{"id":"W4283716960","doi":"10.1371/journal.pcbi.1010238","title":"Discovering molecular features of intrinsically disordered regions by using evolution for contrastive learning","year":2022,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"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; Nvidia","keywords":"Proteome; Computational biology; Human proteome project; Intrinsically disordered proteins; Biology; Structural motif; Homology (biology); Feature (linguistics); Genome; Computer science; Protein superfamily; Artificial intelligence; Genetics; Proteomics; Amino acid; Gene; Biochemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.00005630724,0.00009130256,0.0001305847,0.00003827257,0.0001626014,0.000005450341,0.0001030735,0.00006084695,0.000003385632],"category_scores_gemma":[0.0001203952,0.00009564822,0.00006967188,0.00006651801,0.00008222121,0.000002526439,0.0001306605,0.0001008428,8.338663e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003118851,"about_ca_system_score_gemma":0.00008155605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001575511,"about_ca_topic_score_gemma":0.000003197693,"domain_scores_codex":[0.999321,0.00009391151,0.0001510078,0.0002242392,0.00007284794,0.0001369919],"domain_scores_gemma":[0.9996417,0.00005313648,0.000122578,0.00006746843,0.00009106212,0.00002410392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001948854,0.00005206898,0.001125899,0.0000109713,0.0001104797,5.278615e-7,0.00002918067,0.1725473,0.8080856,0.01734557,0.00008126825,0.0004161877],"study_design_scores_gemma":[0.01050976,0.009232704,0.01012212,0.00006666804,0.0004409211,0.000288202,0.001516253,0.467695,0.2183613,0.2687546,0.01068503,0.002327491],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5607044,0.00055163,0.4382451,0.00006886495,0.000039948,0.0001778804,0.000176947,0.000006250809,0.00002902115],"genre_scores_gemma":[0.9919808,0.000004872218,0.00625127,0.00007815803,0.00003854078,0.00004726078,0.001569728,0.0000123141,0.00001709442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5897244,"threshold_uncertainty_score":0.3900421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006523406774854698,"score_gpt":0.2420687326897004,"score_spread":0.2355453259148457,"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."}}