I am a Research Associate Professor in the Department of Microbiology at University of Washington. My research focuses on the development of data mining tools and their application to computational biology. In particular, I am interested in the development of methods to effectively integrate heterogeneous high-throughput data sources in the construction of regulatory networks and the identification of biologically meaningful biomarkers.
I am a computer scientist by training (Ph.D. in Computer Science from University of Washington under the supervision of Larry Ruzzo). My research spans multiple fields, including computational biology, statistics and machine learning. I have the honor of working with wonderful collaborators, in particular, Roger Bumgarner, and Adrian Raftery).
Publications Software Data Curriculum vitae
Last Update: 1/24/2012
Network inference from diverse genomics data: Interactions among genes and their gene products comprise a regulatory network. The goal of network inference is to generate testable hypotheses of gene-to-gene influences and subsequently design bench experiments to confirm network predictions. In the November 2011 issue of PNAS, Yeung and colleagues presented a methodology to construct gene regulatory networks from time series expression data in yeast, integrating various types of external biological knowledge available from public repositories. We generated microarray data measuring time-dependent gene-expression levels in 95 genotyped yeast segregants subjected to a drug perturbation. Our algorithm is capable of generating feedback loops and we showed that the inferred network recovered existing and novel regulatory relationships. In addition, we generated independent microarray data on selected deletion mutants to prospectively test network predictions.
From computational discoveries to translational research: The development of genetic predictors of clinical outcomes contributes to risk assessment in personalized medicine. In collaboration with Dr. Jerry Radich and Dr. Vivian Oehler at the Fred Hutchinson Cancer Research Center, we aim to develop computational models that can predict patient responses to therapy at diagnosis, which allow us to tailor therapy to individual patients of chonic myeloid leukemia (CML). We have previously applied Bayesian Model Averaging to a gene expression data studying the progression of CML, and identified 6 predictive genes in Blood 2009. Building on this work, we developed a network-driven approach that uses expert knowledge and predicted functional relationships to guide our search for signature genes in the March 2012 issue of Bioinformatics. We showed that our gene signatures of advanced phase CML are predictive of relapse even after adjustment for known risk factors associated with transplant outcomes.
Pattern discovery and feature selection: I have also contributed to the development and application of pattern discovery and feature selection in computational biology, including clustering algorithms and supervised learning methods.