Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD

IntroductionInflammatory bowel disease (IBD), comprising Crohn’s disease (CD) and ulcerative colitis (UC), is a chronic and relapsing inflammatory disorder of the gastrointestinal tract. Current diagnostic approaches are invasive, costly, and time-consuming, underscoring the need for non-invasive, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Miao-Lin Lei, Guan-Wei Bi, Xiao-Lin Yin, Yue Wang, Zi-Ru Sun, Xin-rui Guo, Hui-peng Zhang, Xiao-han Zhao, Feng Li, Yan-Bo Yu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Molecular Biosciences
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmolb.2025.1615047/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850033490990465024
author Miao-Lin Lei
Guan-Wei Bi
Xiao-Lin Yin
Xiao-Lin Yin
Yue Wang
Yue Wang
Yue Wang
Zi-Ru Sun
Zi-Ru Sun
Zi-Ru Sun
Xin-rui Guo
Hui-peng Zhang
Xiao-han Zhao
Feng Li
Feng Li
Yan-Bo Yu
author_facet Miao-Lin Lei
Guan-Wei Bi
Xiao-Lin Yin
Xiao-Lin Yin
Yue Wang
Yue Wang
Yue Wang
Zi-Ru Sun
Zi-Ru Sun
Zi-Ru Sun
Xin-rui Guo
Hui-peng Zhang
Xiao-han Zhao
Feng Li
Feng Li
Yan-Bo Yu
author_sort Miao-Lin Lei
collection DOAJ
description IntroductionInflammatory bowel disease (IBD), comprising Crohn’s disease (CD) and ulcerative colitis (UC), is a chronic and relapsing inflammatory disorder of the gastrointestinal tract. Current diagnostic approaches are invasive, costly, and time-consuming, underscoring the need for non-invasive, accurate diagnostic methods.MethodsWe conducted a targeted metabolomic analysis of 49 metabolites related to central carbon metabolism in urinary samples from individuals with IBD and control group. Diagnostic models were constructed using six machine learning algorithms, and their performance was evaluated by cross-validated area under the receiver operating characteristic curve (AUC). The SHAP (SHapley Additive exPlanations) method was used to interpret the models and identify key discriminatory features.ResultsSix metabolites—xylose, isocitric acid, fructose, L-fucose, N-acetyl-D-glucosamine (GlcNAc), and glycolic acid—differentiated UC from control group, while three metabolites—xylose, L-fucose, and citric acid—distinguished CD from control group. The optimal diagnostic model achieved a mean AUC of 0.84 for UC and 0.93 for CD. These models retained high diagnostic accuracy even after adjusting for disease activity. SHAP analysis identified L-fucose, xylose, and GlcNAc as important features for UC, and citric acid and xylose for CD.DiscussionOur findings highlight distinct metabolic signatures in central carbon metabolism associated with IBD subtypes. The identified metabolite panels, combined with machine learning models, offer promising non-invasive tools for differentiating UC and CD from healthy individuals.
