{"id":"W4405975816","doi":"10.1101/2024.12.18.629275","title":"Probabilistic Annotations of Protein Sequences for Intrinsically Disordered Features","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Probabilistic logic; Intrinsically disordered proteins; Computational biology; Computer science; Statistical physics; Artificial intelligence; Biology; Physics; Biophysics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003996326,0.0004054099,0.0003926578,0.0001464567,0.00008815214,0.0001231363,0.0005122895,0.0005329795,0.000006475221],"category_scores_gemma":[0.001258298,0.0003903489,0.0002069868,0.0002210502,0.000203108,0.000005316984,0.0006136902,0.0005225252,0.000008047698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004680468,"about_ca_system_score_gemma":0.0007592737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002037891,"about_ca_topic_score_gemma":0.000008823185,"domain_scores_codex":[0.9981487,0.00007663517,0.0005751188,0.0006272396,0.0002367729,0.0003355373],"domain_scores_gemma":[0.9980003,0.00003847143,0.0004105906,0.0008727344,0.0005677457,0.0001102184],"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":[0.00008122273,0.0001216936,0.0003155996,0.004212156,0.000289509,0.000003076765,0.00002685823,0.001077188,0.9871581,0.005734347,0.0009660641,0.00001418446],"study_design_scores_gemma":[0.001107542,0.0009550789,0.01136439,0.00170774,0.0004612045,9.300197e-8,0.00001827475,0.004797935,0.9513524,0.0004588295,0.02584454,0.001931925],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889596,0.002012046,0.004059582,0.000572621,0.0005952999,0.00259598,0.001001296,0.0001564403,0.00004716914],"genre_scores_gemma":[0.9674559,0.00005735591,0.03122815,0.00006400059,0.000333041,0.000721766,0.000007881325,0.00009162383,0.00004027817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03580565,"threshold_uncertainty_score":0.9998549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007785331848800327,"score_gpt":0.2389458958694609,"score_spread":0.2311605640206606,"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."}}