{"id":"W4416324697","doi":"10.1021/acs.jcim.5c01915","title":"MAPCliff-WMGR: Exploring Activity Cliffs in Molecular Activity Prediction Enhanced by Weighted Molecular Graph Representations","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Cliff; Interpretability; Virtual screening; Molecular descriptor; Benchmark (surveying); Activity recognition; Dimensionality reduction; Feature (linguistics)","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":[0.0005366936,0.0001160818,0.0002020186,0.0003959722,0.00004773483,0.000147808,0.0002296324,0.00007067613,0.000001178032],"category_scores_gemma":[0.0001841185,0.0001170952,0.0000921336,0.0005293119,0.00002175726,0.003739725,0.0001253293,0.0003253539,5.337471e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001060912,"about_ca_system_score_gemma":0.0001115383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001328593,"about_ca_topic_score_gemma":2.46473e-7,"domain_scores_codex":[0.9986988,0.00009833671,0.0005660168,0.0001344395,0.0003523716,0.0001500366],"domain_scores_gemma":[0.9991386,0.0001300641,0.0002654601,0.0001534457,0.0002305403,0.00008190112],"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":[0.0001247325,0.0001190043,0.000046686,0.00006312664,0.00005726078,0.000002868919,0.0008241019,0.3022048,0.603889,0.005616885,0.00008520919,0.08696623],"study_design_scores_gemma":[0.0004931262,0.00001283542,0.0000621749,0.00006564946,0.000007901457,0.000004791113,0.00003331491,0.6688893,0.3229984,0.007334521,0.00002991274,0.000068104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4876764,0.0000318954,0.5115318,0.0004050027,0.00009676694,0.00005636533,0.000001968304,0.00001429473,0.0001854815],"genre_scores_gemma":[0.9706093,0.00006910831,0.02910128,0.0001859096,0.00001234466,0.00001208774,0.000004830667,0.000003125679,0.000001995265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4829329,"threshold_uncertainty_score":0.4775005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02657644595611224,"score_gpt":0.3095731104214619,"score_spread":0.2829966644653497,"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."}}