Our research is focused on Integrative Drug Discovery Informatics, that is data mining information relating compounds, targets and diseases from multiple sources, including publications, predictive models and experimental databases. Much of our work is being implemented in a tool called WENDI (Web Engine for Nonobvious Drug Information) through a project funded by Eli Lilly. We will soon have publicly-accessible version of WENDI.

Our research focuses on these areas:

Semantic Web for Drug Discovery In collaboration with Professor Ying Ding
  • Data mining compound-disease relationships using OWL and RDF inference
  • Semantic Web in Systems Chemical Biology
  • Composing and ranking scientific workflows using Semantic Web technologies
Mining chemical andbiological information from the literature
  • Semantic markup of chemistry documents using Natural Language Processing and Ontologies
  • Relevant document retrieval using chemical structure and ontological information 
Large scale predictive modeling for drug discovery
  • Frequent Itemset Mining for Classifying Bioactivity 
  • PubChem Bioassay Predictive Models in R 
  • Toxicity models in R 
  • Evaluating Hellinger Distance Trees for predictive modeling 
Next-generation informatics infrastructure for drug discovery
  • Aggregative webservices for drug discovery
  • A cloud computing infrastructure for drug discovery

Faculty in this area include:
Ying Ding, Vikram Jadhao, David Wild