{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008528742,0.0009947764,0.000892434,0.0009482535,0.000286142,0.001126048,0.001526509,0.00125836,0.002993446],"category_scores_gemma":[0.003850371,0.0005638854,0.001265269,0.0007875413,0.0007063679,0.002615318,0.001117413,0.003318581,0.001981081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008772116,"about_ca_system_score_gemma":0.001214774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003949552,"about_ca_topic_score_gemma":0.005417441,"domain_scores_codex":[0.9995618,0.0001387561,0.00003208072,0.0001372181,0.00008507207,0.00004503079],"domain_scores_gemma":[0.9984578,0.001042134,0.0001070508,0.0001594864,0.0001916606,0.0000420064],"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":[0.0001731239,0.0001219507,0.0009570308,0.0002740359,0.0001406677,0.0002087566,0.0001970168,0.744724,0.0108374,0.04494124,0.007178864,0.1902459],"study_design_scores_gemma":[0.000003550898,0.00001573471,0.00006913158,0.00001206473,0.000007671822,0.00002351873,0.000008294013,0.9789067,0.0008622815,0.01892775,0.001156976,0.000006316911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01116198,0.001315114,0.9826737,0.0007333575,0.0001057183,0.00003684179,0.000688904,0.001736512,0.001547796],"genre_scores_gemma":[0.5295616,0.004776376,0.4408128,0.001497086,0.0005435125,0.0006200345,0.007828193,0.0006519924,0.01370835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003949552,"threshold_uncertainty_score":0.01001406,"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."}}