{"id":"W4388721914","doi":"10.1038/s43588-023-00544-w","title":"Predictive analyses of regulatory sequences with EUGENe","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Department of Health and Human Services; National Institutes of Health; National Institute of General Medical Sciences; Canadian Institute for Advanced Research; National Human Genome Research Institute; U.S. National Library of Medicine; Deutsche Forschungsgemeinschaft","keywords":"Deep learning; Workflow; Computer science; Interoperability; Artificial intelligence; Genomics; Set (abstract data type); Deep sequencing; Software; Data science; Machine learning; World Wide Web; Genome; Programming language; Biology; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001864767,0.00005630967,0.00005816479,0.00007295829,0.00008713649,0.00001232393,0.0002097636,0.00005822003,0.000002238113],"category_scores_gemma":[0.00005384551,0.00004378358,0.00002203091,0.0005646257,0.000360424,0.0000045663,0.00006757011,0.00005683208,0.000001603767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001230921,"about_ca_system_score_gemma":0.0002848928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003363525,"about_ca_topic_score_gemma":0.000003754617,"domain_scores_codex":[0.999285,0.000009798424,0.00008428558,0.0002121339,0.0003012592,0.000107554],"domain_scores_gemma":[0.999527,0.00001810648,0.00006681629,0.0001085032,0.0002421705,0.00003740118],"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":[0.00001974345,0.00001386648,0.003615803,0.000008114833,0.00002396187,0.00000163501,0.00003885958,0.4579305,0.5362262,0.001605093,0.0001585498,0.0003576728],"study_design_scores_gemma":[0.0003660034,0.0004543736,0.6032926,0.00002815769,0.00002097436,0.00002447004,0.0001425138,0.1340779,0.2542798,0.006807182,0.0002611512,0.0002448429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956296,0.0001510803,0.003634945,0.00007586448,0.00005524466,0.00005016979,0.00002311303,0.000009425695,0.0003705309],"genre_scores_gemma":[0.994222,0.00001097276,0.005575915,0.00005495814,0.00003510736,0.000002357918,0.00006135031,0.000003748837,0.00003359455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5996768,"threshold_uncertainty_score":0.1785442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009639506463573306,"score_gpt":0.298329943301521,"score_spread":0.2886904368379477,"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."}}