{"id":"W2952646324","doi":"10.1093/bioinformatics/btx603","title":"Segway 2.0: Gaussian mixture models and minibatch training","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University of British Columbia","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; University Health Network","keywords":"Computer science; Scripting language; Annotation; Source code; Gaussian; Mixture model; Training set; Data mining; Code (set theory); Artificial intelligence; Machine learning; Pattern recognition (psychology); Set (abstract data type); Programming language","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":[0.0002348576,0.0001924372,0.0001803888,0.00003023315,0.0004388365,0.0002533727,0.0003561345,0.0002392751,0.000007669585],"category_scores_gemma":[0.00003802365,0.0001668562,0.00006699897,0.00001865545,0.0001573996,0.00003489371,0.000255589,0.0001225185,0.00001283042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006869657,"about_ca_system_score_gemma":0.00006154667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006657035,"about_ca_topic_score_gemma":0.00002050999,"domain_scores_codex":[0.9990915,0.000008147453,0.000326066,0.0001377185,0.0001178966,0.000318642],"domain_scores_gemma":[0.9988608,0.000006872975,0.000254533,0.000682687,0.00004220417,0.0001528823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002909162,0.0001449122,0.002438185,0.0009039276,0.0007194522,0.00001878023,0.02227751,0.001514463,0.008759579,0.02394808,0.1149197,0.8240645],"study_design_scores_gemma":[0.004423298,0.0007987828,0.004710239,0.0002612308,0.0001566048,0.000373843,0.005675697,0.569251,0.004967881,0.01265793,0.3943719,0.002351605],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4721867,0.00184079,0.1704135,0.002501659,0.001556035,0.001164828,0.0002344029,0.0001046401,0.3499975],"genre_scores_gemma":[0.9665604,0.0003631633,0.03063947,0.0006509816,0.0003052915,0.000009479609,0.00009828981,0.00002242587,0.001350444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8217129,"threshold_uncertainty_score":0.6804199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02396829629731378,"score_gpt":0.2503582734419982,"score_spread":0.2263899771446845,"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."}}