Comprehensive vertical sample-based KNN/LSVM classification for gene expression analysis
Journal of Biomedical Informatics - Special issue: Biomedical machine learning
Cancer gene search with data-mining and genetic algorithms
Computers in Biology and Medicine
Hi-index | 0.00 |
It is fundamental and essential to elucidate how cancer-related genes interact with each other. In this study, we build two undirected graphs: one is a graph consisting of edges only observed in tumor samples, and the other is a graph consisting of edges only observed in normal samples. We apply a genetic algorithm for searching sub-networks of these genetic networks. Those gene sub-networks identify new cancer-related genes that might be related with previously known cancer-related genes, and also show a higher accuracy in classifying tumor and normal samples than the current methods.