Cyclic peptide structure prediction and design using AlphaFold
Вставка
- Опубліковано 21 сер 2024
- Tuesday May 9th, 4-5 pm EST
Stephen Rettie (top) - PhD student, University of Washington
Simon Kozlov (bottom) - Computational Biology Fellow, Harvard
Deep learning networks offer considerable opportunities for accurate structure prediction and design of biomolecules. While cyclic peptides have gained significant traction as a therapeutic modality, developing deep learning methods for designing such peptides has been slow, mostly due to the small number of available structures for molecules in this size range. I will describe our approaches to modify the AlphaFold network for accurate structure prediction and design of cyclic peptides, and computational methods for designing sequences of peptide backbones generated by other backbone sampling methods and for de novo design of new macrocyclic peptides. X-ray crystal structures for seven sequences with diverse sizes and structures designed by this approach match very closely with the design models. These computational methods and scaffolds provide the basis for custom-designing peptides for targeted therapeutic applications.
Preprint: www.biorxiv.or...
Github Notebook: github.com/sok...