CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research
Abstract Background Current multi-petaflop supercomputers are powerful systems, but present challenges when faced with problems requiring large machine learning workflows. Complex algorithms running at system scale, often with different patterns that require disparate software packages and complex d...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-12-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-018-2508-4 |
_version_ | 1811318425202458624 |
---|---|
author | Justin M. Wozniak Rajeev Jain Prasanna Balaprakash Jonathan Ozik Nicholson T. Collier John Bauer Fangfang Xia Thomas Brettin Rick Stevens Jamaludin Mohd-Yusof Cristina Garcia Cardona Brian Van Essen Matthew Baughman |
author_facet | Justin M. Wozniak Rajeev Jain Prasanna Balaprakash Jonathan Ozik Nicholson T. Collier John Bauer Fangfang Xia Thomas Brettin Rick Stevens Jamaludin Mohd-Yusof Cristina Garcia Cardona Brian Van Essen Matthew Baughman |
author_sort | Justin M. Wozniak |
collection | DOAJ |
description | Abstract Background Current multi-petaflop supercomputers are powerful systems, but present challenges when faced with problems requiring large machine learning workflows. Complex algorithms running at system scale, often with different patterns that require disparate software packages and complex data flows cause difficulties in assembling and managing large experiments on these machines. Results This paper presents a workflow system that makes progress on scaling machine learning ensembles, specifically in this first release, ensembles of deep neural networks that address problems in cancer research across the atomistic, molecular and population scales. The initial release of the application framework that we call CANDLE/Supervisor addresses the problem of hyper-parameter exploration of deep neural networks. Conclusions Initial results demonstrating CANDLE on DOE systems at ORNL, ANL and NERSC (Titan, Theta and Cori, respectively) demonstrate both scaling and multi-platform execution. |
first_indexed | 2024-04-13T12:25:02Z |
format | Article |
id | doaj.art-4833161dbb994c5f880dc0f042602862 |
institution | Directory Open Access Journal |
issn | 1471-2105 |
language | English |
last_indexed | 2024-04-13T12:25:02Z |
publishDate | 2018-12-01 |
publisher | BMC |
record_format | Article |
series | BMC Bioinformatics |
spelling | doaj.art-4833161dbb994c5f880dc0f0426028622022-12-22T02:47:03ZengBMCBMC Bioinformatics1471-21052018-12-0119S18596910.1186/s12859-018-2508-4CANDLE/Supervisor: a workflow framework for machine learning applied to cancer researchJustin M. Wozniak0Rajeev Jain1Prasanna Balaprakash2Jonathan Ozik3Nicholson T. Collier4John Bauer5Fangfang Xia6Thomas Brettin7Rick Stevens8Jamaludin Mohd-Yusof9Cristina Garcia Cardona10Brian Van Essen11Matthew Baughman12Argonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryArgonne National LaboratoryLos Alamos National LaboratoryLos Alamos National LaboratoryLawrence Livermore National LaboratoryMinervaAbstract Background Current multi-petaflop supercomputers are powerful systems, but present challenges when faced with problems requiring large machine learning workflows. Complex algorithms running at system scale, often with different patterns that require disparate software packages and complex data flows cause difficulties in assembling and managing large experiments on these machines. Results This paper presents a workflow system that makes progress on scaling machine learning ensembles, specifically in this first release, ensembles of deep neural networks that address problems in cancer research across the atomistic, molecular and population scales. The initial release of the application framework that we call CANDLE/Supervisor addresses the problem of hyper-parameter exploration of deep neural networks. Conclusions Initial results demonstrating CANDLE on DOE systems at ORNL, ANL and NERSC (Titan, Theta and Cori, respectively) demonstrate both scaling and multi-platform execution.http://link.springer.com/article/10.1186/s12859-018-2508-4SampleArticleAuthor |
spellingShingle | Justin M. Wozniak Rajeev Jain Prasanna Balaprakash Jonathan Ozik Nicholson T. Collier John Bauer Fangfang Xia Thomas Brettin Rick Stevens Jamaludin Mohd-Yusof Cristina Garcia Cardona Brian Van Essen Matthew Baughman CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research BMC Bioinformatics Sample Article Author |
title | CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research |
title_full | CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research |
title_fullStr | CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research |
title_full_unstemmed | CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research |
title_short | CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research |
title_sort | candle supervisor a workflow framework for machine learning applied to cancer research |
topic | Sample Article Author |
url | http://link.springer.com/article/10.1186/s12859-018-2508-4 |
work_keys_str_mv | AT justinmwozniak candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT rajeevjain candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT prasannabalaprakash candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT jonathanozik candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT nicholsontcollier candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT johnbauer candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT fangfangxia candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT thomasbrettin candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT rickstevens candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT jamaludinmohdyusof candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT cristinagarciacardona candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT brianvanessen candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch AT matthewbaughman candlesupervisoraworkflowframeworkformachinelearningappliedtocancerresearch |