Utility of language model and physics-based approaches in modifying MHC Class-I immune-visibility for the design of vaccines and therapeutics
02:14 Share

Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2023.07.10.548300v1?rss=1

Authors: Gasser, H.-C., Oyarzun, D., Rajan, A., Alfaro, J.

Abstract: Protein therapeutics promise to revolutionize medicine, with an arsenal of applications that include disrupting viral replication, acting as potent vaccines, and replacing genetically deficient proteins. Therapeutics must avoid triggering unwanted immune responses towards the therapeutic protein or viral vector proteins. In contrast, vaccines require a robust immune reaction targeting a broad range of pathogen variants. Therefore, computational methods modifying proteins' immune visibility, while maintaining functionality, are needed. This paper focuses on visibility to cytotoxic T-lymphocytes, which use the MHC Class I pathway to detect destruction targets. To explore the limits of modifying MHC-I immune visibility within the distribution of naturally occurring sequences, we developed a novel machine learning technique, CAPE-XVAE, that combines a language model with reinforcement learning to modify a protein's immune visibility. Our results show that CAPE-XVAE effectively modifies the MHC-I immune visibility of the HIV Nef protein. We contrast CAPE-XVAE to CAPE-Packer, a physics-based method we also developed, and observe that while the machine learning approach generates more natural appearing sequences, the physics-based approach achieves a greater reduction in immune visibility. Compared to CAPE-Packer, CAPE-XVAE has a propensity to suggest sequences that draw upon local sequence similarities in the training set. This is particularly important for vaccine development, to be representative of the real viral population and the approach holds promise for preserving both known and unknown functional constraints, which are essential for deimmunization of therapeutic proteins. CAPE-Packer, solely focuses on preserving the protein's fold, falling short of capturing this complexity.

Copy rights belong to original authors. Visit the link for more info

Podcast created by Paper Player, LLC