{"id":"W2800440295","doi":"10.1021/acs.jctc.8b00110","title":"Many-Body Descriptors for Predicting Molecular Properties with Machine Learning: Analysis of Pairwise and Three-Body Interactions in Molecules","year":2018,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; H2020 Marie Skłodowska-Curie Actions; Bundesministerium für Bildung und Forschung; Banting and Best Diabetes Centre, University of Toronto; National Research Foundation of Korea; National Research Foundation; Deutsche Forschungsgemeinschaft; Ministry of Science, ICT and Future Planning","keywords":"Molecular descriptor; Chemical space; Molecule; Pairwise comparison; Computer science; Support vector machine; chEMBL; Artificial intelligence; Machine learning; Quantitative structure–activity relationship; Chemistry; Computational chemistry; Biological system; Pattern recognition (psychology); Drug discovery","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009311693,0.00009847599,0.0002568053,0.0003269666,0.00004733478,0.00005934184,0.0001343734,0.00002438503,0.00000129128],"category_scores_gemma":[0.0002627239,0.00007514234,0.00007212332,0.0004418759,0.0001254823,0.0003545037,0.00006828432,0.000148689,5.221021e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002500327,"about_ca_system_score_gemma":0.0000389184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004469561,"about_ca_topic_score_gemma":0.000001595645,"domain_scores_codex":[0.9989545,0.0002336054,0.0003709757,0.0001599157,0.0001842269,0.0000967313],"domain_scores_gemma":[0.9987035,0.0005769509,0.000328517,0.0000616261,0.0002762161,0.00005315573],"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":[0.003728856,0.0006196645,0.037414,0.0002555584,0.002332648,0.00003236227,0.007057053,0.3209033,0.368518,0.1857643,0.000008198132,0.07336614],"study_design_scores_gemma":[0.0004733407,0.0003058889,0.0041195,0.00009566244,0.0001714536,0.00003711726,0.00009464685,0.9370321,0.02969801,0.02788264,0.000005828536,0.00008383081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5014704,0.000108262,0.498274,0.00005718732,0.00002255736,0.0000487414,7.103798e-7,0.000005303182,0.00001277164],"genre_scores_gemma":[0.953682,0.00000376683,0.04624153,0.00003019702,0.00002855467,0.00000322022,0.000002553509,0.000005784478,0.000002387193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6161288,"threshold_uncertainty_score":0.3064216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02083932018880957,"score_gpt":0.2935287958371633,"score_spread":0.2726894756483538,"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."}}