HyperLoom: A platform for defining and executing scientific pipelines in distributed environments

dc.contributor.authorCima, Vojtěch
dc.contributor.authorBöhm, Stanislav
dc.contributor.authorMartinovič, Jan
dc.contributor.authorDvorský, Jiří
dc.contributor.authorJanurová, Kateřina
dc.contributor.authorVander Aa, Tom
dc.contributor.authorAshby, Thomas J.
dc.contributor.authorChupakhin, Vladimir
dc.date.accessioned2018-11-30T07:03:38Z
dc.date.available2018-11-30T07:03:38Z
dc.date.issued2018
dc.description.abstractReal-world scientific applications often encompass end-to-end data processing pipelines composed of a large number of interconnected computational tasks of various granularity. We introduce HyperLoom, an open source platform for defining and executing such pipelines in distributed environments and providing a Python interface for defining tasks. HyperLoom is a self-contained system that does not use an external scheduler for the actual execution of the task. We have successfully employed HyperLoom for executing chemogenomics pipelines used in pharmaceutic industry for novel drug discovery.cs
dc.description.firstpage1cs
dc.description.lastpage6cs
dc.format.extent194983 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.citationACM International Conference Proceeding Series. 2018, p. 1-6.cs
dc.identifier.doi10.1145/3183767.3183768
dc.identifier.isbn978-1-4503-6444-7
dc.identifier.urihttp://hdl.handle.net/10084/133294
dc.language.isoencs
dc.publisherAssociation for Computing Machinerycs
dc.relation.ispartofseriesACM International Conference Proceeding Seriescs
dc.relation.projectideu-repo/grantAgreement/EU/H2020/671555/
dc.relation.projectideu-repo/grantAgreement/MSMT/LM2015070
dc.relation.urihttps://doi.org/10.1145/3183767.3183768cs
dc.rights© 2018 ACMcs
dc.rights.accessopenAccesscs
dc.subjectHPCcs
dc.subjectscientific pipelinecs
dc.subjectmachine learningcs
dc.subjectbig datacs
dc.subjectdistributed computingcs
dc.subjectchemogenomicscs
dc.subjecttask schedulingcs
dc.titleHyperLoom: A platform for defining and executing scientific pipelines in distributed environmentscs
dc.typeconference papercs
dc.type.statusPeer-reviewedcs
dc.type.versionsubmittedVersioncs

Files

Original bundle

Now showing 1 - 1 out of 1 results
Loading...
Thumbnail Image
Name:
2018p1.pdf
Size:
190.41 KB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 out of 1 results
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections