RAS pathway activity subtypes identified by machine learning define prognostic and immune microenvironment
1Department of Respiratory and Critical Care Medicine, The Third People's Hospital of Chengdu, Chengdu, 610014, China. 13730899577@163.com.
Discover Oncology
|May 28, 2026
Summary
This study identified two RAS pathway activity subtypes in lung adenocarcinoma (LUAD) and developed a three-gene signature (MAPK10, PLA2G12B, SHC3) for prognosis. These biomarkers offer insights into immune microenvironment remodeling and personalized LUAD treatment strategies.
Area of Science:
- Oncology
- Molecular Biology
- Bioinformatics
Background:
- Lung adenocarcinoma (LUAD) is a major cause of cancer mortality.
- The RAS signaling pathway is crucial in LUAD, but its subtypes and clinical relevance are unclear.
Purpose of the Study:
- To characterize RAS pathway activity subtypes in LUAD.
- To develop a prognostic model for LUAD patients based on RAS pathway activity.
Main Methods:
- Analysis of transcriptomic data from 624 LUAD patients (GEO, TCGA).
- Consensus clustering using 238 RAS pathway-related genes.
- Machine learning algorithms (LASSO, Random Forest, SHAP) for prognostic model construction.
Main Results:
- Two distinct RAS pathway activity subtypes were identified.
- A three-gene prognostic signature (MAPK10, PLA2G12B, SHC3) was established as an independent prognostic factor.
- Distinct immune cell infiltration patterns and potential immunotherapy responses were observed between risk groups.
Conclusions:
- Established a landscape of RAS pathway activity subtypes in LUAD.
- Identified MAPK10, PLA2G12B, and SHC3 as novel prognostic biomarkers.
- Provided insights into immune microenvironment remodeling for personalized LUAD treatment.