Plasma Metabolomics and Machine Learning-Driven Novel Diagnostic Signature for Non-Alcoholic Steatohepatitis
Open Access
- 11 July 2022
- journal article
- research article
- Published by MDPI AG in Biomedicines
- Vol. 10 (7) , 1669
Abstract
We performed targeted metabolomics with machine learning (ML)-based interpretation to identify metabolites that distinguish the progression of nonalcoholic fatty liver disease (NAFLD) in a cohort. Plasma metabolomics analysis was conducted in healthy control subjects (n = 25) and patients with NAFL (n = 42) and nonalcoholic steatohepatitis (NASH, n = 19) by gas chromatography-tandem mass spectrometry (MS/MS) and liquid chromatography-MS/MS as well as RNA sequencing (RNA-seq) analyses on liver tissues from patients with varying stages of NAFLD (n = 12). The resulting metabolomic data were subjected to routine statistical and ML-based analyses and multi-omics interpretation with RNA-seq data. We found 6 metabolites that were significantly altered in NAFLD among 79 detected metabolites. Random-forest and multinomial logistic regression analyses showed that eight metabolites (glutamic acid, cis-aconitic acid, aspartic acid, isocitric acid, α-ketoglutaric acid, oxaloacetic acid, myristoleic acid, and tyrosine) could distinguish the three groups. Then, the recursive partitioning and regression tree algorithm selected three metabolites (glutamic acid, isocitric acid, and aspartic acid) from these eight metabolites. With these three metabolites, we formulated an equation, the MetaNASH score that distinguished NASH with excellent performance. In addition, metabolic map construction and correlation assays integrating metabolomics data into the transcriptome datasets of the liver showed correlations between the concentration of plasma metabolites and the expression of enzymes governing metabolism and specific alterations of these correlations in NASH. Therefore, these findings will be useful for evaluation of altered metabolism in NASH and understanding of pathophysiologic implications from metabolite profiles in relation to NAFLD progression.Keywords
All Related Versions
Funding Information
- Korea Health Industry Development Institute (KHIDI) (HI14C1135, NRF-2021R1A5A2030333, 2015R1A4A1041219, 2018R1D1A1B07041045, 2020R1A2C2010964, 2021R1A5A8029876, FRD2021-03)
- the Basic Science Research Program through the National Research Foundation of Korea (NRF) (HI14C1135, NRF-2021R1A5A2030333, 2015R1A4A1041219, 2018R1D1A1B07041045, 2020R1A2C2010964, 2021R1A5A8029876, FRD2021-03)
- Gachon University Gil Medical Center (HI14C1135, NRF-2021R1A5A2030333, 2015R1A4A1041219, 2018R1D1A1B07041045, 2020R1A2C2010964, 2021R1A5A8029876, FRD2021-03)
This publication has 52 references indexed in Scilit:
- Enhancing nucleotide metabolism protects against mitochondrial dysfunction and neurodegeneration in a PINK1 model of Parkinson’s diseaseNature Cell Biology, 2014
- Genome-scale metabolic modelling of hepatocytes reveals serine deficiency in patients with non-alcoholic fatty liver diseaseNature Communications, 2014
- Elevated citrate levels in non‐alcoholic fatty liver disease: The potential of citrate to promote radical productionFEBS Letters, 2013
- Plasma metabolomic profile in nonalcoholic fatty liver diseaseMetabolism, 2011
- The plasma lipidomic signature of nonalcoholic steatohepatitis†‡Hepatology, 2009
- Activation of the complement system in human nonalcoholic fatty liver disease†Hepatology, 2009
- Supervised learning with decision tree-based methods in computational and systems biologyMolecular BioSystems, 2009
- Hepatic glutamate metabolism: a tale of 2 hepatocytesThe American Journal of Clinical Nutrition, 2009
- Design and validation of a histological scoring system for nonalcoholic fatty liver disease†Hepatology, 2005
- Impaired insulin-mediated amino acid plasma disappearance in non-alcoholic fatty liver disease: a feature of insulin resistanceDigestive and Liver Disease, 2003