{"id":"W4283210431","doi":"10.1016/j.xgen.2022.100129","title":"PrecisionFDA Truth Challenge V2: Calling variants from short and long reads in difficult-to-map regions","year":2022,"lang":"en","type":"article","venue":"Cell Genomics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":204,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Genomics","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Benchmarking; Nanopore sequencing; Computer science; Benchmark (surveying); Computational biology; Identification (biology); Genome; DNA sequencing; Data science; Artificial intelligence; Biology; Genetics; Gene; Geography; Cartography","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":[0.04392611,0.004818202,0.003555084,0.003816239,0.004439214,0.00819312,0.007418159,0.00834535,0.01333474],"category_scores_gemma":[0.1111488,0.002122135,0.004248051,0.004085504,0.002571601,0.003494987,0.01172574,0.006327573,0.01118142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002203032,"about_ca_system_score_gemma":0.007195061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01038345,"about_ca_topic_score_gemma":0.0180131,"domain_scores_codex":[0.9690579,0.01012464,0.002478016,0.009046336,0.007029743,0.002263282],"domain_scores_gemma":[0.937333,0.0322512,0.001952125,0.01163341,0.01353738,0.003292906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006350208,0.0009244967,0.03936294,0.008293361,0.003189573,0.001727858,0.004017158,0.03601727,0.05400783,0.0105581,0.6048459,0.2307052],"study_design_scores_gemma":[0.00321033,0.002717403,0.04104403,0.002119289,0.001370744,0.005338766,0.00194403,0.1187572,0.1091423,0.03816588,0.6745455,0.001644598],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2314503,0.01803118,0.3221514,0.008631055,0.01269883,0.006071588,0.262985,0.1039332,0.0340475],"genre_scores_gemma":[0.1837672,0.001695012,0.2941593,0.006087558,0.001195761,0.004814812,0.4617015,0.03112814,0.01545074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04392611,"threshold_uncertainty_score":0.2323062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01232994171129741,"score_gpt":0.2208601175525669,"score_spread":0.2085301758412695,"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."}}