Cancer cells, illustration

Immunotherapy activates the body’s immune system to fight against cancer cells without using chemotherapy or radiotherapy. In addition, it uses the adaptability of the immune system which may help patients benefit from its therapeutic effects experience sustained anti-cancer effects. However, the current diagnostic techniques do not accurately predict the patient’s response to treatment. Now, researchers from the Johns Hopkins Kimmel Comprehensive Cancer Center and its Bloomberg~Kimmel Institute for Cancer Immunotherapy report that their novel machine learning algorithm helps predict which patients with melanoma would respond to treatment and which would not respond.

The open-source program, DeepTCR, proved valuable as a predictive clinical tool, but it also helped teach the researchers about the biological mechanisms underlying patients’ responses to immunotherapy. Their findings are published in the journal Science Advances.

“T cell receptor (TCR) sequencing has been used to characterize the immune response to cancer. However, most analyses have been restricted to quantitative measures such as clonality that do not leverage the complementarity-determining region 3 (CDR3) sequence,” write the investigators.

“We use DeepTCR, a framework of deep learning algorithms, to reveal sequence concepts that are predictive of response to immunotherapy. We demonstrate that DeepTCR can predict response and use the model to infer the antigenic specificities of the predictive signature and their unique dynamics during therapy. The predictive signature of nonresponse is associated with high frequencies of TCRs predicted to recognize tumor-specific antigens, and these tumor-specific TCRs undergo a higher degree of dynamic changes on therapy in nonresponders versus responders.

“These results are consistent with a biological model where the hallmark of nonresponders is an accumulation of tumor-specific T cells that undergo turnover on therapy, possibly because of the dysfunctional state of these T cells in nonresponders.”

Next step is to develop more robust models

“DeepTCR’s predictive power is exciting,” says John-William Sidhom, MD, PhD, Mount Sinai Hospital at the Icahn School of Medicine and first author of the study, “but what I found more fascinating is that we were able to view what the model learned about the immune system’s response to immunotherapy. We can now exploit that information to develop more robust models, and possibly better treatment approaches, for many diseases, even those outside of oncology.”

Superantigen binding to a T-cell receptor, illustration. A superantigen (SAg, pink) is being presented by an antigen-presenting cell (bottom) to a T-cell (top). Superantigens are released by some viruses and bacteria and can generate a strong immune response by inducing huge releases of cytokines in humans. The superantigen binds to the major histocompatibility complex class II molecules (blue) of an antigen-presenting cell. This is then presented to a T-cell via a T-cell receptor (TCR, green). This activates the T-cell (non-specific activation), which results in excessive cytokine release. [Nanoclustering/Science Photo Library/Getty Images]

DeepTCR was developed at the Johns Hopkins University School of Medicine by Sidhom when he was an MD/PhD student. It uses deep learning to recognize patterns in large volumes of data. In this case, the data is the amino acid sequences of T-cell receptors, or TCRs. When a TCR is activated by a protein from cancer, bacteria, or viruses, its T cell releases molecules to destroy the threat while cloning itself to fortify the response.

Unfortunately, some tumor cells develop ways of blocking the T cells’ response, even though the TCRs have been activated. Current immunotherapy drugs, known as checkpoint inhibitors, consist of proteins that stymie this capacity in tumors, causing T cells to respond to cancer. However, these drugs help only a minority of patients.

In the current study, Sidhom, now a resident, used materials collected during the CheckMate 038 clinical trial that tested the efficacy of one immunotherapy drug (nivolumab) compared to a combination of two (nivolumab and ipilimumab) for 43 patients with inoperable melanoma. Biopsies of the tumors, containing an array of infiltrating T cells, were taken before and during treatment.

In the CheckMate study, no significant differences were seen in patients treated with the single drug versus the two-drug combination. Some patients in both groups responded and others did not.

Sidhom used genetic sequencing to discover the TCR repertoire surrounding each tumor by determining the type and number of TCRs in each biopsy. He then fed that data to the DeepTCR program and told it which data sets belonged to responders versus nonresponders. Then the algorithm looked for patterns.

The researchers first asked if there were differences before treatment between the TCR repertoires of immunotherapy in responders and nonresponders. The differences that the algorithm identified were as predictive of patient response as known biomarkers—molecular characteristics of tumors used to guide therapy. However, before the algorithm can be used clinically to guide therapy, the researchers need to confirm these findings in a larger patient population.

“Precision immunotherapy based on the immune microenvironment in the tumor is critical to guide the optimal choice of treatment options for each patient,” says Drew Pardoll, MD, PhD, professor of oncology and director of the Bloomberg~Kimmel Institute for Cancer Immunotherapy. “These DeepTCR findings define a new dimension for predicting a tumor’s response to immune checkpoint blockade by applying a novel artificial intelligence strategy to deconvolute the vast array of receptors expressed by tumor-infiltrating T cells, the key immune components responsible for direct killing of tumor cells.”

Also of Interest