• Designed, implemented and analyzed a sequence homology based protein function prediction technique called Extended Similarity Group (ESG) method using Java and MySQL on Linux platform• Worked on the development and analysis of functional similarity networks based on Protein Function Prediction (PFP) algorithm developed in Kihara Lab of Bioinformatics, Purdue University• Designed a method to compute associations between pairs of protein function annotation terms in Gene Ontology vocabulary. Further analyzed the applicability of these associations to identify functionally coherent groups of proteins• Identify missing enzymes in the metabolic pathways based on the functional annotations of neighboring enzymes using SVMs (Support Vector Machines) and Markov Random Fields (In progress)• Participated in conception of new projects in lab and contributed ideas on existing research group projects • Actively maintain and improve ESG & PFP protein function prediction web servers • Managed and mentored more than five undergraduate students by assigning them bioinformatics based projects, delegating project tasks and monitoring their progress and results.

• Conducted biweekly recitations for undergraduate ‘Software Engineering’ course involving student group projects with industrial partners like IBM, Cerner Corporation, HP, Yahoo!, and Caterpillar• Mentored the students throughout the project development lifecycle and helped them understand the Software Engineering concepts with hands on experience.

• Extract-Transform-Load (ETL) tool development for Cancer Biomedical Information Grid at Washington University in St. Louis. Designed a module that parses gene annotation data from NCBI data sources, and loads the extracted data into a warehouse after converting it into a unified format. ( Java and Oracle) • Software development for the data collected by an instrument called ‘ALP 5100 HT Expert’ manufactured by Agilent Technologies, Germany. Contributed to the development of the analysis module, which allows users to construct and execute complex analysis rules to segregate the data samples. (C++)