Most cancers are created by the accumulation of somatic genetic mutations, or variants. Many of the variants involved in numerous types of cancer have been identified with genetic sequencing research of large numbers of patients. Yet, this information isn’t always clinically useful on an individual level. Cancer “drivers” can be different for every individual. There are no practical clinical tools to foresee which variants in an individual’s genome are driving the disease and which are present but not causing disease. Kai Wang, PhD, associate professor of biomedical informatics and director of clinical informatics at the Institute for Genomic Medicine at CUMC stated, “Even when the genes driving cancer are known, clinicians don’t have an efficient way to choose among the hundreds of possible drug therapies.”
Focusing on this shortcoming, Doctor Wang and his associates developed a computational tool called Integrated Cancer Genome Score (iCAGES). First, iCAGES tests the individual’s entire genome, comparing it to the genomic sequence of that person’s tumor to identify possible cancer-causing variants. After, iCAGES cross-references these variants to databases of known cancer-causing genes, using statistical analyses and machine learning techniques to prioritize the most likely driver genes. Lastly, iCAGES matches the variants to FDA-approved and experimental drug treatments that target those variants or genes specifically . The procedure takes about 30 minutes. In contrast, traditional approaches require many different steps which involve human input, that could take many weeks.
In an analysis created to show how the tool would be used in actual practice, Doctor Wang tested iCAGES in the past using detailed sequencing information from a lung cancer patient. Out of 129 possible cancer drivers, iCAGES targeted a gene called ARAF. iCAGES used the genomic sequencing information to select sorafenib as the top drug candidate. The patient’s oncologists had come to the same results. However, they used a more intricate concept which involved expert knowledge throughout the decision-making process. Doctor Wang stated, “The patient was given sorafenib and had an extraordinary clinical response. It’s worth noting that sorafenib is not FDA-approved for this indication. Nonetheless, the result suggests that iCAGES may help to identify novel treatment strategies and off-label use of existing approved drugs.”
When analyzed on different cancer patient databases, iCAGES was discovered to be superior to other computational tools at predicting cancer drivers from personal genomes and at identifying sufficient treatment. Doctor Wang said, “We hope that iCAGES can help clinicians take full advantage of the massive amounts of data on genomic sequencing and cancer variants, and shed light on personalized cancer therapy.”