Abstract:
Considering today’s surge of information, the need for well organized knowledge
bases is increasing rapidly for providing simplified access to knowledge and its
further processing. In biomedical domain, heaps of information is buried in scientific
publications and online forums. This calls for representing this information in a more
expressive semantic way by determining and storing relational information into a
machine readable form. So, the primary goal of this research endeavor has been to
build a knowledge base on entities and relations containing amass of formalized
background knowledge suitable for supporting reasoning in biomedical domain.
In this work, we introduce a way for easily accessing the knowledge about body parts
and symptoms of human diseases, along with environmental, social, nutritional and
diagnostic factors that cause these diseases. The information for this knowledge base
is extracted from the controlled vocabulary thesaurus “Medical Subject Headings”
(MeSH), which is published by National Library of Medicine.
The result is a semantic graph of typed entities and relations between diseases, their
symptoms, affected body parts and determining factors, with emphasis on
environmental, social, nutritional and diagnostic factors. The facts stored in our
ontology are provided to the user in a visual web interface.
Currently, our ontology contains 53020 individuals, 96835 synonymous terms and
197731 facts related to seven pre-defined categories of our biomedical ontology. In
this way, it fulfils an identified need to provide detailed semantic knowledge
regarding different biomedical sub-domains at one place through one core KB