format Article
id doaj-art-a7dd058018404c4fa064fce207c7132d
institution DOAJ
issn 2296-889X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Molecular Biosciences
spelling doaj-art-a7dd058018404c4fa064fce207c7132d2025-08-20T02:58:11ZengFrontiers Media S.A.Frontiers in Molecular Biosciences2296-889X2025-08-011210.3389/fmolb.2025.16150471615047Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBDMiao-Lin Lei0Guan-Wei Bi1Xiao-Lin Yin2Xiao-Lin Yin3Yue Wang4Yue Wang5Yue Wang6Zi-Ru Sun7Zi-Ru Sun8Zi-Ru Sun9Xin-rui Guo10Hui-peng Zhang11Xiao-han Zhao12Feng Li13Feng Li14Yan-Bo Yu15Department of Gastroenterology, Qilu Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Gastroenterology, Qilu Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Gastroenterology, Qilu Hospital of Shandong University, Jinan, ChinaClinical Epidemiology Unit, Qilu Hospital of Shandong University, Jinan, ChinaNational Key Laboratory for Innovation and Transformation of Luobing Theory, Jinan, ChinaThe Key Laboratory of Cardiovascular Remodeling and Function Research, Chinese Ministry of Education, Chinese National Health Commission and Chinese Academy of Medical Sciences, Jinan, ChinaDepartment of Cardiology, Qilu Hospital of Shandong University, Jinan, ChinaNational Key Laboratory for Innovation and Transformation of Luobing Theory, Jinan, ChinaThe Key Laboratory of Cardiovascular Remodeling and Function Research, Chinese Ministry of Education, Chinese National Health Commission and Chinese Academy of Medical Sciences, Jinan, ChinaDepartment of Cardiology, Qilu Hospital of Shandong University, Jinan, ChinaDepartment of Gastroenterology, Qilu Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Gastroenterology, Qilu Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Gastroenterology, Qilu Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Pancreatic Surgery, General Surgery, Qilu Hospital of Shandong University, Jinan, ChinaDepartment of Gastroentero-Pancreatic Surgery, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao, Shandong, ChinaDepartment of Gastroenterology, Qilu Hospital, Shandong University, Jinan, Shandong, ChinaIntroductionInflammatory bowel disease (IBD), comprising Crohn’s disease (CD) and ulcerative colitis (UC), is a chronic and relapsing inflammatory disorder of the gastrointestinal tract. Current diagnostic approaches are invasive, costly, and time-consuming, underscoring the need for non-invasive, accurate diagnostic methods.MethodsWe conducted a targeted metabolomic analysis of 49 metabolites related to central carbon metabolism in urinary samples from individuals with IBD and control group. Diagnostic models were constructed using six machine learning algorithms, and their performance was evaluated by cross-validated area under the receiver operating characteristic curve (AUC). The SHAP (SHapley Additive exPlanations) method was used to interpret the models and identify key discriminatory features.ResultsSix metabolites—xylose, isocitric acid, fructose, L-fucose, N-acetyl-D-glucosamine (GlcNAc), and glycolic acid—differentiated UC from control group, while three metabolites—xylose, L-fucose, and citric acid—distinguished CD from control group. The optimal diagnostic model achieved a mean AUC of 0.84 for UC and 0.93 for CD. These models retained high diagnostic accuracy even after adjusting for disease activity. SHAP analysis identified L-fucose, xylose, and GlcNAc as important features for UC, and citric acid and xylose for CD.DiscussionOur findings highlight distinct metabolic signatures in central carbon metabolism associated with IBD subtypes. The identified metabolite panels, combined with machine learning models, offer promising non-invasive tools for differentiating UC and CD from healthy individuals.https://www.frontiersin.org/articles/10.3389/fmolb.2025.1615047/fullinflammatory bowel diseaseulcerative colitisCrohn’s diseaseurinary metabolomicsmachine learningcentral carbon metabolism
spellingShingle Miao-Lin Lei
Guan-Wei Bi
Xiao-Lin Yin
Xiao-Lin Yin
Yue Wang
Yue Wang
Yue Wang
Zi-Ru Sun
Zi-Ru Sun
Zi-Ru Sun
Xin-rui Guo
Hui-peng Zhang
Xiao-han Zhao
Feng Li
Feng Li
Yan-Bo Yu
Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD
Frontiers in Molecular Biosciences
inflammatory bowel disease
ulcerative colitis
Crohn’s disease
urinary metabolomics
machine learning
central carbon metabolism
title Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD
title_full Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD
title_fullStr Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD
title_full_unstemmed Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD
title_short Targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for IBD
title_sort targeted urinary metabolomics combined with machine learning to identify biomarkers related to central carbon metabolism for ibd
topic inflammatory bowel disease
ulcerative colitis
Crohn’s disease
urinary metabolomics
machine learning
central carbon metabolism
url https://www.frontiersin.org/articles/10.3389/fmolb.2025.1615047/full
work_keys_str_mv AT miaolinlei targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT guanweibi targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT xiaolinyin targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT xiaolinyin targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT yuewang targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT yuewang targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT yuewang targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT zirusun targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT zirusun targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT zirusun targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT xinruiguo targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT huipengzhang targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT xiaohanzhao targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT fengli targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT fengli targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd
AT yanboyu targetedurinarymetabolomicscombinedwithmachinelearningtoidentifybiomarkersrelatedtocentralcarbonmetabolismforibd