Artificial neural networks for prediction of mycobacterial promoter sequences.

A multilayered feed-forward ANN architecture trained using the error-back-propagation (EBP) algorithm has been developed for predicting whether a given nucleotide sequence is a mycobacterial promoter sequence. Owing to the high prediction capability ( congruent with 97%) of the developed network model, it has been further used in conjunction with the caliper randomization (CR) approach for determining the structurally/functionally important regions in the promoter sequences. The results obtained thereby indicate that: (i) upstream region of -35 box, (ii) -35 region, (iii) spacer region and, (iv) -10 box, are important for mycobacterial promoters. The CR approach also suggests that the -38 to -29 region plays a significant role in determining whether a given sequence is a mycobacterial promoter. In essence, the present study establishes ANNs as a tool for predicting mycobacterial promoter sequences and determining structurally/functionally important sub-regions therein.

Analysis of DNA curvature distribution in mycobacterial promoters using theoretical models.

In this paper, 125 different mycobacterial promoters are analyzed for their DNA curvature distribution using several di- and tri-nucleotide dependent models of DNA curvature. Different models give similar behavior and therefore qualitative validation of the results. Mycobacterial promoters resembling the E. coli sigma(70) type have almost 81% (85%) sequences having medium and high curvature profiles using dinucleotide-dependent models. Non-E. coli sigma(70) type mycobacterial promoters have comparatively higher percent of low curvature profiles. Very few extended -10 promoters have low curvature profiles. Mycobacterial promoters having A(n)T(m) (n+m > or =3) tract in the upstream region of -35 box and repeated in phase with each other have high curvature profiles. M. smegmatis promoters have high curvature profiles compared to M. tuberculosis promoters.