Constrained Submodular Optimization for Vaccine Design
Abstract
Advances in machine learning have enabled the prediction of immune system responses to prophylactic and therapeutic vaccines. However, the engineering task of designing vaccines remains a challenge. In particular, the genetic variability of the human immune system makes it difficult to design peptide vaccines that provide widespread immunity in vaccinated populations. We introduce a framework for evaluating and designing peptide vaccines that uses probabilistic machine learning models, and demonstrate its ability to produce designs for a SARS-CoV-2 vaccine that outperform previous designs. We provide a theoretical analysis of the approximability, scalability, and complexity of our framework.
Cite
Text
Dai and Gifford. "Constrained Submodular Optimization for Vaccine Design." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I4.25632Markdown
[Dai and Gifford. "Constrained Submodular Optimization for Vaccine Design." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/dai2023aaai-constrained/) doi:10.1609/AAAI.V37I4.25632BibTeX
@inproceedings{dai2023aaai-constrained,
title = {{Constrained Submodular Optimization for Vaccine Design}},
author = {Dai, Zheng and Gifford, David K.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2023},
pages = {5045-5053},
doi = {10.1609/AAAI.V37I4.25632},
url = {https://mlanthology.org/aaai/2023/dai2023aaai-constrained/}
}