Two Studies Point to the Quality of Neoantigens in Determining Long-Term Cancer Survival

Benjamin Greenbaum, PhD

The quality, not quantity, of tumor neoantigens may best predict a patient’s response to cancer immunotherapy and his or her chance of long-term survival. That finding was based on two groundbreaking studies co-authored by Benjamin Greenbaum, PhD, Assistant Professor, Medicine (Hematology and Medical Oncology), and Pathology, Icahn School of Medicine at Mount Sinai. Now, it is being further explored by Dr. Greenbaum and Vinod Balachandran, MD, Memorial Sloan Kettering Cancer Center, through a Stand Up to Cancer Convergence 2.0 Grant and funding from the Lustgarten Foundation.

Their goal is to understand the underpinnings of pancreatic cancer survivorship, and their team is one of seven research groups that comprise Stand Up to Cancer’s broad $11 million initiative that was announced in January 2018. Neoantigens, or peptides found on the surface of cancer cells, are considered promising targets for cancer immunotherapy.

“Previous research has shown that T cell immunity is linked to exceptional outcomes for the few long-term survivors of pancreatic cancer, but it wasn’t clear if neoantigens played a role,” says Dr. Greenbaum. “Our newest research shows there are particular neoantigens that seem to be driving this long-term response in patients with pancreatic cancer, and further suggests that targeting those neoantigens might be a viable therapeutic strategy.”

According to Dr. Greenbaum, who was trained as a physicist and quantitative biologist, “One of the most exciting aspects of our work is collaborating with academic teams that can combine the tools and knowledge from diverse fields like theoretical physics, structural biology, mathematics, computer science, and translational genomics. We never lose sight of the fact that our combined efforts could one day result in clinical breakthroughs that benefit countless numbers of people.”

Earlier research formed the basis of the team’s efforts. In the first of two back-to-back studies published in Nature (November 2017), researchers described a mathematical model they developed—the first of its kind—to predict how a cancer patient would benefit from certain immunotherapies. Dr. Greenbaum was the senior author on this work with first author Marta Luksza, PhD, Assistant Professor of Oncological Sciences, Icahn School of Medicine at Mount Sinai.

By capturing aspects of a tumor’s evolution and ways in which it interacted with the underlying immune system, the new model appeared to offer an approach beyond previous biomarkers. Going forward, it also has the potential to uncover new therapeutic targets within the immune system, and help in the design of vaccines for patients who do not respond to immunotherapy.

The second study, whose first author was Dr. Balachandran, applied the modeling framework in order to better understand immune response in patients with pancreatic cancer and, more specifically, the unique role of neoantigens.

As part of the broad initiative, the Mount Sinai researchers are focused on better understanding what makes a neoantigen a good immune target, and the role of the microbiome in neoantigen recognition. By advancing the core science behind developing a vaccine for pancreatic cancer, the research could eventually improve treatment prospects for patients with this deadly form of the disease.

As they investigate the immune system’s response to cancers, the Convergence 2.0 team will be encouraged to draw upon the knowledge of Microsoft Research experts in machine learning and artificial intelligence. In addition to Dr. Luksza, the research team includes Nina Bhardwaj, MD, PhD, from the Icahn School of Medicine at Mount Sinai; and Eileen M. O’Reilly, MD; Taha Merghoub, PhD; and Jedd D. Wolchok, MD, PhD, from Memorial Sloan Kettering Cancer Center.

Machine Learning Techniques Generate Clinical Labels of Medical Scans


Researchers used machine learning techniques, including natural language processing algorithms, to identify clinical concepts in radiologist reports for CT scans, according to a study conducted at the Icahn School of Medicine at Mount Sinai and published in the journal Radiology.  The technology is an important first step in the development of artificial intelligence that could interpret scans and diagnose conditions.

Read the press release

Researchers Studying More Precise Methods for Prostate Cancer Screening

On the heels of new recommendations for prostate cancer screening, researchers at Mount Sinai are studying how to more precisely diagnose the disease.

“In prostate cancer, the primary method that clinicians use to characterize a cancer and decide on a treatment protocol is the Gleason grade, or the Gleason score, of the patient,” says Gerardo Fernandez, MD, the Medical Director of Pathology at Mount Sinai St. Luke’s  in New York. “Over the years, though, it turns out that we have over-treated prostate cancer by quite a bit. So the idea of having cancer leads a lot of patients to decide on radical treatments, namely surgery. What we’re trying to do is characterize prostate cancer more effectively than just by using the Gleason score.”

He adds: “Google might use similar techniques to characterize facial properties that allows them to do facial recognition software. We apply similar computer and engineering technology to images of cancer — how separated are the nuclei from one another, how bigger the nuclei, what protein markers do those nuclei contain. So we characterize these images with complex methods, and we extract these features out of them. Now, once we have the features, we use artificial intelligence-type approaches to take all of that data and figure out what combinations of features do a better job of predicting the behavior of the cancer than Gleason alone.”