BigMHC Identifies Immune Response-Triggering Neoantigens with Precision

A novel deep-learning technology called BigMHC, developed by a collaborative team of Johns Hopkins engineers and cancer researchers, has shown promise in accurately predicting and identifying cancer-related protein fragments that could activate an immune response. Detailed in a study published in Nature Machine Intelligence, this method could pave the way for overcoming a significant obstacle in developing personalized immunotherapies and vaccines.

The cancer protein fragments that elicit this tumor-killing immune response may originate from changes in the genetic makeup of cancer cells, called mutation-associated neoantigens. Each patient’s tumor has a unique set of such neoantigens that determine tumor foreignness, in other words, how different the tumor makeup is compared to self. Scientists can identify which mutation-associated neoantigens a patient’s tumor has by analyzing the genome of the cancer.

Determining those which are most likely to trigger a tumor-killing immune response could enable scientists to develop personalized cancer vaccines or customized immune therapies as well as inform patient selection for these therapies. However, current methods for identifying and validating immune response-triggering neoantigens are time-consuming and costly, as these typically rely on labor-intense, wet laboratory experiments.

Because neoantigen validation is so resource intensive, there are few data to train deep-learning models. To address this, the researchers trained BigMHC, a set of deep neural networks, in a two-stage process called transfer learning. First, BigMHC learned to identify antigens that are presented at the cell surface, an early stage of the adaptive immune response for which many data are available. Then, BigMHC was fine-tuned by learning a later stage, T-cell recognition, for which few data exist. In this manner, the researchers leveraged massive data to build a model of antigen presentation, and refined this model to predict immunogenic antigens.

BigMHC's efficacy was verified through extensive testing on independent datasets, demonstrating its superior accuracy in predicting antigen presentation compared to existing methods. When applied to data from cancer immunotherapy specialist and co-author Kellie Smith, BigMHC outperformed seven other techniques in identifying neoantigens that provoke T-cell responses.

The researchers anticipate applying BigMHC in immunotherapy clinical trials to efficiently sift through vast neoantigen datasets and identify those most likely to initiate an immune response. This innovation holds promise in guiding the development of immunotherapies applicable to multiple patients or personalized vaccines designed to enhance individual immune responses against cancer cells.