Academic Research Projects

All of my research so far has dealt with either text mining or network theory (hence the image in the title). My primary focus right now is a multilabel hierarchical document classification (not listed below). These are all projects I maintain in the Bioinformatics Division at MUSC.

• pymur: a Python interface to The Lemur Toolkit
• GOGrapher (manuscript in preparation): GOGrapher is a python library that uses the Gene Ontology to create a network relating terms to each other and proteins to terms.
• GOSteiner (manuscript in preparation): A project developing a general measure of protein-group functional coherence, based on the Gene Ontology and utilizing GOGrapher.
• mapducer: A mapreduce implementation for (actual) clusters.