Related Experiment Video
Updated: Jan 13, 2026
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
Predicting Immunotherapy Outcomes in NSCLC Using RNA and Pathology from Multicenter Clinical Trials
Zhaojun Wang1, Yiran Fang1, Xiatong Huang1
1Department of Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, P. R. China.
Abstract:
Immune checkpoint inhibitors (ICIs) are widely used to treat advanced non-small cell lung cancer (NSCLC). However, it remains crucial to identify patients who are unlikely to benefit from immunotherapy and to explore potential combination treatment strategies. In this study, 1127 advanced NSCLC patients from multicenter randomized clinical trials (OAK, POPLAR, ORIENT-11) and an in-house cohort who received ICIs, ICIs combined with chemotherapy, or chemotherapy alone are analyzed. Using bulk RNA-seq transcriptomic data, an RNA-based model, named the Lung Cancer Immunotherapy Response Assessment (LIRA), is developed, utilizing interaction analysis and a random forest algorithm to predict immunotherapy outcomes. LIRA outperforms PD-L1 expression and tumor mutation burden in predicting responses, particularly in identifying early progression risk during ICI monotherapy (HR: 0.15, 95% CI: 0.11-0.20). Tumor profile analysis reveals that LRP8 and HDAC4 are associated with immunotherapy outcomes. Additionally, scRNA-seq analysis of NSCLC tumors indicates a higher prevalence of T cells and a reduced proportion of epithelial cells in samples with a high LIRA-score. The deep learning model pinpointed critical high-attention regions within whole-slide images that contributed decisively to the LIRA predictions. In summary, these results demonstrate that LIRA enables independent risk stratification of NSCLC patients and provides insights into potential resistance mechanisms.
Insights
A new RNA-based model, the Lung Cancer Immunotherapy Response Assessment (LIRA), accurately predicts non-small cell lung cancer patient response to immunotherapy. LIRA identifies patients unlikely to benefit, improving treatment strategies.
Area of Science:
- Oncology
- Immunotherapy
- Genomics
Background:
- Immune checkpoint inhibitors (ICIs) are standard for advanced non-small cell lung cancer (NSCLC).
- Predicting patient response to ICIs and identifying non-responders is critical for optimizing treatment.
- Exploring combination therapies and resistance mechanisms is essential for improving outcomes.
Purpose of the Study:
- To develop and validate an RNA-based predictive model for immunotherapy response in advanced NSCLC.
- To compare the predictive performance of the novel model against established biomarkers like PD-L1 and tumor mutation burden.
- To investigate potential molecular mechanisms and cellular profiles associated with immunotherapy response and resistance.
Main Methods:
- Analysis of bulk RNA-seq transcriptomic data from 1127 advanced NSCLC patients across multiple clinical trials and an in-house cohort.
- Development of the Lung Cancer Immunotherapy Response Assessment (LIRA) model using interaction analysis and a random forest algorithm.
- Validation using scRNA-seq and deep learning analysis of whole-slide images to identify cellular and spatial features.
Main Results:
- The LIRA model demonstrated superior predictive performance compared to PD-L1 expression and tumor mutation burden.
- LIRA effectively identified patients at high risk of early progression during ICI monotherapy (HR: 0.15).
- Specific genes (LRP8, HDAC4) and distinct immune cell profiles (increased T cells, decreased epithelial cells) were associated with LIRA scores and treatment outcomes.
Conclusions:
- The LIRA model provides an independent and accurate method for risk stratification of NSCLC patients undergoing immunotherapy.
- LIRA offers valuable insights into potential mechanisms of immunotherapy resistance.
- The findings support the use of LIRA for personalized treatment decisions in advanced NSCLC.
