{"id":"W3164523874","doi":"10.1101/2021.05.24.445406","title":"Pathway analysis in metabolomics: pitfalls and best practice for the use of over-representation analysis","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Agence Nationale de la Recherche; National Institute for Health and Care Research; NIHR Imperial Biomedical Research Centre; National Institutes of Health; Ontario Institute for Cancer Research; Ministère de l'Enseignement supérieur, de la Recherche et de l'Innovation; Deutsche Forschungsgemeinschaft; Wellcome Trust","keywords":"Metabolomics; Pathway analysis; KEGG; Set (abstract data type); Computer science; Computational biology; Data mining; Bioinformatics; Biology; Genetics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006931587,0.0003512329,0.0008857158,0.0005263959,0.00009689222,0.0001893005,0.0002812695,0.0003275523,0.000008612477],"category_scores_gemma":[0.001502353,0.0003127603,0.0005032163,0.001656901,0.0001190325,0.00002283841,0.0005752302,0.0002414428,2.59845e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003578713,"about_ca_system_score_gemma":0.0002148248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005166539,"about_ca_topic_score_gemma":0.0002712548,"domain_scores_codex":[0.9977272,0.0002174187,0.0005943712,0.0009338142,0.0002270229,0.0003001947],"domain_scores_gemma":[0.9971204,0.0002965341,0.0006585429,0.00117641,0.000669204,0.00007889874],"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":[0.0001277587,0.0003674806,0.07212332,0.0001087273,0.01851629,0.000006212815,0.00002164437,0.004276028,0.9039735,0.0004206191,0.00005223907,0.000006215135],"study_design_scores_gemma":[0.0011163,0.0001942527,0.4250762,0.00004536523,0.02569904,1.722954e-8,0.0001205847,0.005173886,0.5225501,0.000002128899,0.0190406,0.000981523],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638098,0.01168162,0.02302799,0.0001980827,0.0002036677,0.0005749936,0.0004923153,0.000009700033,0.000001786649],"genre_scores_gemma":[0.973922,0.009910423,0.01568137,0.0001150631,0.0001252456,0.0001898122,0.000009106202,0.00003775924,0.000009200438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3814234,"threshold_uncertainty_score":0.9999325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02596632023368275,"score_gpt":0.268043385516039,"score_spread":0.2420770652823563,"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."}}