{"id":"W4389028818","doi":"10.1101/2023.11.26.568742","title":"Learning sequence, structure, and function representations of proteins with language models","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Flatiron Health; Division of Chemical, Bioengineering, Environmental, and Transport Systems; Samsung Advanced Institute of Technology; Samsung; National Institutes of Health; National Science Foundation","keywords":"Sequence (biology); Function (biology); Computer science; Computational biology; Natural language processing; Artificial intelligence; Biology; Evolutionary biology; Genetics","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":[0.001561565,0.0009344322,0.0008581313,0.001304517,0.0003407643,0.001700238,0.00116834,0.001362295,0.0006215533],"category_scores_gemma":[0.004221088,0.0004029855,0.001522466,0.001263164,0.0006711729,0.002668629,0.001241995,0.00163264,0.0006237467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001112567,"about_ca_system_score_gemma":0.001029732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002429747,"about_ca_topic_score_gemma":0.002746837,"domain_scores_codex":[0.9992896,0.0002671721,0.0000425566,0.000217903,0.0001205098,0.00006213522],"domain_scores_gemma":[0.9985821,0.000841506,0.0001777074,0.0002040006,0.0001335938,0.00006110009],"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":[0.0005077336,0.0004881583,0.004294962,0.0003219933,0.0002324827,0.0004208051,0.0003543423,0.5904096,0.03236206,0.04568396,0.01033748,0.3145865],"study_design_scores_gemma":[0.000008455343,0.00002219562,0.0001045502,0.000005430289,0.000009058645,0.00002296069,0.00001491085,0.9824582,0.001546663,0.01539912,0.0004008155,0.000007666302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06162266,0.000643054,0.9322745,0.0007444327,0.00004478599,0.000056021,0.0008283552,0.002836375,0.0009497768],"genre_scores_gemma":[0.5851042,0.0008378372,0.405726,0.0005338223,0.0001491529,0.0002655129,0.004874217,0.0003596887,0.002149518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002429747,"threshold_uncertainty_score":0.008258462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01277411729885679,"score_gpt":0.2404532850849711,"score_spread":0.2276791677861143,"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."}}