Microarray data are expected to be of significant help in the prediction of gene function. The feature gene selection process is very difficult due to the properties of the data as a small number of samples compared to the huge number of genes, irrelevant genes, and noisy genes. In
order to solve the difficult problems, this paper proposes a method combined filter and wrapper. It mainly includes three steps: removing noisy genes using Signal-to-Noise Ratio, then selecting feature gene subsets using clustering algorithm based on Locally Linear Embedding (LLE), finally
getting a best feature gene subset which have the best classification performance using Support Vector Machine (SVM). The result of our experiments shows our method can be successfully used to select feature genes with clustering algorithm.
Journal of Computational and Theoretical Nanoscience is an international peer-reviewed journal with a wide-ranging coverage, consolidates research activities in all aspects of computational and theoretical nanoscience into a single reference source. This journal offers scientists and engineers peer-reviewed research papers in all aspects of computational and theoretical nanoscience and nanotechnology in chemistry, physics, materials science, engineering and biology to publish original full papers and timely state-of-the-art reviews and short communications encompassing the fundamental and applied research.