BDWorld: A grid-based workflow manager for high-throughput distributed computing in biodiversity research
Neil Caithness 1 , Shonil Bhagwat 3 , Peter Brewer 1 , Oliver Bromley 4 , Frank A. Bisby 1 , Alastair Culham 1 , Nick J. Fiddian 2 , W. Alex Gray 2 , Andrew C. Jones 2 , Malcolm Scoble 3 , Tim Sutton 1 , Richard J. White 2 , Paul Williams 3 , Xuebiao Xu 2 , and Chris Yesson 1
1 Centre for Plant Diversity & Systematics, School of Plant Sciences, The University of Reading , Reading RG6 6AS , UK . {P.W.Brewer|F.A.Bisby|N.Caithness|A.Culham|T.Sutton|C.Yesson}@reading.ac.uk
2 Cardiff University, School of Computer Science , Queen’s Buildings, 5 The Parade, Cardiff CF24 3AA , UK . {N.J.Fiddian|W.A.Gray||Andrew.C.Jones|R.J.White|X.Xu}@cs.cardiff.ac.uk
3 Department of Entomology, The Natural History Museum , London SW7 5BD , UK . {S.Bhagwat|M.Scoble|P.Williams}@nhm.ac.uk
4 School of Biological Sciences, University of Southampton , Southampton SO16 7PX , UK . O.Bromley@soton.ac.ukThe goals of the BDWorld project are to create an extensible framework for supporting distributed computing in biodiversity research, and to use this framework in three real exemplar study areas. From the researcher’s perspective the system consists of a graphical work-flow manager that provides access to a suite of remote data resources and analytical tools. From the system’s perspective there is a layered architecture that protects us from the ever changing grid communications technology, a workflow designer, a workflow enactment engine, a metadata repository, a resource locator, a resource matcher, and a suite of wrappers or proxies for the actual resources. We present an overview of the system, and show examples of its use in high-throughput computing in the field of bioclimatic modelling.