Exploiting Parallel R in the Cloud with SPRINT

Summary

Background: Advances in DNA Microarray devices and next-generation massively parallel DNA sequencing platforms have led to an exponential growth in data availability but the arising opportunities require adequate computing resources. High Performance Computing (HPC) in the Cloud offers an affordable way of meeting this need.

Objectives: Bioconductor, a popular tool for high-throughput genomic data analysis, is distributed as add-on modules for the R statistical programming language but R has no native capabilities for exploiting multiprocessor architectures. SPRINT is an R package that enables easy access to HPC for genomics researchers. This paper investigates: setting up and running SPRINT-enabled genomic analyses on Amazon’s Elastic Compute Cloud (EC2), the advantages of submitting applications to EC2 from different parts of the world and, if resource underutilization can improve application performance.

Methods: The SPRINT parallel implementations of correlation, permutation testing, partitioning around medoids and the multi-purpose papply have been benchmarked on data sets of various size on Amazon EC2. Jobs have been submitted from both the UK and Thailand to investigate monetary differences.

Results: It is possible to obtain good, scalable performance but the level of improvement is dependent upon the nature of the algorithm. Resource underutilization can further improve the time to result. End-user’s location impacts on costs due to factors such as local taxation.

Conclusions: Although not designed to satisfy HPC requirements, Amazon EC2 and cloud computing in general provides an interesting alternative and provides new possibilities for smaller organisations with limited funds.

