{"id":"W2938712064","doi":"10.1093/bioinformatics/btz266","title":"Discovering novel mutation signatures by latent Dirichlet allocation with variational Bayes inference","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Japan Society for the Promotion of Science; Waseda University; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Mutation; Latent Dirichlet allocation; Computer science; Cluster analysis; Bayes' theorem; Inference; Mutation rate; Genetics; Computational biology; Biology; Bayesian probability; Artificial intelligence; Topic model; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005547988,0.001667194,0.002494041,0.002782999,0.001381201,0.002430372,0.003721677,0.00266097,0.003681595],"category_scores_gemma":[0.01307843,0.001885694,0.003625873,0.001731681,0.001937815,0.002469188,0.002500675,0.003722246,0.0008814331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00211486,"about_ca_system_score_gemma":0.002768083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01352469,"about_ca_topic_score_gemma":0.01361359,"domain_scores_codex":[0.9967992,0.001405418,0.0001480472,0.0008661385,0.0004881394,0.0002929319],"domain_scores_gemma":[0.9929717,0.00565851,0.0003507016,0.0003066088,0.0004855039,0.000226932],"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":[0.0002794496,0.0001493458,0.007061665,0.0003756541,0.0003134791,0.000270897,0.0003650748,0.8296967,0.003282365,0.0546005,0.005812748,0.09779206],"study_design_scores_gemma":[0.00001276881,0.000005044576,0.000122224,0.00001396595,0.00001399584,0.00002230608,0.00001281656,0.978519,0.0003420024,0.02045075,0.0004724814,0.00001265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01021532,0.000320584,0.9877551,0.0003192869,0.00003783006,0.00007598411,0.0002410352,0.0004797633,0.000555081],"genre_scores_gemma":[0.2900614,0.0006341395,0.7010685,0.0005615644,0.0002323093,0.0005983551,0.002658691,0.0006065911,0.003578522],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01352469,"threshold_uncertainty_score":0.02934092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005256585999953559,"score_gpt":0.2151006418825204,"score_spread":0.2098440558825668,"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."}}