{"id":"W4229072282","doi":"10.1126/sciadv.abj1624","title":"CancerVar: An artificial intelligence–empowered platform for clinical interpretation of somatic mutations in cancer","year":2022,"lang":"en","type":"article","venue":"Science Advances","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences","keywords":"Somatic cell; Computer science; Consistency (knowledge bases); Artificial intelligence; Machine learning; Germline mutation; Computational biology; Bioinformatics; Mutation; Biology; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0005747816,0.0000682688,0.0001196186,0.00008506581,0.0001612412,0.00001773464,0.0003099347,0.00002253549,0.00002988612],"category_scores_gemma":[0.0002461381,0.00007153785,0.00004822635,0.0002638671,0.000307884,0.00002830865,0.00009002578,0.00005783694,4.18479e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000665543,"about_ca_system_score_gemma":0.0005696448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001068647,"about_ca_topic_score_gemma":0.001936199,"domain_scores_codex":[0.9989702,0.00001958434,0.0003709421,0.0003023661,0.0001580113,0.0001789206],"domain_scores_gemma":[0.9994618,0.00006666662,0.0001575041,0.0001768478,0.0000867464,0.00005039423],"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":[0.0005956346,0.0004524298,0.01193235,0.00005188252,0.00001695799,0.000001135339,0.001902501,0.1851472,0.195919,0.002818165,0.00006107777,0.6011016],"study_design_scores_gemma":[0.001219147,0.006354924,0.010506,0.00008467757,0.00006983003,0.000009177386,0.02128289,0.1370109,0.7168505,0.0871145,0.01846072,0.001036741],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879057,0.001169892,0.009451466,0.00009493885,0.0008435231,0.0002958598,0.0001527994,0.000003900486,0.00008195916],"genre_scores_gemma":[0.9968512,0.000269314,0.002384499,0.000118901,0.00009174679,0.0002160501,0.0000499321,0.000006569768,0.00001175578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6000649,"threshold_uncertainty_score":0.2917229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0513542110605231,"score_gpt":0.4123568745778924,"score_spread":0.3610026635173693,"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."}}