Machine learning-guided design of modular, protein-based medical countermeasures
Abstract
The overarching goal of this proposal is to address this challenge. We will integrate design, screening, and production platforms into an MCM development pipeline capable of responding quickly to emergent chemical and biological threats. This will be achieved by designing large libraries of miniprotein binders, using cell-free protein synthesis (CFPS) methods for producing and testing the binders, and assembling the binders on multivalent scaffolds to yield potent therapeutics capable of neutralizing threats and preventing immune escape. To facilitate therapeutic efficacy, glycosylation will also be considered. The use of artificial intelligence (AI) and machine learning (ML) will allow for seamless incorporation of experimental data (successes and failures) into a broad, knowledge base for forward engineering. The proposed work will significantly advance the basic science of computationally guided optimization and preparation of active, therapeutically important MCMs (see “Targets” below), forging a broad range of innovative technologies that will transform public health, commercial, and defense applications. For example, our work may allow emergency use therapeutics to be developed and deployed on the magnitude of months, minimizing the risk of the warfighter to emerging chemical and biological threat agents.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jun 14, 2022
- Source ID
- HDTRA12110038
Entities
People
- Michael C Jewett
Organizations
- Defense Threat Reduction Agency
- Northwestern University