{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007332297,0.000508346,0.0004305417,0.000493311,0.0002570601,0.0004648848,0.0009011831,0.0006711998,0.00059697],"category_scores_gemma":[0.00232287,0.0002934355,0.0005437723,0.000310106,0.0009335299,0.00108729,0.0007493061,0.001303939,0.0001081287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008682928,"about_ca_system_score_gemma":0.0003706967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001339948,"about_ca_topic_score_gemma":0.002370593,"domain_scores_codex":[0.9998469,0.00005462503,0.000007431885,0.00005085644,0.00002600383,0.00001421172],"domain_scores_gemma":[0.9992275,0.0004502958,0.0001042361,0.0001095013,0.00007008973,0.00003844437],"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":[0.0001755326,0.0001542456,0.008046686,0.0000939917,0.0001152856,0.0001925552,0.0001087068,0.8160132,0.04004704,0.03466856,0.0007470222,0.09963704],"study_design_scores_gemma":[0.000003464321,0.00001450223,0.0002063382,0.000001879204,0.000003162394,0.00001160942,0.000002310535,0.990837,0.001626779,0.007185704,0.0001045542,0.000002773879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1754618,0.0002153572,0.8223523,0.0004130477,0.00002050537,0.00003206801,0.00008943164,0.0003844725,0.001030999],"genre_scores_gemma":[0.8385003,0.0001139928,0.1600856,0.0001468493,0.00002453349,0.00005518046,0.0001628126,0.00005297723,0.0008577328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001339948,"threshold_uncertainty_score":0.006299913,"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."}}