In recent years, gene selection for cancer classification based on the expression of a small number of gene biomarkers has been the subject of much research in genetics and molecular biology. The successful identification of gene biomarkers will help in the classification of different types of cancer and improve the prediction accuracy. Recently, regularized logistic regression using the L 1 regularization has been successfully applied in high-dimensional cancer classification to tackle both the estimation of gene coefficients and the simultaneous performance of gene selection. However, the L 1 has a biased gene selection and dose not have the oracle property. To address these problems, we investigate L 1 / 2 regularized logistic regression for gene selection in cancer classification. Experimental results on three DNA microarray datasets demonstrate that our proposed method outperforms other commonly used sparse methods ( L 1 and L E N ) in terms of classification performance.

No abstract

ABSTRACT.Identifying biomarker genes and characterizing interaction pathways with high-dimensional and low-sample size microarray data is a major challenge in computational biology. In this field, the construction of protein-protein interaction (PPI) networks using disease-related selected genes has garnered much attention. Support vector machines (SVMs) are commonly used to classify patients, and a number of useful tools such as lasso, elastic net, SCAD, or other regularization methods can be combined with SVM models to select genes that are related to a disease. In the current study, we propose a new Net-SVM model that is different from other SVM models as it is combined with L 1/2 -norm regularization, which has good performance with high-dimensional and low-sample size microarray data for cancer classification, gene selection, and PPI network construction. Both simulation studies and real data experiments demonstrated that our 2 H. Chai et al. Genetics and Molecular Research 15 (3): gmr.15038794 proposed method outperformed other regularization methods such as lasso, SCAD, and elastic net. In conclusion, our model may help to select fewer but more relevant genes, and can be used to construct simple and informative PPI networks that are highly relevant to cancer.

Terrain classification is one of the critical steps used in lunar geomorphologic analysis and landing site selection. Most of the published works have focused on a Digital Elevation Model (DEM) to distinguish different regions of lunar terrain. This paper presents an algorithm that can be applied to lunar CCD images by blocking and clustering according to image features, which can accurately distinguish between lunar highland and lunar mare. The new algorithm, compared with the traditional algorithm, can improve classification accuracy. The new algorithm incorporates two new features and one Tamura texture feature. The new features are generating an enhanced image histogram and modeling the properties of light reflection, which can represent the geological characteristics based on CCD gray level images. These features are applied to identify texture in order to perform image clustering and segmentation by a weighted Euclidean distance to distinguish between lunar mare and lunar highlands. The new algorithm has been tested on Chang'e-1 CCD data and the testing result has been compared with geological data published by the U.S. Geological Survey. The result has shown that the algorithm can effectively distinguish the lunar mare from highlands in CCD images. The overall accuracy of the proposed algorithm is satisfactory, and the Kappa coefficient is 0.802, which is higher than the result of combining the DEM with CCD images.

No abstract