Current projects the group is taking part in.
The goal of the GenData 2020 project is the organization of genetic data through a GenData 2020 data model, enabling scientists to query, search, mine and analyze the huge genomic datasets generated by sequencing technology. The Data Mining and Knowledge Discovery Group will study distributed and parallel data mining algorithms for genomic analysis. Our objective in the project is to leverage our experiences in parallel and distributed data mining to explore new high-performance solutions for mining genomic data with massively parallel techniques. We plan to design many-core data mining algorithms running on General Purpose Graphic Processing Units, thus deriving suitable techniques to partition the data and exploit data locality to process large genome data sets.
July, 2013