Applies statistical modeling and machine learning to elucidate the impact of tumor and patient heterogeneity on disease outcome and therapeutical response.
Emerging single-cell transcriptomic and highly-multiplexed imaging methodologies are advancing our basic understanding of tumor heterogeneity and its impact on patient outcome and therapeutic response. My previous work involved predicting disease progression and drug response using bulk (principally, expression) data. My interests lie in leveraging these new single-cell modalities to improve our ability to extract insight from the wealth of existing (and clinically annotated) bulk data. For example, we have recently completed a deconvolution DREAM challenge comparing methods that infer immune sub-populations from bulk expression data. Several participant methods used single-cell RNA-seq to identify markers that could subsequently be used to detect the corresponding population in bulk data.
Education:
Cornell University
Postdoctoral Fellow, Dept. of Molecular Biology and Genetics
Adv: Prof. David Shalloway
2008 - 2012
Cornell University
Ph.D., Computer Engineering
Adv: Prof. Sally A. McKee
2002 - 2008
University of Virginia
Master's, Computer Science
1998 - 2002
Carnegie Mellon University
B.S., Computer Science
1994 - 1998
Experience:
The Jackson Laboratory
Senior Computational Scientist
2020 - Present
Sage Bionetworks
Senior Scientist
2016 - 2020
Division of Oncology and McDonnell Genome Institute, Washington University School of Medicine
Research Assistant Professor
2012 - 2016