{"id":"W3036984361","doi":"10.1101/2020.06.23.167361","title":"Identifying molecular features that are associated with biological function of intrinsically disordered protein regions","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Intrinsically disordered proteins; Computational biology; Sequence (biology); Function (biology); Biology; Isoelectric point; Similarity (geometry); Genetics; Biochemistry; Computer science; Artificial intelligence","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":[0.0001600735,0.0001986776,0.0002276953,0.0003705763,0.0001379841,0.0002661889,0.0001240582,0.000208505,0.0004494939],"category_scores_gemma":[0.0002703515,0.00008019064,0.0001851595,0.0002147194,0.0002334537,0.0001971108,0.0001336447,0.0003472763,0.0001813009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001685642,"about_ca_system_score_gemma":0.00009245145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000214481,"about_ca_topic_score_gemma":0.0002732807,"domain_scores_codex":[0.9999437,0.000009862934,0.000005914305,0.00001554463,0.00001724829,0.000007579069],"domain_scores_gemma":[0.9997435,0.00006355349,0.0001091885,0.00002575307,0.00002384411,0.00003421356],"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":[0.0001066119,0.00001690577,0.003960289,0.00003930643,0.000007743069,0.00009187684,0.0000174969,0.0003175735,0.9937849,0.0001854712,0.00003188874,0.001440006],"study_design_scores_gemma":[0.00001905798,0.0001822248,0.08001649,0.00001001094,0.00003917229,0.000849797,0.00006536232,0.01670637,0.899981,0.0006478144,0.001465163,0.00001766258],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930589,0.0001950467,0.006115969,0.0000353903,0.000005396765,0.000006762543,0.0001807843,0.00005180487,0.0003499583],"genre_scores_gemma":[0.9933668,0.00007353602,0.006016575,0.00001705895,0.000003327229,0.000004932709,0.0003275474,0.00001490141,0.0001752606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0004494939,"threshold_uncertainty_score":0.001503766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01514207218746761,"score_gpt":0.2129728374685076,"score_spread":0.19783076528104,"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."}}