acm-header
Sign In

Communications of the ACM

ACM TechNews

Computers Learn to Recognize Molecules That Can Enter Cells


View as: Print Mobile App Share:
molecules, illustration

Credit: Lawrence Berkeley National Laboratory

Researchers at the University of California, Los Angeles (UCLA) and the University of Illinois at Urbana-Champaign, while trying to design antimicrobial peptides, found their computer program started to recognize features of peptides that could alter the shape of membranes. The researchers note this shape-altering feature helps peptides travel through the membrane and into the cell, enabling peptides to possibly carry and deliver medicines directly into diseased cells.

"Using machine learning, we developed a computer program that can differentiate between a peptide sequence that is antimicrobial and one that isn't antimicrobial," says UCLA researcher Gerard Wong. During this process, the researchers discovered a way to differentiate between peptides that permeate membranes and those that do not. They focused on a class of well-known peptides called antimicrobial peptides, which are proteins that help the immune system by killing bacteria primarily by permeating the membrane. In addition, the researchers found that the program, originally created to recognize anti-microbial peptides, also was finding peptides that generate saddle-shaped curvature on the cell membrane. The researchers used the new tool to perform a search of possible peptide sequences to find new membrane-active peptides that do not occur naturally, but can be created chemically.

From UCLA
View Full Article

 

Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account