{"id":"W4319748040","doi":"10.1186/s12859-023-05141-2","title":"Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data","year":2023,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Institute of General Medical Sciences; Intellectual and Developmental Disabilities Research Center; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of Pennsylvania","keywords":"Interpretability; Leverage (statistics); Computer science; Machine learning; Artificial intelligence; Annotation; Labeled data; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005759823,0.00177202,0.000918054,0.0008306867,0.000544053,0.0009224144,0.001483068,0.001305125,0.001593594],"category_scores_gemma":[0.01215917,0.0004224537,0.0009464343,0.0003220337,0.0014505,0.001213784,0.001276855,0.002263567,0.0003768282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00167167,"about_ca_system_score_gemma":0.001185186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009646139,"about_ca_topic_score_gemma":0.008145578,"domain_scores_codex":[0.9987262,0.0006798915,0.000056363,0.0002768892,0.0001551372,0.0001056194],"domain_scores_gemma":[0.9883128,0.009687765,0.000498568,0.0004652677,0.0007980547,0.0002375057],"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":[0.0001016911,0.00004053295,0.001977366,0.00002541511,0.00003257364,0.00003333771,0.00002902633,0.9857755,0.0003123167,0.00165043,0.0005919044,0.009429965],"study_design_scores_gemma":[0.000002134171,0.000008741928,0.00008750115,0.000003462411,0.000002561321,0.000004028682,0.000001957582,0.9988488,0.0001255764,0.0008881826,0.000024897,0.000002252016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.4141837,0.001675812,0.5718705,0.002589468,0.0002642976,0.0002522253,0.0009335827,0.001810618,0.006419875],"genre_scores_gemma":[0.9646501,0.0002017831,0.03104602,0.0004049296,0.00006300474,0.0001239216,0.001076621,0.00007331408,0.002360292],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009646139,"threshold_uncertainty_score":0.03046119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06189355387424046,"score_gpt":0.3003453905127546,"score_spread":0.2384518366385141,"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."}}