ORIGINAL RESEARCH article
Front. Immunol.
Sec. Cancer Immunity and Immunotherapy
This article is part of the Research TopicRNA Modifications in Cancer: Unraveling Roles and Therapeutic Potential in Immunity and Immunotherapy, Volume IIView all 3 articles
Deep Learning Model and Omics Screening Highlight Angiotensinogen as a 5-Methylcytosine (m5C)-Regulated Mediator of Tumor-Microenvironment Communication in Liver Cancer
Provisionally accepted
- Peking University, Beijing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The tumor microenvironment (TME) of liver cancer plays a critical role in cancer progression and treatment response, yet the molecular mechanisms by which m5C modification mediates intercellular communication within the TME remain less understood, despite being a key post-transcriptional RNA modification. Here, we developed GAT-MeRIP, a graph attention neural network-based algorithm for identifying crucial m5C-modified target genes, and applied it to the m5C methylome of liver cancer cells. Through further integration of single-cell transcriptomic data and cell-cell communication analysis, angiotensinogen (AGT) was identified as a key m5C-regulated secretory factor contributing to tumor-microenvironment communication in liver cancer. AGT expression was negatively correlated with NSUN2 and positively correlated with natural killer (NK) cell infiltration. Functional validation demonstrated that AGT treatment significantly enhanced NK cell cytotoxicity against liver cancer cells, as evidenced by increased IFN-γ, TNF-α, and perforin expression, as well as an elevated proportion of CD107a⁺ NK cells. Furthermore, liver cancer patients with low NSUN2 and high AGT expression exhibited significantly improved overall survival rates, indicating AGT and NSUN2 co-expression as a promising prognostic biomarker. This study unveils novel regulatory function of m5C-modified AGT in modulating the liver TME that could be helpful for improving liver cancer prognosis and immunotherapy.
Keywords: Angiotensinogen, deep learning, liver cancer, m5C modification, Natural Killer cell, Tumor Microenvironment
Received: 24 Nov 2025; Accepted: 04 Feb 2026.
Copyright: © 2026 Pang, Wang, Li and Zhou. 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) or licensor 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.
* Correspondence: Yuan Zhou
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.