Bioinformatics concerns the development of computer databases and algorithms for learning, managing and processing biological information. Currently we are focusing on extracting structured information such as protein names and relationships from biological documents using natural language learning for information extraction.

By mining over 750,000 Medline abstracts for human protein interactions and integrating the results with existing databases, we have developed a fairly comprehensive database of 31,609 known human protein interactions. The resulting database is accessible though a web interface at Human Gene ID-SERVE