Predictive Analytics Detects Genes That Accelerate Cancer Progression

Using a predictive analytics tool, researchers from the University of California, Irvine (UCI) were able to discover previously undetected genes that drive cancer progression, according to a study published in Science Advances.

The algorithm, called DORGE (Discovery of Oncogenes and tumor suppressoR genes using Genetic and Epigenetic features), has deepened researchers’ understanding of epigenetic mechanisms in tumorigenesis.

Cancer is the result of an accumulation of key genetic alterations that disrupt the balance between cell division and apoptosis. Genes with driver mutations that affect cancer progression are known as cancer driver genes, and can be classified as tumor suppressor genes (TSGs) and oncogenes (OGs) based on their roles in cancer progression.

The study demonstrated how cancer driver genes predicted by DORGE included both known cancer driver genes and novel driver genes not reported in current literature. Researchers also found that the novel dual-functional genes, which DORGE predicted as both TSGs and OGs, are highly enriched at hubs in protein-protein interaction (PPI) and drug/compound gene networks.

Researchers also compared DORGE with ten existing predictive analytics algorithms for cancer driver gene prediction using four accuracy measures, including sensitivity, specificity, precision, and overall accuracy. The team found that DORGE performed the best in all of these measures except specificity, for which DORGE was 0.997 and the best algorithm was 1.000.

"Existing bioinformatics algorithms do not sufficiently leverage epigenetic features to predict cancer driver genes, despite the fact that epigenetic alterations are known to be associated with cancer driver genes," said senior author Wei Li, PhD, the Grace B. Bell chair and professor of bioinformatics in the Department of Biological Chemistry at the UCI School of Medicine.

"Our computational algorithm integrates public data on epigenetic and genetic alternations, to improve the prediction of cancer driver genes."

The researchers noted that the DORGE tool could help healthcare leaders better understand the genetic components of cancer.

“This study highlights the integration of epigenetic data to achieve a more comprehensive prediction of cancer driver genes. DORGE will serve as an essential resource for cancer biology, particularly in the development of targeted therapeutics and personalized medicine for cancer treatment,” researchers concluded.

The results could contribute to improved cancer care going forward.

"Our DORGE algorithm successfully leveraged public data to discover the genetic and epigenetic alterations that play significant roles in cancer driver gene dysregulation," explained Li. "These findings could be instrumental in improving cancer prevention, diagnosis and treatment efforts in the future."

Researchers have recently made advancements in understanding the genetic factors associated with cancer development and progression.

A study recently published in JAMA Oncology found that broad-based genetic testing could identify inherited genetic mutations and accelerate precision medicine therapies for patients with cancer.

The study showed that when physicians used standard guidelines to select patients for genetic testing, providers were only able to find 48 percent of patients with an inherited genetic mutation.

“We found that 13.5 percent of patients had an inherited mutation in a gene associated with the development of their cancer,” said Niloy Jewel Samadder, MD, a Mayo Clinic gastroenterologist and hepatologist, who is the study's author.

“More than half of the patients who developed cancer due to inherited mutations were being missed, and that has major implications for family members. Everyone has some risk of developing cancer, and in most cases the disease develops by chance. However, some people are genetically predisposed to developing certain types of cancer, such as breast or colon cancers.”