Special Issue Article Open Access

PhzPred ? A Tool for Prediction of Phenazine Synthesizing Genes in Plant Growth Promoting Pseudomonas spp

Abstract

Phenazines are natural products produced by the bacterial strain of Pseudomonas spp. which possess anti-microbial activities and include more than 50 pigmented heterocyclic nitrogen containing secondary metabolites. Seven core phenazine biosynthetic genes have been identified in nearly all identified bacterial strains that produce phenazine compounds. In this study, a model has been developed to predict the phenazine biosynthetic genes from a set of protein sequences usingmachine learning algorithms from whole genomes of Pseudomonas spp. Initially, protein sequences from the Pseudomonas spp. were retrieved from public databases and used to train the WEKA models. To train the different classifiers in WEKA, three amino acid compositions were used: monomer amino acids, dipeptide amino acids, and a hybridmethod. The trained models were then used for the prediction of phenazine synthesizing gene in anuser submitted sequence. The best WEKA modules were selected based on the performance of different classifiers in training and testing. The performances of the classifier’s were then evaluated based on 10-fold cross validationand independent data set validation techniques. In the proposed methodology, better performance was observed for the hybrid feature extraction method. The development of a genome wide prediction tool for phenazinesynthesizing genes will substantially have an impact on bacterial genome annotation and devising crop protection strategies using plant growth promoting rhizobacteria.

Shilpa S, Anil Paul, Naganeeswaran S, Hemalatha N, Rajesh M.K