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.
Please enable JavaScript to view the comments powered by Disqus.
R&D Solutions for Pharma & Life Sciences
We’re happy to discuss your needs and show you how Elsevier’s Solution can help.
!function(f,b,e,v,n,t,s){if(f.fbq)return;n=f.fbq=function()
{n.callMethod? n.callMethod.apply(n,arguments):n.queue.push(arguments)}
;if(!f._fbq)f._fbq=n;
n.push=n;n.loaded=!0;n.version=’2.0′;n.queue=[];t=b.createElement(e);t.async=!0;
t.src=v;s=b.getElementsByTagName(e)[0];s.parentNode.insertBefore(t,s)}(window,
document,’script’,’https://connect.facebook.net/en_US/fbevents.js’);
fbq(‘init’, ‘533182150132648’);
fbq(‘track’, “PageView”);
!function(f,b,e,v,n,t,s){if(f.fbq)return;n=f.fbq=function()
{n.callMethod? n.callMethod.apply(n,arguments):n.queue.push(arguments)}
;if(!f._fbq)f._fbq=n;
n.push=n;n.loaded=!0;n.version=’2.0′;n.queue=[];t=b.createElement(e);t.async=!0;
t.src=v;s=b.getElementsByTagName(e)[0];s.parentNode.insertBefore(t,s)}(window,
document,’script’,’https://connect.facebook.net/en_US/fbevents.js’);
fbq(‘init’, ‘1737613393127776’,
{ em: ‘insert_email_variable,’ }
);
fbq(‘track’, ‘PageView’);
