Introduction

Large-scale gene expression profiling has been widely used to characterize cellular states in response to various disease conditions, genetic perturbations, etc. Although the cost of whole-genome expression profiles has been dropping steadily, generating a compendium of expression profiling over thousands of samples is still very expensive. Recognizing that gene expressions are often highly correlated, researchers from the NIH LINCS program have developed a cost-effective strategy of profiling only ∼1000 carefully selected landmark genes and relying on computational methods to infer the expression of remaining target genes. However, the computational approach adopted by the LINCS program is currently based on linear regression (LR), limiting its accuracy since it does not capture complex nonlinear relationship between expressions of genes.We present a deep learning method (abbreviated as D-GEX) to infer the expression of target genes from the expression of landmark genes. We used the microarray-based Gene Expression Omnibus dataset, consisting of 111K expression profiles, to train our model and compare its performance to those from other methods. In terms of mean absolute error averaged across all genes, deep learning significantly outperforms LR with 15.33% relative improvement. A gene-wise comparative analysis shows that deep learning achieves lower error than LR in 99.97% of the target genes. We also tested the performance of our learned model on an independent RNA-Seq-based GTEx dataset, which consists of 2921 expression profiles. Deep learning still outperforms LR with 6.57% relative improvement, and achieves lower error in 81.31% of the target genes.D-GEX is available at https://github.com/uci-cbcl/D-GEX CONTACT: xhx@ics.uci.eduSupplementary data are available at Bioinformatics online.

Publications

  1. Gene expression inference with deep learning.
    Cite this
    Chen Y, Li Y, Narayan R, Subramanian A, Xie X, 2016-06-01 - Bioinformatics (Oxford, England)

Credits

  1. Yifei Chen
    Developer

    Department of Computer Science, University of California, United States of America

  2. Yi Li
    Developer

    Department of Computer Science, University of California, United States of America

  3. Rajiv Narayan
    Developer

    -, Broad Institute of MIT and Harvard, United States of America

  4. Aravind Subramanian
    Developer

    -, Broad Institute of MIT and Harvard, United States of America

  5. Xiaohui Xie
    Investigator

    Department of Computer Science, University of California, United States of America

Community Ratings

UsabilityEfficiencyReliabilityRated By
0 user
Sign in to rate
Summary
AccessionBT006513
Tool TypeApplication
Category
PlatformsLinux/Unix
Technologies
User InterfaceTerminal Command Line
Download Count0
Country/RegionUnited States of America
Submitted ByXiaohui Xie