{"id":"W7108637041","doi":"10.5376/cmb.2025.15.0011","title":"Deep Learning for Predicting Gene Expression from Genomic Sequences","year":2025,"lang":"","type":"article","venue":"Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Deep learning; Genomics; Functional genomics; Gene regulatory network; Gene; Gene expression; Regulation of gene expression; Expression quantitative trait loci","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003926949,0.0004779085,0.0004627751,0.000195172,0.0005069282,0.0001000026,0.0006032086,0.0007077731,0.00004258422],"category_scores_gemma":[0.0009282656,0.0005186761,0.0003099325,0.0001932402,0.0003138539,0.000009644437,0.0005771692,0.0004491422,0.00001819073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008593911,"about_ca_system_score_gemma":0.0004052242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003970323,"about_ca_topic_score_gemma":0.000006467013,"domain_scores_codex":[0.9970168,0.0004491593,0.0008802966,0.0009146492,0.0001574003,0.0005816388],"domain_scores_gemma":[0.9982228,0.0003780877,0.0005165008,0.0003894822,0.0003687901,0.0001243774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000201346,0.00005749315,0.0162716,0.000104338,0.0003966419,0.000003213024,0.0001190225,0.3913956,0.5786194,0.003347234,0.0001144341,0.009369667],"study_design_scores_gemma":[0.003037696,0.0009923545,0.004137544,0.0002280236,0.0002687022,0.00002311732,0.0002312749,0.811218,0.077169,0.08201254,0.01964288,0.001038835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2018938,0.006108705,0.789201,0.0003664269,0.0007554855,0.0005657901,0.0001192952,0.00003960536,0.0009498679],"genre_scores_gemma":[0.8397025,0.0001036018,0.1520734,0.0008925809,0.0003229064,0.00008528494,0.006599824,0.00004202306,0.000177863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6378087,"threshold_uncertainty_score":0.9997265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006501902357756156,"score_gpt":0.2839541897874955,"score_spread":0.2774522874297394,"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."}}