Identification of predictive biomarkers and applications in patient enrichment strategies

The partner had a pipeline molecule that was under clinical development. The interest area was to identify biomarkers indicative of drug-response in patients and further utilize the biomarkers for patient stratification in clinical trials.

Client’s requirement

Our client is in the clinical development phase of a pipeline molecule seeking comprehensive analysis of biomarkers associated with drug response in patients. The primary objective is to leverage proprietary gene-expression data from 118 treated cell lines to identify and validate biomarkers. These biomarkers will then be utilized for effective patient stratification in upcoming clinical trials. They want to predict drug-response biomarkers and retrospectively classify 11 patients into responders and non-responders based on their gene expression profiles. The focus is on delivering actionable insights that will enhance decision-making in the ongoing clinical development process.

Our approach

Machine learning models were built using three different methods to prioritize biomarkers associated with drug-response. Pathway enrichment analysis was performed to understand the role of the biomarkers in disease pathophysiology. Stratification of patients based on these biomarkers resulted in correct prediction of drug response in 8 out of 11 patients.

Download case study