{"id":"W4387139413","doi":"10.21203/rs.3.rs-3338667/v1","title":"Bayesian optimization of separation gradients to maximize the performance of untargeted LC-MS","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Separation (statistics); Bayesian optimization; Chromatography; Bayesian probability; Computer science; Chemistry; Biochemical engineering; Artificial intelligence; Machine learning; Engineering","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":[0.002239221,0.002066013,0.001081805,0.0005570714,0.0004863296,0.001271084,0.001312323,0.001576682,0.002539956],"category_scores_gemma":[0.007027134,0.0009818887,0.0006272568,0.0005971247,0.001021147,0.001842413,0.00137495,0.001746718,0.001316913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163892,"about_ca_system_score_gemma":0.002673783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003712281,"about_ca_topic_score_gemma":0.004918261,"domain_scores_codex":[0.9991851,0.000303687,0.00003729326,0.0001823213,0.0001988036,0.00009270874],"domain_scores_gemma":[0.9982764,0.001031109,0.0001640711,0.0001119988,0.0003358884,0.00008047809],"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":[0.0008231552,0.0003507565,0.0007975868,0.0004213031,0.0001796079,0.00008314128,0.0001499396,0.7530671,0.0588273,0.02274259,0.004292051,0.1582655],"study_design_scores_gemma":[0.00003562014,0.00005866829,0.0003129338,0.00001482886,0.00001840033,0.00002355075,0.000007259391,0.9810655,0.01164223,0.006042277,0.0007574151,0.00002130667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01914184,0.0003431819,0.9774429,0.0003155374,0.00002534833,0.00006043539,0.0001151457,0.0009264763,0.001629272],"genre_scores_gemma":[0.3370934,0.000405479,0.6539646,0.0003272399,0.00006472065,0.000285237,0.000532517,0.0008267906,0.006500047],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003712281,"threshold_uncertainty_score":0.01184231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0440566599252457,"score_gpt":0.3694816426654911,"score_spread":0.3254249827402453,"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."}}