CONSTRUCTING GENE REGULATORY NETWORK USING TIME SERIES GENE EXPRESSION

Abstract

Inferring Gene Regulatory Network (GRN) is important to understand genetic changes occurring in cells. GRNs help in designing drugs and vaccines. As changes occurred in cell are dynamic, time series gene expression is very important to understand how genes regulates each other. There are many competitions to infer GRN, here we used DREAM4 in-silico 10 genes, DREAM 4 insilico-100 genes and DREAM 5. As H1N1 is the most endemic disease recently and still does not have a known medication. To comprehend alterations in genes due to H1N1 infection, we attempted to build GRN based on gene expressions of H1N1 infected cells. We improved two algorithms to infer GRN GENIE 3 and PLSNET by one-way ANOVA and produce two new hybrids Algorithms ANOVAPLSN and ANOVAG3 which record best results to infer large scale GRN from time series gene Expression. we used other methods to infer GRN as sparse linear Equation, Distance matrices and Artificial neural network to infer GRN