Abstract 5086: Machine learning prediction and single-cell landscape of distant organ metastasis in non-small cell lung cancer

Abstract Introduction: Management of non-small cell lung cancer (NSCLC) depends on the presence and site of distant metastasis. Machine learning (ML) models have shown promise in analyzing clinical and molecular data to predict cancer outcomes and prognosis. Advancements in single-cell RNA sequencing (scRNA) provide deeper understanding of the tumor microenvironment (TME) and in metastasis. We aim to analyze NSCLC metastasis across different organs, investigate the clinical and molecular predictors of distant organ metastasis, and the single-cell landscape driving tumor metastasis. Methods: We used the cBioportal and the Gene Expression Omnibus (GEO) databases to retrieve clinical and scRNA data from the MSKCC Metastasis Cohort and GSE131907. The MSKCC dataset included 4, 601 NSCLC patients with distant organ metastasis to adrenal, bone, CNS/brain, liver, lung, mediastinum, and pleura. Seven random forest classifiers (RFC) were built for each organ metastasis and trained on clinical and genomic features like age, sex, race, histology, overall survival, fraction genome altered (FGA), microsatellite instability (MSI), mutation count, tumor mutational burden (TMB), and tumor purity. Models were evaluated using area under the receiver operating characteristics curve (AUC/ROC), 10-fold cross-validation (CV), accuracy score, and feature importance. Single-cell RNA data was filtered to include primary tumor samples (n=65, 702) and brain metastasis (n=28, 429) for cell distribution analysis. Results: Distant metastasis occurred in 3, 784 (82%) patients. The most common metastatic sites were lung (41%), bone (38%), pleura (35%), CNS (26%), liver (18%), adrenal gland (12%), and mediastinum (8.7%). The RFC-Mediastinum model showed the highest accuracy (0.89), AUC (0.61), and 10-fold CV (0.90), followed by RFC-Adrenal (0.86, AUC=0.62, 10-fold CV=0.86). The lowest performance was seen in RFC-Lung (0.57, AUC=0.56, 10-fold CV=0.52). The most important predictive features across all models were FGA, MSI, TMB, and mutation count, while histology was the least important. Single-cell analysis revealed that brain metastasis had a predominance of stromal cells, particularly epithelial, compared to primary tumor samples. Primary tumor samples consisted mostly of CD8+ T-cells and macrophages. COL1A1/2 genes were significantly expressed in brain metastatic stromal cells, suggesting extracellular matrix remodeling in the TME. Conclusion: Our study highlights the potential of ML models in accurately predicting distant organ metastasis in NSCLC. Variations in TME cellular compositions may be driven by complex intercellular communications in metastatic disease. Citation Format: Zaid Nassar Abu Rjai’, Ahmad Majid Bani-Ata, Ayah N. AL-Bzour. Machine learning prediction and single-cell landscape of distant organ metastasis in non-small cell lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 5086.