Knowledge Graphs Inference from Biomedical literature
The biological literature is a key resource to automatically extract and gain knowledge concerning biological elements and their relations. Biological Knowledge Graphs (BKGs) are helpful tools in the context of biological knowledge discovery and modeling. For scientists, especially those in the field of Biology, because of the increasing amount of scientific literature in PubMed, PubMed Central, and BioRxiv, identifying the most relevant articles dealing with a topic is not straightforward and time-consuming, which often leads to missing essential references and relevant literature. For machines, supporting scientists in their daily work of sophisticated drug designs and analysis needs a BKG that is properly structured, easily accessible, and up-to-date in the stored and indexed information coming from the scientific literature.
We present NetME, a tool that, starting from a set of full texts obtained from PubMed, automatically extracts biological entities from ontological databases and then synthesizes a network describing relations among such entities (i.e., it builds a small BKG). Next, we introduce a recent NetME extension that allows synthesizing BKG from the whole PubMed Central.