Machine learning-driven NGS-based diagnostic tests to optimize clinical response in oncology
Next-Generation Sequencing (NGS) is proving to be an invaluable asset in the fight against cancer. First-generation analysis of tumor mutational burden (TMB) through NGS has improved the utility of therapeutic agents such as immune checkpoint inhibitors (ICI) in certain tumor types. However, TMB fails to accurately identify the ideal target patient population in numerous other cancers. Further leveraging NGS, SickKids researchers, Dr. Adam Shlien, an Associate Director of Translation Genetics in the Department of Paediatric Laboratory Medicine at SickKids, and Dr. Uri Tabori, a paediatric oncologist and principal investigator at The Arthur and Sonia Labatt Brain Tumour Research Centre, have developed a next generation complex biomarker analysis based on tumor-specific transcriptional output, called RNAmp. Through analysis of 10,000 patient samples with their proprietary machine learning algorithm, tumors identified with increased transcriptional output were found to express more mutations, which is a hallmark for improved ICI response. From preliminary clinical testing on more than 100 patients, RNAmp is a better prognostic indicator of ICI response as compared to TMB. RNAmp, combined with other diagnostic tests, such as genomic hyper mutant analysis, MSI, SNV, MMRD and POLE signatures developed at SickKids, provides a company creation/investment opportunity with a unique position in the industry.