{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02367646,0.002402471,0.002121251,0.007611792,0.002168579,0.007552704,0.004557721,0.003294357,0.004809421],"category_scores_gemma":[0.1147157,0.001454541,0.002936776,0.007034595,0.001156155,0.003094301,0.003660822,0.002579944,0.003721792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00171138,"about_ca_system_score_gemma":0.00359997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01136754,"about_ca_topic_score_gemma":0.01763267,"domain_scores_codex":[0.9699233,0.01248983,0.004352473,0.005401257,0.006537114,0.001296103],"domain_scores_gemma":[0.9487453,0.02511791,0.001989555,0.01540412,0.007615908,0.00112726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003561604,0.0008330955,0.0603623,0.004654115,0.005725839,0.001506326,0.00275708,0.1461494,0.07035961,0.01923218,0.06458977,0.6202686],"study_design_scores_gemma":[0.0009611684,0.001026497,0.04312903,0.001474885,0.001637318,0.00238949,0.0016042,0.6025429,0.180158,0.08339002,0.08083235,0.0008539895],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.110801,0.00464791,0.7182483,0.001180047,0.0007369577,0.0007987944,0.02345779,0.1317528,0.008376372],"genre_scores_gemma":[0.2287962,0.000822153,0.7247955,0.0005102109,0.00009231085,0.0006348412,0.03249842,0.01054585,0.001304487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02367646,"threshold_uncertainty_score":0.1252146,"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."}}