{"id":"W3095672581","doi":"10.26434/chemrxiv.11869692","title":"RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"NeuroDevNet","funders":"Cancer Prevention and Research Institute of Texas","keywords":"Retrosynthetic analysis; Synthon; Interpretability; Computer science; Artificial intelligence; Chemistry; Stereochemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001248268,0.00200097,0.001034961,0.0009047545,0.0004784794,0.001136508,0.002762903,0.001701951,0.01713258],"category_scores_gemma":[0.002772303,0.000855059,0.001391645,0.0005406396,0.000601889,0.002144212,0.001216303,0.001877936,0.006282774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009775134,"about_ca_system_score_gemma":0.002149719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002979205,"about_ca_topic_score_gemma":0.007200152,"domain_scores_codex":[0.9995214,0.00006986025,0.00002075791,0.000229271,0.000124522,0.0000342286],"domain_scores_gemma":[0.9990731,0.0004817033,0.00006856757,0.0002224144,0.0001046215,0.00004954343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001012837,0.0003288974,0.002899091,0.0007445706,0.0001910805,0.0003254167,0.00013292,0.2193156,0.02857953,0.0274215,0.04881119,0.6702374],"study_design_scores_gemma":[0.00007071247,0.00007029479,0.000163092,0.00002100755,0.00003167374,0.00006086432,0.00001544851,0.9603315,0.01308606,0.01245307,0.01367751,0.00001877065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01353214,0.0004060967,0.9362606,0.0006933702,0.0002044185,0.0002765951,0.00136619,0.04077227,0.006488275],"genre_scores_gemma":[0.0990962,0.000296391,0.8844362,0.00070153,0.00009552971,0.00033448,0.002707557,0.002566706,0.009765385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01713258,"threshold_uncertainty_score":0.05731422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02020156239878657,"score_gpt":0.260537496444046,"score_spread":0.2403359340452594,"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."}}