skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research

Journal Article · · BMC Bioinformatics
 [1];  [1];  [1];  [1];  [1];  [1];  [1];  [1];  [1];  [2];  [2];  [3];  [4]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  3. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  4. Minerva, San Francisco, CA (United States)
+ Show Author Affiliations

BackgroundCurrent 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.ResultsThis 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.ConclusionsInitial results demonstrating CANDLE on DOE systems at ORNL, ANL and NERSC (Titan, Theta and Cori, respectively) demonstrate both scaling and multi-platform execution.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC); National Institutes of Health (NIH)
Grant/Contract Number:
AC02-06CH11357
OSTI ID:
1510031
Journal Information:
BMC Bioinformatics, Vol. 19, Issue S18; ISSN 1471-2105
Publisher:
BioMed CentralCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 26 works
Citation information provided by
Web of Science

References (11)

A community effort to assess and improve drug sensitivity prediction algorithms journal June 2014
Hyperopt: a Python library for model selection and hyperparameter optimization journal January 2015
Compiler Techniques for Massively Scalable Implicit Task Parallelism
  • Armstrong, Timothy G.; Wozniak, Justin M.; Wilde, Michael
  • SC14: International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1109/SC.2014.30
conference November 2014
LBANN: livermore big artificial neural network HPC toolkit conference January 2015
Deep learning journal May 2015
Evolving Neural Networks through Augmenting Topologies journal June 2002
Caffe: Convolutional Architecture for Fast Feature Embedding conference January 2014
From desktop to Large-Scale Model Exploration with Swift/T conference December 2016
Swift/T: scalable data flow programming for many-task applications journal August 2013
A training algorithm for networks of high-variability reservoirs journal September 2020
CNTK: Microsoft's Open-Source Deep-Learning Toolkit conference January 2016

Cited By (2)

Development of training environment for deep learning with medical images on supercomputer system based on asynchronous parallel Bayesian optimization journal January 2020
AI Meets Exascale Computing: Advancing Cancer Research With Large-Scale High Performance Computing journal October 2019

Figures / Tables (5)

Figure 1(p. 4)figure Figure 1
Figure 2(p. 7)figure Figure 2
Figure 3(p. 8)figure Figure 3
Figure 4(p. 8)figure Figure 4
Figure 5(p. 8)figure Figure 5

Similar Records

Related Subjects

60 APPLIED LIFE SCIENCES