Federal Grant Award Summary

The University of Washington received a $517,083 Project Grant award from the National Institute of General Medical Sciences (NIGMS) under the Biomedical Research and Research Training program (CFDA 93.859), effective June 10, 2026, with completion scheduled for March 31, 2031. This award funds research and development of artificial intelligence (AI)-enabled computational tools for de novo design of functional macrocyclic peptides, which are targeted therapeutic molecules with potential applications in treating previously "undruggable" intracellular protein-protein interactions. The research addresses significant limitations of traditional peptide discovery and optimization methods by developing structure-guided deep learning (DL) methods to systematically explore chemical and structural space while simultaneously optimizing multiple therapeutic properties including target binding, selectivity, and membrane permeability.

The primary deliverables under this award include: (1) development of deep learning methodologies to enumerate and characterize the chemical and structural space of constrained and membrane-traversing peptides to establish foundational design scaffolds and principles; and (2) high-throughput computational design and experimental data collection initiatives to improve design selection and validation. These outputs represent next-generation computational tools intended to accelerate and democratize peptide-based therapeutic development by enabling rapid, precise, and custom design of functional macrocycles beyond the limitations of natural product discovery and conventional screening approaches.