A Perturbation based Algorithm for Inference of Gene Regulatory Networks for Multiple Myeloma

The expression of genes within the body of an organism is responsible for manufacturing normal proteins and other molecular compounds required for normal operation of the cell and whole body. Often the genes influence each other and the activity of one gene leads to activation or deactivation of one or more other genes. Such groups of interacting genes is known as a gene regulatory network. Many computational researchers have used machine learning algorithms on genomic datasets for analysis and discovery of the gene regulatory networks. This knowledge is being used to discover new drug targets for genetic diseases like cancer. This paper has proposed an algorithm using partial correlation with data perturbation for inference of gene regulatory networks that are involved in incidence of blood malignancy called as multiple myeloma. The proposed method has been compared with existing methods and the results show superior performance of the proposed method.