C4.5: programs for machine learning
C4.5: programs for machine learning
Hi-index | 0.00 |
In this article, the dependencies among the genes have been identified from microarray gene expression data. Here we propose a methodology for identifying the dependencies among the genes that have deviated quite significantly from normal stage to diseased stage with respect to their expression patterns. This idea leads to predict the disease mediating genes along with their deviated dependencies. The proposed methodology involves measuring information content of individual genes using fuzzy entropy, conditional fuzzy entropy of a gene on another, dependencies of a pair of genes in both normal and diseased states, and finally identifying the dependencies being deviated from normal to carcinogenic state. The deviated dependencies among the genes have been represented using a network, called gene prediction network (GPN), in which each node represents a gene and a directed edge signifies deviated dependency between a pair of nodes (genes). The methodology has been demonstrated on two gene expression data sets dealing with human lung cancer and breast cancer. The results are appropriately validated by earlier investigations in terms of gene regulation. We have also used some statistical techniques like t-test, accuracy in terms of sensitivity and specificity to validate the results.