Robust AI-driven counter-measures: screening, guiding, combining
Abstract
Our goal is to develop an AI platform for drug discovery that supports rapid and cost-effective medical countermeasure (MC) development for emerging chemical and biological (CB) threats. This scenario commonly implies that we have limited knowledge About the new threat and that relevant screening data may be lacking. Therefore, traditional AI algorithms that require large, target-specific data for training are not directly applicable here. Moreover, we assume that the relevant bioactivity data will be collected iteratively, rather than available at the outset of the development program. The proposed in-silico screening tools must be helpful from the start in order to efficiently guide rapid response experimental efforts. Finally, these tools must be transparent to human experts, who ultimately lead drug design efforts and thus need to make decisions based on model predictions.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jun 14, 2022
- Source ID
- HDTRA12110013
Entities
People
- Regina Barzilay
Organizations
- Defense Threat Reduction Agency
- Massachusetts Institute of Technology