Deep knowledge AI system could speed up drug research

Monday, 12 November, 2018

Deep knowledge AI system could speed up drug research

Researchers from the University of Waterloo have developed a system that could significantly speed up the discovery of new drugs, reducing the need for costly and time-consuming laboratory tests.

Known as Pattern to Knowledge (P2K) and described in the journal Scientific Reports, the new technology uses artificial intelligence (AI) to leverage deep knowledge from data instead of relying solely on classical machine learning. This enables it to predict the binding of biosequences in seconds, potentially reducing bottlenecks in drug research.

“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,” said Professor Andrew Wong, Founding Director of Waterloo’s Centre for Pattern Analysis and Machine Intelligence (CPAMI). “The ability to access this deep knowledge from proven scientific results will shift biological research going forward. P2K has the power to transform how data could be used in the future.”

Although a large amount of biological sequence data has been collected, extracting meaningful and useful knowledge hasn’t been easy. P2K algorithms tackle this challenge by disentangling multiple associations to identify and predict amino acid bindings that govern protein interactions.

Since P2K is faster than existing biosequence analysis software, and said to have almost 30% better prediction accuracy, it could significantly speed up the discovery of new drugs. By drawing information from databases in the cloud, P2K could predict how tumour proteins and potential cancer treatments would interact.

And since it analyses sequential data, the applicability of P2K isn’t limited to biomedical research. The system could benefit the financial industry by making useful associations and predictions for smart trading or the cybersecurity sector by predicting the likelihood of a potential cyber attack.

Although still in the early prototype stage, Prof Wong and his team have made the P2K system available publicly at, enabling researchers to start identifying new biosequence interactions. The system’s co-inventor, Research Associate Antonio Sze-To, said, “Putting this AI technology in the hands of biomedical researchers will generate immediate results, which could be used for future scientific discoveries.”

Image credit: ©agsandew/Dollar Photo Club

Related News

AI image analysis helps diagnose COVID-19

An advanced medical report generation method, based on AI technology, has been shown to...

Free access for research engagement platform

Kudos is providing the global academic community with complimentary access to its premium service...

Computer model identifies drug-resistant mutations

The approach could significantly improve the ongoing challenge of developing drugs that combat...

  • All content Copyright © 2020 Westwick-Farrow Pty Ltd