{"id":"W4409184428","doi":"10.1021/acs.jctc.5c00074","title":"Persistent Directed Flag Laplacian (PDFL)-Based Machine Learning for Protein–Ligand Binding Affinity Prediction","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Michigan State University; Bristol-Myers Squibb; National Institutes of Health; National Science Foundation","keywords":"Flag (linear algebra); Computer science; Ligand (biochemistry); Artificial intelligence; Machine learning; Chemistry; Computational biology; Mathematics; Receptor; Biology; Biochemistry","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":[0.001740006,0.0001202967,0.0002155328,0.0002184791,0.0001495949,0.0001344385,0.0001981778,0.0000673609,0.000001394724],"category_scores_gemma":[0.0005983205,0.0001083466,0.0001564328,0.0003281203,0.00004641629,0.000324289,0.00006162856,0.0002521841,4.099871e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008381622,"about_ca_system_score_gemma":0.0001308529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.275455e-7,"about_ca_topic_score_gemma":8.751309e-8,"domain_scores_codex":[0.9986482,0.0004008894,0.0003985131,0.0001917132,0.0002259277,0.0001347817],"domain_scores_gemma":[0.9981164,0.001166539,0.0003019912,0.00006776251,0.0002762943,0.00007098908],"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":[0.002925639,0.0006018552,0.0007628388,0.0005169022,0.0004727556,0.00001410722,0.001224069,0.3877085,0.2785342,0.1157318,0.0001981976,0.2113092],"study_design_scores_gemma":[0.001305809,0.0002343208,0.000329778,0.0002145086,0.00005086569,0.00002007833,0.000048568,0.834369,0.08716872,0.07594772,0.0001953771,0.000115276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4496849,0.0001168714,0.5495411,0.0002851975,0.000137132,0.0001209684,0.000002253247,0.00003635148,0.00007529965],"genre_scores_gemma":[0.9507365,0.000002589259,0.04903669,0.0000902572,0.00006977918,0.000007904178,0.00001239668,0.000005824048,0.00003806847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5010516,"threshold_uncertainty_score":0.4418245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01610145339089029,"score_gpt":0.2853000915023668,"score_spread":0.2691986381114765,"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."}}