Pharma R&D Today
Ideas and Insight supporting all stages of Drug Discovery & Development
Ontologies – what do they have to do with pharma research?
Posted on August 24th, 2022 by Ann-Marie Roche in AI & Data
You would be forgiven for thinking that the topic of ontology is more the domain of philosophers or linguists – and not necessarily the concern of someone working in the life sciences. After all, the first definition you get if you Google the word ontology is “the branch of metaphysics dealing with the nature of being”. But dive deeper into the term, and you’ll discover that it’s about classifications of things and their relationships to each other – and that can most certainly be of interest to scientists.
Now more than ever, life science researchers have reason to be interested in ontologies as a tool that can help create high-quality data for AI that is being used in scientific research.
AI accelerates research
Machine learning and AI technologies are opening up exciting new frontiers in areas like pharmaceutical R&D, where the fast pace of artificial intelligence can make it feasible and affordable to advance personalized medicine and research rare diseases. But, as Dr. Jane Lomax of SciBite writes in a new article in Technology Networks, “the success of precision medicine will rest on companies being able to harness vast volumes and variety of data – including published literature, proprietary and experimental data, as well as patient and healthcare records.”
The data is the thing. And as the saying goes, ‘garbage in, garbage out,’ so the AI is only as useful as the data that is fed into it.
Making data FAIR with ontologies
The FAIRification of data has become a critical project to ensuring that data is AI-ready. FAIR stands for ‘Findable, Accessible, Interoperable, Reusable’ – these are among the most important attributes for data, and they are currently lacking for many types of data out there right now. But ontologies can be very helpful in making data FAIR.
“Ontologies provide unique identifiers with associated names and synonyms which can help with the normalization of scientific language,” explained Dr. Lomax. “Tagging data with these identifiers makes it easier to search and analyze for scientists, as it includes results that contain synonyms or associated terms that the ontology recognizes as being related to the search query.”
One way that she suggests newly-generated data could be made FAIR with the aid of ontologies would be through “smart data entry,” which could involve using ontology-powered type ahead when inputting new information.
Better data leads to bigger discoveries
Powerful AI technology will be at the heart of the next wave of innovation. Any life sciences organization intent on finding success in precision medicine will not only need to invest resources into machine learning and AI, but also into making their legacy data FAIR and ensuring that new data is FAIR as well.
To learn more about the role that ontologies play in this process, read Dr. Jane Lomax’s article here.
R&D Solutions for Pharma & Life SciencesWe're happy to discuss your needs and show you how Elsevier's Solution can help.
Director, Corporate Markets Marketing, Elsevier
- Increasing trial participation for new cancer treatments
- Reaxys User Day 2022: Sharing insights and tips for streamlining the chemist workflow
- Reaxys User Day 2022: Researcher secrets in the spotlight
- Elsevier and LG: Turning data into action
- Umesh Nandal: Chemist and data scientist in one