Jodi Schneider (MS '08), assistant professor, is the recipient of a start-up allocation award from the Extreme Science and Engineering Discovery Environment (XSEDE). XSEDE is a project of the National Science Foundation that provides researchers with access to the world’s most advanced and powerful collection of integrated digital resources and services.
The award will support Schneider's research in biomedical informatics. The goal of her project is to make sense of large-scale networks of knowledge in biomedical literature. Her underlying code and data are provided by collaborators at the National Library of Medicine, who used text mining to process data from NLM's PubMed/MEDLINE to create a new database, SemMedDB.
"SemMedDB is a database with 'predications' like Drug X treats Disease Y. We consider this as a semantic network with drugs as vertices and relationships (e.g., treats) as edges. You can think of the algorithm as sending 'pulses' through the network to find what is closely connected. By developing computational views of the database, we can make new, task-oriented interfaces that (hopefully) help people find information faster and better,” said Schneider.
Schneider will receive assistance from XSEDE staff with parallelizing code, a type of computation in which several calculations or processes can be executed simultaneously. She also will use XSEDE's high-performance computing resources—the Pittsburgh supercomputer, BRIDGES—for her project. "It would take 327,000 years for a normal computer to run our code and data," she said.