KnowLife: a Knowledge Graph for Health and Life Sciences
Large knowledge bases (KB's) about entities, their properties, and the relationships between entities,
have become an important asset for semantic search, analytics, and smart recommendations
over Web contents and other kinds of Big Data.
However, In the biomedical domain KB's are often highly specialized and cover only on a relative narrow topic within the life sciences, and there is very little interlinkage between the KB's.
Thus, in contrast to the general-domain KB's that power Web search and analytics, there is no way of obtaining an integrated view on all aspects of biomedical knowledge.
The lack of a
one-stop KB that spans biological, medical, and health knowledge hinders the development of advanced search and analytic applications in this field.
In contrast, we pursued a holistic approach with KnowLife to construct a comprehensive biomedical KB.
KnowLife is a large KB that captures a variety of biomedical knowledge and is automatically extracted from different genres of input sources.
Specifically, we overcome these limitations of prior work:
- Beyond manual curation:
Biomedical knowledge is advanced at a rate far greater than any single human
can absorb. Therefore, relying on manual curation of KB's is bound to be a bottleneck.
- Beyond scientific literature:
Prior work on biomedical IE has mainly focused on scientific literature only, and often disregards
the opportunities that lie in tapping health portals and communities for automated IE.
KnowLife does not only extracts knowledge from scientific publications, but also taps previously neglected textual sources like Web portals on health issues and online communities with discussion boards.
- Beyond molecular entities:
IE from biomedical texts has strongly focused on entities and relations
at the molecular level; a typical IE task is to extract protein-protein interactions.
The entities and facts in KnowLife go far beyond
the traditionally covered level of proteins and genes.
Besides genetic factors of diseases, the KB also captures diseases, therapies, drugs,
and risk factors like nutritional habits, life style, and side effects of treatments.
Powering a One-stop Health Portal
To showcase the potential of a holistic knowledge base like KnowLife, we created the KnowLife web portal and demonstrate its usefulness by several use-case scenarios: