Communications of the ACM
New Deep Knowledge AI System Could Resolve Bottlenecks in Drug Research
University of Waterloo researchers have developed a system that could significantly speed up the discovery of new drugs, and reduce the need for costly, time-consuming laboratory tests.
Credit: promeddx.com
Researchers at the University of Waterloo in Canada have developed a new system that can predict the binding of biosequences in seconds and potentially reduce bottlenecks in drug research.
Pattern to Knowledge (P2K) relies on artificial intelligence to leverage deep knowledge from data, instead of relying on classical machine learning.
P2K's algorithms disentangle multiple associations to identify and predict amino acid bindings that govern protein interactions.
During testing, the researchers found P2K is much faster than existing biosequence analysis software, with nearly 30% better prediction accuracy.
By tapping information from databases in the cloud, P2K could predict interactions between tumor proteins and potential cancer treatments.
Said Waterloo's Andrew Wong, "P2K is a game changer given its ability to reveal subtle protein associations entangled in complex physiochemical environments and powerfully predict interactions based only on sequence data."
From University of Waterloo News
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found