Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses

Xiaoxiao Wang; Xinran Hao; Jie Yan; Ji Xu; Dandan Hu; Fenfen Ji; Ting Zeng; Fuyue Wang; Bolun Wang; Jiacheng Fang; Jing Ji; Hemi Luan; Yanjun Hong; Yanhao Zhang; Jinyao Chen; Min Li; Zhu Yang; Doudou Zhang; Wenlan Liu; Xiaodong Cai; Zongwei Cai

doi:10.1016/j.cclet.2023.108230

Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses

Xiaoxiao Wang, Xinran Hao, Jie Yan, Ji Xu, Dandan Hu, Fenfen Ji, Ting Zeng, Fuyue Wang, Bolun Wang, Jiacheng Fang, Jing Ji, Hemi Luan, Yanjun Hong, Yanhao Zhang, Jinyao Chen, Min Li, Zhu Yang, Doudou Zhang^*, Wenlan Liu^*, Xiaodong Cai^*Zongwei Cai^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › peer-review

11 Citations (Scopus)

Abstract

Parkinson's disease (PD) is a complex neurological disorder that typically worsens with age. A wide range of pathologies makes PD a very heterogeneous condition, and there are currently no reliable diagnostic tests for this disease. The application of metabolomics to the study of PD has the potential to identify disease biomarkers through the systematic evaluation of metabolites. In this study, urine metabolic profiles of 215 urine samples from 104 PD patients and 111 healthy individuals were assessed based on liquid chromatography-mass spectrometry. The urine metabolic profile was first evaluated with partial least-squares discriminant analysis, and then we integrated the metabolomic data with ensemble machine learning techniques using the voting strategy to achieve better predictive performance. A combination of 8-metabolite predictive panel performed well with an accuracy of over 90.7%. Compared to control subjects, PD patients had higher levels of 3-methoxytyramine, N-acetyl-L-tyrosine, orotic acid, uric acid, vanillic acid, and xanthine, and lower levels of 3,3-dimethylglutaric acid and imidazolelactic acid in their urine. The multi-metabolite prediction model developed in this study can serve as an initial point for future clinical studies.

Original language	English
Article number	108230
Journal	Chinese Chemical Letters
Volume	34
Issue number	10
Early online date	16 Feb 2023
DOIs	https://doi.org/10.1016/j.cclet.2023.108230
Publication status	Published - Oct 2023

User-Defined Keywords

Biomarker
High-resolution mass spectrometry
Machine learning
Metabolomic
Parkinson's disease

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.cclet.2023.108230

Cite this

Wang, X., Hao, X., Yan, J., Xu, J., Hu, D., Ji, F., Zeng, T., Wang, F., Wang, B., Fang, J., Ji, J., Luan, H., Hong, Y., Zhang, Y., Chen, J., Li, M., Yang, Z., Zhang, D., Liu, W., ... Cai, Z. (2023). Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses. Chinese Chemical Letters, 34(10), Article 108230. https://doi.org/10.1016/j.cclet.2023.108230

@article{8aa47e2f92764384a753fd8fc769e10a,

title = "Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses",

abstract = "Parkinson's disease (PD) is a complex neurological disorder that typically worsens with age. A wide range of pathologies makes PD a very heterogeneous condition, and there are currently no reliable diagnostic tests for this disease. The application of metabolomics to the study of PD has the potential to identify disease biomarkers through the systematic evaluation of metabolites. In this study, urine metabolic profiles of 215 urine samples from 104 PD patients and 111 healthy individuals were assessed based on liquid chromatography-mass spectrometry. The urine metabolic profile was first evaluated with partial least-squares discriminant analysis, and then we integrated the metabolomic data with ensemble machine learning techniques using the voting strategy to achieve better predictive performance. A combination of 8-metabolite predictive panel performed well with an accuracy of over 90.7%. Compared to control subjects, PD patients had higher levels of 3-methoxytyramine, N-acetyl-L-tyrosine, orotic acid, uric acid, vanillic acid, and xanthine, and lower levels of 3,3-dimethylglutaric acid and imidazolelactic acid in their urine. The multi-metabolite prediction model developed in this study can serve as an initial point for future clinical studies.",

keywords = "Biomarker, High-resolution mass spectrometry, Machine learning, Metabolomic, Parkinson's disease",

author = "Xiaoxiao Wang and Xinran Hao and Jie Yan and Ji Xu and Dandan Hu and Fenfen Ji and Ting Zeng and Fuyue Wang and Bolun Wang and Jiacheng Fang and Jing Ji and Hemi Luan and Yanjun Hong and Yanhao Zhang and Jinyao Chen and Min Li and Zhu Yang and Doudou Zhang and Wenlan Liu and Xiaodong Cai and Zongwei Cai",

