IEEE Transactions on Computational Biology and Bioinformatics (TCBB) will move to the OnlinePlus publication model starting with 2015 issues!

From the November/December 2014 Issue

Latent Feature Decompositions for Integrative Analysis of Multi-Platform Genomic Data

By Karl B. Gregory, Amin A. Momin, Kevin R. Coombes, and Veerabhadran Baladandayuthapani

Featured article thumbnail imageIncreased availability of multi-platform genomics data on matched samples has sparked research efforts to discover how diverse molecular features interact both within and between platforms. In addition, simultaneous measurements of genetic and epigenetic characteristics illuminate the roles their complex relationships play in disease progression and outcomes. However, integrative methods for diverse genomics data are faced with the challenges of ultra-high dimensionality and the existence of complex interactions both within and between platforms. We propose a novel modeling framework for integrative analysis based on decompositions of the large number of platform-specific features into a smaller number of latent features. Subsequently we build a predictive model for clinical outcomes accounting for both within- and between-platform interactions based on Bayesian model averaging procedures. Principal components, partial least squares and non-negative matrix factorization as well as sparse counterparts of each are used to define the latent features, and the performance of these decompositions is compared both on real and simulated data. The latent feature interactions are shown to preserve interactions between the original features and not only aid prediction but also allow explicit selection of outcome-related features. The methods are motivated by and applied to a glioblastoma multiforme data set from The Cancer Genome Atlas to predict patient survival times integrating gene expression, microRNA, copy number and methylation data. For the glioblastoma data, we find a high concordance between our selected prognostic genes and genes with known associations with glioblastoma. In addition, our model discovers several relevant cross-platform interactions such as copy number variation associated gene dosing and epigenetic regulation through promoter methylation. On simulated data, we show that our proposed method successfully incorporates interactions within and between genomic platforms to aid accurate prediction and variable selection. Our methods perform best when principal components are used to define the latent features.

download PDF View the PDF of this article      csdl View this issue in the digital library


Editorials and Announcements

Announcements

  • Get Your Journals as eBooks for Free

  • TCBB celebrates its 10th Anniversary. Editor-in-Chief Ying Xu says, "The emergence and maturation of increasingly more and powerful molecular measurement technologies such as next generation sequencing and chromosome conformation capture allow scientists to tackle biological problems at the depth and breadth that we have never seen before. At the same time the enormity and complexity of the data generated using these technologies raised tremendous challenges to computational scientists to develop more effective techniques to store, transmit, organize, process, analyze and mine the data, and to construct models to assist interpreting the data. Since its creation ten years ago, TCBB has been playing a major role in bridging the world of computing and the world of biology. I want to congratulate what the journal has done in providing biologists with the most powerful computational tools to help address their data and modeling needs. I fully expect that TCBB will continue to play increasingly significant roles in attracting more computational scientists to address the ever increasing needs for new and more powerful computational techniques and to introduce to new comers the important and challenging computational biology problems in a timely fashion."

  • eBooks of issues of TCBB can now be downloaded from the Computer Society Digital Library

  • Subscribe to TCBB in 2014. Click for more information. (PDF)

Editorials

Guest Editorials

Call for Papers


Access All Recently Published TCBB Articles

RSS Subscribe to the RSS feed of latest TCBB content added to the digital library

Mail Sign up for the Transactions Connection newsletter.


TCBB is a joint publication of the IEEE Computer Society, Association for Computing Machinery, IEEE Computational Intelligence Society, and the IEEE Engineering in Medicine and Biology Society.

IEEE Computer Society    ACM    Computational Intelligence Society    Engineering in Medicine and Biology Society

Published in cooperation with: IEEE Control Systems Society


MEDLINE      PubMed

Indexed in MEDLINE®/PubMed® & ISI

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB) is a bimonthly journal that publishes archival research results related to the algorithmic, mathematical, statistical, and computational methods that are central in bioinformatics and computational biology. 
Read the full scope of TCBB