My current research in the field of bioinformatics can be summarized as developing novel computational methods for biomolecular sequence analysis, protein function prediction and computational drug discovery; using statistical learning, data mining and machine learning techniques and graph theory approaches. As an interdisciplinary researcher, I always try to approach biological problems from different angles, using the fundamentals and techniques generally applied in other relevant disciplines, to be able to propose novel and effective solutions to prevalent issues. My overall research philosophy is to utilize the knowledge obtained by valuable and hard-to-conduct wet-lab experiments to accurately model the biological systems in-silico, with the aim of assisting the ongoing work in biomedical research.
For this, I divide my work in 3 major parts: (i) integrating complementary biological data from various open access data repositories in order to generate a bigger picture using the current bio-knowledge; (ii) developing novel in-silico methods and applying on large-scale biological data in order to estimate/predict what has been missing from the current knowledge; and (iii) further analysing the specific parts of the produced well-annotated biological data (enriched/completed with the in-silico predictions) to infer biological insight. I give emphasis on publishing the produced data via open-access data repositories where the whole research community can work on it to further our biological understanding on different subjects. In this sense, I'm currently developing myself to be able to construct and maintain better resources.