No abstract

No abstract

No abstract

This paper presents a novel feature selection approach to deal with issues of high dimensionality in biomedical data classification. Extensive research has been performed in the field of pattern recognition and machine learning. Dozens of feature selection methods have been developed in the literature, which can be classified into three main categories: filter, wrapper and hybrid approaches. Filter methods apply an independent test without involving any learning algorithm, while wrapper methods require a predetermined learning algorithm for feature subset evaluation. Filter and wrapper methods have their, respectively, drawbacks and are complementary to each other in that filter approaches have low computational cost with insufficient reliability in classification while wrapper methods tend to have superior classification accuracy but require great computational power. The approach proposed in this paper integrates filter and wrapper methods into a sequential search procedure with the aim to improve the classification performance of the features selected. The proposed approach is featured by (1) adding a pre-selection step to improve the effectiveness in searching the feature subsets with improved classification performances and (2) using Receiver Operating Characteristics (ROC) curves to characterize the performance of individual features and feature subsets in the classification. Compared with the conventional Sequential Forward Floating Search (SFFS), which has been considered as one of the best feature selection methods in the literature, experimental results demonstrate that (i) the proposed approach is able to select feature subsets with better classification performance than the SFFS method and (ii) the integrated feature pre-selection mechanism, by means of a new selection criterion and filter method, helps to solve the over-fitting problems and reduces the chances of getting a local optimal solution.

The nucleus of epidermal keratinocytes is a complex and highly compartmentalized organelle, whose structure is markedly changed during terminal differentiation and transition of the genome from a transcriptionally active state seen in the basal and spinous epidermal cells to a fully inactive state in the keratinized cells of the cornified layer. Here, using multi-color confocal microscopy, followed by computational image analysis and mathematical modelling, we demonstrate that in normal mouse foot-pad epidermis transition of keratinocytes from basal epidermal layer to the granular layer is accompanied by marked differences in nuclear architecture and micro-environment including: i) decrease of the nuclear volume, ii) decrease in expression of the markers of transcriptionally-active chromatin; iii) internalization and decrease in the number of nucleoli; iv) increase in the number of pericentromeric heterochromatic clusters; v) increase in the frequency of associations between pericentromeric clusters, chromosomal territory 3, and nucleoli. These data suggest a role for nucleoli and pericentromeric heterochromatin clusters as organizers of nuclear micro-environment required for proper execution of gene expression programs in differentiating keratinocytes and provide important background information for further analyses of alterations in the topological genome organization seen in pathological skin conditions including disorders of epidermal differentiation and epidermal tumors.