Engineers at the University of Oklahoma (OU) and the University of Rochester (UR) have closed the gap between experimental and computer sciences to better predict peptide structures with a molecular framework.
OU's Handan Acar said the team concentrated on small peptides with six amino acids, and designed the framework to keep four of the amino acids the same, while the other two were altered to observe the effects on peptide interactions and the end product.
UR's Andrew White said, "The advantage of this framework is, it is simple enough to make computational simulations, which provide an opportunity to use machine learning."
He also said future applications will be able to utilize deep learning and artificial intelligence to model peptide structures to produce materials with required traits for a desired function.
From University of Oklahoma
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found