Neural Network Based Virtual Reality Spaces for Visual Data Mining of Cancer Data: An Unsupervised Perspective

Three microarray gene expression cancer databases are represented using neural networks and visual data mining with virtual reality spaces. The databases contains dats from cancerous and noncancerous tissues. In order to understand the structure of the data, structurepreserving virtual spaces are constructed using Samann neural networks. High quality visual representations are obtained. For the databases under study, the vitual spaces are clearly polarized with two distribution modes, each one corresponding to a different class.