We are interested in the application of data mining and machine learning techniques to several problems in Bioinformatics. These applications vary from
- a) identification of secondary structures in proteins
- b) the fold classification problem
- c) motif determination and
- d) biomedical text mining.
One focus area is to develop tools and methods for analysing OMICs datasets including genomics, transcriptomics, proteomics and structural genomics. The various datasets are combined and integrated to extract knowledge and novel insights from their vast volume. The primary focus of the researchers lies in the identification of molecular mechanisms in various genetic disorders and cancer types.
A second focus in this area is Protein Engineering and Design. We devise methodologies for designing value added molecules. We use molecular mechanics, dynamics and modelling techniques to design or optimize new or existing protein molecules. We collaborate with molecular biologist to verify the validity of the in silico protein computational models.
A third focus of the research in this field is the analysis of genetic networks, network properties and protein-protein interactions. We use graph theory approaches to tackle these problems. Several examples of successful contributions are related to the development of analysis tools for Next Generation Sequencing (NGS), microarray and SAGE data analysis tools, usage of natural language processing techniques in bioinformatics and the comparative analysis of genetic networks for automated gene identification, ligand binding and protein-protein interaction.