Self-organizing maps
Sparse component analysis and blind source separation of underdetermined mixtures
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
An important topic in computational biology is to identify transcriptionalmodules through sequence analysis and gene expression profiling. Atranscriptional module is formed by a group of genes under control of one orseveral transcription factors (TFs) that bind to cis-regulatory elements in thepromoter regions of those genes. In this paper, we develop an integrative approach,namely motif-guided sparse decomposition (mSD), to uncover transcriptionalmodules by combining motif information and gene expression data.The method exploits the interplay of co-expression and co-regulation to findregulated gene patterns guided by TF binding information. Specifically, a motif-guided clustering method is first developed to estimate transcription factorbinding activities (TFBAs); sparse component analysis is then followed to furtheridentify TFs' target genes. The experimental results show that the mSD approachcan successfully help uncover condition-specific transcriptional modulesthat may have important implications in endocrine therapy of breast cancer.