{"id":"W4321606216","doi":"10.1101/2023.02.22.529597","title":"Retrieved Sequence Augmentation for Protein Representation Learning","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":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Preprocessor; Inference; Protein sequencing; Sequence (biology); Artificial intelligence; Representation (politics); Machine learning; Peptide sequence; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008366945,0.000409381,0.0003221878,0.000121423,0.0002236587,0.0001912991,0.0004369576,0.0006115017,0.000009108755],"category_scores_gemma":[0.001933757,0.0004781575,0.0001710298,0.0002875148,0.00008187535,0.0000162404,0.000461323,0.0005953789,0.00004595579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001202647,"about_ca_system_score_gemma":0.0003651337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003675223,"about_ca_topic_score_gemma":0.00000255333,"domain_scores_codex":[0.9976556,0.0001667511,0.0005832496,0.0008301361,0.0003270314,0.0004371907],"domain_scores_gemma":[0.9977585,0.00003562603,0.0006767589,0.0008999798,0.0004966099,0.0001325108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008818954,0.00002455835,0.004312235,0.0004906067,0.0001101992,0.000003423293,0.00001357655,0.002441508,0.9917691,0.0001154411,0.0006245909,0.000006528773],"study_design_scores_gemma":[0.000794104,0.0002461336,0.01253252,0.0002871708,0.00007734856,2.011284e-8,0.0000120221,0.008632763,0.9680826,0.000008835013,0.008549971,0.0007764988],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9501206,0.0001288565,0.04604361,0.0002892432,0.0007454177,0.002093755,0.0001746432,0.000390519,0.00001339719],"genre_scores_gemma":[0.969746,0.0001028385,0.02826912,0.0001000301,0.0005859351,0.0008013171,0.00003479896,0.0001707297,0.0001892277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02368653,"threshold_uncertainty_score":0.999767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02938578089126726,"score_gpt":0.2844136217408884,"score_spread":0.2550278408496212,"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."}}