{"id":"W2802080790","doi":"10.1038/s41598-018-25022-6","title":"DNAp: A Pipeline for DNA-seq Data Analysis","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institute of General Medical Sciences; U.S. National Library of Medicine; U.S. Food and Drug Administration; Hamilton Health Sciences Foundation; National Science Foundation","keywords":"Pipeline (software); Computer science; Documentation; Exome sequencing; Software; DNA sequencing; Exome; Computational biology; Data mining; Mutation; Biology; Genetics; DNA; Gene; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009073289,0.0001003776,0.0001392391,0.00009383961,0.0002017602,0.0001552238,0.0003001655,0.00006874901,0.00006362229],"category_scores_gemma":[0.0005176462,0.00009528917,0.0001122919,0.0003561327,0.0002209144,0.000004394629,0.0003236315,0.00002329788,0.00001003203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000107176,"about_ca_system_score_gemma":0.0001971333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000026916,"about_ca_topic_score_gemma":0.000695536,"domain_scores_codex":[0.9983601,0.000009924287,0.0003027687,0.0009415691,0.0001502218,0.0002354253],"domain_scores_gemma":[0.9972034,0.00001313704,0.0001638413,0.002246393,0.0002772417,0.0000959991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004699569,0.00009499338,0.004747584,0.00001293395,0.0002800103,0.00002331465,0.00004835597,0.00008069284,0.3086778,0.0000625658,0.6795262,0.006398659],"study_design_scores_gemma":[0.0001261097,0.00005572346,0.0003204004,0.000002673827,0.0002228469,0.00002065488,0.00001645114,0.002315491,0.132266,0.00100356,0.8634977,0.0001523181],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8184552,0.001133082,0.163016,0.0005229783,0.01205231,0.0007243273,0.0005334027,0.00003724461,0.003525373],"genre_scores_gemma":[0.9827575,0.00002079256,0.003769736,0.0001886061,0.0009876849,0.00002034361,0.004685713,0.00001678221,0.007552854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1839716,"threshold_uncertainty_score":0.388578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02573596516031558,"score_gpt":0.3005871940490115,"score_spread":0.274851228888696,"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."}}