GigaSOM.jl: High-performance clustering and visualization of huge cytometry datasets

Kratochvil, Miroslav; Hunewald, Oliver; Heirendt, Laurent; Verissimo, Vasco; Vondrášek, Jiří; Satagopam, Venkata; Schneider, Reinhard; Trefois, Christophe; Ollert, Markus

doi:10.1093/gigascience/giaa127

Reference : GigaSOM.jl: High-performance clustering and visualization of huge cytometry datasets


	Document type :	Scientific journals : Article
	Discipline(s) :	Life sciences : Multidisciplinary, general & others Engineering, computing & technology : Multidisciplinary, general & others
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/46296

Title :	GigaSOM.jl: High-performance clustering and visualization of huge cytometry datasets
Language :	English
Author, co-author :	Kratochvil, Miroslav* [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core > ; Institute of Organic Chemistry and Biochemistry of the CAS, Prague]
	Hunewald, Oliver* [Luxembourg Institute of Health - LIH]
	Heirendt, Laurent [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core >]
	Verissimo, Vasco [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)]
	Vondrášek, Jiří [Institute of Organic Chemistry and Biochemistry of the CAS, Prague]
	Satagopam, Venkata [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core >]
	Schneider, Reinhard [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core >]
	Trefois, Christophe [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core >]
	Ollert, Markus [Luxembourg Institute of Health - LIH]
	* These authors have contributed equally to this work.
Publication date :	18-Nov-2020
Journal title :	GigaScience
Publisher :	Oxford University Press
Volume :	9
Issue/season :	11
Peer reviewed :	Yes
Audience :	International
e-ISSN :	2047-217X
Country :	United Kingdom
Abstract :	[en] Background: The amount of data generated in large clinical and phenotyping studies that use single-cell cytometry is constantly growing. Recent technological advances allow the easy generation of data with hundreds of millions of single-cell data points with >40 parameters, originating from thousands of individual samples. The analysis of that amount of high-dimensional data becomes demanding in both hardware and software of high-performance computational resources. Current software tools often do not scale to the datasets of such size; users are thus forced to downsample the data to bearable sizes, in turn losing accuracy and ability to detect many underlying complex phenomena. Results: We present GigaSOM.jl, a fast and scalable implementation of clustering and dimensionality reduction for flow and mass cytometry data. The implementation of GigaSOM.jl in the high-level and high-performance programming language Julia makes it accessible to the scientific community and allows for efficient handling and processing of datasets with billions of data points using distributed computing infrastructures. We describe the design of GigaSOM.jl, measure its performance and horizontal scaling capability, and showcase the functionality on a large dataset from a recent study. Conclusions: GigaSOM.jl facilitates the use of commonly available high-performance computing resources to process the largest available datasets within minutes, while producing results of the same quality as the current state-of-art software. Measurements indicate that the performance scales to much larger datasets. The example use on the data from a massive mouse phenotyping effort confirms the applicability of GigaSOM.jl to huge-scale studies.
Research centres :	University of Luxembourg: High Performance Computing - ULHPC ; Luxembourg Centre for Systems Biomedicine (LCSB): Bioinformatics Core (R. Schneider Group)
Funders :	ELIXIR CZ LM2018131 (MEYS) ; FNR AFR-RIKEN bilateral program (TregBar 2015/11228353) ; FNR PRIDE Doctoral Training Unit program (PRIDE/11012546/NEXTIMMUNE) ; Institute of Organic Chemistry and Biochemistry of the CAS (RVO: 61388963) ; ELIXIR Staff Exchange programme 2020
Target :	Researchers ; Professionals
Permalink :	http://hdl.handle.net/10993/46296
DOI :	10.1093/gigascience/giaa127
Other URL :	https://academic.oup.com/gigascience/article/9/11/giaa127/5987271

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	giaa127.pdf		Publisher postprint	14.22 MB	View/Open

Additional material(s):

	File	Commentary	Size	Access
Open access	giaa127_supplemental_file.pdf		2.32 MB	View/Open

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices