{"id":"W2112005039","doi":"10.1093/bioinformatics/btr629","title":"Feature-based classifiers for somatic mutation detection in tumour–normal paired sequencing data","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":154,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Computer science; Discriminative model; Artificial intelligence; Feature selection; Random forest; Machine learning; Ground truth; Genome; Support vector machine; Germline mutation; Cluster analysis; Computational biology; Mutation; Data mining; Biology; Genetics; 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":[0.0002628832,0.0001252977,0.000113003,0.00007801211,0.00006525665,0.00003069779,0.0002295003,0.0001366358,0.000003210794],"category_scores_gemma":[0.0002496847,0.0001281869,0.00004549788,0.00008741774,0.00003425207,0.0000202557,0.00007252151,0.00006313594,0.000004827749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006792189,"about_ca_system_score_gemma":0.0002218767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004035013,"about_ca_topic_score_gemma":0.0004359738,"domain_scores_codex":[0.9992644,0.00001406781,0.0002606508,0.0001567245,0.00008413594,0.0002200746],"domain_scores_gemma":[0.9992932,0.0000289881,0.0001516353,0.0004104714,0.00005747013,0.00005820491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003167361,0.0007327702,0.01208896,0.003843672,0.0004728351,0.00005118383,0.008499238,0.01009753,0.6257664,0.001090972,0.03013618,0.3040529],"study_design_scores_gemma":[0.002594074,0.0006410272,0.003372447,0.00007121773,0.00006974134,0.00002404146,0.001322941,0.5670371,0.4171394,0.00028537,0.006924656,0.0005179844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5420939,0.0001910564,0.4543119,0.0001174941,0.0005868137,0.0009694942,0.000328673,0.00003957863,0.00136111],"genre_scores_gemma":[0.9498287,0.00002595702,0.04873109,0.0002923361,0.00009706298,0.00004232724,0.0009375253,0.00001814861,0.00002685076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5569395,"threshold_uncertainty_score":0.5227309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04724989446934112,"score_gpt":0.2508523294330022,"score_spread":0.2036024349636611,"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."}}