{"id":"W2948452166","doi":"10.1101/664623","title":"A robust benchmark for germline structural variant detection","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Centre Hospitalier Universitaire Sainte-Justine; Ontario Institute for Cancer Research","funders":"U.S. National Library of Medicine; National Human Genome Research Institute; National Institute of Standards and Technology; National Institutes of Health","keywords":"Benchmark (surveying); False positive paradox; Structural variation; Concordance; Computational biology; Set (abstract data type); Computer science; Biology; 1000 Genomes Project; Genetics; Genome; Data mining; Artificial intelligence; Genotype; Gene; Single-nucleotide polymorphism","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002998096,0.0004981281,0.0004387828,0.00009199565,0.0001737442,0.00009937747,0.0004008281,0.0005988484,0.000009606986],"category_scores_gemma":[0.0001315434,0.0005183206,0.0002575189,0.0000993914,0.00007052013,0.000001645621,0.0005453359,0.0002668419,0.000007899058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006890311,"about_ca_system_score_gemma":0.0002924049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000284293,"about_ca_topic_score_gemma":0.00000991298,"domain_scores_codex":[0.9978693,0.00005546269,0.0004035629,0.001038508,0.0001531224,0.0004800524],"domain_scores_gemma":[0.998058,0.00002332454,0.0003175521,0.00104107,0.0004300645,0.0001299915],"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":[0.00008647322,0.00002593547,0.001209488,0.0002164588,0.0003067287,0.00000308164,0.000004102554,0.001860881,0.9960018,0.00005837246,0.000220361,0.00000629405],"study_design_scores_gemma":[0.001247627,0.0003876743,0.08042993,0.00009390641,0.0002621397,1.01239e-7,0.000003121296,0.003083589,0.8913537,0.00001518214,0.02179525,0.001327751],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9806478,0.002657427,0.01252909,0.00006755676,0.002344625,0.001102631,0.0006160891,0.000025851,0.000008939862],"genre_scores_gemma":[0.9901598,0.0003444371,0.007631041,0.0001378024,0.001337447,0.0002594415,0.000003390426,0.0001106543,0.00001599024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1046481,"threshold_uncertainty_score":0.9997268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01349212029323562,"score_gpt":0.2103841555244128,"score_spread":0.1968920352311771,"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."}}