0.01689234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007449527,"about_ca_system_score_gemma":0.00153587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001790193,"about_ca_topic_score_gemma":0.002084677,"domain_scores_codex":[0.9977403,0.0003439134,0.00025785,0.00067744,0.0008206951,0.0001597868],"domain_scores_gemma":[0.9953647,0.002393865,0.0004855419,0.000860031,0.0006253512,0.0002705709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002421126,0.0002642729,0.005372021,0.003969119,0.0005769114,0.001440881,0.00229174,0.0217245,0.07823249,0.008084456,0.3292931,0.5463294],"study_design_scores_gemma":[0.001107091,0.0009627846,0.006983161,0.0008189294,0.0002381223,0.002015693,0.0008167081,0.3286654,0.204523,0.02437579,0.4287521,0.0007411927],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.008691485,0.0005677408,0.3701465,0.0002104059,0.0002047454,0.0003197173,0.008305163,0.6089101,0.002644156],"genre_scores_gemma":[0.05840451,0.0006113591,0.8526796,0.0004428174,0.0001031054,0.000912967,0.03081064,0.05095035,0.005084733],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02901225,"threshold_uncertainty_score":0.09705567,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107815233","doi":"10.1186/1471-2105-9-101","title":"Prediction of mucin-type O-glycosylation sites in mammalian proteins using the composition of k-spaced amino acid pairs","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Program for New Century Excellent Talents in University; China Agricultural University; University of Alberta","keywords":"Glycosylation; Threonine; Computational biology; Serine; Encoding (memory); Binary classification; Support vector machine; Mucin; Computer science; Amino acid; Biology; Bioinformatics; Artificial intelligence; Biochemistry; Phosphorylation","authors":[{"name":"Yongzi Chen","is_ca":false},{"name":"Yurong Tang","is_ca":false},{"name":"Ziding Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05543503999968876,"gpt":0.2762255201344427,"spread":0.2207904801347539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004776603,0.000503995,0.0003848824,0.0007312232,0.0001840725,0.0003310403,0.0002722782,0.000362486,0.0004859195],"category_scores_gemma":[0.0007530416,0.0001187918,0.0006037114,0.0006265912,0.0001331295,0.0004169269,0.0002748849,0.0004801633,0.0003475421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002399729,"about_ca_system_score_gemma":0.0004361568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001306488,"about_ca_topic_score_gemma":0.001454679,"domain_scores_codex":[0.9998528,0.00002483299,0.00001601298,0.0000457197,0.00004396451,0.00001665198],"domain_scores_gemma":[0.9996777,0.0000692926,0.00009074415,0.00002415213,0.0001024239,0.00003581203],"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":[0.002420564,0.00067694,0.2349666,0.0007370454,0.0004467261,0.0006520445,0.0001209698,0.08993766,0.4462823,0.0007520893,0.005016906,0.2179901],"study_design_scores_gemma":[0.00004962079,0.0003877376,0.05217331,0.00003831777,0.0001119871,0.0004295725,0.00006542298,0.8791041,0.06528798,0.0005656427,0.001753043,0.00003340134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9448767,0.0008895042,0.05138383,0.00008120889,0.00003404496,0.00004718004,0.001183127,0.0008208416,0.0006836157],"genre_scores_gemma":[0.9178797,0.0005439649,0.0776354,0.00004275772,0.00001549963,0.00003697543,0.00336917,0.00003862595,0.0004378762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001306488,"threshold_uncertainty_score":0.002597749,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017229033","doi":"10.1186/1471-2105-9-226","title":"SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Structural alignment; Protein structure prediction; Computer science; Structural similarity; Similarity (geometry); Classifier (UML); Protein secondary structure; Structural Classification of Proteins database; Protein structure; Sequence alignment; Mathematics; Biology; Peptide sequence; Genetics","authors":[{"name":"Lukasz Kurgan","is_ca":true},{"name":"Krzysztof J. Cios","is_ca":false},{"name":"Ke Chen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01965501526011024,"gpt":0.243559004356052,"spread":0.2239039890959418,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009098896,0.001277412,0.0006621523,0.001488505,0.0004877079,0.0007631305,0.0008867887,0.0008027182,0.00353071],"category_scores_gemma":[0.002372068,0.0003099219,0.0008360601,0.0010132,0.0002396503,0.000908211,0.000533804,0.0008582106,0.002890836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004069329,"about_ca_system_score_gemma":0.0008104125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001415179,"about_ca_topic_score_gemma":0.002262158,"domain_scores_codex":[0.9993073,0.00008397484,0.00006361306,0.0002117723,0.0002706004,0.00006269848],"domain_scores_gemma":[0.9988128,0.0003703922,0.0002558028,0.0001472598,0.0003280344,0.00008575589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003121908,0.0009809083,0.1606772,0.001548928,0.0005712809,0.00117786,0.0001952406,0.04497714,0.1656798,0.001354506,0.08828839,0.5314268],"study_design_scores_gemma":[0.0001419341,0.0006992319,0.0381715,0.00009453414,0.00009431531,0.00101322,0.0001067689,0.8697292,0.07725751,0.001465468,0.01117567,0.000050732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6914071,0.001850881,0.2421167,0.0005638056,0.0001948997,0.000560361,0.02137296,0.03722912,0.004704076],"genre_scores_gemma":[0.6900648,0.0005480454,0.2575833,0.0002052841,0.0000842911,0.0005259846,0.04804214,0.0004976628,0.002448339],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00353071,"threshold_uncertainty_score":0.01181138,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1759632117","doi":"10.1186/1471-2105-5-24","title":"Biochemical Network Stochastic Simulator (BioNetS): software for stochastic modeling of biochemical networks","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Defense Advanced Research Projects Agency; Alfred P. Sloan Foundation","keywords":"Computer science; Software; Stochastic modelling; Simulation; Programming language; Mathematics; Statistics","authors":[{"name":"David Adalsteinsson","is_ca":false},{"name":"David R. McMillen","is_ca":true},{"name":"Timothy C. Elston","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01449411906631034,"gpt":0.2385294678884628,"spread":0.2240353488221525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001130643,0.001230264,0.0009002596,0.0007574348,0.0005132532,0.0009118228,0.002389461,0.001558877,0.01462912],"category_scores_gemma":[0.003648049,0.0009626082,0.00128351,0.0007436912,0.0005662946,0.001464544,0.001216923,0.001993223,0.003818016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009513833,"about_ca_system_score_gemma":0.002272828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005983202,"about_ca_topic_score_gemma":0.005694424,"domain_scores_codex":[0.9995765,0.0001178311,0.00004709302,0.00006490276,0.0001577944,0.00003597531],"domain_scores_gemma":[0.9984857,0.0008757886,0.0001405028,0.0001487075,0.0002556104,0.00009378025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001099353,0.00008915698,0.002105997,0.0006602526,0.0001423225,0.0001870892,0.0001586032,0.8875412,0.006451505,0.04544745,0.03023312,0.02687342],"study_design_scores_gemma":[0.0000458064,0.00001301724,0.0001483329,0.00002473494,0.00001178465,0.00005195675,0.000006720777,0.9736805,0.001893039,0.008227409,0.01587951,0.00001718959],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01101076,0.0003847245,0.9300786,0.0003198528,0.0001591385,0.0001833994,0.007042371,0.04341148,0.00740964],"genre_scores_gemma":[0.1940699,0.002042133,0.7515609,0.0005316566,0.0001359071,0.002637599,0.02221916,0.01449997,0.01230277],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01462912,"threshold_uncertainty_score":0.04893929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}