Development and Validation of a Prognostic and Predictive 32-Gene Signature for Gastric Cancer

Genomic profiling can provide prognostic and predictive information to guide clinical care. Biomarkers that reliably predict patient response to chemotherapy and immune checkpoint inhibition in gastric cancer are lacking. In this retrospective analysis, we use our machine learning algorithm NTriPath [Park, Sunho et al. “An integrative somatic mutation analysis to identify pathways linked with survival outcomes across 19 cancer types.” Bioinformatics (2016): 1643-51. doi:10.1093/bioinformatics/btv692] to identify a gastric-cancer specific 32-gene signature. Using unsupervised clustering on expression levels of these 32 genes in tumors from 567 patients, we identify four molecular subtypes that are prognostic for survival. We then built a support vector machine with linear kernel to generate a risk score that is prognostic for five-year overall survival and validate the risk score using three independent datasets. We also find that the molecular subtypes predict response to adjuvant 5-fluorouracil and platinum therapy after gastrectomy and to immune checkpoint inhibitors in patients with metastatic or recurrent disease. In sum, we show that the 32-gene signature is a promising prognostic and predictive biomarker to guide the clinical care of gastric cancer patients and should be validated in a prospective manner. We generated microarray-based mRNA expression profiles from pre-treatment tumor samples from 567 patients who underwent resection at Yonsei University. This series includes a subset of the dataset (135 samples) and the rest of the dataset has been available in series GSE84437 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE84437). For more detailed information, please refer to the individual samples.