Knowledge-based analysis of genome-scale data project
- A short lead paragraph
This project involves building a network of available biological knowledge to aid in the interpretation of high throughput molecular biology data. The network, a composition of a number of ontologies, is augmented by information extracted from the literature.
We've used the Janus cluster to learn and explore scaling techniques for text mining, to perform text mining for gene mentions over the Pub Med Open Access collection of 250,000 documents, and to do co-occurrence analysis on the mined mentions.
- Links to award summaries for each source of funding
Christophe Roeder, William A. Baumgartner Jr., Kevin Livingston, Lawrence Hunter, University of Colorado Denver; A Distributed Framework for Computation on the Results of Large Scale NLP, Rocky Mountain Bioinformatics Conference 2011, Snowmass, CO link
Kevin M. Livingston, Michael Bada, William A. Baumgartner Jr, Yuriy Malenkiy, Lawrence E. Hunter, University of Colorado Denver; Integrating Curated Databases and Text Mining Output into a Biomedical Knowledge Base, Rocky Mountain Bioinformatics Conference 2011, Snowmass, CO link
- Links to project's websites