The integration of multi-dimensional datasets remains a key challenge in systems biology and genomic medicine. Modern high-throughput technologies generate a broad array of different data types, providing distinct - but often complementary - information. However, the large amount of data adds burden to any inference task. Flexible Bayesian methods may reduce the necessity for strong modelling assumptions, but can also increase the computational burden. We present an improved implementation of a Bayesian correlated clustering algorithm, that permits integrated clustering to be routinely performed across multiple datasets, each with tens of thousands of items. By exploiting GPU based computation, we are able to improve runtime performance of the algorithm by almost four orders of magnitude. This permits analysis across genomic-scale data sets, greatly expanding the range of applications over those originally possible. MDI is available here: http://www2.warwick.ac.uk/fac/sci/systemsbiology/research/software/.
%0 Journal Article
%1 Mason2016MDIGPU
%A Mason, Samuel A.
%A Sayyid, Faiz
%A Kirk, Paul D.
%A Starr, Colin
%A Wild, David L.
%D 2016
%J Statistical applications in genetics and molecular biology
%K bayesian-networks gpu
%N 1
%P 83--86
%T MDI-GPU: accelerating integrative modelling for genomic-scale data using GP-GPU computing.
%U http://view.ncbi.nlm.nih.gov/pubmed/26910751
%V 15
%X The integration of multi-dimensional datasets remains a key challenge in systems biology and genomic medicine. Modern high-throughput technologies generate a broad array of different data types, providing distinct - but often complementary - information. However, the large amount of data adds burden to any inference task. Flexible Bayesian methods may reduce the necessity for strong modelling assumptions, but can also increase the computational burden. We present an improved implementation of a Bayesian correlated clustering algorithm, that permits integrated clustering to be routinely performed across multiple datasets, each with tens of thousands of items. By exploiting GPU based computation, we are able to improve runtime performance of the algorithm by almost four orders of magnitude. This permits analysis across genomic-scale data sets, greatly expanding the range of applications over those originally possible. MDI is available here: http://www2.warwick.ac.uk/fac/sci/systemsbiology/research/software/.
@article{Mason2016MDIGPU,
abstract = {The integration of multi-dimensional datasets remains a key challenge in systems biology and genomic medicine. Modern high-throughput technologies generate a broad array of different data types, providing distinct - but often complementary - information. However, the large amount of data adds burden to any inference task. Flexible Bayesian methods may reduce the necessity for strong modelling assumptions, but can also increase the computational burden. We present an improved implementation of a Bayesian correlated clustering algorithm, that permits integrated clustering to be routinely performed across multiple datasets, each with tens of thousands of items. By exploiting {GPU} based computation, we are able to improve runtime performance of the algorithm by almost four orders of magnitude. This permits analysis across genomic-scale data sets, greatly expanding the range of applications over those originally possible. {MDI} is available here: http://www2.warwick.ac.uk/fac/sci/systemsbiology/research/software/.},
added-at = {2018-12-02T16:09:07.000+0100},
author = {Mason, Samuel A. and Sayyid, Faiz and Kirk, Paul D. and Starr, Colin and Wild, David L.},
biburl = {https://www.bibsonomy.org/bibtex/20858b1e27f699962acb536681b18dc15/karthikraman},
citeulike-article-id = {13947416},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/26910751},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=26910751},
day = 1,
interhash = {abe6b3e42e780e0efafd9cc2fda23022},
intrahash = {0858b1e27f699962acb536681b18dc15},
issn = {1544-6115},
journal = {Statistical applications in genetics and molecular biology},
keywords = {bayesian-networks gpu},
month = mar,
number = 1,
pages = {83--86},
pmid = {26910751},
posted-at = {2016-03-01 06:50:31},
priority = {2},
timestamp = {2018-12-02T16:09:07.000+0100},
title = {{MDI}-{GPU}: accelerating integrative modelling for genomic-scale data using {GP}-{GPU} computing.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/26910751},
volume = 15,
year = 2016
}