{"id":"W4411354622","doi":"10.1021/acs.jcim.5c00940","title":"CAML: Commutative Algebra Machine Learning─A Case Study on Protein–Ligand Binding Affinity Prediction","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Basic Energy Sciences; NIH Clinical Center; National Institute of Allergy and Infectious Diseases; Office of Science; Defense Threat Reduction Agency; King Fahd University of Petroleum and Minerals; Michigan State University Foundation; Pacific Northwest National Laboratory; Bristol-Myers Squibb; National Institute of General Medical Sciences; Battelle; U.S. Department of Energy; National Institutes of Health; National Science Foundation","keywords":"Ligand (biochemistry); Commutative property; Algebra over a field; Computer science; Chemistry; Stereochemistry; Mathematics; Biochemistry; Discrete mathematics; Pure mathematics","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":[0.0009629877,0.00009906218,0.0001654852,0.0002837726,0.0001388648,0.0002040185,0.0001654136,0.00004306487,8.019709e-7],"category_scores_gemma":[0.0002682671,0.00008384402,0.00004857873,0.0002503413,0.00001640694,0.001535536,0.0001276111,0.0004393328,0.000001149759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000737394,"about_ca_system_score_gemma":0.00009862115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001618876,"about_ca_topic_score_gemma":5.38175e-7,"domain_scores_codex":[0.9988452,0.0001189733,0.0005784796,0.00007832561,0.0002823444,0.00009667622],"domain_scores_gemma":[0.9990982,0.000192858,0.0002843227,0.00008656512,0.0002703611,0.00006773345],"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":[0.0002594795,0.0004018713,0.0005593312,0.00009775332,0.0001725992,0.0001062067,0.01839891,0.9044755,0.004679072,0.007257371,0.00006347669,0.06352848],"study_design_scores_gemma":[0.000941172,0.0001894187,0.00001846566,0.00008479736,0.00001485676,0.0003151206,0.001750288,0.9883155,0.006672918,0.00158619,0.00004052019,0.00007073947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5639998,0.00001533837,0.4355134,0.0001579703,0.00006183136,0.0001014434,0.000001396326,0.00001655043,0.000132307],"genre_scores_gemma":[0.9895675,0.000003407321,0.01026422,0.000128651,0.00002164205,0.000004199017,0.000003115638,0.000002286436,0.000005050001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4255677,"threshold_uncertainty_score":0.341906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03558747447669083,"score_gpt":0.3247736259208959,"score_spread":0.2891861514442051,"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."}}