At AACR 2024, Genialis unveiled krasID, a groundbreaking RNA-based biomarker using machine learning to forecast how patients with non-small cell lung cancer (NSCLC) will respond to KRAS inhibitors like sotorasib. By harnessing data-driven insights and innovative classifiers, this pioneering technology offers a personalized approach to therapy, revolutionizing treatment strategies.
To achieve this, Genialis employed RNA sequencing to measure gene expression in tumor tissues, including FFPE samples, identifying several biological “modules” related to or associated with KRAS. One such module represented cellular dependency, a gene expression signature distinguishing tumors reliant on KRAS for survival and pathway activation. The krasID classifier was trained using five of these modules to predict the likelihood of response to KRAS inhibition.
Once trained, krasID was applied to gene expression data from a real-world cohort of NSCLC patients before they received sotorasib (Lumakras) to predict their treatment response. Grouping patients by krasID score—either “krasID-high” or “krasID-low”—resulted in two distinct Kaplan-Meier survival curves. Patients classified as “krasID-high” had a median survival of 338 days, more than double the 158 days for those classified as “krasID-low.”
Discover more here.