My blog
AstraZeneca's knowledge graph: Drug discovery is a lot about connections

AstraZeneca's knowledge graph: Drug discovery is a lot about connections

The biomedical knowledge graph built by AstraZeneca helps the company find new drugs and drug targets.

Published on by Anton Vasetenkov
Updated on

AstraZeneca is one of the world's most prominent drugmakers whose ever-growing portfolio includes a number of FDA-approved brands such as Crestor, Symbicort, and Nexium. Like all pharma companies, it invests heavily in research and development and spends billions of dollars on clinical trials for all of its experimental drugs before it can bring them to market.

As drug discovery requires a thorough understanding of the complex network of interactions between a drug and its target and its effect on the body, researchers and pharma companies are increasingly turning to knowledge graphs as means to synthesize, integrate, and fully leverage all prior knowledge and streamline the efforts involved in identifying novel drugs and drug targets. Known for its focus on real medical needs and globally integrated approach to R&D, AstraZeneca is one of the companies that have jumped on the bandwagon and embraced knowledge graphs to speed up and strengthen their drug discovery and development.

While there are many ways to organize and aggregate different kinds of structured biomedical data, graphs are perhaps the most common and flexible approach to solving this problem because of their ability to naturally represent the functions, interactions, and other types of relationships (connections) between biological entities. These networks of contextualized scientific data connect all known drugs to their drug targets which go all the way down to the level of individual genes and the proteins that they encode.

AstraZeneca's knowledge graph is known to be a large-scale and continuously updated graph network which integrates both the public biochemical and biomedical data sources as well as the company's internal research data in the areas of oncology, immunology, metabolism, and so on. Assembled in this way, the knowledge graph is then used to make predictions—identify the missing links between its entities which may potentially represent the currently unknown drug–target interactions or relationships between the druggable genes and various medical conditions.

Bottom line

In the context of drug discovery and development, knowledge graphs help organize the wealth of both structured and unstructured data about candidate drugs and their targets.

AstraZeneca is one of the many pharmaceutical companies that are known to have used knowledge graphs to identify promising drug candidates and accelerate their drug discovery efforts.

See also

The RDF model of the Gene Ontology, demystified
An outline of the structure of the Gene Ontology RDF graph and ways to query it.
WikiPathways: A Wikipedia for biological pathways
An overview of the collaboratively edited structured pathway encyclopedia.
What is FHIR and why is it important?
An overview of FHIR and its impact on patient care.
Linked data for the enterprise: Focus on Bayer's corporate asset register
An overview of COLID, the data asset management platform built using semantic technologies.
A network of drugs: The New Zealand Medicines Terminology
An overview of New Zealand's drug vocabulary.

Thanks for stopping by my digital playground! If you want to say hi, you can reach out to me on LinkedIn or via email. I'm always keen to chat and connect.

If you really-really like my work, you can support me by buying me a coffee.