by Michael Seifert, Marc Strickert, Alexander Schliep, and Ivo Grosse
Changes in gene expression levels play a central role in tumors. Additional information about the distribution of gene expression levels and distances between adjacent genes on chromosomes should be integrated into the analysis of tumor expression profiles.
We use a Hidden Markov Model with distance-scaled transition matrices (DSHMM) to incorporate chromosomal distances of adjacent genes on chromosomes into the identification of differentially expressed genes in breast cancer. We train the DSHMM by integrating prior knowledge about potential distributions of expression levels of differentially expressed and unchanged genes in tumor. We find that especially the combination of this data and to a lesser extent the modeling of distances between adjacent genes contribute to a substantial improvement of the identification of differentially expressed genes in comparison to other existing methods. This performance benefit is also supported by the identification of genes well-known to be associated with breast cancer. That suggests applications of DSHMMs for screening of other tumor expression profiles.
- Supplementary data: Containing the breast cancer gene expression data set and the breast cancer gene copy number data set (Pollack et al. (2002)) analyzed in the manuscript, and the predictions and scores of the compared methods.
- Model trainer: JAR file for analyzing a data set by Gaussian mixture models, HMMs, SHMMs, and DSHMMs.
- ARHMM: integrating local chromosomal dependencies into the analysis of tumor expression profiles
- PHHMM: improved analysis of Array-CGH data
- SHMM: utilizing gene-pair orientations for improved analysis of ChIP-chip promoter array data
- MeDIP-HMM: HMM-based analysis of DNA methylation profiles
- HMM Book: Hidden Markov Models with Applications in Computational Biology