Genomic annotation prediction based on integrated information

In the recent years, an increasingly large amount of biomedical and biomolecular information and data has become available to researchers, allowing the scientific community to infer new knowledge and reach new objectives. As these information increase, so does the difficulty in managing it efficiently. In this paper, we present a short overview of our proposal to solve this problem, a prototypal multi-organism Genomic and Proteomic Data Warehouse called GPDW, based at Politecnico di Milano. We also present the computational methods we implemented to exploit it. Experimental studies on datasets demonstrated the effectiveness of our resource and methods.