automated discovery of functional generality of human gene expression programs自动发现功能的一般性的人类基因表达程序.pdf

Automated Discovery of Functional Generality of Human Gene Expression Programs 1,2 1 1 1,3* Georg K. Gerber , Robin D. Dowell , Tommi S. Jaakkola , David K. Gifford 1 Department of Computer Science and Electrical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America, 2 Harvard– Massachusetts Institute of Technology Division of Health Sciences and Technology, Cambridge, Massachusetts, United States of America, 3 Whitehead Institute for Biomedical Research, Cambridge Massachusetts, United States of America An important research problem in computational biology is the identification of expression programs, sets of co- expressed genes orchestrating normal or pathological processes, and the characterization of the functional breadth of these programs. The use of human expression data compendia for discovery of such programs presents several challenges including cellular inhomogeneity within samples, genetic and environmental variation across samples, uncertainty in the numbers of programs and sample populations, and temporal behavior. We developed GeneProgram, a new unsupervised computational framework based on Hierarchical Dirichlet Processes that addresses each of the above challenges. GeneProgram uses expression data to simultaneously organize tissues into groups and genes into overlapping programs with consistent temporal behavior, to produce maps of expression programs, which are sorted by generality scores that exploit the automatically learned groupings. Using synthetic and real gene expression data, we showed that GeneProgram outperformed several popular expression analysis methods. We applied GeneProgram to a compendium of 62 short time-series gene expression datasets exploring the responses of human cells to infectious agents and i