{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001417638,0.0001376004,0.0001401044,0.00003989642,0.0005707156,0.0001169884,0.0006722702,0.00002715095,0.00001220169],"category_scores_gemma":[0.0001495617,0.00006733427,0.00005433869,0.0002786941,0.00252809,0.00003771007,0.0008340761,0.0001323992,0.000008588681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002181035,"about_ca_system_score_gemma":0.00001138385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001376468,"about_ca_topic_score_gemma":0.00002317605,"domain_scores_codex":[0.9986314,0.00006724946,0.0002050508,0.0003922586,0.0003731142,0.0003309521],"domain_scores_gemma":[0.9994015,0.0001297781,0.00008920684,0.0003416621,0.000004730879,0.00003318977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001601562,0.00001997647,0.003748604,0.000007213708,0.00001361355,0.000003068632,0.0003996469,0.00001540685,0.9937458,0.0008209204,0.0002417507,0.0009679842],"study_design_scores_gemma":[0.001059496,0.00003948866,0.02474239,0.00002912735,0.00004134148,0.00005890459,0.01962238,0.0002860682,0.9302808,0.005421492,0.01804389,0.0003746142],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916669,0.00595498,0.00002433622,0.001357984,0.0001167397,0.0002318168,0.00001867218,0.000008151477,0.0006204678],"genre_scores_gemma":[0.9939414,0.005139316,0.0001906266,0.0004356605,0.00009265738,0.00006473587,0.00002515489,0.000006244168,0.0001041696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.063465,"threshold_uncertainty_score":0.9314852,"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."}}