Many cancer patients undergo treatment with multiple drugs, each of which attacks cancer in a different way, so the combination fights cancer on many fronts. But more drugs mean higher risks of side effects.
“Most cancer therapy is now a combination treatment,” says Avinash (Avi) Sahu, PhD, assistant professor at The University of New Mexico Comprehensive Cancer Center. Sahu joined UNM from Harvard and Dana-Farber Cancer Institute. “We wanted to find drugs that could suppress two cancer-causing pathways at the same time.”
But instead of spending hours in a lab, Sahu turned to his computer.
Sahu and his research team created two approaches. The first, called BiopotentR, uses publicly available genomic data to find drugs that can attack cancer in multiple ways and identify genes that the drugs target. The second applies machine learning methods to this information to predict how people will respond to immunotherapy.
Machine learning is similar to the way people learn. Just as people learn new things — such as riding a bike or driving a car — through lots of experience, computer-driven machine learning assimilates vast amounts of data and gleans patterns that it can then apply to other tasks.
But cancer research data alone wasn't enough for Sahu and his team to predict how people would respond to a drug. They needed additional biological data that they could then apply to cancer patients and cancer drug responses. In machine learning terms, they needed to learn from the biological context and apply that knowledge to a cancer context; it’s a technique called transfer learning.
Sahu and his team partnered with a company to find a compound that would target the top cancer gene candidate they identified using BipotentR. In preclinical testing, they confirmed that their predictions were accurate.
But the work can be expanded, Sahu says.
“When tumors have overactive multi-functional drug targets, patients are less likely to respond to immunotherapy,” he says. “However, patients with these types of tumors could potentially benefit from a combination of immunotherapy and multi-functional drugs.”
The team’s work is not limited to just metabolism and immune targets; it can be tailored to explore any two factors to find better multi-purpose drugs. Sahu says this approach thus presents an exciting opportunity for new research in a variety of cancer-focused projects.
And faster drug discovery means more accurate personalized medicine.
About Avinash Sahu, PhD
Avinash Sahu, PhD, is an Assistant Professor at The University of New Mexico School of Medicine, in the Department of Internal Medicine, Division of Translational Informatics. He joined the UNM faculty in January 2023. Dr. Sahu holds a doctorate from University of Maryland. His research focuses on applications of machine learning and deep learning to improve the understanding and treatment of cancer.
Paper Reference
“Discovery of targets for immune-metabolic antitumor drugs identifies Estrogen Related Receptor Alpha” was published online on January 27, 2023, in Cancer Discovery (https://aacrjournals.org/cancerdiscovery). Authors are: Avinash D. Sahu, Xiaoman Wang, Phillip Munson, Jan Klomp, Xiaoqing Wang, Shengqing Gu, Gege Qian, Phillip Nicol, Zexian Zeng, Chenfei Wang, Collin Tokheim, Wubing Zhang, Jingxin Fu, Jin Wang, Nishanth U. Nair, Joost Rens, Meriem Bourajjaj, Bas Jansen, Inge Leenders, Jaap Lemmers, Mark Musters, Sanne van Zanten, Laura van Zelst, Jenny Worthington, Myles Brown, Jun S. Liu, Dejan Juric, Cliff A. Meyer, Arthur Oubrie, X. Shirley Liu, David E. Fisher, Keith T. Flaherty.
UNM Comprehensive Cancer Center
The University of New Mexico Comprehensive Cancer Center is the Official Cancer Center of New Mexico and the only National Cancer Institute-designated Cancer Center in a 500-mile radius.
Its more than 136 board-certified oncology specialty physicians include cancer surgeons in every specialty (abdominal, thoracic, bone and soft tissue, neurosurgery, genitourinary, gynecology, and head and neck cancers), adult and pediatric hematologists/medical oncologists, gynecologic oncologists, and radiation oncologists. They, along with more than 600 other cancer healthcare professionals (nurses, pharmacists, nutritionists, navigators, psychologists and social workers), provide treatment to 65% of New Mexico’s cancer patients from all across the state and partner with community health systems statewide to provide cancer care closer to home. They treated almost 15,000 patients in more than 100,000 ambulatory clinic visits in addition to in-patient hospitalizations at UNM Hospital.
A total of nearly 1,855 patients participated in cancer clinical trials testing new cancer treatments that include tests of novel cancer prevention strategies and cancer genome sequencing.
The more than 123 cancer research scientists affiliated with the UNMCCC were awarded $38.2 million in federal and private grants and contracts for cancer research projects. Since 2015, they have published nearly 1000 manuscripts, and promoting economic development, they filed 136 new patents and launched 10 new biotechnology start-up companies.
Finally, the physicians, scientists and staff have provided education and training experiences to more than 500 high school, undergraduate, graduate, and postdoctoral fellowship students in cancer research and cancer health care delivery.