Abstract
Sparse Singular Value Decomposition (SSVD) model has been proposed to bicluster gene expression data to identify gene modules. However, traditional SSVD model can only handle the gene expression data where no gene-gene interaction information is integrated. Here, we develop a Sparse Network-regularized SVD (SNSVD) method, which can integrate the gene-gene interaction information into the SSVD model, to identify the underlying gene functional modules from the gene expression data. The simulation results on synthetic data show that SNSVD is more effective than the traditional SVD-based methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have