{"id":"W4386693866","doi":"10.1101/2023.09.08.556930","title":"Bayesian optimization of separation gradients to maximize the performance of untargeted LC-MS","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Chromatography; Liquid chromatography–mass spectrometry; Gradient elution; Python (programming language); Computer science; Elution; Tandem mass spectrometry; Mass spectrometry; Chemistry; High-performance liquid chromatography","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":[0.003079264,0.001633718,0.001116473,0.0007238153,0.0003919992,0.001205418,0.001086523,0.001242606,0.001489513],"category_scores_gemma":[0.006561175,0.0007565197,0.0007261054,0.0004484338,0.0009231723,0.001274784,0.001427091,0.001334374,0.0006895586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000902187,"about_ca_system_score_gemma":0.001423166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001688454,"about_ca_topic_score_gemma":0.002215473,"domain_scores_codex":[0.9991251,0.0003498144,0.0000434433,0.0002006978,0.0001866406,0.00009432832],"domain_scores_gemma":[0.9982798,0.001069338,0.0001812723,0.000108167,0.0002707125,0.00009073201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007439896,0.0002398642,0.002730924,0.0004532503,0.0002012779,0.0001049172,0.0001283576,0.7887601,0.06410678,0.01128776,0.00320784,0.1280351],"study_design_scores_gemma":[0.00002407877,0.00004399644,0.0003053938,0.00001094192,0.00001288992,0.00001524224,0.000006059654,0.9862339,0.009200173,0.003539159,0.0005913524,0.00001686237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04405728,0.0004966513,0.9516864,0.0002768819,0.00003262076,0.00006876909,0.0001747025,0.001893997,0.001312641],"genre_scores_gemma":[0.4345093,0.0003052457,0.5604514,0.0004415115,0.00003980131,0.0003098018,0.0006879428,0.001018862,0.002236079],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003079264,"threshold_uncertainty_score":0.01628488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01216557687555846,"score_gpt":0.232378015817271,"score_spread":0.2202124389417125,"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."}}