{"id":"W4407220000","doi":"10.1101/2025.01.31.635962","title":"Predicting molecular recognition features in protein sequences with MoRFchibi 2.0","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational biology; Pattern recognition (psychology); Artificial intelligence; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00115476,0.001359369,0.0007181715,0.00152572,0.0003553255,0.0009568011,0.0009787369,0.000764974,0.00273211],"category_scores_gemma":[0.002685814,0.0004225143,0.0006887665,0.0008796212,0.0002344709,0.0007088069,0.0009629081,0.0009544734,0.00201436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007078848,"about_ca_system_score_gemma":0.001321061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006475949,"about_ca_topic_score_gemma":0.01103739,"domain_scores_codex":[0.9996988,0.00004754071,0.00001487558,0.00007745447,0.0001091269,0.00005224712],"domain_scores_gemma":[0.999177,0.0003957648,0.00009703232,0.000117044,0.0001513202,0.00006172751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00218789,0.0006100478,0.08933724,0.001121094,0.0009235459,0.0007976845,0.0003479423,0.2352302,0.09671466,0.005647465,0.1621003,0.4049819],"study_design_scores_gemma":[0.00004325239,0.0001356449,0.008833098,0.00002595847,0.00005818547,0.000216217,0.00004352449,0.9449607,0.03394859,0.002412919,0.009264364,0.0000574685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5262088,0.002276684,0.2608345,0.0009169233,0.0002266789,0.0003494158,0.028349,0.169523,0.01131496],"genre_scores_gemma":[0.6051489,0.0008653715,0.3264394,0.0004044135,0.00008047605,0.0004423689,0.05767307,0.002578545,0.006367385],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006475949,"threshold_uncertainty_score":0.01287651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006238984681612775,"score_gpt":0.2181261897920967,"score_spread":0.211887205110484,"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."}}