%0 Journal Article %1 mcphillips2015yesworkflow %A McPhillips, Timothy %A Song, Tianhong %A Kolisnik, Tyler %A Aulenbach, Steve %A Belhajjame, Khalid %A Bocinsky, Kyle %A Cao, Yang %A Chirigati, Fernando %A Dey, Saumen %A Freire, Juliana %A Huntzinger, Deborah %A Jones, Christopher %A Koop, David %A Missier, Paolo %A Schildhauer, Mark %A Schwalm, Christopher %A Wei, Yaxing %A Cheney, James %A Bieda, Mark %A Ludaescher, Bertram %D 2015 %K forschungsdaten software workflowTracking %T YesWorkflow: A User-Oriented, Language-Independent Tool for Recovering Workflow Information from Scripts %U http://arxiv.org/abs/1502.02403 %X Scientific workflow management systems offer features for composing complex computational pipelines from modular building blocks, for executing the resulting automated workflows, and for recording the provenance of data products resulting from workflow runs. Despite the advantages such features provide, many automated workflows continue to be implemented and executed outside of scientific workflow systems due to the convenience and familiarity of scripting languages (such as Perl, Python, R, and MATLAB), and to the high productivity many scientists experience when using these languages. YesWorkflow is a set of software tools that aim to provide such users of scripting languages with many of the benefits of scientific workflow systems. YesWorkflow requires neither the use of a workflow engine nor the overhead of adapting code to run effectively in such a system. Instead, YesWorkflow enables scientists to annotate existing scripts with special comments that reveal the computational modules and dataflows otherwise implicit in these scripts. YesWorkflow tools extract and analyze these comments, represent the scripts in terms of entities based on the typical scientific workflow model, and provide graphical renderings of this workflow-like view of the scripts. Future versions of YesWorkflow also will allow the prospective provenance of the data products of these scripts to be queried in ways similar to those available to users of scientific workflow systems.

@article{mcphillips2015yesworkflow, abstract = {Scientific workflow management systems offer features for composing complex computational pipelines from modular building blocks, for executing the resulting automated workflows, and for recording the provenance of data products resulting from workflow runs. Despite the advantages such features provide, many automated workflows continue to be implemented and executed outside of scientific workflow systems due to the convenience and familiarity of scripting languages (such as Perl, Python, R, and MATLAB), and to the high productivity many scientists experience when using these languages. YesWorkflow is a set of software tools that aim to provide such users of scripting languages with many of the benefits of scientific workflow systems. YesWorkflow requires neither the use of a workflow engine nor the overhead of adapting code to run effectively in such a system. Instead, YesWorkflow enables scientists to annotate existing scripts with special comments that reveal the computational modules and dataflows otherwise implicit in these scripts. YesWorkflow tools extract and analyze these comments, represent the scripts in terms of entities based on the typical scientific workflow model, and provide graphical renderings of this workflow-like view of the scripts. Future versions of YesWorkflow also will allow the prospective provenance of the data products of these scripts to be queried in ways similar to those available to users of scientific workflow systems.}, added-at = {2018-02-14T21:49:16.000+0100}, author = {McPhillips, Timothy and Song, Tianhong and Kolisnik, Tyler and Aulenbach, Steve and Belhajjame, Khalid and Bocinsky, Kyle and Cao, Yang and Chirigati, Fernando and Dey, Saumen and Freire, Juliana and Huntzinger, Deborah and Jones, Christopher and Koop, David and Missier, Paolo and Schildhauer, Mark and Schwalm, Christopher and Wei, Yaxing and Cheney, James and Bieda, Mark and Ludaescher, Bertram}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e8be1c01e172e42cefde3367c43d86e1/hermann}, description = {[1502.02403] YesWorkflow: A User-Oriented, Language-Independent Tool for Recovering Workflow Information from Scripts}, interhash = {b711d076272dcb270f155e652dd14782}, intrahash = {e8be1c01e172e42cefde3367c43d86e1}, keywords = {forschungsdaten software workflowTracking}, note = {cite arxiv:1502.02403}, timestamp = {2018-02-14T20:49:16.000+0100}, title = {YesWorkflow: A User-Oriented, Language-Independent Tool for Recovering Workflow Information from Scripts}, url = {http://arxiv.org/abs/1502.02403}, year = 2015 }