{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001721176,0.0007255048,0.0004219297,0.0009649952,0.0006035466,0.00133238,0.001640755,0.0008367339,0.007308578],"category_scores_gemma":[0.005154945,0.0005948001,0.001452812,0.0006298651,0.0007032124,0.001849165,0.001537645,0.001842962,0.001934319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001140624,"about_ca_system_score_gemma":0.001295394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007449966,"about_ca_topic_score_gemma":0.01326659,"domain_scores_codex":[0.9993584,0.0001197119,0.00003890152,0.0002250457,0.0002124086,0.00004556084],"domain_scores_gemma":[0.9986129,0.000935002,0.00007835032,0.0002240989,0.0001098294,0.00003975443],"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":[0.0007899405,0.000274959,0.01304447,0.0004085493,0.0003253758,0.0005013667,0.0005693496,0.6402628,0.04224123,0.1039507,0.03843341,0.1591979],"study_design_scores_gemma":[0.00002364607,0.0000435931,0.0008478181,0.00002476254,0.00002053274,0.00004235367,0.00002847363,0.9326463,0.01710386,0.03356648,0.01561403,0.00003813726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03677848,0.0002023419,0.8908987,0.0004226877,0.00009488785,0.000079331,0.005442272,0.06107898,0.00500227],"genre_scores_gemma":[0.3090272,0.0003724223,0.6614909,0.0005405429,0.00002527336,0.0004009148,0.01263065,0.006687029,0.008825039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007449966,"threshold_uncertainty_score":0.02444959,"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."}}