{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001913124,0.0006416555,0.0004743571,0.002314142,0.0004126951,0.001338417,0.0009165674,0.0007339931,0.003100603],"category_scores_gemma":[0.0114952,0.0002887691,0.0006898087,0.001537111,0.000571634,0.00132603,0.001171088,0.0009716951,0.001625776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004888864,"about_ca_system_score_gemma":0.0006055739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009780513,"about_ca_topic_score_gemma":0.001342795,"domain_scores_codex":[0.9985418,0.0003957207,0.00008330533,0.0003589708,0.0005232787,0.00009693161],"domain_scores_gemma":[0.9958284,0.002361239,0.000538804,0.0005492005,0.0006161261,0.0001061996],"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":[0.001357804,0.0002753006,0.08123492,0.0008669647,0.0002511656,0.001022693,0.000762894,0.2929392,0.1335791,0.09222826,0.01650539,0.3789763],"study_design_scores_gemma":[0.0000243555,0.00005630911,0.009219836,0.00006316686,0.00003453095,0.0002494255,0.00006300634,0.885882,0.02801399,0.06963037,0.00671081,0.00005226638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1408768,0.000282831,0.8442385,0.0004198252,0.00009157429,0.00005860949,0.003870744,0.006350717,0.003810348],"genre_scores_gemma":[0.7814162,0.0001965029,0.210276,0.0001125909,0.00006340145,0.00008314015,0.005694674,0.000654569,0.001502794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003100603,"threshold_uncertainty_score":0.01037258,"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."}}