{"id":"W3083386021","doi":"10.1101/2020.09.04.283929","title":"Self-Supervised Contrastive Learning of Protein Representations By Mutual Information Maximization","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Vector Institute; Microsoft Research","keywords":"Maximization; Computer science; Mutual information; Embedding; Artificial intelligence; Hyperparameter; Machine learning; Autoregressive model; Supervised learning; Contrast (vision); Mathematics; Artificial neural network","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":[0.003159846,0.001133337,0.0009714942,0.0008730881,0.0003096903,0.0009124902,0.001750964,0.001430266,0.001366701],"category_scores_gemma":[0.008539037,0.0005770348,0.0008256492,0.0005691512,0.001438647,0.002603747,0.001934282,0.002555206,0.0006461552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005153,"about_ca_system_score_gemma":0.0006615449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001078836,"about_ca_topic_score_gemma":0.001721998,"domain_scores_codex":[0.9988355,0.0005771745,0.00004308911,0.0003187172,0.0001551657,0.00007033678],"domain_scores_gemma":[0.9958935,0.002345396,0.0004868245,0.000661278,0.0004705142,0.0001424282],"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":[0.0004196092,0.0003378007,0.003021737,0.0001808852,0.0002056272,0.00009682365,0.0001403373,0.8033014,0.02317915,0.01298592,0.004549006,0.1515817],"study_design_scores_gemma":[0.000004876087,0.0000249706,0.0001035911,0.00000321314,0.000003044148,0.000008938337,0.00000291423,0.9945164,0.002566768,0.002658461,0.0001031858,0.000003587157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09388607,0.0002915922,0.9022034,0.0004281815,0.00004310006,0.00007635884,0.0001812703,0.001644478,0.001245494],"genre_scores_gemma":[0.7554861,0.0001601934,0.2398486,0.0003168168,0.00008519956,0.000175701,0.0008228024,0.0003548664,0.002749655],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003159846,"threshold_uncertainty_score":0.01671112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006008598428195527,"score_gpt":0.2124216015829576,"score_spread":0.2064130031547621,"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."}}