{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00140888,0.001187591,0.0007989842,0.0008832411,0.0004395948,0.0008066615,0.001180736,0.001110894,0.002369131],"category_scores_gemma":[0.002423091,0.0002483357,0.0007130321,0.0005533477,0.0003543186,0.001565158,0.001018292,0.001372203,0.002345768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001109519,"about_ca_system_score_gemma":0.001601137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008529467,"about_ca_topic_score_gemma":0.01040156,"domain_scores_codex":[0.9994262,0.0001313231,0.00003821556,0.0002064539,0.0001016519,0.00009610103],"domain_scores_gemma":[0.9990531,0.0004016689,0.00007654454,0.0001371934,0.0002259747,0.0001056134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003923593,0.001511827,0.02859838,0.0008247982,0.0003427786,0.0004971014,0.0001507527,0.3474912,0.05947867,0.003599397,0.05377409,0.4998075],"study_design_scores_gemma":[0.00004561862,0.0001573858,0.0011544,0.0000219802,0.0000271063,0.0000597601,0.00002390729,0.985368,0.01025873,0.001458911,0.001405504,0.00001865424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7266247,0.004798627,0.2184616,0.001571293,0.0009124702,0.0001643635,0.0091157,0.03044465,0.007906579],"genre_scores_gemma":[0.9069682,0.0004924241,0.07369038,0.0005836655,0.0001044158,0.00009308389,0.01180015,0.000400109,0.005867658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008529467,"threshold_uncertainty_score":0.01695961,"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."}}