{"id":"W4226151130","doi":"10.1016/j.xgen.2022.100128","title":"Benchmarking challenging small variants with linked and long reads","year":2022,"lang":"en","type":"article","venue":"Cell Genomics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":209,"is_retracted":false,"has_abstract":true,"ca_institutions":"Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Standards and Technology; National Institutes of Health; German Network for Bioinformatics Infrastructure; National Human Genome Research Institute; Bundesministerium für Bildung und Forschung; U.S. National Library of Medicine; Deutsche Forschungsgemeinschaft","keywords":"Benchmarking; Indel; False positive paradox; Computational biology; Computer science; Benchmark (surveying); False positives and false negatives; Genome; Biology; Data mining; Genetics; Artificial intelligence; 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":[0.0001121175,0.0001247379,0.00009823023,0.00003429285,0.0002663589,0.00002875839,0.0001426502,0.00004437913,0.00002661477],"category_scores_gemma":[0.000003242169,0.0001269055,0.00003670917,0.00004064518,0.00003086575,0.000001289436,0.000291858,0.00009194831,0.000001379899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002369647,"about_ca_system_score_gemma":0.00008050189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001065714,"about_ca_topic_score_gemma":0.00001471944,"domain_scores_codex":[0.9992654,0.00002854567,0.0001095731,0.0003283082,0.00005629777,0.0002118985],"domain_scores_gemma":[0.9995865,0.000006888074,0.00006177343,0.0002372723,0.00002127762,0.00008625212],"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":[0.000618029,0.0003982254,0.02114133,0.0001776378,0.0002712748,0.0003701788,0.001342733,0.01870384,0.939852,0.0002971092,0.0006135502,0.01621412],"study_design_scores_gemma":[0.01738418,0.009236498,0.2305726,0.0001159797,0.001052316,0.003592286,0.01295987,0.02179225,0.1097441,0.001073319,0.5844662,0.008010457],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944412,0.002757222,0.001040108,0.00003644153,0.0001246744,0.0001364735,0.00002724327,0.000008304743,0.00142833],"genre_scores_gemma":[0.9972473,0.0005866434,0.001162939,0.000195751,0.0001768044,0.00002018415,0.0001737917,0.00003286251,0.00040373],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8301079,"threshold_uncertainty_score":0.5175056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007597151974323766,"score_gpt":0.1813223733136201,"score_spread":0.1737252213392963,"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."}}