{"id":"W4408845790","doi":"10.1021/acs.jcim.4c02291","title":"A Deep Retrieval-Enhanced Meta-Learning Framework for Enzyme Optimum pH Prediction","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Chongqing Municipality Key Research and Development Program of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Artificial intelligence; Machine learning; Support vector machine; Similarity (geometry); Function (biology); Deep learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002256253,0.00007975974,0.0001564603,0.00005723237,0.00004840209,0.00004811543,0.00006710028,0.0001744456,0.000002547549],"category_scores_gemma":[0.000450881,0.00006436629,0.0001239798,0.00005491071,0.00001496847,0.00004542254,0.0000318912,0.0001813229,1.39217e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000013176,"about_ca_system_score_gemma":0.00004689035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.102282e-7,"about_ca_topic_score_gemma":5.115931e-8,"domain_scores_codex":[0.9993531,0.000009832983,0.000395526,0.0000579533,0.0000897412,0.00009389695],"domain_scores_gemma":[0.9994116,0.00001930596,0.000191604,0.00006107541,0.0002705054,0.00004588909],"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":[0.001201467,0.00001934591,0.00000990539,0.0001579327,0.0007078928,1.751809e-7,0.0003208841,0.2223244,0.7585433,0.002119208,0.0001692752,0.01442621],"study_design_scores_gemma":[0.0006603413,0.0001108988,8.525139e-7,0.00004814503,0.0002267661,0.00001239798,0.0001399423,0.6448925,0.3451652,0.006645676,0.002013487,0.00008382915],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1418958,0.0007240779,0.8569277,0.0001332695,0.00009099515,0.00008051779,0.000002301336,0.000004878119,0.0001404977],"genre_scores_gemma":[0.9530637,0.0002783814,0.0460696,0.000413612,0.000120048,0.000004215676,0.00003338153,0.000003693192,0.00001334493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.811168,"threshold_uncertainty_score":0.2624781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01221594980971524,"score_gpt":0.2718146821029185,"score_spread":0.2595987322932032,"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."}}