{"id":"W4283659942","doi":"10.1093/bioinformatics/btac420","title":"Improving candidate Biosynthetic Gene Clusters in fungi through reinforcement learning","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Université du Québec à Montréal","keywords":"Candidate gene; Aspergillus nidulans; Computer science; Task (project management); Reinforcement learning; Genome; Computational biology; Gene; Artificial intelligence; Biology; Genetics; Engineering","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":[0.0004578899,0.0002132067,0.0001904788,0.00009304909,0.0003088471,0.00005268178,0.0003257167,0.00009712591,0.00007560088],"category_scores_gemma":[0.00002561489,0.0002186662,0.00009572523,0.0001929968,0.00004967698,0.00001920584,0.0006425088,0.0003073637,0.00002267193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056685,"about_ca_system_score_gemma":0.0001178934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007179334,"about_ca_topic_score_gemma":0.00002676056,"domain_scores_codex":[0.9984319,0.00004431903,0.0006304837,0.0001732628,0.0002449407,0.0004751416],"domain_scores_gemma":[0.9992306,0.00001225908,0.0002828656,0.0003723667,0.00002786742,0.00007399404],"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":[0.0004884489,0.0001753811,0.00302698,0.000441369,0.0002310846,0.00002261443,0.008186378,0.8571467,0.03764211,0.0009825184,0.008921837,0.08273461],"study_design_scores_gemma":[0.002635068,0.001078882,0.00018314,0.00003393156,0.00004468329,0.0001410834,0.005933264,0.8214869,0.01138004,0.000120035,0.1558975,0.001065431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7340065,0.002513899,0.2284261,0.0004602382,0.001983875,0.00207647,0.0001100901,0.0001447707,0.03027807],"genre_scores_gemma":[0.9901941,0.0002303884,0.007199204,0.0009549136,0.00009316472,0.00006044911,0.0004854079,0.00002868393,0.0007536373],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2561876,"threshold_uncertainty_score":0.891695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007802561118249228,"score_gpt":0.2136643489196424,"score_spread":0.2058617878013932,"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."}}