Machine Learning-Based Plasma Metabolomics in Liraglutide-Treated Type 2 Diabetes Mellitus Patients and Diet-Induced Obese Mice - Research findings

Aug 3, 2026

Liraglutide, a GLP-1 receptor agonist, improves glycemic control and supports weight loss in type 2 diabetes mellitus (T2DM) and obesity, yet its shared metabolic effects and cross-species relationships remain unclear. This study applies advanced machine learning to plasma metabolomic data from diet-induced obese mice and T2DM patients receiving liraglutide. Support Vector Machine best fits DIO mice, while Gradient Boosting performs best for patients. Cross-model evaluation shows liraglutide drives metabolic shifts and reveals interspecies correlations, informing future therapeutic strategies.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Liraglutide and the need for cross-species metabolic understanding

Metabolomics challenges and biomarker discovery

Machine learning-based comparative plasma metabolomics

Model selection for mice versus patients

Cross-evaluation and identification of shared metabolic correlations

Comparative analysis and therapeutic implications

Article Machine Learning-Based Plasma Metabolomics in Liraglutide-Treated Type 2 Diabetes Mellitus Patients and Diet-Induced Obese Mice Seokjae Park 1,2 and Eun-Kyoung Kim 1,2, * Citation: Park, S.; Kim, E.-K. Machine Learning-Based Plasma Metabolomicsin Liraglutide-Treated Type 2 Diabetes Mellitus Patients and Diet-Induced Obese Mice. Metabolites 2024, 14, 483 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)metabo14090483 Academic Editor: Xinhui Wang Received: 12 August 2024 Revised: 30 August 2024 Accepted: 30 August 2024 Published: 2 September 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Brain Sciences, Daegu Gyeongbuk Institute of Science and Technology, Daegu 42988, Republic of Korea; [godclover7@dgist.ac.kr](godclover7@dgist.ac.kr) 2 Neurometabolomics Research Center, Daegu Gyeongbuk Institute of Science and Technology, Daegu 42988, Republic of Korea * Correspondence: [ekkim@dgist.ac.kr](ekkim@dgist.ac.kr) Abstract: Liraglutide, a glucagon-like peptide-1 receptor agonist, is effective in the treatment of type 2 diabetes mellitus (T2DM) and obesity. Despite its benefits, including improved glycemic control and weight loss, the common metabolic changes induced by liraglutide and correlations between those in rodents and humans remain unknown. Here, we used advanced machine learning techniques to analyze the plasma metabolomic data in diet-induced obese (DIO) mice and patients with T2DM treated with liraglutide. Among the machine learning models, Support Vector Machine was the most suitable for DIO mice, and Gradient Boosting was the most suitable for patients with T2DM. Through the cross-evaluation of machine learning models, we found that liraglutide promotes metabolic shifts and interspecies correlations in these shifts between DIO mice and patients with T2DM. Our comparative analysis helped identify metabolic correlations influenced by liraglutide between humans and rodents and may guide future therapeutic strategies for T2DM and obesity. Keywords: type 2 diabetes mellitus; obesity; liraglutide; metabolomics; metabolic profiling; machine learning 1. Introduction Type 2 diabetes mellitus (T2DM) and obesity are major global health issues that have significant complications and increase the risk of morbidity and mortality [1,2] . Over the past 20 years, therapies based on incretin hormones, particularly glucagon-like peptide-1 receptor agonists (GLP-1 RAs), have become the preferred treatment for T2DM and obesity due to their efficacy and safety in numerous clinical trials [2–4] . Among the most widely adopted GLP-1 RAs, liraglutide substantially improves glycemic control and promotes weight loss [5–10] . Recent advancements in omics technologies, including proteomics and metabolomics, have demonstrated that liraglutide treatment significantly changes protein expression and metabolite levels across various biological samples in patients with T2DM and obesity and in mouse models [11–17] . The identified proteins and metabolites provide insights into liraglutide’s multifaceted mechanisms of action, which improve glycemic control and lipid profiles, reduce inflammation, and potentially offer cardiovascular and renal benefits [11–17] . Metabolomics encompasses the analysis of a vast array of metabolites present in biological samples using sophisticated analytical techniques. The ongoing challenges of such analysis include obtaining metabolic snapshots and surrogate diagnostics, identifying biomarkers, elucidating the mechanisms driving metabolic disorders, and evaluating drug efficacy and therapeutic outcomes [18, 19] . Understandi

FAQs

What is the main goal of analyzing plasma metabolomics in this study?

To determine common metabolic changes induced by liraglutide and to clarify correlations between those changes in rodents and humans.

Which machine learning models performed best for the two groups?

Support Vector Machine was most suitable for diet-induced obese (DIO) mice, while Gradient Boosting was most suitable for T2DM patients.

What does the cross-evaluation of models show about liraglutide’s effects?

Liraglutide promotes metabolic shifts and reveals interspecies correlations in these shifts between DIO mice and T2DM patients.

Aug 3, 2026

Upload by Theodore