About
I’m a PhD level data scientist with 10 years of experience in statistics, bioinformatics, machine learning and data management. I have a particular interest in reproducible analyses: making it easy to reproduce environment, data and code on another machine. I work for the University of Michigan BRCF Bioinformatics Core analyzing genomics data including WGS, bulkRNASeq and single-cell RNASeq. In my previous position at Wayne State University I implemented a system for cataloging public data to make them compliant with the FAIR principles for data analyses. We also implemented a solution for sharing computational workflows using Docker.
Lately I’ve also been interested in spectral clustering and other analyses that use kernel distance matrices, (eg. support vector machines).
I recieved my PhD from Wayne State in 2008 and a MS in Data Science & Business Analytics also from Wayne State in 2019. My background in machine learning and statistics is strong and my technical skills include R and python programming and workflow and environment management. I operate a data analytics and reporting company Activatechnology.
I’ve written over 20 scientific publications.