{"id":"W3034581902","doi":"10.1038/s41587-020-0538-8","title":"A robust benchmark for detection of germline large deletions and insertions","year":2020,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":483,"is_retracted":false,"has_abstract":false,"ca_institutions":"Genome British Columbia; Centre Hospitalier Universitaire Sainte-Justine; Ontario Institute for Cancer Research","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; National Institute of Standards and Technology; U.S. National Library of Medicine; U.S. Food and Drug Administration; U.S. Department of Health and Human Services; National Institutes of Health; U.S. Department of Commerce","keywords":"Benchmark (surveying); False positive paradox; Computational biology; Genome; Germline; Biology; Human genome; Set (abstract data type); Genetics; Computer science; Structural variation; Sequence (biology); 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":[0.0000475231,0.00008339513,0.0001157554,0.00003869316,0.00007579916,0.000002742446,0.00008353905,0.0005714061,0.000001737481],"category_scores_gemma":[0.0001768586,0.00008049382,0.00004893487,0.0001001157,0.00007505871,3.717237e-7,0.00009881725,0.0001437797,3.39832e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003184339,"about_ca_system_score_gemma":0.00001575676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002664315,"about_ca_topic_score_gemma":0.00005006625,"domain_scores_codex":[0.9994841,0.000008573721,0.0001198602,0.000232092,0.00002806859,0.0001273282],"domain_scores_gemma":[0.9997054,0.00001005746,0.00005387096,0.0001315898,0.0000692389,0.0000298867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004519568,0.00002130309,0.0002651684,0.00001898222,0.00004507149,1.632732e-7,0.00002383133,0.00001176031,0.9963786,0.001036536,0.0003425481,0.001810846],"study_design_scores_gemma":[0.0005821296,0.0006121087,0.003120076,0.000003150014,0.00003278481,0.000007666957,0.00008595033,0.0003299522,0.8299796,0.000299905,0.1648287,0.0001180256],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9701898,0.006738849,0.01826658,0.004315021,0.00008865182,0.0002177539,0.0001422848,0.00001005804,0.00003102874],"genre_scores_gemma":[0.99512,0.0007594772,0.003468474,0.0004727303,0.0001008666,0.00002522085,0.00003454494,0.000009381378,0.000009327791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.166399,"threshold_uncertainty_score":0.4407207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101585750646057,"score_gpt":0.2244963837058896,"score_spread":0.2143378086412839,"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."}}