[Machine learning study of DNA binding by transcription factors from the LacI family].

We studied 1372 LacI-family transcription factors and their 4484 DNA binding sites using machine learning algorithms and feature selection techniques. The Naive Bayes classifier and Logistic Regression were used to predict binding sites given transcription factor sequences and to classify factor-site pairs on binding and non-binding ones. Prediction accuracy was estimated using 10-fold cross-validation. Experiments showed that the best prediction of nucleotide densities at selected site positions is obtained using only a few key protein sequence positions. These positions are stably selected by the forward feature selection based on the mutual information of factor-site position pairs.

[Computer analysis of regulating metabolism of glycerol-3-phosphate in proteobacteria genome]. / Komp'iuternyi analiz reguliatsii metabolizma glitserol-3-fosfata v genomakh proteobakterii.

Comparative computer-assisted analysis was used to study putative GlpR-regulons responsible for metabolism of glycerol and glycerol-3-phosphate in genomes of alpha-, beta-, and gamma-proteobacteria. New palindromic GlpR-binding signals were identified in gamma-proteobacteria; consensus sequences being TGTTCGATAACGAACA for Enterobacteriaceae, wTTTTCGTATACGAAAAw for Pseudomonadaceae, and AATGCTCGATCGAGCATT for Vibrionaceae. The signals in alpha- and beta-proteobacteria were also identified: they contained 3-4 direct TTTCGTT repeats separated by 3-4 nucleotide pairs.

Computational analysis of the transcriptional regulation of pentose utilization systems in the gamma subdivision of Proteobacteria.

The comparative approach to the recognition of transcription regulatory sites is based on the assumption that as long as a regulator is conserved in several genomes, one can expect that sets of co-regulated genes (regulons) and regulatory sites for the regulator in these genomes are conserved as well. We used this approach to analyze the ribose (RbsR), arabinose (AraC), and xylose (XylR) regulons of gamma Proteobacteria for which (almost) completely sequenced genomes were available. Candidate binding sites for RbsR and AraC were detected. The improved XylR site consensus was proposed. Potential new members of the xylose regulons were found in the Escherichia coli, Salmonella typhi, and Klebsiella pneumoniae genomes. The function of these new xylose-regulated operons is likely to be the utilization of oligosaccharides containing xylose. Finally, candidate cAMP receptor-protein sites were identified in the regulatory regions of the majority of RbsR-, AraC-, and XylR-regulated operons.