Machine learning-based identification of glycosyltransferase-related mRNAs for improving outcomes and the anti-tumor therapeutic response of gliomas

Aug 5, 2026

Upload by Patrick

Glycosyltransferases shape glycosylation and their dysregulation contributes to glioma carcinogenesis, progression, and immune evasion, yet their links to clinical outcomes and treatment response remain insufficiently characterized. Differentially expressed genes were analyzed using public expression databases, and 10 survival-oriented machine learning models were integrated into a glycosyltransferase-related mRNA signature (GRMS). GRMS stratified patients with robust, independent prognostic value and associated immune features.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Background and clinical challenge

Methods

Differential gene analysis and machine learning models

Pathway analysis and immune cell estimation

Results

GRMS construction and prognostic performance

Immune and therapeutic response associations

Conclusion

TYPE Original Research PUBLISHED 16 August 2023 DOI 10.3389/fphar.2023.1200795 OPEN ACCESS EDITED BY Chen Ling, Fudan University, China REVIEWED BY Jiajia Chen, Fudan University, China Chen Zhong, Fudan University, China *CORRESPONDENCE Wei Zhou, [zhou_wei66@163.com](zhou_wei66@163.com) RECEIVED 05 April 2023 ACCEPTED 02 August 2023 PUBLISHED 16 August 2023 CITATION Zhang C and Zhou W (2023), Machine learning-based identiﬁcation of glycosyltransferase-related mRNAs for improving outcomes and the anti-tumor therapeutic response of gliomas. Front. Pharmacol. 14:1200795 . doi: 10.3389/fphar.2023.1200795 COPYRIGHT © 2023 Zhang and Zhou. This is an openaccess 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. Machine learning-based identiﬁcation of glycosyltransferase-related mRNAs for improving outcomesand the anti-tumor therapeutic response of gliomas Chunyu Zhang 1 and Wei Zhou 2* 1School of Medicine, Tongji University, Shanghai, China, 2Department of Anesthesiology, Huzhou Central Hospital, The Afﬁliated Huzhou Hospital, Zhejiang University School of Medicine, Huzhou, Zhejiang, China Background: Glycosyltransferase participates in glycosylation modiﬁcation, and glycosyltransferase alterations are involved in carcinogenesis, progression, and immune evasion, leading to poor outcomes. However, in-depth studies on the inﬂuence of glycosyltransferase on clinical outcomes and treatments are lacking. Methods: The analysis of differentially expressed genes was performed using the Gene Expression Proﬁling Interactive Analysis 2 database. A total of 10 machine learning algorithms were introduced, namely, random survival forest, elastic network, least absolute shrinkage and selection operator, Ridge, stepwise Cox, CoxBoost, partial least squares regression for Cox, supervised principal components, generalized boosted regression modeling, and survival support vector machine. Gene Set Enrichment Analysis was performed to explore signaling pathways regulated by the signature. Cell-type identiﬁcation by estimating relative subsets of RNA transcripts was used for estimating the fractions of immune cell types. Results: Here, we analyzed the genomic and expressive alterations inglycosyltransferase-related genes in gliomas. A combination of 80 machine learning algorithms was introduced to establish the glycosyltransferase-related mRNA signature (GRMS) based on 2,030 glioma samples from The Cancer Genome Atlas Program, Chinese Glioma Genome Atlas, Rembrandt, Gravendeel, and Kamoun cohorts. The GRMS was identiﬁed as an independent hazardous factor for overall survival and exhibited stable and robust performance. Notably, gliomas in the high-GRMS subgroup exhibited abundant tumorinﬁltrating lymphocytes and tumor mutation burden values, increased expressive levels of hepatitis A virus cellular receptor 2 and CD274, and improved progression-free survival when subjected to anti-tumor immunotherapy. Conclusion: The GRMS may act as a powerful and promising biomarker for improving the clinical prognosis of glioma patients. KEYWORDS glioma, glycosyltransferase, machine learning algorithms, prognosis, biomarker Frontiers in Pharmacology 01 [frontiersin.org](frontiersin.org) Introduction Glioma is the most frequently occurring type of brain cancer, and its most aggressive pathological form is known as brain glioblastoma (Louis et al., 2021) . Gliomas have signiﬁcant heterogeneity, and recent research has reported the tools for further classiﬁcation of gliomas (Carlson et al., 2021; Rui et al., 2023) . In clinical interventi

FAQs

What problem does the study address about glycosyltransferase in glioma?

It targets the lack of in-depth evidence connecting glycosyltransferase-related changes to clinical outcomes and anti-tumor treatment response in glioma.

How was the glycosyltransferase-related mRNA signature (GRMS) built?

The work analyzed differentially expressed genes and integrated multiple machine learning algorithms to establish the GRMS based on 2,030 glioma samples from several cohorts.

What clinical relevance did GRMS show for glioma patients?

GRMS acted as an independent hazardous factor for overall survival and showed stable performance, with the high-GRMS group displaying immune-related characteristics and improved progression-free survival under anti-tumor immunotherapy.

Aug 5, 2026

Upload by Patrick