{"id":"W4391404301","doi":"10.1021/acs.analchem.3c05124","title":"ChloroDBPFinder: Machine Learning-Guided Recognition of Chlorinated Disinfection Byproducts from Nontargeted LC-HRMS Analysis","year":2024,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Water Treatment and Disinfection","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of British Columbia","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Chemistry; PubChem; Artificial intelligence; Machine learning; Support vector machine; Random forest; Pattern recognition (psychology); Chromatography; Computer science; Organic 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00102095,0.001409971,0.0007785255,0.00193605,0.0004269484,0.0008364174,0.001575894,0.001124875,0.002759956],"category_scores_gemma":[0.001626473,0.0005063144,0.0008651954,0.0006408851,0.0003332648,0.001080677,0.001202269,0.0008120671,0.001801664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006645375,"about_ca_system_score_gemma":0.001173888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003877891,"about_ca_topic_score_gemma":0.006441449,"domain_scores_codex":[0.9993877,0.0000564381,0.00002738377,0.0002833809,0.0001685072,0.00007658399],"domain_scores_gemma":[0.9993848,0.0002007085,0.0001242477,0.00009661126,0.0001442201,0.00004931701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001724729,0.0005599036,0.04521591,0.001760251,0.0005538295,0.0007629879,0.0002581932,0.03261709,0.3448263,0.001164713,0.03486935,0.5356867],"study_design_scores_gemma":[0.0001656284,0.0004113844,0.0173649,0.00009050632,0.0001339187,0.0007866671,0.00008026044,0.6600553,0.2956496,0.002021091,0.02308543,0.0001554121],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2385213,0.00318933,0.6235808,0.0005862897,0.0002073385,0.0004817925,0.01687986,0.1121681,0.004385116],"genre_scores_gemma":[0.4376358,0.0007420797,0.5299126,0.0007484936,0.00007213486,0.000560137,0.02366567,0.001694248,0.004968807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003877891,"threshold_uncertainty_score":0.009232998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01407578044700938,"score_gpt":0.2315549019643788,"score_spread":0.2174791215173694,"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."}}