A simple tool for browsing large sets of relational data.
Each row in the matrix is a piece of evidence extracted from Bioinformatics publications using Natural Language Processing techniques. Each column is an existing bioinformatics datum, as found in a large database of bioinformatics entities and relationships. Each square in the matrix can be seen as a “potential match” between biological information extracted via the analysis of natural language with existing bioinformatics data.
The tool can be used by NLP researchers to evaluate the output of their algorithms and to search for potentially interesting relationships between novel and existing data.
Part of my work related to (and with support from) the DARPA Big Mechanism Project