{"id":"W4323781060","doi":"10.1039/d2va00225f","title":"Getting the SMILES right: identifying inconsistent chemical identities in the ECHA database, PubChem and the CompTox Chemicals Dashboard","year":2023,"lang":"en","type":"article","venue":"Environmental Science Advances","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto; Bundesamt für Umwelt; U.S. Environmental Protection Agency","keywords":"PubChem; Identifier; Dashboard; Computer science; Database; Chemical database; Information retrieval; Data science; World Wide Web; Computational biology; Bioinformatics; Computer network; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01512978,0.001854976,0.001897567,0.008259219,0.003342056,0.008076143,0.002658546,0.004065275,0.08336356],"category_scores_gemma":[0.09131262,0.001778931,0.00106297,0.009720343,0.001800952,0.008980785,0.007334205,0.004147293,0.05622124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534357,"about_ca_system_score_gemma":0.005008476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002169519,"about_ca_topic_score_gemma":0.003473746,"domain_scores_codex":[0.9861335,0.002965412,0.002974103,0.001538802,0.005756724,0.0006314359],"domain_scores_gemma":[0.9259945,0.03115273,0.01426605,0.0134592,0.01257617,0.002551249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001853123,0.0003336557,0.01062208,0.001465754,0.0001123797,0.001828937,0.001256451,0.0005791291,0.006984221,0.01243902,0.8451502,0.1173751],"study_design_scores_gemma":[0.0002306295,0.0002057913,0.007630865,0.001331985,0.0001129119,0.00144694,0.0013542,0.003633995,0.02809606,0.02213835,0.9335665,0.0002518166],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.07014342,0.004737737,0.1734309,0.08459297,0.02763684,0.001458581,0.3355553,0.2159964,0.08644779],"genre_scores_gemma":[0.1379322,0.006402875,0.4340622,0.03104147,0.003289667,0.001424603,0.2500366,0.06490423,0.07090611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08336356,"threshold_uncertainty_score":0.2788789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01005662560071053,"score_gpt":0.2573975245140022,"score_spread":0.2473408989132916,"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."}}