In silico design of MHC class I high binding affinity peptides through motifs activation map

Finding peptides with high binding affinity to Class I major histocompatibility complex (MHC-I) attracts intensive research, and it serves a crucial part of developing a better vaccine for precision medicine. Traditional methods cost highly for designing such peptides. The advancement of computational approaches reduces the cost of new drug discovery dramatically. Compared with flourishing computational drug discovery area, the immunology area lacks tools focused on in silico design for the peptides with high binding affinity. Attributed to the ever-expanding amount of MHC-peptides binding data, it enables the tremendous influx of deep learning techniques for modeling MHC-peptides binding. To leverage the availability of these data, it is of great significance to find MHC-peptides binding specificities. The binding motifs are one of the key components to decide the MHC-peptides combination, which generally refer to a combination of some certain amino acids at certain sites which highly contribute to the binding affinity.

In this work, we propose the Motif Activation Mapping (MAM) network for MHC-I and peptides binding to extract motifs from peptides. Then, we substitute amino acid randomly according to the motifs for generating peptides with high affinity. We demonstrated the MAM network could extract motifs which are the features of peptides of highly binding affinities, as well as generate peptides with high-affinities; that is, 0.859 for HLA-A*0201, 0.75 for HLA-A*0206, 0.92 for HLA-B*2702, 0.9 for HLA-A*6802 and 0.839 for Mamu-A1*001:01. Besides, its binding prediction result reaches the state of the art. The experiment also reveals the network is appropriate for most MHC-I with transfer learning.

We design the MAM network to extract the motifs from MHC-peptides binding through prediction, which are proved to generate the peptides with high binding affinity successfully. The new peptides preserve the motifs but vary in sequences.