Section: New Results
Data Integration
With the increasing popularity of scientific workflows, public and private repositories are gaining importance as a means to share, find, and reuse such workflows.
As the sizes of these repositories grow, methods to compare the scientific workflows stored in them become a necessity, for instance, to allow duplicate detection or similarity search. Scientific workflows are complex objects, and their comparison entails a number of distinct steps from comparing atomic elements to comparison of the workflows as a whole. Various studies have implemented methods for scientific workflow comparison and came up with often contradicting conclusions upon which algorithms work best. Comparing these results is cumbersome, as the original studies mixed different approaches for different steps and used different evaluation data and metrics.
In collaboration with members of the University of Humboldt (Berlin), we first contribute to the field [17] by (i) comparing in isolation different approaches taken at each step of scientific workflow comparison, reporting on an number of unexpected findings, (ii) investigating how these can best be combined into aggregated measures, and (iii) making available a gold standard of over 2000 similarity ratings contributed by 15 workflow experts on a corpus of 1500 workflows and re-implementations of all methods we evaluated. In this context, we have designed new approaches based on consensus ranking [21] to provide a consensus of the experts' answers.
Then, with members of the University of Pennsylvania, we have presented a novel and intuitive workflow similarity measure that is based on layer decomposition [27] (designed during the month SCB spent at UPenn). Layer decomposition accounts for the directed dataflow underlying scientific workflows, a property which has not been adequately considered in previous methods. We comparatively evaluate our algorithm using our gold standard and show that it a) delivers the best results for similarity search, b) has a much lower runtime than other, often highly complex competitors in structure-aware workflow comparison, and c) can be stacked easily with even faster, structure-agnostic approaches to further reduce runtime while retaining result quality.
Another way to make scientific workflows easier to reuse is to reduce their structural complexity to make them easier to apprehend. In particular, we have continued to work in collaboration with the University of Manchester on DistillFlow, an approach to remove the structural redundancy in workflows. Our contribution is four fold. Firstly, we identify a set of anti-patterns that contribute to the structural workflow complexity. Secondly, we design a series of refactoring transformations to replace each anti-pattern by a new semantically-equivalent pattern with less redundancy and simplified structure. Thirdly, we introduce a distilling algorithm that takes in a workflow and produces a distilled semantically-equivalent workflow [8] . Lastly, we provide an implementation of our refactoring approach (dedicated demo published [24] ) that we evaluate on both the public Taverna workflows and on a private collection of workflows from the BioVel project. On going work includes extending the list of anti-patterns to be considered and identifying good patterns, that is, patterns which are easy to maintain and have systematically been able to be executed. This has been done in the context of the master internship of Stéphanie Kamgnia Wonkap [37] . First results obtained are promising.