Parallel data mining in genetic databases

Abstract

The large amounts of data stored in genetic databases represent an important challenge in order to understand and to analyze many biological processes. Therefore, it is essential to explore data mining techniques for data analysis. In several cases, these demand a high computational power and data processing. Hence, parallel processing on data mining emerges as an alternative in order to improve the performance. This project is interested in to explore parallel algorithms for two data mining problems: identification of Lattice Dynamical Systems, that are applied for modeling gene expression networks and learning of stochastic grammars for homology discovery. Since these demand a high computational power. This project would improve the performance of an information management system for analysis of gene expression, which is being developed within the CAGE (Cooperation for Analysis of Gene Expression) Project financed by FAPESP. (AU)