{"id":"W4417520771","doi":"10.64898/2025.12.18.694875","title":"Enigma: An Efficient Model for Deciphering Regulatory Genomics","year":2025,"lang":"","type":"article","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Set (abstract data type); Computational model; Genomics; Training set; Genome; Scale (ratio)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001140647,0.001107472,0.00102859,0.0009533705,0.0005825357,0.001183864,0.002953603,0.001779751,0.004804506],"category_scores_gemma":[0.003175769,0.000684611,0.00162895,0.0006477355,0.0006991859,0.001310425,0.001154682,0.002272039,0.002079211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001423039,"about_ca_system_score_gemma":0.001822766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01525245,"about_ca_topic_score_gemma":0.01804576,"domain_scores_codex":[0.9997253,0.00006926042,0.00001124297,0.0001069903,0.00005571827,0.00003147707],"domain_scores_gemma":[0.9992616,0.0004477448,0.00004618738,0.00008476764,0.0001120185,0.00004774377],"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":[0.0001411853,0.00006517957,0.002174046,0.0001012035,0.0001126127,0.00009957139,0.00004990099,0.9502693,0.002954378,0.005800426,0.008391812,0.02984043],"study_design_scores_gemma":[0.000009489171,0.000006593216,0.00008744615,0.000004812897,0.000007516775,0.00001051131,0.000003802325,0.9951128,0.0002938888,0.003380387,0.001078732,0.000004136682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.110983,0.0027301,0.8379568,0.002654958,0.0003573323,0.0001696318,0.008763325,0.02754193,0.008842862],"genre_scores_gemma":[0.5860721,0.001214195,0.3771379,0.002127311,0.0002419641,0.0008761514,0.01666129,0.003679602,0.01198947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01525245,"threshold_uncertainty_score":0.03032732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007570151171111024,"score_gpt":0.2298271598598404,"score_spread":0.2222570086887294,"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."}}