Cambridge Team Uses AI to Aid Cancer Drug Development

DZone 's Guide to

Cambridge Team Uses AI to Aid Cancer Drug Development

AI is increasingly playing a part in the drug development process.

· AI Zone ·
Free Resource

AI is increasingly playing a part in the drug development process, with a common use case being to deploy it to sift through vast quantities of data to find potential avenues for exploration. A similar system has recently been developed by a team from the University of Cambridge to help scientists search for cancer-related discoveries.

The system, which is known as LION LBD, has been documented in a recently published paper, takes a different approach to many such tools, in that the data if sifts through is not so much medical data as scientific literature. The researchers reason that the literature is so vast that scientists struggle to keep up with it.

“As a cancer researcher, even if you knew what you were looking for, there are literally thousands of papers appearing every day,” the researchers explain. “LION LBD uses AI to help scientists keep up-to-date with published discoveries in their field, but could also help them make new discoveries by combining what is already known in the literature by making connections between sources that may appear to be unrelated.”

Literature-Based Discovery

The focus of the system is illustrated in their name, with the LBD standing for literature-based discovery.  This is a concept that was developed a few decades ago that aims to uncover new discoveries as a result of combining information from seemingly disconnected sources.  The rationale is that whilst concepts may not be explicitly linked in the literature, they may still be indirectly linked via intermediate concepts.

The system works to try and uncover indirect associations between various entities in the published literature, and with tens of millions of such publications in existence, the team hopes that it provides an ample haystack within which to find some needles.

“For example, you may know that a cancer drug affects the behavior of a certain pathway, but with LION LBD, you may find that a drug developed for a totally different disease affects the same pathway,” they explain.

The team believes that the project is the first to specifically target cancer, and especially the molecular biology of cancer.  In early tests, it has proven effective at identifying previously undiscovered links, and even in ranking the potency of these links.

It’s built using open data and open source standards, and as such, the team hopes that it will prove to be a valuable tool for the cancer research community to utilize.

ai and cancer, artificial intelligence, using ai to aid in cancer drug development

Published at DZone with permission of Adi Gaskell , DZone MVB. See the original article here.

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}