{"id":"W4225839207","doi":"10.1093/bioinformatics/btac259","title":"PhyloPGM: boosting regulatory function prediction accuracy using evolutionary information","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computational biology; Computer science; Boosting (machine learning); Context (archaeology); Probabilistic logic; Sequence (biology); Function (biology); Data mining; Extant taxon; Genomics; DNA binding site; Gene regulatory network; Machine learning; Biology; Genome; Gene; Artificial intelligence; Genetics; Gene expression; Evolutionary biology; Promoter","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000216709,0.0001308894,0.00008559242,0.00009315233,0.0005273294,0.00004306031,0.0001546263,0.00007878606,0.00004125396],"category_scores_gemma":[0.00006495061,0.0001500307,0.00007158219,0.0001318771,0.00003072929,0.00005494289,0.0002798961,0.0001248623,0.00001278162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001348241,"about_ca_system_score_gemma":0.0001602702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007619914,"about_ca_topic_score_gemma":8.582103e-7,"domain_scores_codex":[0.9989744,0.00003000918,0.0004377305,0.00009878946,0.0002575432,0.0002015172],"domain_scores_gemma":[0.9992531,0.000008878655,0.000307148,0.0002899486,0.00008812875,0.00005279128],"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":[0.0007560124,0.0003982261,0.02382181,0.000788525,0.0005215418,0.000002933986,0.003529772,0.6119614,0.2020269,0.003747083,0.0743661,0.07807973],"study_design_scores_gemma":[0.0008723298,0.0004457808,0.01438028,0.00001419407,0.0000560118,0.0001405979,0.002529178,0.8346618,0.001105396,0.0002425671,0.1451521,0.0003998275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9706963,0.0001439743,0.02587567,0.00002816992,0.000720924,0.0002906686,0.0002233166,0.00004942601,0.001971533],"genre_scores_gemma":[0.9866652,0.00002773395,0.01065863,0.0003862347,0.0001789734,0.00002972451,0.001945064,0.00001629007,0.00009213413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2227004,"threshold_uncertainty_score":0.6118076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008650630458668988,"score_gpt":0.2058492327359707,"score_spread":0.1971986022773017,"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."}}