{"id":"W3192065341","doi":"10.1101/2021.07.29.454330","title":"Discovering molecular features of intrinsically disordered regions by using evolution for contrastive learning","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Proteome; Computational biology; Human proteome project; Feature (linguistics); Homology (biology); Structural motif; Intrinsically disordered proteins; Computer science; Protein superfamily; Genome; Biology; Identification (biology); Function (biology); Artificial intelligence; Amino acid; Genetics; Proteomics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006587853,0.000405538,0.0003371426,0.0004461658,0.0001842891,0.0004245117,0.0006820793,0.0005933591,0.00069415],"category_scores_gemma":[0.001770363,0.0002168763,0.0004003975,0.000259848,0.0007406041,0.0008268495,0.0005761039,0.0009504551,0.0001205352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007660599,"about_ca_system_score_gemma":0.000291559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001357976,"about_ca_topic_score_gemma":0.001918982,"domain_scores_codex":[0.9998692,0.00004589523,0.000005850955,0.00004309904,0.00002336045,0.00001260711],"domain_scores_gemma":[0.999358,0.0003541009,0.00009413002,0.00008684029,0.00006853351,0.00003840431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001872286,0.0001672916,0.009978292,0.00008827201,0.0001010554,0.0002023768,0.00008397052,0.8037459,0.06795274,0.02615433,0.0009754393,0.09036313],"study_design_scores_gemma":[0.000002239427,0.00001058204,0.0002152006,0.000001378012,0.000001988717,0.000008239882,0.00000159123,0.9934967,0.002176314,0.004010668,0.00007332279,0.000001864605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2960691,0.0002159562,0.7012957,0.0005150511,0.00002426175,0.00003068488,0.0001288707,0.0004883126,0.001232069],"genre_scores_gemma":[0.8958792,0.00006877969,0.1028642,0.00009280836,0.00001828663,0.00002475021,0.0001441205,0.00004787508,0.0008600738],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001357976,"threshold_uncertainty_score":0.005558133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005197239089126328,"score_gpt":0.2147147168419881,"score_spread":0.2095174777528618,"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."}}