@conference {ccgrid2008, title = {Initializing a National Grid Infrastructure Lessons Learned from the Swiss National Grid Association Seed Project}, booktitle = {8th IEEE International Symposium on Cluster Computing and the Grid (CCGRID 2008)}, year = {2008}, month = {May}, pages = {169-176}, publisher = {IEEE}, organization = {IEEE}, address = {Lyon, France}, abstract = {In addition to multi-national Grid infrastructures, several countries operate their own national Grid infrastructures to support science and industry within national borders. These infrastructures have the benefit of better satisfying the needs of local, regional and national user communities. Although Switzerland has strong research groups in several fields of distributed computing, only recently a national Grid effort was kick-started to integrate a truly heterogeneous set of resource providers, middleware pools, and users. In the following article we discuss our efforts to start Grid activities at a national scale to combine several scientific communities and geographical domains. We make a strong case for the need of standards that have to be built on top of existing software systems in order to provide support for a heterogeneous Grid infrastructure.}, keywords = {distributed computing, grid computing, middleware, national grid infrastructure}, doi = {10.1109/CCGRID.2008.62}, author = {Nabil Abdennadher and Peter Engel and Derek Feichtinger and Dean Flanders and Placi Flury and Sigve Haug and Pascal Jermini and Sergio Maffioletti and Cesare Pautasso and Heinz Stockinger and Wibke Sudholt and Michela Thi{\'e}mard and Nadya Williams and Christoph Witzig} } @conference {jophealthgrid07, title = {Grid-based Analysis of Tandem Mass Spectrometry Data in Clinical Proteomics}, booktitle = {Health Grid 2007}, year = {2007}, address = {Geneva, Switzerland}, abstract = {Biomarker detection is one of the greatest challenges in Clinical Proteomics. Today, great hopes are placed into tandem mass spectrometry (MS/MS) to discover potential biomarkers. MS/MS is a technique that allows large scale data analysis, including the identification, characterization, and quantification of molecules. Especially the identification process, that implies to compare experimental spectra with theoretical amino acid sequences stored in specialized databases, has been subject for extensive research in bioinformatics since many years. Dozens of identification programs have been developed addressing different aspects of the identification process but in general, clinicians are only using a single tools for their data analysis along with a single set of specific parameters. Hence, a significant proportion of the experimental spectra do not lead to a confident identification score due to inappropriate parameters or scoring schemes of the applied analysis software. The swissPIT (Swiss Protein Identification Toolbox) project was initiated to provide the scientific community with an expandable multi-tool platform for automated and in-depth analysis of mass spectrometry data. The swissPIT uses multiple identification tools to automatic analyze mass spectra. The tools are concatenated as analysis workflows. In order to realize these calculation-intensive workflows we are using the Swiss Bio Grid infrastructure. A first version of the web-based front-end is available (http://www.swisspit.cscs.ch) and can be freely accessed after requesting an account. The source code of the project will be also made available in near future.}, keywords = {grid computing, JOpera, scientific workflow management}, url = {http://www.ncbi.nlm.nih.gov/pubmed/17476043}, author = {Andreas Quandt and Patricia Hernandez and Peter Kunzst and Cesare Pautasso and Marc Tuloup and Ron D. Appel} } @conference {jopera:2006:ccgrid, title = {Mirroring Resources or Mapping Requests: implementing WS-RF for Grid workflows}, booktitle = {6th IEEE International Symposium on Cluster Computing and the Grid (CCGrid2006)}, year = {2006}, month = {May}, address = {Singapore}, abstract = {The Web Services Resource Framework (WS-RF) and the Web Services Notification (WS-N) specifications are a crucial component of Grid infrastructures. They provide a standardized interface to stateful services so that they can be managed remotely. There are already several implementations of these specifications and initial performance studies have compared them in terms of the overhead observed by a single client. In this paper we address the problem of implementing the WS-RF and WS-N specifications for large scale systems. In particular, we discuss how to implement WS-RF and WSN as the management interfaces to a Grid workflow engine. In the paper we describe and compare two different architectures for mapping resources to processes. The first one mirrors the state of the process as a resource. The second one maps the client requests to access the state of a resource embedded into the Grid workflow engine. We include an extensive performance evaluation, comparing the resulting systems in terms of scalability when servicing a large number of concurrent clients. }, keywords = {grid computing, JOpera, scientific workflow management}, doi = {10.1109/CCGRID.2006.69}, author = {Thomas Heinis and Cesare Pautasso and Gustavo Alonso} } @inproceedings {jopera:2006:works, title = {Parallel Computing Patterns for Grid Workflows}, year = {2006}, month = {June}, address = {Paris, France}, abstract = {Whereas a consensus has been reached on defining the set of workflow patterns for business process modeling languages, no such patterns exists for workflows applied to scientific computing on the Grid. By looking at different kinds of parallelism, in this paper we identify a set of workflow patterns related to parallel and pipelined execution. The paper presents how these patterns can be represented in different Grid workflow languages and discusses their implications for the design of the underlying workflow management and execution infrastructure. A preliminary classification of these patterns is introduced by surveying how they are supported by several existing advanced scientific and Grid workflow languages.}, keywords = {grid computing, scientific workflow management, survey, workflow patterns}, author = {Cesare Pautasso and Gustavo Alonso} } @conference {jopera:2005:escience, title = {Publishing Persistent Grid Computations as WS Resources}, booktitle = {1st IEEE International Conference on e-Science and Grid Computing (e-Science 2005)}, year = {2005}, month = {December}, publisher = {IEEE}, organization = {IEEE}, address = {Melbourne, Australia}, abstract = {Grid services can be composed into processes, providing a high level definition of the computations involved in terms of their data exchanges and control flow dependencies. We show how processes themselves can be efficiently published as Grid services by mapping the persistent state of the process executions to standard compliant interfaces as defined by the Web Services Resource Framework (WS-RF). Mapping processes to resources is a fundamental step to enable recursive Grid service composition, where composite Grid services are themselves published as services. This gives processes a standardized and wellunderstood interface that enables their management, monitoring, steering and adaptation. Additionally it eases their reusability and simplifies integration into existing Grid applications and portals. In order to determine the mapping{\textquoteright}s overhead, we include the results of a comprehensive performance evaluation.}, keywords = {grid computing, JOpera, scientific workflow management}, doi = {10.1109/E-SCIENCE.2005.67}, author = {Thomas Heinis and Cesare Pautasso and Oliver Deak and Gustavo Alonso} } @article {98, title = {JOpera: Visual Composition of Grid Services}, year = {2004}, month = {October}, pages = {46-47}, abstract = {The recent shift to service-based Grids enables the use of service composition tools for rapidly building and efficiently running distributed computations. At ETH Zurich, we have developed JOpera, a visual composition language and a set of integrated software development tools for composing Grid services. The system can be freely downloaded and has been successfully tested with data-intensive bioinformatics applications as well as large-scale, Monte-Carlo network simulations.}, keywords = {grid computing, JOpera, scientific workflow management}, url = {http://www.ercim.eu/publication/Ercim_News/enw59/pautasso.html}, author = {Cesare Pautasso} } @conference {93, title = {Programming for dependability in a service-based grid}, booktitle = {3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, 2003 (CCGrid 2003)}, year = {2003}, month = {May}, pages = {164 - 171}, publisher = {IEEE}, organization = {IEEE}, address = {Tokyo, Japan}, abstract = {Service-based Grid infrastructures emphasize service composition rather than sharing of low level resources. The idea is to build Grid applications out of computational services provided by the different sites of the Grid. Recent developments in the area of Web services have strengthened this idea by standardizing procedures like service description, publication and invocation. What is still missing is the infrastructure necessary to support the complete life cycle of applications running on service based Grids, i.e., suitable programming paradigms, execution infrastructure, and the ability to monitor and control such computations. Moreover, once computations are made of composable services, dependability becomes a key issue that needs to be addressed by the infrastructure as it cannot be addressed separately by each individual service. To address these concerns, we have developed the BioOpera Grid computing platform. BioOpera is a process support system for dependable cluster computing that has been extended with additional functionality to provide adequate support for service-based Grids. In this paper we describe how BioOpera can be used to develop, execute, and administer highly dependable computations over service-based Grids.}, keywords = {BioOpera, distributed business process execution engines, grid computing, Web services}, isbn = {0-7695-1919-9}, doi = {10.1109/CCGRID.2003.1199365}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1199365}, author = {Win Bausch and Cesare Pautasso and Gustavo Alonso} }