{"id":"W4410501150","doi":"10.1002/anie.202503259","title":"Mitigating Molecular Aggregation in Drug Discovery With Predictive Insights From Explainable AI","year":2025,"lang":"en","type":"article","venue":"Angewandte Chemie International Edition","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Canadian Institutes of Health Research; Bundesministerium für Bildung und Forschung","keywords":"Leverage (statistics); Counterfactual conditional; Drug discovery; Identification (biology); False positive paradox; Computer science; Machine learning; Artificial intelligence; Data science; Chemistry; Counterfactual thinking; Psychology; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001487355,0.000799282,0.0007444503,0.001108935,0.0003761486,0.0008552562,0.0009256653,0.0008918326,0.001034098],"category_scores_gemma":[0.005279736,0.0003172219,0.0007138815,0.0005499182,0.001055126,0.001387513,0.0009355689,0.001242107,0.0001183405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031026,"about_ca_system_score_gemma":0.0007706798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002910642,"about_ca_topic_score_gemma":0.00330906,"domain_scores_codex":[0.999496,0.0002289455,0.00001944568,0.0001008954,0.0001106212,0.00004414162],"domain_scores_gemma":[0.9968122,0.002322235,0.0004124706,0.0002107222,0.0001660458,0.00007644091],"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":[0.0001126816,0.0000692243,0.004612452,0.0001730701,0.0001196804,0.000149137,0.00007444034,0.909802,0.003639322,0.05206539,0.0008557767,0.02832679],"study_design_scores_gemma":[0.000003999738,0.00002171798,0.0002147754,0.000003498909,0.00001059455,0.00001394074,0.000003541405,0.9796762,0.000336638,0.01949752,0.0002132789,0.000004338338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1917318,0.002204072,0.7962067,0.002601995,0.0001192374,0.00008636931,0.0003509124,0.0008044933,0.005894528],"genre_scores_gemma":[0.9579414,0.0008014794,0.0393443,0.0003022795,0.00009200401,0.00009277496,0.0002133559,0.00003877644,0.001173592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002910642,"threshold_uncertainty_score":0.007866025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003727183954696887,"score_gpt":0.2374616992526132,"score_spread":0.2337345152979163,"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."}}