சுருக்கம்

A Machine Learning Approach for Discovery of Novel Non- Ribosomal Peptide Synthetases (NRPS) in genomes of Plant Growth Promoting Pseudomonas Spp

Philip Job N., Jamshinath T.P., Hemalatha N., Rajesh M.K.

Non-ribosomal peptide synthetases (NRPSs) are multi-modular megasynthasespossessing the ability to catalyze biosynthesis of small bioactive peptides through a thiotemplate mechanismwhich is independent of ribosomes. These enzymes are invovled in production of a wide range of chemical products of broad structural and biological activity. The present study was performed with an aim to develop a gene prediction tool using a machine learning work bench called WEKA (Waikato Environment for Knowledge Analysis) for NRPS in plant growth promoting Pseudomonas spp.First, a model was developed using the training data which was generated using many classifiers. The trained model was then used for the prediction of NRPS in a given set of unknown sequences. Cross-validation results showed that the ‘Logisticof Functions’ was the best classifier when compared to others, showing high accuracy and performance in classifying the instances. We hope that the tool will aid in discovering of novel NRPS by predicting them from sequence data obtained by whole genome sequencing of bacteria or metagenomics.