A novel information theory method for filter feature selection

In this paper, we propose a novel filter for feature selection. Such filter relies on the estimation of the mutual information between features and classes. We bypass the estimation of the probability density function with the aid of the entropic-graphs approximation of Rényi entropy, and the subsequent approximation of the Shannon one. The complexity of such bypassing process does not depend on the number of dimensions but on the number of patterns/samples, and thus the curse of dimensionality is circumvented. We show that it is then possible to outperform a greedy algorithm based on the maximal relevance and minimal redundancy criterion. We successfully test our method both in the contexts of image classification and microarray data classification.

Transcriptional profiles of Haloferax mediterranei based on nitrogen availability

The haloarchaeon Haloferax mediterranei is able to grow in the presence of different inorganic and organic nitrogen sources by means of the assimilatory pathway under aerobic conditions. In order to identify genes of potential importance in nitrogen metabolism and its regulation in the halophilic microorganism, we have analysed its global gene expression in three culture media with different nitrogen sources: (a) cells were grown stationary and exponentially in ammonium, (b) cells were grown exponentially in nitrate, and (c) cells were shifted to nitrogen starvation conditions. The main differences in the transcriptional profiles have been identified between the cultures with ammonium as nitrogen source and the cultures with nitrate or nitrogen starvation, supporting previous results which indicate the absence of ammonium as the factor responsible for the expression of genes involved in nitrate assimilation pathway. The results have also permitted the identification of transcriptional regulators and changes in metabolic pathways related to the catabolism and anabolism of amino acids or nucleotides. The microarray data was validated by real-time quantitative PCR on 4 selected genes involved in nitrogen metabolism. This work represents the first transcriptional profiles study related to nitrogen assimilation metabolism in extreme halophilic microorganisms using microarray technology.