The client, a Biotech company based out of Europe, had a large molecule asset that was under development for blood cancer. They were interested in expanding the therapeutic potential of the molecule to solid tumours to augment the existing portfolio.
Client’s requirement
The focus was on leveraging public gene expression datasets from cancer patients treated with a drug candidate with a similar mechanism of action. Machine learning in drug discovery and predictive modeling for oncology were applied using information on drug responsiveness and disease gene signatures.
Learn more about our expertise in Computational Biology Services and Scientific Data Management
Our approach
Predictive models were built using an iterative approach wherein patient-level and disease-level gene expression analysis profiles were used as input data. Clustering of cancer indications was done to prioritize indications that were potentially sensitive to the treatment.
The use of bioinformatics analysis and scientific informatics allowed Excelra’s team to converge the drug mechanism of action with disease pathophysiology, thereby building strong biological rationale for each prioritized indication. This systematic approach ensured that the biologic drug development process was supported by accurate and reliable data-driven insights.
Similar strategies were highlighted in our Comprehensive Analysis of Putative Drug Targets case study.
