{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1738114,0.002543644,0.003105794,0.005587598,0.002377755,0.01368892,0.009501587,0.004253355,0.003981788],"category_scores_gemma":[0.396292,0.001631551,0.002908632,0.007857829,0.01083079,0.0141617,0.009213457,0.01624861,0.003908902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003676374,"about_ca_system_score_gemma":0.01030158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005530586,"about_ca_topic_score_gemma":0.005680402,"domain_scores_codex":[0.842388,0.1089026,0.01423219,0.00790942,0.02534143,0.001226373],"domain_scores_gemma":[0.4710089,0.354895,0.01861636,0.07897684,0.07186054,0.00464247],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007757939,0.0004197489,0.01362052,0.008465204,0.001065186,0.0009592387,0.004414337,0.01731756,0.008608144,0.1793554,0.123841,0.6411579],"study_design_scores_gemma":[0.000163238,0.0003721269,0.004720917,0.01641659,0.0003541585,0.00160663,0.002584371,0.04599841,0.01410266,0.6038271,0.3090875,0.000766247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01016338,0.04712172,0.8043676,0.118541,0.002805342,0.0004223234,0.001115801,0.008188777,0.007274132],"genre_scores_gemma":[0.07140128,0.01984746,0.8892519,0.01309958,0.0008746761,0.0006307066,0.0009267896,0.00271348,0.001254064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8261886,"threshold_uncertainty_score":0.9192135,"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."}}