{"id":"W4312094950","doi":"","title":"Enzyme Activity Prediction of Sequence Variants on Novel Substrates using Improved Substrate Encodings and Convolutional Pooling.","year":2022,"lang":"en","type":"article","venue":"PubMed","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pooling; Computer science; Artificial intelligence; Workflow; Machine learning; Computational biology; Data mining; Biology; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.001041714,0.0001286304,0.000158006,0.0001497118,0.0002446672,0.00007576036,0.0003452873,0.00003249594,0.000004609372],"category_scores_gemma":[0.0001176371,0.0001434175,0.00004523805,0.0004210152,0.00008558523,0.000607098,0.0002737528,0.0002010565,2.236823e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001760022,"about_ca_system_score_gemma":0.0002196339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001306466,"about_ca_topic_score_gemma":0.0000018957,"domain_scores_codex":[0.9984959,0.0001519674,0.0002344842,0.0004263968,0.0004128533,0.0002783691],"domain_scores_gemma":[0.9990643,0.0003388661,0.0002119996,0.0002044127,0.00009247654,0.00008789611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004318714,0.0009869601,0.00682337,0.0001044635,0.0001936609,0.00002250343,0.001087446,0.3383763,0.4489973,0.1320913,0.00003971266,0.07084507],"study_design_scores_gemma":[0.0003545916,0.00003915816,0.3529316,0.000003620345,0.000007459522,0.00004338378,0.00001176219,0.6307166,0.01312632,0.002655391,0.00001441208,0.00009579982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8087398,0.00003257414,0.1901148,0.0001588639,0.0003677854,0.0003032619,0.0001272353,0.00005655954,0.00009911357],"genre_scores_gemma":[0.9906018,0.000002065664,0.00908212,0.00006637067,0.00004221158,0.0001683491,0.000006580984,0.000007607698,0.00002289364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.435871,"threshold_uncertainty_score":0.5848394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08933320113248036,"score_gpt":0.2743013484337087,"score_spread":0.1849681473012283,"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."}}