Scaling computational genomics to millions of individuals with GPUs

Current genomics methods are designed to handle tens to thousands of samples but will need to scale to millions to match the pace of data and hypothesis generation in biomedical science. Here, we show that high efficiency at low cost can be achieved by leveraging general-purpose libraries for comput...

Descripción completa

Detalles Bibliográficos
Autores principales: Taylor-Weiner, Amaro, Aguet, François, Haradhvala, Nicholas J., Gosai, Sager, Anand, Shankara, Kim, Jaegil, Ardlie, Kristin, Van Allen, Eliezer M., Getz, Gad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2019
Materias:
Short Report
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6823959/
https://www.ncbi.nlm.nih.gov/pubmed/31675989
http://dx.doi.org/10.1186/s13059-019-1836-7
_version_ 1783464628454424576
author Taylor-Weiner, Amaro
Aguet, François
Haradhvala, Nicholas J.
Gosai, Sager
Anand, Shankara
Kim, Jaegil
Ardlie, Kristin
Van Allen, Eliezer M.
Getz, Gad
author_facet Taylor-Weiner, Amaro
Aguet, François
Haradhvala, Nicholas J.
Gosai, Sager
Anand, Shankara
Kim, Jaegil
Ardlie, Kristin
Van Allen, Eliezer M.
Getz, Gad
author_sort Taylor-Weiner, Amaro
collection PubMed
description Current genomics methods are designed to handle tens to thousands of samples but will need to scale to millions to match the pace of data and hypothesis generation in biomedical science. Here, we show that high efficiency at low cost can be achieved by leveraging general-purpose libraries for computing using graphics processing units (GPUs), such as PyTorch and TensorFlow. We demonstrate > 200-fold decreases in runtime and ~ 5–10-fold reductions in cost relative to CPUs. We anticipate that the accessibility of these libraries will lead to a widespread adoption of GPUs in computational genomics.
format Online
Article
Text
id pubmed-6823959
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-68239592019-11-06 Scaling computational genomics to millions of individuals with GPUs Taylor-Weiner, Amaro Aguet, François Haradhvala, Nicholas J. Gosai, Sager Anand, Shankara Kim, Jaegil Ardlie, Kristin Van Allen, Eliezer M. Getz, Gad Genome Biol Short Report Current genomics methods are designed to handle tens to thousands of samples but will need to scale to millions to match the pace of data and hypothesis generation in biomedical science. Here, we show that high efficiency at low cost can be achieved by leveraging general-purpose libraries for computing using graphics processing units (GPUs), such as PyTorch and TensorFlow. We demonstrate > 200-fold decreases in runtime and ~ 5–10-fold reductions in cost relative to CPUs. We anticipate that the accessibility of these libraries will lead to a widespread adoption of GPUs in computational genomics. BioMed Central 2019-11-01 /pmc/articles/PMC6823959/ /pubmed/31675989 http://dx.doi.org/10.1186/s13059-019-1836-7 Text en © The Author(s). 2019 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.
spellingShingle Short Report
Taylor-Weiner, Amaro
Aguet, François
Haradhvala, Nicholas J.
Gosai, Sager
Anand, Shankara
Kim, Jaegil
Ardlie, Kristin
Van Allen, Eliezer M.
Getz, Gad
Scaling computational genomics to millions of individuals with GPUs
title Scaling computational genomics to millions of individuals with GPUs
title_full Scaling computational genomics to millions of individuals with GPUs
title_fullStr Scaling computational genomics to millions of individuals with GPUs
title_full_unstemmed Scaling computational genomics to millions of individuals with GPUs
title_short Scaling computational genomics to millions of individuals with GPUs
title_sort scaling computational genomics to millions of individuals with gpus
topic Short Report
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6823959/
https://www.ncbi.nlm.nih.gov/pubmed/31675989
http://dx.doi.org/10.1186/s13059-019-1836-7
work_keys_str_mv AT taylorweineramaro scalingcomputationalgenomicstomillionsofindividualswithgpus
AT aguetfrancois scalingcomputationalgenomicstomillionsofindividualswithgpus
AT haradhvalanicholasj scalingcomputationalgenomicstomillionsofindividualswithgpus
AT gosaisager scalingcomputationalgenomicstomillionsofindividualswithgpus
AT anandshankara scalingcomputationalgenomicstomillionsofindividualswithgpus
AT kimjaegil scalingcomputationalgenomicstomillionsofindividualswithgpus
AT ardliekristin scalingcomputationalgenomicstomillionsofindividualswithgpus
AT vanalleneliezerm scalingcomputationalgenomicstomillionsofindividualswithgpus
AT getzgad scalingcomputationalgenomicstomillionsofindividualswithgpus

Ejemplares similares