Application of machine learning for mass spectrometry-based multi-omics in thyroid diseases - review

Aug 5, 2026

Upload by Levi

Thyroid diseases impose a substantial health burden, making timely and accurate diagnosis essential. Mass spectrometry (MS)-based multi-omics has emerged as an effective approach to uncover complex biological mechanisms underlying thyroid disorders. The rapid expansion of biomedical data has driven the use of machine learning (ML) to address new analytical and clinical challenges. This review summarizes MS-based multi-omics applications in thyroid disease and discusses proteomics and metabolomics workflows, then evaluates key unsupervised and supervised learning methods for diagnostic integration.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Thyroid gland and disease classification

Omics and multi-omics in thyroid research

MS-based multi-omics and ML integration

TYPE Review PUBLISHED 17 December 2024 DOI 10.3389/fmolb.2024.1483326 OPEN ACCESS EDITED BY Michele Costanzo, University of Naples Federico II, Italy REVIEWED BY Giuseppina Fanelli, University of Tuscia, Italy Renu Pandey, Indian Institute of Technology Bombay, India *CORRESPONDENCE Zhibin Zhang, [zhibin-zhang@nankai.edu.cn](zhibin-zhang@nankai.edu.cn)[ ](zhibin-zhang@nankai.edu.cn)Xiangyang Zhang, [xiangyang.zhang@tju.edu.cn](xiangyang.zhang@tju.edu.cn) RECEIVED 23 August 2024 ACCEPTED 02 December 2024 PUBLISHED 17 December 2024 CITATION Che Y, Zhao M, Gao Y, Zhang Z and Zhang X (2024) Application of machine learning for mass spectrometry-based multi-omics in thyroid diseases. Front. Mol. Biosci. 11:1483326 . doi: 10.3389/fmolb.2024.1483326 COPYRIGHT © 2024 Che, Zhao, Gao, Zhang and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Application of machine learning for mass spectrometry-based multi-omics in thyroid diseases Yanan Che 1, Meng Zhao 1, Yan Gao 1, Zhibin Zhang 2* and Xiangyang Zhang 1* 1School of Pharmaceutical Science and Technology, Tianjin University, Tianjin, China, 2 Department of General Surgery, Tianjin First Central Hospital, Tianjin, China Thyroid diseases, including functional and neoplastic diseases, bring a huge burden to people’s health. Therefore, a timely and accurate diagnosis is necessary. Mass spectrometry (MS) based multi-omics has become an effective strategy to reveal the complex biological mechanisms of thyroid diseases. The exponential growth of biomedical data has promoted the applications of machine learning (ML) techniques to address new challenges in biology and clinical research. In this review, we presented the detailed review of applications of ML for MS-based multi-omics in thyroid disease. It is primarily divided into two sections. In the first section, MS-based multi-omics, primarily proteomics and metabolomics, and their applications in clinical diseases are briefly discussed. In the second section, several commonly used unsupervised learning and supervised algorithms, such as principal component analysis, hierarchical clustering, random forest, and support vector machines are addressed, and the integration of ML techniques with MS-based multi-omics data and its application in thyroid disease diagnosis is explored. KEYWORDS mass spectrometry, proteomics, metabolomics, multi-omics, thyroid diseases, machine learning 1 Introduction The thyroid gland is a small, butterfly-shaped gland located at the base of the neck (Sofia et al., 2019; Mullur et al., 2014) . It plays a crucial role in regulating various metabolic processes by secreting hormones (Sofia et al., 2019; Mullur et al., 2014) . Thyroid disease refers to various diseases affecting the thyroid gland, categorized into functional and neoplastic diseases (Vanderpump, 2011; Zhang et al., 2022) . Functional diseases are classified as hyperthyroidism or hypothyroidism, whereas neoplastic diseases are classified as benign or malignant (Zhang et al., 2022) . In the field of neoplastic diseases, tumors are classified as benign tumors, lowrisk neoplasms, and malignant neoplasms according to prognostic risk categories (Basolo et al., 2023) . Thyroid cancer refers to malignant tumors, originating from follicular or parafollicular thyroid cells, which can metastasize to other places in the body (Omurand Baran, 2014) . Thyroid cancer is one of the most common endocrine neoplasia, and its incidence has been on the rise in the past 40 years, disproportionately affecting women (Chen

FAQs

Why are early and accurate diagnosis methods important for thyroid diseases?

Thyroid diseases create a large health burden, and timely diagnosis is required to better manage functional and neoplastic conditions.

What role does MS-based multi-omics play in understanding thyroid diseases?

MS-based multi-omics helps reveal complex biological mechanisms by profiling multiple biomolecule layers, particularly proteomics and metabolomics.

Which machine learning approaches are highlighted for MS-based multi-omics in thyroid diagnosis?

The review discusses commonly used unsupervised and supervised algorithms, including principal component analysis, hierarchical clustering, random forest, and support vector machines, for integrating multi-omics data to support diagnosis.

Aug 5, 2026

Upload by Levi