LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes

BackgroundChanges in certain metabolites are linked to an increased risk of type I diabetes (T1D), making metabolite analysis a valuable tool for T1D diagnosis and treatment. This study aimed to identify a metabolic signature linked with T1D.MethodsUntargeted metabolomic profiling was performed usin...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhadasi Tuerxunyiming, Qing Zhao, Qiaosheng Hu, Ping Zhu, Shiting Zhu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Endocrinology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fendo.2025.1588718/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393121483292672
author Muhadasi Tuerxunyiming
Muhadasi Tuerxunyiming
Qing Zhao
Qiaosheng Hu
Ping Zhu
Shiting Zhu
author_facet Muhadasi Tuerxunyiming
Muhadasi Tuerxunyiming
Qing Zhao
Qiaosheng Hu
Ping Zhu
Shiting Zhu
author_sort Muhadasi Tuerxunyiming
collection DOAJ
description BackgroundChanges in certain metabolites are linked to an increased risk of type I diabetes (T1D), making metabolite analysis a valuable tool for T1D diagnosis and treatment. This study aimed to identify a metabolic signature linked with T1D.MethodsUntargeted metabolomic profiling was performed using liquid chromatography–mass spectrometry (LC-MS) on peripheral blood samples from T1D patients (n = 45) and healthy controls (n = 40). Data preprocessing and quality control were conducted using MetaboAnalyst 4.0. Differential metabolites (DMs) were identified via Wilcoxon rank-sum test (P< 0.05), and key diagnostic markers were selected using least absolute shrinkage and selection operator (LASSO) regression. A streptozotocin (STZ)-induced diabetic rat model was used for in vivo validation.ResultsA total of 157 annotated metabolites were detected (58 in ESI− and 99 in ESI+ mode). Twenty-six DMs were identified, including 25 upregulated and 1 downregulated in the T1D group, mainly involving Acylcarnitines and xanthine metabolites. LASSO regression selected Hydroxyhexadecanoyl carnitine, Propionylcarnitine, and Valerylcarnitine as candidate markers. In the rat model, Hydroxyhexadecanoyl carnitine and Valerylcarnitine demonstrated strong diagnostic performance, with AUCs of 0.9383 (95% CI: 0.8786–0.9980) and 0.8395 (95% CI: 0.7451–0.9338), respectively (P< 0.01).ConclusionHydroxyhexadecanoyl carnitine and Valerylcarnitine are closely linked to altered lipid oxidation in T1D and show strong potential as diagnostic biomarkers. These findings provide new insights into the metabolic basis of T1D and offer promising targets for early detection.
format Article
id doaj-art-03fcaaa41e01458ba32be79b2eb345f7
institution Kabale University
issn 1664-2392
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Endocrinology
spelling doaj-art-03fcaaa41e01458ba32be79b2eb345f72025-08-20T03:40:31ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922025-08-011610.3389/fendo.2025.15887181588718LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetesMuhadasi Tuerxunyiming0Muhadasi Tuerxunyiming1Qing Zhao2Qiaosheng Hu3Ping Zhu4Shiting Zhu5Zhejiang University School of Medicine, Hangzhou, ChinaSchool of Medicine, Hangzhou City University, Hangzhou, ChinaEndocrinology Department, Lianshui County People’s Hospital, Huai’an, Jiangsu, ChinaEndocrinology Department, Lianshui County People’s Hospital, Huai’an, Jiangsu, ChinaEndocrinology Department, The Affiliated Chuzhou Hospital of Traditional Chinese Medicine of Jiangsu College of Nursing, Huai’an, Jiangsu, ChinaRehabilitation Medicine Department, Lianshui County People’s Hospital, Huai’an, Jiangsu, ChinaBackgroundChanges in certain metabolites are linked to an increased risk of type I diabetes (T1D), making metabolite analysis a valuable tool for T1D diagnosis and treatment. This study aimed to identify a metabolic signature linked with T1D.MethodsUntargeted metabolomic profiling was performed using liquid chromatography–mass spectrometry (LC-MS) on peripheral blood samples from T1D patients (n = 45) and healthy controls (n = 40). Data preprocessing and quality control were conducted using MetaboAnalyst 4.0. Differential metabolites (DMs) were identified via Wilcoxon rank-sum test (P< 0.05), and key diagnostic markers were selected using least absolute shrinkage and selection operator (LASSO) regression. A streptozotocin (STZ)-induced diabetic rat model was used for in vivo validation.ResultsA total of 157 annotated metabolites were detected (58 in ESI− and 99 in ESI+ mode). Twenty-six DMs were identified, including 25 upregulated and 1 downregulated in the T1D group, mainly involving Acylcarnitines and xanthine metabolites. LASSO regression selected Hydroxyhexadecanoyl carnitine, Propionylcarnitine, and Valerylcarnitine as candidate markers. In the rat model, Hydroxyhexadecanoyl carnitine and Valerylcarnitine demonstrated strong diagnostic performance, with AUCs of 0.9383 (95% CI: 0.8786–0.9980) and 0.8395 (95% CI: 0.7451–0.9338), respectively (P< 0.01).ConclusionHydroxyhexadecanoyl carnitine and Valerylcarnitine are closely linked to altered lipid oxidation in T1D and show strong potential as diagnostic biomarkers. These findings provide new insights into the metabolic basis of T1D and offer promising targets for early detection.https://www.frontiersin.org/articles/10.3389/fendo.2025.1588718/fulltype 1 diabetesmetabolomicsLC-MSmetabolic markersLASSO
spellingShingle Muhadasi Tuerxunyiming
Muhadasi Tuerxunyiming
Qing Zhao
Qiaosheng Hu
Ping Zhu
Shiting Zhu
LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes
Frontiers in Endocrinology
type 1 diabetes
metabolomics
LC-MS
metabolic markers
LASSO
title LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes
title_full LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes
title_fullStr LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes
title_full_unstemmed LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes
title_short LC-MS-based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type I diabetes
title_sort lc ms based conventional metabolomics combined with machine learning models to identify metabolic markers for the diagnosis of type i diabetes
topic type 1 diabetes
metabolomics
LC-MS
metabolic markers
LASSO
url https://www.frontiersin.org/articles/10.3389/fendo.2025.1588718/full
work_keys_str_mv AT muhadasituerxunyiming lcmsbasedconventionalmetabolomicscombinedwithmachinelearningmodelstoidentifymetabolicmarkersforthediagnosisoftypeidiabetes
AT muhadasituerxunyiming lcmsbasedconventionalmetabolomicscombinedwithmachinelearningmodelstoidentifymetabolicmarkersforthediagnosisoftypeidiabetes
AT qingzhao lcmsbasedconventionalmetabolomicscombinedwithmachinelearningmodelstoidentifymetabolicmarkersforthediagnosisoftypeidiabetes
AT qiaoshenghu lcmsbasedconventionalmetabolomicscombinedwithmachinelearningmodelstoidentifymetabolicmarkersforthediagnosisoftypeidiabetes
AT pingzhu lcmsbasedconventionalmetabolomicscombinedwithmachinelearningmodelstoidentifymetabolicmarkersforthediagnosisoftypeidiabetes
AT shitingzhu lcmsbasedconventionalmetabolomicscombinedwithmachinelearningmodelstoidentifymetabolicmarkersforthediagnosisoftypeidiabetes