A composable data management architecture for scientific applications

Abstract

With ever increasing computational power, data management has become crucial for scientific applications today. Most on-going research efforts are dedicated to generalizing universal requirements and schemas for building generic data management systems. By closely studying a broad range of scientific applications including X-ray crystallography, radiation therapy, automated photometry and comparative genomics, a composable data management architecture for scientific applications is presented, which instead aims at providing a set of orthogonal components for each scientific application to quickly and easily construct its customized data management system. The prototype architecture is described in detail, and the component interfaces are defined in SIDL (Scientific Interface Definition Language). Results of building customized data management systems for a variety of scientific applications are also discussed.