Deep Learning of the Immune Synapse


Poster Artificial intelligence is poised to revolutionize every aspect of human life, finding applications in everything from self-driving cars to diagnosing cancer. In fact, almost any task that involves pattern recognition can be formulated in a way that modern AI algorithms can be used to achieve super-human performance. The immune synapse is a highly complex interaction between several proteins and peptides that allows for a constant surveillance of foreign invaders. However, modeling these interactions is extremely difficult as the combinations of interactions is simply intractable. In immune-oncology, the study of this interaction is crucial as anti-tumor responses rely on sensitive and specific recognition of tumor-specific antigens. Implications of accurately predicting and modeling these interactions in immune-oncology range from improved and potent vaccine design to biomarkers for predicting response to immunotherapy to furthering our understanding of immune recognition. Our group has developed a variety of deep learning models to model the signal transmission within the immune synapse. We first present AI-MHC, an applied deep convolutional neural network for class-specific MHC binding algorithm that achieves state-of-the-art performance in both Class and Class II predictions. By incorporating ‘meaning’ of the allele within the network, we are able to model the interaction of allele and peptide within the context of a neural network. We take these concepts further in the development of DeepMANA, a deep learning framework which combines sequence-specific information about an allele/peptide pairing to not only predict binding affinity for any allele with a known protein sequence but also provide an antigen ‘quality’ score. We observe that in three immunotherapy clinical trials, these quality neoantigens are enriched in long-term survivors/responders. Finally, we apply a variety of unsupervised and supervised deep learning algorithms to reveal structure in T-cell receptor sequencing that is predictive of various pathologies and therapies.

Oct 1, 2018
Boston, MA. USA