{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000412371,0.0004696976,0.0003457536,0.0002545874,0.00007274615,0.0001197212,0.0004418501,0.0006161953,0.00001645463],"category_scores_gemma":[0.0003633283,0.0004633785,0.00008435777,0.0003134513,0.0001062659,0.000009754352,0.0004294202,0.0007827021,0.00001082015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007215424,"about_ca_system_score_gemma":0.0005021866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001140049,"about_ca_topic_score_gemma":0.00003454765,"domain_scores_codex":[0.9980108,0.0001545399,0.0004154477,0.0007351327,0.0002706844,0.0004133951],"domain_scores_gemma":[0.9984453,0.00001243727,0.000381939,0.0008447165,0.0002059942,0.0001095893],"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":[0.00009860893,0.00009024013,0.02798774,0.0009058397,0.0001802725,0.00005236066,0.0000130569,0.001485195,0.9689012,0.000144476,0.0001221085,0.00001885854],"study_design_scores_gemma":[0.0007582671,0.0002100101,0.02447437,0.001960414,0.00007565937,1.035217e-7,0.000007998686,0.000931226,0.9689083,0.000005629575,0.001730019,0.0009380782],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950694,0.0006878479,0.002004011,0.0001181757,0.0001588757,0.001102891,0.0001287215,0.0001542524,0.0005758622],"genre_scores_gemma":[0.9711417,0.00007649044,0.02795218,0.0001762944,0.0001553719,0.0003184482,0.000004927527,0.00009305288,0.0000815177],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02594817,"threshold_uncertainty_score":0.9997818,"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."}}