This technology is an algorithm that leverages patient cancer genomic data to provide a personalized chemotherapy regimen.
While it is well understood that cancer results from the acquisition of somatic mutations in the genome, only a small proportion of mutations, known as “drivers”, are responsible for oncogenesis. Identification and classification of these mutations are essential to delivering personalized therapy, as different mutations in the same gene may cause diverse clinical outcomes. However, existing computational tools are often ill-suited to analyze personal cancer genomes. As such, there is a need for improved methods of processing individual cancer genomes to enable personalized cancer treatment.
This technology identifies cancer driver mutations in patient-specific cancer genomes and then leverages these mutations to provide a personalized treatment plan. To accomplish this, iCAGES first prioritizes personalized cancer driver mutations, which are then linked to mutation features of genes using a trained statistical model. Based on this information, iCAGES then generates a prioritized list of drugs targeting the potential driver genes for a personalized chemotherapy regimen. By optimizing treatment plans, this technology may help reduce side effects and improve treatment outcomes.
This technology successfully predicted patient response to drug treatment and long-term survival in analysis of a dataset from The Cancer Genome Atlas (TCGA).
IR CU17137
Licensing Contact: Joan Martinez