{"id":"W2951331911","doi":"10.1038/s41587-019-0054-x","title":"Best practices for benchmarking germline small-variant calls in human genomes","year":2019,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":503,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Benchmarking; Context (archaeology); Concordance; Computer science; Best practice; Genomics; Set (abstract data type); Genome; Data science; Data mining; Computational biology; Biology; Bioinformatics; Genetics; 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":[0.0002296685,0.0001868853,0.0002391199,0.0001288165,0.00007173567,0.00001543922,0.0003232116,0.00124588,0.00001151078],"category_scores_gemma":[0.0001369266,0.0001764578,0.00007939903,0.000117743,0.00007324688,9.115807e-7,0.0002238152,0.000377575,0.00000597295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002133432,"about_ca_system_score_gemma":0.00004831518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007882614,"about_ca_topic_score_gemma":0.0006643714,"domain_scores_codex":[0.9988033,0.00002339574,0.0002295267,0.0005463831,0.00005658958,0.0003408642],"domain_scores_gemma":[0.9992067,0.00003518739,0.0002304335,0.0004317283,0.0000669369,0.00002898317],"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":[0.00005028206,0.00007327245,0.004577179,0.00003510933,0.00007588688,0.000005537992,0.00002504043,0.00002512442,0.9855112,0.002884314,0.0001911606,0.006545938],"study_design_scores_gemma":[0.001566047,0.001308884,0.004832997,0.00002939715,0.00004294595,0.00005088843,0.0002050213,0.0001072389,0.3676848,0.0009345482,0.6227347,0.0005025298],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837567,0.01296207,0.0001284038,0.001427139,0.0004139247,0.0005344936,0.00003282048,0.000009608624,0.0007348995],"genre_scores_gemma":[0.9921886,0.00116909,0.005299462,0.0003285195,0.000295723,0.00004814217,0.0000728243,0.00002550539,0.0005721525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6225435,"threshold_uncertainty_score":0.9609365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01563068847371022,"score_gpt":0.288926172505657,"score_spread":0.2732954840319468,"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."}}