A Local and Global Preserving Based Semi-supervised Dimensionality Reduction Method for Cancer Classification

摘要

Cancer classification of gene expression data helps offer appropriate prognosis and better treatment. Accurate prediction to the type or size of tumors relies on adopting powerful and efficient classification models such that patients can be provided with better treatment. In this paper, a Local and Global Preserving based Semi-supervised Dimensionality Reduction method was applied to cancer classification, which can not only preserve the positive and negative constraints but also preserve the local and global structure of the whole data manifold in the low dimensional embedding subspace. Experimental results using public gene expression datasets show the superior performance of the method.