Machine Learning for De Novo Design of Macrocyclic Peptides as Strain-Specific

Abstract

In this proposal, we will integrate the recent advances from our labs to develop a high throughput machine-learning (ML) guided framework for the rapid design of macrocyclic peptides as affinity reagents against pathogenic strains of bacteria. We expect these new ML models will improve our design accuracy and provide a general framework for the rapid creation of proteome-targeting macrocycles. Overall, we aim to use our iterative design-synthesis-test-learn approach to develop a new machine learning framework for the custom design of new peptide affinity reagents as leads for diagnostics and therapeutic leads.

Document Details

Document Type
DoD Grant Award
Publication Date
Jun 14, 2022
Source ID
HDTRA12110007

Entities

People

  • David Baker

Organizations

  • Defense Threat Reduction Agency
  • University of Washington

Tags

Fields of Study

  • Computer science

Readers

  • Immunology
  • Neural Network Machine Learning.
  • Organic Chemistry

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Biotechnology