{"id":"W2555298751","doi":"10.1186/s12864-016-3281-2","title":"SNooPer: a machine learning-based method for somatic variant identification from low-pass next-generation sequencing","year":2016,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Université de Montréal; Terry Fox Research Institute; Canadian Institutes of Health Research; Terry Fox Foundation; Compute Canada","keywords":"Biology; DNA sequencing; Deep sequencing; Exome sequencing; Exome; Computational biology; Massive parallel sequencing; Concordance; Genome; Genetics; Computer science; Mutation; Gene","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000348603,0.0001721614,0.0001649029,0.00004234747,0.0001359677,0.00009280119,0.0001813089,0.0001445664,0.00002181939],"category_scores_gemma":[0.0004517969,0.0001494395,0.0001197798,0.0000430726,0.00002452209,0.000006768601,0.00005530113,0.00004639767,0.00002042106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001623515,"about_ca_system_score_gemma":0.0003961482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779889,"about_ca_topic_score_gemma":0.0009697054,"domain_scores_codex":[0.998818,0.00008525549,0.0003450287,0.0004482344,0.00008085809,0.00022261],"domain_scores_gemma":[0.9990501,0.0001501317,0.0002010863,0.0003986856,0.000120218,0.0000797401],"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":[0.0000701566,0.00002624299,0.0003453274,0.00002134549,0.00003182829,6.244294e-7,0.0000427904,0.01302684,0.9815733,0.00009854366,0.0002599976,0.004502943],"study_design_scores_gemma":[0.00126173,0.0001311692,0.0002450051,0.00001780053,0.00006913186,0.000003114878,0.00003130811,0.2393993,0.7465109,0.0004240229,0.01162493,0.0002816172],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3669778,0.0003529045,0.6317314,0.0001566884,0.000241167,0.0002846256,0.0002305256,0.00001268344,0.00001221737],"genre_scores_gemma":[0.9050056,0.000199793,0.09194404,0.0003215735,0.0008339533,0.0001325372,0.001198393,0.00005823317,0.0003058319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5397874,"threshold_uncertainty_score":0.6093968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04016280255660809,"score_gpt":0.2683695990611045,"score_spread":0.2282067965044964,"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."}}