GCC2019 has ended
The 2019 Galaxy Community Conference (GCC2019) was held in Freiburg, Germany, 1-8 July.  There was one day of training, three days of mixed meeting and training, and then two to four days of CollaborationFest.  The meeting featured joint & parallel sessions; invited, accepted, and lightning talks; poster and demo sessions; birds-of-a-feather meetups; social events; and training sessions every day.

Thanks to everyone who helped make GCC2019 a success!
Back To Schedule
Wednesday, July 3 • 15:25 - 15:45
Demo 08 B: Tool Prediction in Galaxy Workflows using Deep Learning

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Galaxy workflows are scientific data processing pipelines for performing and
reproducing data analyses. The workflows are complex and difficult to create from a
suite of 2,000+ tools available in Galaxy, especially for new Galaxy users. In order to
make creating workflows easier, faster and less error-prone, a recommendation
system was developed to predict following tools. The predictive system analyses the
complete set of workflows available on Galaxy’s European server using a deep
learning approach to create a tool prediction model.

Workflows are directed acyclic graphs. To create the predictive model, sequences
(paths) of tools are extracted from these graphs and learned by a deep learning
approach ( Gated Recurrent Neural Network ). The hyperparameters of the deep
learning model are optimised using bayesian optimisation. The usage frequency of
tools is integrated in the model so that the tools which have not been used recently do
not appear in the set of possible tools. This is achieved by learning the usage of each
tool over time using a support vector regression model.

An API was developed to predict tools and visualize them using a user interface. It can
be used in the Galaxy workflow editor (It is not yet available publicly. The complete
code is located here ). The API can be also used for multiple user interface
integrations. Using the tool recommendation system, a user does not need to search
for the tools in the tool box to create a workflow. The possible tools are available in
the “recommended tools” modal popup.

avatar for Anup Kumar

Anup Kumar

PhD candidate, University of Freiburg

Wednesday July 3, 2019 15:25 - 15:45 CEST