{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001178742,0.0001586186,0.0001612119,0.00005872593,0.0001600099,0.00003012099,0.0002474641,0.00008422083,0.00003247161],"category_scores_gemma":[0.0000242065,0.0001706973,0.0000570131,0.00007377991,0.00002500911,0.000002282821,0.0004693433,0.0001255463,0.000006330653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005163451,"about_ca_system_score_gemma":0.00008903689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004585204,"about_ca_topic_score_gemma":0.00006325502,"domain_scores_codex":[0.9988691,0.00005268905,0.0002185107,0.0005188904,0.00009194366,0.000248858],"domain_scores_gemma":[0.9993637,0.0000270747,0.00004149059,0.0003805412,0.00002845857,0.0001587233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001178288,0.001746796,0.0157691,0.00009609932,0.0002415716,0.0005774157,0.003888586,0.02485361,0.9310581,0.0005507999,0.006042494,0.0139971],"study_design_scores_gemma":[0.007864157,0.002759087,0.2021969,0.0001238702,0.0004158234,0.0001906975,0.009651045,0.00698863,0.05433422,0.003995361,0.7063837,0.005096436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944068,0.003732051,0.0006382695,0.0001269686,0.0002937825,0.0002478098,0.0002193831,0.000008055235,0.0003269404],"genre_scores_gemma":[0.9971895,0.0009521862,0.0006541459,0.0002242,0.0001711048,0.0000479595,0.0004622086,0.00003608526,0.0002626074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8767239,"threshold_uncertainty_score":0.6960835,"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."}}