{"id":"W4408387458","doi":"10.1038/s42256-025-01007-9","title":"Transformers and genome language models","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Vector Institute; Public Health Ontario; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Transformer; Computational biology; Genome; Biology; Gene; Genetics; Engineering; Electrical engineering","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":[0.0000898384,0.0001252248,0.000105167,0.00004295674,0.00006677912,0.00001455747,0.0001393537,0.0001639801,0.000006411311],"category_scores_gemma":[0.00002182998,0.0001087952,0.00004710326,0.00008143431,0.00006482795,6.745222e-7,0.00008165718,0.0001748165,0.000001398153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005731879,"about_ca_system_score_gemma":0.00002383128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003177043,"about_ca_topic_score_gemma":0.00007469717,"domain_scores_codex":[0.9994041,0.00001498564,0.0001168144,0.0002606847,0.00005339687,0.0001500464],"domain_scores_gemma":[0.9997464,0.00001105657,0.00001919845,0.0001527516,0.00003545832,0.00003506856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001089262,0.00004598766,0.001140306,0.00006565311,0.0001994564,0.000004863575,0.0005136354,0.001006367,0.9066639,0.008930247,0.0002149683,0.08110571],"study_design_scores_gemma":[0.0006857697,0.0004818955,0.01289482,0.00005586389,0.0001416499,0.00004810558,0.00128741,0.005194727,0.8411583,0.02177563,0.1151873,0.0010885],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.798831,0.1093758,0.0679981,0.0007578896,0.000287719,0.0002767879,0.0000729081,0.00001022006,0.02238964],"genre_scores_gemma":[0.9948572,0.002619724,0.0008006007,0.0008183472,0.00005129892,0.000008724805,0.00002109399,0.000008484628,0.0008145471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1960262,"threshold_uncertainty_score":0.4436541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004233397503920612,"score_gpt":0.258521215793566,"score_spread":0.2542878182896454,"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."}}