{"id":"W3136596816","doi":"10.1101/2021.03.18.21253763","title":"A scalable EHR-based approach for phenotype discovery and variant interpretation for hereditary cancer genes","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"U.S. National Library of Medicine; National Human Genome Research Institute","keywords":"Phenome; Phenotype; Pathogenicity; Gene; Computational biology; Genetics; Biology; Disease; Bioinformatics; Medicine; Internal medicine","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":[0.006557247,0.001321347,0.001653684,0.005902993,0.0005621274,0.002797566,0.001799205,0.001098076,0.007427581],"category_scores_gemma":[0.02258472,0.0007368469,0.001500306,0.004641982,0.0003313077,0.001451894,0.003569861,0.0012091,0.004384932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007522291,"about_ca_system_score_gemma":0.001993761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006882549,"about_ca_topic_score_gemma":0.01079547,"domain_scores_codex":[0.9957365,0.001463325,0.0004131607,0.001149154,0.001064645,0.0001731381],"domain_scores_gemma":[0.9904034,0.004562884,0.0006938235,0.002560665,0.001234354,0.0005448335],"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":[0.002586765,0.0008263469,0.1111018,0.001222258,0.001942198,0.002736632,0.0006353544,0.04054449,0.01374946,0.01331329,0.1889448,0.6223966],"study_design_scores_gemma":[0.001225491,0.0002803045,0.03176122,0.0002538946,0.0004822693,0.001272953,0.0005817873,0.8046928,0.009348822,0.0795149,0.0703956,0.0001899774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04909137,0.002548893,0.7326047,0.004599455,0.0004818777,0.001351486,0.08958632,0.1118441,0.007891918],"genre_scores_gemma":[0.2833496,0.001075268,0.6250165,0.001149114,0.0004321832,0.0008448982,0.08386359,0.001757534,0.002511279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007427581,"threshold_uncertainty_score":0.0346784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01418390314579064,"score_gpt":0.2569781154206166,"score_spread":0.242794212274826,"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."}}