{"id":"W4417017350","doi":"10.5376/cmb.2025.15.0014","title":"Pretrained Language Models for Biological Sequence Understanding","year":2025,"lang":"","type":"article","venue":"Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Sequence (biology); Field (mathematics); Biological data; Biological database; Function (biology); Computational model; Language model","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":[0.0004968931,0.0004543631,0.0004455013,0.0002217389,0.000289875,0.00007575684,0.0005725512,0.0007788863,0.00002476926],"category_scores_gemma":[0.0006694919,0.000458451,0.0003308801,0.0003037091,0.0005469004,0.000009762827,0.0003766873,0.0003054581,0.000007722557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710103,"about_ca_system_score_gemma":0.000522715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006545049,"about_ca_topic_score_gemma":0.000002746082,"domain_scores_codex":[0.9974326,0.000303853,0.00071071,0.0007926825,0.0001320385,0.0006281448],"domain_scores_gemma":[0.9986352,0.0002822455,0.00028061,0.0004287137,0.0002524788,0.0001207128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002763551,0.0001032454,0.0004275365,0.000212773,0.0004794007,0.000006393257,0.0001916141,0.1256361,0.08696824,0.781348,0.000642385,0.003707958],"study_design_scores_gemma":[0.001598834,0.0006945307,0.00004339074,0.00007985068,0.00007230268,0.00002382888,0.0002758597,0.4751679,0.001877785,0.5173649,0.002282186,0.0005185961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01689737,0.002339864,0.9708333,0.001332203,0.0005439686,0.0009308524,0.0004011542,0.00004651136,0.006674775],"genre_scores_gemma":[0.9249498,0.00005616987,0.06863124,0.002394588,0.00011538,0.00008083262,0.003507009,0.00003075994,0.0002342041],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9080524,"threshold_uncertainty_score":0.9997867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04331735219292956,"score_gpt":0.3521607780462377,"score_spread":0.3088434258533082,"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."}}