LION LBD helps Cancer researchers form hypotheses by giving them a graph based view of the research literature.
We text mine abstracts from Pubmed and extract relevant biological concepts (entities). These entities are represented is a node in our graph and edges between entities represent co-occurence of two entities in a sentence.
The system is built with a particular focus on the molecular biology of cancer using state-of-the-art machine learning and natural language processing methods, including named entity recognition and grounding to domain ontologies covering a wide range of entity types and a novel approach to detecting references to the hallmarks of cancer in text. LION LBD implements a broad selection of co-occurrence based metrics for analyzing the strength of entity associations, and its design allows real-time search to discover indirect associations between entities in a database of tens of millions of publications while preserving the ability of users to explore each mention in its original context in the literature.
You can find LION LBD here: http://lbd.lionproject.net/
This work is a collaboration with Cancer Research UK Cambridge Institute (Narita group) and Karolinska Institutet (Institute of Environmental Medicine).