{"id":"W4311556529","doi":"10.1371/journal.pcbi.1010779","title":"Genome-wide identification and characterization of DNA enhancers with a stacked multivariate fusion framework","year":2022,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Enhancer; Computational biology; Interpretability; Sequence motif; Computer science; Classifier (UML); Artificial intelligence; Biology; Genetics; Gene; Transcription factor","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":[0.00008848406,0.00008441143,0.0001069801,0.00004886517,0.000119598,0.000008004195,0.00009328834,0.00005513746,0.00002836855],"category_scores_gemma":[0.00002418545,0.00008365064,0.00002040482,0.00007883665,0.00006662087,0.000002775169,0.0001247793,0.00006241493,0.000001046848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001940146,"about_ca_system_score_gemma":0.00005628143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003468525,"about_ca_topic_score_gemma":0.000001464284,"domain_scores_codex":[0.9993101,0.00007717336,0.000197272,0.0002418048,0.0000778644,0.00009576787],"domain_scores_gemma":[0.9995409,0.0000325755,0.0001998615,0.0001113574,0.00008930333,0.00002598453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001056768,0.00006823451,0.005415755,0.00001503816,0.00005800964,3.08881e-7,0.000150844,0.003921722,0.9892133,0.0007567098,0.00000135954,0.0002930068],"study_design_scores_gemma":[0.001789312,0.001854879,0.7937133,0.00002521375,0.00008048314,0.0000302399,0.0003237723,0.05199993,0.1375116,0.01035373,0.001687443,0.0006300267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9401794,0.00003870234,0.05925694,0.0001293081,0.00004831143,0.000173268,0.0001511182,0.00000654412,0.00001642601],"genre_scores_gemma":[0.9922812,0.00002833508,0.003980555,0.000116741,0.00003089774,0.00004043282,0.003480094,0.00001222759,0.00002952642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8517017,"threshold_uncertainty_score":0.3411174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006543573522402382,"score_gpt":0.2190268578626539,"score_spread":0.2124832843402515,"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."}}