I hope to spend this summer providing much-needed additional functionality to InterMine, a software project which helps researchers create and manage genomic data for specific organisms. InterMine currently supports structured queries of these databases through a simple graphical interface, but this is a barrier of entry for many researchers (even for those with computing backgrounds). I'm proposing to create a natural language parser to generate structured PathQuery queries (JSON or XML) from English-language sentences, allowing a wider range of researchers to easily navigate InterMine databases. The project would largely be implemented in Clojure/ClojureScript, which are used at InterMine, possibly relying as well on 3rd-party NLP libraries or services.



Jacob Macneal


  • Aaron Golden
  • Yo Yehudi