{"id":"W4402650770","doi":"10.1038/s41524-024-01413-4","title":"MEPO-ML: a robust graph attention network model for rapid generation of partial atomic charges in metal-organic frameworks","year":2024,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Total; Mitacs; Alliance de recherche numérique du Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Metal-organic framework; Partial charge; Graph; Computer science; Theoretical computer science; Chemistry; Charge (physics); Physics; Quantum mechanics; Physical chemistry","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002617108,0.0002587657,0.0004844719,0.000217086,0.0001572899,0.0004079383,0.0003321897,0.0002300757,0.001483037],"category_scores_gemma":[0.0001950572,0.0002447326,0.0001050979,0.0003638682,0.0001240919,0.0004628564,0.0001037897,0.0001325909,0.00009286515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007484002,"about_ca_system_score_gemma":0.0001758077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003285389,"about_ca_topic_score_gemma":0.000009889931,"domain_scores_codex":[0.9971127,0.0003430581,0.0009744462,0.0006553037,0.0004806855,0.0004338417],"domain_scores_gemma":[0.9989513,0.0002829207,0.0003106526,0.0002222076,0.0001690485,0.00006391216],"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":[0.00003460526,0.00002556575,0.00003559657,0.0001154822,0.000008797924,0.000001227022,0.0001238622,0.4738599,0.5154853,0.009992207,0.0002554697,0.00006194304],"study_design_scores_gemma":[0.0003095896,0.00006712452,0.0007953944,0.0001613249,0.00003595844,0.000006690498,0.000007767751,0.8541753,0.1111764,0.03300035,0.00002823345,0.0002359666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6192632,0.0001534945,0.3775213,0.0002449483,0.00216444,0.0004196975,0.0001146002,0.0001081519,0.00001016071],"genre_scores_gemma":[0.9171419,0.00001315296,0.08155929,0.0001122392,0.0006400968,0.000169645,0.0002687751,0.00004426287,0.00005066639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.404309,"threshold_uncertainty_score":0.9994298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03396385085223951,"score_gpt":0.2839576733863097,"score_spread":0.2499938225340702,"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."}}