Keywords

Genomics - computing methodologies

• References

• 1 Heller MJ. DNA microarray technology: devices, systems, and applications. Annual review of biomedical engineering 2002; 4: 129-153.
• 2 Xu L, German D, Winslow RL. Large-scale integration of cancer microarray data identifies a robust common cancer signature. BMC Bioinformatics 2007; 8: 1471-2105.
• 3 Edgar R, Domrachev M, Lash AE. Gene Expression Omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Res 2002; 30 (01) 207-210.
• 4 Parkinson, et al. ArrayExpress update - an archive of microarray and high-throughput sequencing-based functional genomics experiments. Nucl Acids Res, Pubmed ID 21071405.
• 5 Shendure J, Ji H. Next-generation DNA sequencing. Nature biotechnology 2008; 26: 1135-1145.
• 6 Richter BG, Sexton DP. Managing and analyzing next-generation sequence data. PLoS Computational Biology 2009; 5: e1000369
• 7 Gentleman R, Carey V, Huber W, Irizarry R, Dudoit S. (eds) Bioinformatics and Computational Biology Solutions Using R and Bioconductor. Springer: 2005.
• 8 The R Project for Statistical Computing. http://www.r-project.org/.
• 9 Hill J, Hambley M, Forster T, Mewissen M, Sloan TM, Scharinger F, Trew A, Ghazal P. SPRINT: a new parallel framework for R. BMC Bioinformatics 2008; 9: 558
• 10 Petrou S, Sloan TM, Mewissen M, Forster T, Piotrowski M, Dobrzelecki B, Ghazal P, Trew A, Hill J. Optimization of a parallel permutation testing function for the SPRINT R package Concurrency and Computation: Practice and Experience 2011. http://dx.doi.org/10.1002/cpe.1787.
• 11 Piotrowski M, Forster T, Dobrezelecki B, Sloan TM, Mitchell L, Ghazal P, Mewsissen M, Petrou S, Trew A, Hill J. Optimisation and parallelisation of the partitioning around medoids function in R. International Conference on High Performance Computing and Simulation (HPCS). 2011: 707-713.
• 12 Mitchell L, Sloan TM, Mewissen M, Ghazal P, Forster T, Piotrowski M, Trew AS. A parallel random forest classifier for R. Proceedings of the second international workshop on Emerging computational methods for the life sciences (ECMLS ’11). 2011: 1-6.
• 13 Amazon Elastic Cloud (EC2). http:// aws.amazon.com/ec2/. Accessed 27th October 27, 2011
• 14 Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. Basic local alignment search tool. Journal of Molecular Biology 1990; 215: 403-410.
• 15 Matsunaga A, Tsugawa Ma, Fortes J. CloudBLAST: Combining MapReduce and Virtualization on Distributed Resources for Bioinformatics Applications. IEEE Fourth International Conference on eScience. 2008: 222-229.
• 16 Lu W, Jackson J, Barga R. AzureBlast: A Case Study of Developing Science Applications on the Cloud. HPDC ’10: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing 2010; 413-420.
• 17 McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo M. The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome research 2010; 20: 1297-1303.
• 18 Schmidberger M, Morgan M, Eddelbuettel D, Yu H, Tierney L, Mansmann U. State of the Art in Parallel Computing with R. Journal of Statistical Software 2009; 31 (01) 1-27.
• 19 Yu H. Rmpi: Parallel Statistical Computing in R. RNews 2002; 2 (02) 10-14.
• 20 Amazon EC2 FAQs. http://aws.amazon.com/ec2/faqs/. Accessed Oct 27, 2011
• 21 Clarke L, Glendinning I, Hempel R. The MPI Message Passing Interface Standard. Programming Environments for massively distributed systems: working conference of the IFIP WG10.3. Monte Verita; Switzerland: 1994.
• 22 Dobrzelecki B, Krause A, Piotrowski M, Chue Hong N. Managing and Analysing Genomic Data Using HPC and Clouds. Grid and Cloud Database Management. Berlin Heidelberg: Springer; 2011.
• 23 MPICH2. http://www.mcs.anl.gov/research/projects/mpich2/. Accessed 31/10/2011
• 24 Nadgowda SJ, Sion R. Cloud Performance Benchmark Series: Amazon Elastic Block Store (EBS); Amazon Simple Storage Service (S3; Amazon EC2 Instance Local Storage v0.8. Cloud Computing Center, Stony Brook Network Security and Applied Cryptography Lab.
• 25 Walker E. Benchmarking Amazon EC2 for high-performance scientific computing. Login 2008; 33: 18-23.
• 26 He Q, Shujia Z, Kobler B, Duffy D, McGlynn T. Case study for running HPC applications in public clouds. HPDC’10 Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. 2010: 395-401.
• 27 Hammond M, Hawtin R, Gillam L, Oppenheim C. Cloud computing for research. Technical Report. Curtis and Cartwright; June. 2010
• 28 Iakymchuk R, Napper J, Bientinesi P. Improving high-performance computations on clouds through resource underutilization. Proceedings of the 2011 ACM Symposium on Applied Computing. 2011: 19-126.
• 29 Iosup A, Yigitbasi N, Epema D. On the performance variability of production cloud services. Proceedings of the IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing. 2011
• 30 Schad J, Dittrich J, Quian ìe-Ruiz J. Runtime measurements in the cloud: observing, analyzing, and reducing variance. Proc VLDB Endow 2010; 3: 460-471.
• 31 Hill Z, Humphrey M. A quantitative analysis of high performance computing with Amazon’s ec2 infrastructure: The death of the local cluster?. In: 10th IEEE/ACM International Conference on Grid Computing. 2009: 26-33.
• 32 Jackson KR, Ramakrishan L, Muriki K, Canon S, Cholia S, Shalf J, Wasserman HJ, Wright NJ. Performance analysis of high performance computing applications on the Amazon Web Services cloud. Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science. 2010
• 33 Armbrust M, Fox A, Griffith R, Joseph AD, Katz R, Konwinski A, Lee G, Patterson D, Rabkin A, Stoica I, Zaharia M. Above the clouds: A Berkeley view of cloud computing. Technical Report, UC Berkeley Reliable Adaptive Distributed Systems Laboratory, February. 2009
• 34 Amazon Web Services High Performance Computing. http://aws.amazon.com/hpc-applications/. Accessed 31/10/2011
• 35 Petrou S. SPRINTing with HECToR, 2010. http://www.hector.ac.uk/cse/distributedcse/reports/sprint/sprint.pdf. Accessed 09/05/2011
• 36 Oosterhuis F, Dodoková A, Gerdes H, Greño P, Jantzen J, Mudgal S, Neubauer A, Rayment M, Stocker A, Tinetti B, van der Woerd Varma A. The use of differential VAT rates to promote changes in consumption and innovation. Final Report under DG Environment, Contract 070307/2007/482673/G1. 2008.
• 37 This data is available from the Documents section of. http://www.r-sprint.org/. Accessed 17/03/2011
• 38 Quackenbush J. Computational Approaches to Analysis of DNA Microarray Data. Methods Inf Med. IMIA Yearbook 2006; Assessing Information - Technologies for Health 2006; 1: 91-103.
• 39 Bolshakova N, Azuaje F. Computational Approaches to Analysis of DNA Microarray Data. Estimating the Number of Clusters in DNA Microarray Data. Methods Inf Med 2006; 45 (02) 153-157.