{"id":"W4284675311","doi":"10.1101/2022.07.06.499043","title":"An interpretable machine learning algorithm to predict disordered protein phase separation based on biophysical interactions","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"","keywords":"Protein Data Bank (RCSB PDB); Intrinsically disordered proteins; Computer science; Phase (matter); Proteome; Artificial intelligence; Set (abstract data type); Structural bioinformatics; Protein structure; Machine learning; Chemical physics; Biological system; Chemistry; Bioinformatics; Biology; Biochemistry","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":[0.00102162,0.0009734311,0.0007244815,0.001431514,0.0003485596,0.0008052403,0.001181608,0.0009557087,0.003192171],"category_scores_gemma":[0.003205371,0.0003379939,0.0006269328,0.0008259577,0.0004504379,0.0006212291,0.0007100638,0.0012202,0.00111522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006860521,"about_ca_system_score_gemma":0.0009362574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243593,"about_ca_topic_score_gemma":0.002157792,"domain_scores_codex":[0.9997057,0.00006981286,0.00002136472,0.00009568723,0.00007077977,0.00003664683],"domain_scores_gemma":[0.9987827,0.0007000513,0.00010429,0.00007679264,0.0002793898,0.00005675114],"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":[0.0005138839,0.0003343466,0.008703416,0.0001478368,0.0001336855,0.0002167106,0.00004166747,0.6894681,0.00745594,0.006305882,0.01185197,0.2748265],"study_design_scores_gemma":[0.00001382201,0.00001368273,0.0001503858,0.000003263539,0.000003018407,0.000009438249,0.000002728412,0.9969699,0.0005354315,0.002126364,0.0001697744,0.000002183592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07852432,0.0004490423,0.9104316,0.0006140675,0.0001144309,0.000139541,0.001079219,0.006183678,0.002464055],"genre_scores_gemma":[0.6094341,0.0002257295,0.380153,0.0004724516,0.0001898742,0.0003496334,0.004446712,0.000330378,0.004398032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003192171,"threshold_uncertainty_score":0.01067883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009608515026818226,"score_gpt":0.2869088590141953,"score_spread":0.277300343987377,"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."}}