Integrating Single‐Cell Transcriptomics and Machine Learning to Define an ac4C Gene Signature in Lung Adenocarcinoma

ABSTRACT Introduction Lung adenocarcinoma, the most common subtype of non‐small cell lung cancer, faces challenges such as drug resistance and tumor heterogeneity. N4‐acetylcytidine (ac4C) is an important RNA modification involved in cancer progression, but its role in lung adenocarcinoma remains un...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan Wang, Wei Su, Guangyao Zhou, Yijie Wang, Chunnuan Wu, Pengpeng Zhang, Lianmin Zhang
Format: Article
Language:English
Published: Wiley 2025-08-01
Series:Thoracic Cancer
Subjects:
Online Access:https://doi.org/10.1111/1759-7714.70140
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:ABSTRACT Introduction Lung adenocarcinoma, the most common subtype of non‐small cell lung cancer, faces challenges such as drug resistance and tumor heterogeneity. N4‐acetylcytidine (ac4C) is an important RNA modification involved in cancer progression, but its role in lung adenocarcinoma remains unclear. Methods This study analyzed transcriptomic and single‐cell RNA sequencing data from public databases to investigate the expression and clinical significance of ac4C‐related genes in lung adenocarcinoma. Ten machine learning algorithms were applied to develop and validate an ac4C‐related gene signature (ARGSig) for prognosis prediction across multiple independent cohorts. Results Cells with high ac4C activity showed increased intercellular communication and activation of tumor‐associated pathways. The ARGSig model effectively stratified patients by survival outcomes and predicted sensitivity to immune checkpoint inhibitors and chemotherapy agents. Conclusion ac4C modification and its related genes play a critical role in lung adenocarcinoma development. The ARGSig model provides a promising molecular tool for prognosis evaluation and personalized treatment guidance in lung adenocarcinoma patients.
ISSN:1759-7706
1759-7714