Biomedical Knowledge Engineering Group


We are relocating our website to

Biology and medicine are complex, multi-faceted and deeply involved disciplines. Our work is concerned with developing computational theories, methodologies and tools to unpack, elucidate, and explain this complexity in order to help scientists make discoveries. We primarily support the work of neuroscientists, but strive to make our systems applicable to any complex field of scientific investigation.

Here is a short ISI promotional video about my work:

See this slide show by Gully Burns at Google to provide an in-depth introduction to our work:

Also, this 30-minute talk at the INCF Annual Congress in 2013 describes one of our efforts in detail (using experimental design to inform the development of knowledge engineering systems):  

In brief, we develop practical, knowledge-centric solutions for biomedical researchers. We focus on finding the strategic information bottlenecks in the current biomedical informatics architecture and work with top-level computer scientists to create well-engineered solutions and infrastructure. We place our focus on developing tools for specific biomedical communities and domains, whilst attempting to have the technology that we construct be general enough to be applied to any biomedical domain. The research we are engaged in leverages cutting-edge research in Artificial Intelligence and applies it to biomedicine. This primarily involves the following areas:

  • Natural Language Processing, Text Mining and Machine Reading
  • Knowledge Representation and Reasoning, Ontology Engineering and Semantic Web
  • Information Integration, Domain Modeling 
  • User Interfaces, Data Visualization
  • Software Engineering, Tool Development and Deployment  

In particular, we wish to understand and empower discovery informatics. This is a new field of research, specifically focussed on investigating how AI technology may be brought to bear on the act of scientific discovery itself. See Gully Burns' science blog 'Building the Breakthrough Machine'.

We maintain an active 'Wiki' that provides a working record and documentation for our work, if you'd like to dive into a little more detail. We are a subgroup within the large dynamic team of the Information Integration Group under Craig Knoblock at ISI.