{"id":"W3112031261","doi":"10.1126/sciadv.abe3722","title":"Integration of intra-sample contextual error modeling for improved detection of somatic mutations from deep sequencing","year":2020,"lang":"en","type":"article","venue":"Science Advances","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Terry Fox Foundation; Wellcome Trust; Genome Canada","keywords":"Somatic cell; Deep sequencing; Computational biology; Sample (material); DNA sequencing; Computer science; Genetics; Artificial intelligence; Biology; DNA; Gene; Genome; Chromatography; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005097412,0.00123986,0.0009412958,0.0006507009,0.0003260703,0.0009464154,0.001371708,0.000838616,0.0006535608],"category_scores_gemma":[0.009911115,0.0005119677,0.0009605121,0.0005279703,0.000589352,0.001037688,0.001512436,0.001559444,0.0002253639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005862986,"about_ca_system_score_gemma":0.001465088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003498864,"about_ca_topic_score_gemma":0.008587345,"domain_scores_codex":[0.9985963,0.0005076447,0.00008732149,0.0003738649,0.0003364882,0.00009828404],"domain_scores_gemma":[0.9959002,0.00260274,0.0004162262,0.0004773901,0.0004797689,0.0001236164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006017498,0.0001557528,0.01929851,0.0002924275,0.000364445,0.0003016688,0.0003237001,0.7341411,0.03606217,0.009670359,0.001789946,0.1969982],"study_design_scores_gemma":[0.000007579908,0.00004310744,0.001053667,0.0000106399,0.00002567453,0.00004579425,0.00001030036,0.9896986,0.005240462,0.003122066,0.0007244881,0.00001773153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03399295,0.0003501312,0.9639527,0.0001404304,0.0000406848,0.00003431844,0.0001401518,0.0009786923,0.0003699476],"genre_scores_gemma":[0.5424499,0.000480845,0.4534712,0.000370826,0.0000842573,0.0002075227,0.001033322,0.0004999047,0.001402326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005097412,"threshold_uncertainty_score":0.02695799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02619011589609421,"score_gpt":0.2881327197457373,"score_spread":0.2619426038496431,"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."}}