Related Experiment Video
Updated: Jan 9, 2026
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
Published on: June 3, 2022
Development of a lactylation-related molecular classification and machine learning-based gene signature to predict
Nannan Luan1, Feng Jin1, Zhenhua Hu2
1Department of Obstetrics and Gynecology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China.
Background:
Lactylation is acknowledged as a regulator of numerous biological processes related to cancer. Research on the ability of lactylation-related genes (LacRGs) to predict prognosis and immunotherapeutic response in ovarian cancer (OC) patients is limited.
Methods:
Consensus clustering was utilized to identify prognostic differentially expressed genes (DEGs) across clusters. A consensus lactylation-related gene signature (LRGS) was established from TCGA-OC and four independent GSE datasets through a machine learning-based integrative approach.
Results:
LRGS demonstrates consistent and robust performance as an independent risk factor for overall survival. Furthermore, while the low-LRGS group is more likely to exhibit the "hot tumor" phenotype, it also shows a more favorable prognosis and enhanced responsiveness to immunotherapy. Patients exhibiting a high LRGS demonstrated a reduced probability of deriving benefit from immunotherapy and faced a poor prognosis. The oncogenic role of the risk gene RPS6KA2 was preliminarily validated.
Conclusions:
An in-depth analysis of the LacRGs data may yield valuable insights and enhance the molecular classification of OC. The identification of LRGS serves as a crucial factor in the early prognosis of patients and the selection of potential candidates for immunotherapy. The findings have significant implications for individual patients with OC.
