{"id":"W4365444089","doi":"10.1093/bioinformatics/btad189","title":"Structure-aware protein self-supervised learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Pairwise comparison; Leverage (statistics); Graph; Supervised learning; Artificial neural network; Theoretical computer science","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":[0.0008986446,0.0007632279,0.0007851162,0.0004489708,0.0002841303,0.0004244387,0.00199065,0.001011441,0.00126003],"category_scores_gemma":[0.002264177,0.0003059054,0.0005681875,0.0005305381,0.0008367299,0.001333037,0.0009621685,0.001138065,0.0007092158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007049519,"about_ca_system_score_gemma":0.0007445875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001903801,"about_ca_topic_score_gemma":0.002312719,"domain_scores_codex":[0.9993436,0.0001643935,0.00002913124,0.0002289633,0.0001800747,0.00005373114],"domain_scores_gemma":[0.9984054,0.0004508071,0.0002430554,0.0003287736,0.0004910789,0.00008094852],"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":[0.0001691497,0.0002204179,0.001786638,0.0002279454,0.00006830124,0.0001091586,0.00008368435,0.7893791,0.01559643,0.005103167,0.006215718,0.1810404],"study_design_scores_gemma":[0.000003624807,0.00001273329,0.00009492494,0.00000190514,0.000002213071,0.00001178298,0.000002292024,0.9960372,0.001946965,0.001650772,0.0002330689,0.000002660644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07435577,0.0005901098,0.9182565,0.0004382812,0.00006928784,0.00007344979,0.0002702661,0.003747143,0.002199213],"genre_scores_gemma":[0.750258,0.0003389049,0.2421616,0.000437321,0.0001220765,0.0001724493,0.001607471,0.0003744498,0.004527668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00199065,"threshold_uncertainty_score":0.005114853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007098345358430243,"score_gpt":0.2367498723285093,"score_spread":0.2296515269700791,"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."}}