{"id":"W3199639770","doi":"10.1016/j.ajhg.2021.08.012","title":"Improved pathogenicity prediction for rare human missense variants","year":2021,"lang":"en","type":"article","venue":"The American Journal of Human Genetics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":183,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Lunenfeld-Tanenbaum Research Institute; Ontario Institute for Cancer Research; University of Toronto","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research","keywords":"Missense mutation; Pathogenicity; Inference; Computer science; Artificial intelligence; Machine learning; Annotation; Exploit; Limit (mathematics); Feature (linguistics); Personalized medicine; Computational biology; Data mining; Genetics; Biology; Mutation; Mathematics; Gene","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002106583,0.0001252149,0.0002022257,0.00002761912,0.0002280686,0.00003725813,0.0002460909,0.00003689548,0.00001120716],"category_scores_gemma":[0.00005222418,0.0000964042,0.000199728,0.00006436039,0.0001489013,0.000002027893,0.00007508619,0.00008800824,4.382374e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000135362,"about_ca_system_score_gemma":0.0001489242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003414472,"about_ca_topic_score_gemma":0.00001023413,"domain_scores_codex":[0.9990984,0.0001011604,0.0003381295,0.0001670661,0.0001072995,0.000188009],"domain_scores_gemma":[0.9987164,0.00001511203,0.0004289575,0.0003360876,0.0003969874,0.0001064408],"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":[0.0001069759,0.00008619204,0.0004564349,0.000007925276,0.0001470424,0.00002578167,0.00008039024,0.00009896451,0.9956807,0.00002112699,0.0009740031,0.002314389],"study_design_scores_gemma":[0.004214699,0.01303216,0.09291709,0.00007244436,0.001028057,0.002837263,0.003505197,0.000449818,0.8589697,0.002627278,0.01948083,0.0008654793],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965962,0.001441068,0.001447655,0.0001141665,0.0001389071,0.0001054211,0.000110052,0.000002969761,0.00004362905],"genre_scores_gemma":[0.9972661,0.0002596766,0.0011929,0.0003185085,0.0006881668,0.000003776466,0.00006392966,0.00002643022,0.00018056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1367111,"threshold_uncertainty_score":0.3931249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01106866392971394,"score_gpt":0.2631910648771735,"score_spread":0.2521224009474595,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}