Identification of biomarkers and therapeutic combinations for immune checkpoint inhibitors (ICIs) using explanatory subgroup discovery for cancer patients without EGFR mutation

Phenotypic and genotypic heterogeneity are characteristic features of cancer patients. To tackle patients’ heterogeneity, immune checkpoint inhibitors (ICIs) represent one of the most promising therapeutic approaches to treat cancer. However, 50% of cancer patients that are eligible for treatment with ICIs will not respond well to this kind of therapies. Over the years, multiple patient stratification techniques have been developed to identify homogenous patient subgroups, although, matching patient subgroup to treatment option that can improve patients’ health outcome remains a challenging task. To address this problem, we developed a novel informatics framework that consists of two modules: subgroup discovery and drug targets discovery. The subgroup discovery module identifies homogenous patient subgroups based on both phenotypic and genotypic parameters and explains the differences between these subgroups using gene expression patterns. The drug targets discovery module employs proportional odds model to identify significant drug targets for uses in combination therapies with ICIs. We hypothesize that most of cancer patients without targetable mutations can benefit from compounds that have been used for immuno-targeted combination therapies. Our pipeline identifies six significant drug targets and thirteen compounds for cancer patients with EGFR WT gene in four malignancies: head & neck cancer, lung adenocarcinoma, lung squamous carcinoma, and melanoma. Three out of six drug targets – FCGR2B, IGF1R and KIT – substantially increase the odds of having a stable disease versus progressive disease. Our approach can help to better select responders for combination therapy with ICIs and improve health outcome for cancer patients without targetable mutations.   

For Zoom information, please contact Robert Sanders (