{"id":"W7114908522","doi":"10.1093/bib/bbaf631.062","title":"ProtBert-BFD token classification improves intrinsically disordered protein region prediction","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Security token; Inference; Generalizability theory; Scalability; Classifier (UML); Annotation; Multilayer perceptron; Pattern recognition (psychology); Deep learning","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":[0.0001514853,0.0001755246,0.0001542495,0.0001217444,0.00008732427,0.00005967715,0.0002184174,0.0002772181,0.000001226372],"category_scores_gemma":[0.0002478156,0.0001669041,0.00005877798,0.0002569407,0.00008652375,0.00002499889,0.0001359764,0.0001686778,0.000003249216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004661264,"about_ca_system_score_gemma":0.0001397294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003920639,"about_ca_topic_score_gemma":0.00005298079,"domain_scores_codex":[0.9988801,0.00002656755,0.0004993947,0.0002210676,0.0001301969,0.0002426388],"domain_scores_gemma":[0.999293,0.000007899406,0.0001745523,0.0003889809,0.00009442082,0.0000411379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008738351,0.0003415425,0.007179625,0.001275778,0.000160937,0.000004876974,0.0009540381,0.0001737188,0.4508434,0.03399683,0.01193748,0.4922579],"study_design_scores_gemma":[0.009694775,0.001798162,0.1372609,0.00130387,0.0001364229,0.0001022556,0.001274782,0.1666982,0.235686,0.02967627,0.4140598,0.002308497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.75692,0.0003747263,0.2138833,0.004244782,0.0003460021,0.004083276,0.0000393477,0.0001574003,0.01995124],"genre_scores_gemma":[0.9803182,0.000141533,0.01625637,0.001319015,0.00009509323,0.0003264639,0.0003422756,0.00002084703,0.001180201],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4899494,"threshold_uncertainty_score":0.6806152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005802979697390921,"score_gpt":0.2233382062721013,"score_spread":0.2175352265747104,"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."}}