note = "Funding Information: The authors would like to acknowledge the financial support from the Collaborative Research Fund (No. C2011–21GF) and from Guangdong Province Basic and Applied Basic Research Foundation (No. 2021B1515120051). Publisher Copyright: {\textcopyright} 2023 Published by Elsevier B.V. on behalf of Chinese Chemical Society and Institute of Materia Medica, Chinese Academy of Medical Sciences.",

year = "2023",

month = oct,

doi = "10.1016/j.cclet.2023.108230",

language = "English",

volume = "34",

journal = "Chinese Chemical Letters",

issn = "1001-8417",

publisher = "Elsevier B.V.",

number = "10",

}

Wang, X, Hao, X, Yan, J, Xu, J, Hu, D, Ji, F, Zeng, T, Wang, F, Wang, B, Fang, J, Ji, J, Luan, H, Hong, Y, Zhang, Y, Chen, J, Li, M , Yang, Z, Zhang, D, Liu, W, Cai, X & Cai, Z 2023, 'Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses', Chinese Chemical Letters, vol. 34, no. 10, 108230. https://doi.org/10.1016/j.cclet.2023.108230

TY - JOUR

T1 - Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses

AU - Wang, Xiaoxiao

AU - Hao, Xinran

AU - Yan, Jie

AU - Xu, Ji

AU - Hu, Dandan

AU - Ji, Fenfen

AU - Zeng, Ting

AU - Wang, Fuyue

AU - Wang, Bolun

AU - Fang, Jiacheng

AU - Ji, Jing

AU - Luan, Hemi

AU - Hong, Yanjun

AU - Zhang, Yanhao

AU - Chen, Jinyao

AU - Li, Min

AU - Yang, Zhu

AU - Zhang, Doudou

AU - Liu, Wenlan

AU - Cai, Xiaodong

AU - Cai, Zongwei

N1 - Funding Information: The authors would like to acknowledge the financial support from the Collaborative Research Fund (No. C2011–21GF) and from Guangdong Province Basic and Applied Basic Research Foundation (No. 2021B1515120051). Publisher Copyright: © 2023 Published by Elsevier B.V. on behalf of Chinese Chemical Society and Institute of Materia Medica, Chinese Academy of Medical Sciences.

PY - 2023/10

Y1 - 2023/10

N2 - Parkinson's disease (PD) is a complex neurological disorder that typically worsens with age. A wide range of pathologies makes PD a very heterogeneous condition, and there are currently no reliable diagnostic tests for this disease. The application of metabolomics to the study of PD has the potential to identify disease biomarkers through the systematic evaluation of metabolites. In this study, urine metabolic profiles of 215 urine samples from 104 PD patients and 111 healthy individuals were assessed based on liquid chromatography-mass spectrometry. The urine metabolic profile was first evaluated with partial least-squares discriminant analysis, and then we integrated the metabolomic data with ensemble machine learning techniques using the voting strategy to achieve better predictive performance. A combination of 8-metabolite predictive panel performed well with an accuracy of over 90.7%. Compared to control subjects, PD patients had higher levels of 3-methoxytyramine, N-acetyl-L-tyrosine, orotic acid, uric acid, vanillic acid, and xanthine, and lower levels of 3,3-dimethylglutaric acid and imidazolelactic acid in their urine. The multi-metabolite prediction model developed in this study can serve as an initial point for future clinical studies.

AB - Parkinson's disease (PD) is a complex neurological disorder that typically worsens with age. A wide range of pathologies makes PD a very heterogeneous condition, and there are currently no reliable diagnostic tests for this disease. The application of metabolomics to the study of PD has the potential to identify disease biomarkers through the systematic evaluation of metabolites. In this study, urine metabolic profiles of 215 urine samples from 104 PD patients and 111 healthy individuals were assessed based on liquid chromatography-mass spectrometry. The urine metabolic profile was first evaluated with partial least-squares discriminant analysis, and then we integrated the metabolomic data with ensemble machine learning techniques using the voting strategy to achieve better predictive performance. A combination of 8-metabolite predictive panel performed well with an accuracy of over 90.7%. Compared to control subjects, PD patients had higher levels of 3-methoxytyramine, N-acetyl-L-tyrosine, orotic acid, uric acid, vanillic acid, and xanthine, and lower levels of 3,3-dimethylglutaric acid and imidazolelactic acid in their urine. The multi-metabolite prediction model developed in this study can serve as an initial point for future clinical studies.

KW - Biomarker

KW - High-resolution mass spectrometry

KW - Machine learning

KW - Metabolomic

KW - Parkinson's disease

UR - http://www.scopus.com/inward/record.url?scp=85164722666&partnerID=8YFLogxK

U2 - 10.1016/j.cclet.2023.108230

DO - 10.1016/j.cclet.2023.108230

M3 - Journal article

AN - SCOPUS:85164722666

SN - 1001-8417

VL - 34

JO - Chinese Chemical Letters

JF - Chinese Chemical Letters

IS - 10

M1 - 108230

ER -

Urine biomarkers discovery by metabolomics and machine learning for Parkinson's disease diagnoses

Abstract

User-Defined Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this