Insilico Reseach Group

The goal of the In Silico Research Group is to extract meaningful biological information from the noise in high-dimensional biological data. We augment standard approaches, which may miss interaction effects, with machine learning and systems-level network models of integrated data. We are particularly interested in developing systems/network models of human immune response to vaccines and neuropsychiatric disorders.

Our data-driven algorithms draw from the fields of machine learning, information theory, network theory, mathematical modeling, physics, and statistical learning. We develop algorithms to integrate static and time-course data, next-generation sequence, transcriptomic, structural and functional MRI, and genome-wide association data into mechanistic models for disease susceptibility prediction and identification of therapeutic targets.

Principal Investigator
Brett McKinney, Ph.D.

Congratulations!

Undergrad lab members win prestigious awards: Caleb Lareau (Goldwater) and Tricity Andrew (NSF Fellowshihp)

Check out Epistasis Network Visualization (ENViz): Demo

Check out our under-development Insilico Galaxy: Demo

TUNWG Lab Materials - 6/7/13

ZIP file