{"id":"W7117296782","doi":"10.1021/acs.jproteome.5c00506","title":"Protein Language Models: Applications and Perspectives","year":2025,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval","funders":"","keywords":"Key (lock); Sequence (biology); Protein sequencing; Drug discovery; Proteomics; Language model","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":[0.001195515,0.00005472883,0.00008773611,0.0001903554,0.00009908647,0.00004418642,0.0002005431,0.00006858569,0.000007600682],"category_scores_gemma":[0.0003216873,0.00004386448,0.00003619811,0.0001806163,0.0001186126,0.000008253121,0.0001437493,0.0003745667,0.00000223705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002352657,"about_ca_system_score_gemma":0.0001741989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006616957,"about_ca_topic_score_gemma":0.000002085078,"domain_scores_codex":[0.9992374,0.0001141349,0.000186797,0.00008930484,0.0002268228,0.000145514],"domain_scores_gemma":[0.9992899,0.00001885732,0.00007757959,0.0001699081,0.0003917915,0.00005199024],"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":[0.0001926851,0.0001418501,0.0004108834,0.0003318347,0.0001246795,0.00000557059,0.001651655,0.0001811884,0.9674278,0.01204776,0.001581884,0.01590224],"study_design_scores_gemma":[0.006523256,0.005293349,0.005648982,0.001191313,0.00008550128,0.0005125929,0.04614021,0.02222291,0.6267854,0.05039658,0.2341269,0.001073051],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8730633,0.009274884,0.08954997,0.003790304,0.00002429178,0.001580784,0.000006170926,0.000009442444,0.02270084],"genre_scores_gemma":[0.9782702,0.0002188351,0.01784192,0.00002097656,0.0001420978,0.00007188607,0.000001944929,0.000007774501,0.003424364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3406424,"threshold_uncertainty_score":0.1788741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.031509319623001,"score_gpt":0.3799376186048076,"score_spread":0.3484282989818066,"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."}}