{"id":"W4389525196","doi":"10.1093/molbev/msad270","title":"A Fast, Reproducible, High-throughput Variant Calling Workflow for Population Genomics","year":2023,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University","funders":"Division of Biological Infrastructure; FAS Division of Science, Harvard University; Harvard University; National Science Foundation","keywords":"Workflow; Biology; Genomics; Reuse; Pipeline (software); Population; Flexibility (engineering); Population genomics; Cloud computing; Computer science; Genome; Computational biology; Data mining; Data science; Database; Genetics; Gene; Ecology","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":[0.0003162364,0.0001484874,0.000157119,0.00006416391,0.0002045936,0.00001261523,0.00008188457,0.0002109525,9.466325e-7],"category_scores_gemma":[0.00009698317,0.0001490252,0.00006942492,0.0001206905,0.00006520768,0.00000105394,0.0001191501,0.00005058459,0.000004848589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000193425,"about_ca_system_score_gemma":0.00002907986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009548695,"about_ca_topic_score_gemma":0.0000329608,"domain_scores_codex":[0.9988577,0.00005298814,0.0001937502,0.0005692787,0.00003598262,0.0002902551],"domain_scores_gemma":[0.9995182,0.00001428054,0.00006936106,0.0002907616,0.00006333774,0.00004410473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001071419,0.00001897161,0.0121423,0.00002172185,0.0001184445,0.000002445524,0.00003736207,0.00265695,0.9720933,0.00848477,0.0003435478,0.00397304],"study_design_scores_gemma":[0.00452468,0.002413581,0.5714398,0.00006079679,0.0003720363,0.0001214206,0.0002340575,0.01193565,0.156481,0.2040683,0.04633743,0.002011222],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9025405,0.001848981,0.09458128,0.0003001493,0.0003302237,0.0002944579,0.00004953134,0.00001597397,0.00003888266],"genre_scores_gemma":[0.9905686,0.0004524259,0.007737055,0.0001261941,0.0002925249,0.00007510764,0.000586841,0.00002231374,0.0001388938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8156123,"threshold_uncertainty_score":0.6077072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01095052351500947,"score_gpt":0.2587298556143819,"score_spread":0.2477793320993724,"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."}}