Skip to main content

Unfortunately we don't fully support your browser. If you have the option to, please upgrade to a newer version or use Mozilla Firefox, Microsoft Edge, Google Chrome, or Safari 14 or newer. If you are unable to, and need support, please send us your feedback.

We'd appreciate your feedback.Tell us what you think!

Elsevier
Publish with us
researcher looking into a microscope
Case study

Using knowledge graphs to drive epigenetic target discovery in oncology with AstraZeneca

An AstraZeneca oncology team wanted to predict novel drug targets in the context of epigenetic regulation of specific cancers. Elsevier created a custom knowledge graph for this purpose, which confirmed known results and answered new research questions.

Based on specific research questions from AstraZeneca, Elsevier mined data on epigenetic relations from peer-reviewed articles. This data was combined with a subset of Elsevier’s Biology Knowledge Graph, creating a custom knowledge graph called the “EpiMap.”

This knowledge graph contextualized these epigenetic phenomena in other known biology and disease processes. The team then built analytical and predictive models based on these data.

Working with Elsevier, the company gained:

  • A number of testable mechanisms of drug resistance across the literature that would have been nearly impossible to identify through manual literature searches

  • An order of magnitude increase in the search space for new epigenetic drug targets. On average, for each cancer segment studied, the top 10 predictions yielded four known positives (increasing confidence in the approach) and three interesting but unknown candidates