Bayesian variable selection for linear regression in high dimensional microarray data

Wellington Cabrera; Carlos Ordonez; David Sergio Matusevich; Veerabhadran Baladandayuthapani

doi:10.1145/2512089.2512094

Bayesian variable selection for linear regression in high dimensional microarray data

Wellington Cabrera, Carlos Ordonez, David Sergio Matusevich, Veerabhadran Baladandayuthapani

Biostatistics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Variable selection is a fundamental problem in Bayesian statistics whose solution requires exploring a combinatorial search space. We study the solution of variable selection with a well-known MCMC method, which requires thousands of iterations. We present several algorithmic optimizations to accelerate the MCMC method to make it work efficiently inside a database system. Our optimizations include sufficient statistics, variable preselection, hash tables and calling a linear algebra library. We present experiments with very high dimensional microarray data sets to predict cancer survival time. We discuss encouraging findings, identifying specific genes likely to predict the survival time for brain cancer patients. We also show our DBMS-based algorithm is orders of magnitude faster than the R statistical package. Our work shows a DBMS is a promising platform to analyze microarray data.

Original language	English (US)
Title of host publication	DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013
Pages	17-18
Number of pages	2
DOIs	https://doi.org/10.1145/2512089.2512094
State	Published - 2013
Event	7th ACM International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO 2013, in Conjunction with the 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013 - San Francisco, CA, United States Duration: Nov 1 2013 → Nov 1 2013

Publication series

Name	International Conference on Information and Knowledge Management, Proceedings

Other

Other	7th ACM International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO 2013, in Conjunction with the 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013
Country/Territory	United States
City	San Francisco, CA
Period	11/1/13 → 11/1/13

Keywords

Algorithms
DBMS
MCMC
Microarray
Variable selection

ASJC Scopus subject areas

General Decision Sciences
General Business, Management and Accounting

Access to Document

10.1145/2512089.2512094

Cite this

Cabrera, W., Ordonez, C., Matusevich, D. S., & Baladandayuthapani, V. (2013). Bayesian variable selection for linear regression in high dimensional microarray data. In DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013 (pp. 17-18). (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2512089.2512094

Bayesian variable selection for linear regression in high dimensional microarray data. / Cabrera, Wellington; Ordonez, Carlos; Matusevich, David Sergio et al.
DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013. 2013. p. 17-18 (International Conference on Information and Knowledge Management, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Cabrera, W, Ordonez, C, Matusevich, DS & Baladandayuthapani, V 2013, Bayesian variable selection for linear regression in high dimensional microarray data. in DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013. International Conference on Information and Knowledge Management, Proceedings, pp. 17-18, 7th ACM International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO 2013, in Conjunction with the 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013, San Francisco, CA, United States, 11/1/13. https://doi.org/10.1145/2512089.2512094

Cabrera W, Ordonez C, Matusevich DS, Baladandayuthapani V. Bayesian variable selection for linear regression in high dimensional microarray data. In DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013. 2013. p. 17-18. (International Conference on Information and Knowledge Management, Proceedings). doi: 10.1145/2512089.2512094

Cabrera, Wellington ; Ordonez, Carlos ; Matusevich, David Sergio et al. / Bayesian variable selection for linear regression in high dimensional microarray data. DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013. 2013. pp. 17-18 (International Conference on Information and Knowledge Management, Proceedings).

@inproceedings{39240853a63348239436da5d63098865,

title = "Bayesian variable selection for linear regression in high dimensional microarray data",

abstract = "Variable selection is a fundamental problem in Bayesian statistics whose solution requires exploring a combinatorial search space. We study the solution of variable selection with a well-known MCMC method, which requires thousands of iterations. We present several algorithmic optimizations to accelerate the MCMC method to make it work efficiently inside a database system. Our optimizations include sufficient statistics, variable preselection, hash tables and calling a linear algebra library. We present experiments with very high dimensional microarray data sets to predict cancer survival time. We discuss encouraging findings, identifying specific genes likely to predict the survival time for brain cancer patients. We also show our DBMS-based algorithm is orders of magnitude faster than the R statistical package. Our work shows a DBMS is a promising platform to analyze microarray data.",

keywords = "Algorithms, DBMS, MCMC, Microarray, Variable selection",

author = "Wellington Cabrera and Carlos Ordonez and Matusevich, {David Sergio} and Veerabhadran Baladandayuthapani",

note = "Copyright: Copyright 2013 Elsevier B.V., All rights reserved.; 7th ACM International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO 2013, in Conjunction with the 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013 ; Conference date: 01-11-2013 Through 01-11-2013",

year = "2013",

doi = "10.1145/2512089.2512094",

language = "English (US)",

isbn = "9781450324199",

series = "International Conference on Information and Knowledge Management, Proceedings",

pages = "17--18",

booktitle = "DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013",

}

TY - GEN

T1 - Bayesian variable selection for linear regression in high dimensional microarray data

AU - Cabrera, Wellington

AU - Ordonez, Carlos

AU - Matusevich, David Sergio

AU - Baladandayuthapani, Veerabhadran

PY - 2013

Y1 - 2013

N2 - Variable selection is a fundamental problem in Bayesian statistics whose solution requires exploring a combinatorial search space. We study the solution of variable selection with a well-known MCMC method, which requires thousands of iterations. We present several algorithmic optimizations to accelerate the MCMC method to make it work efficiently inside a database system. Our optimizations include sufficient statistics, variable preselection, hash tables and calling a linear algebra library. We present experiments with very high dimensional microarray data sets to predict cancer survival time. We discuss encouraging findings, identifying specific genes likely to predict the survival time for brain cancer patients. We also show our DBMS-based algorithm is orders of magnitude faster than the R statistical package. Our work shows a DBMS is a promising platform to analyze microarray data.

AB - Variable selection is a fundamental problem in Bayesian statistics whose solution requires exploring a combinatorial search space. We study the solution of variable selection with a well-known MCMC method, which requires thousands of iterations. We present several algorithmic optimizations to accelerate the MCMC method to make it work efficiently inside a database system. Our optimizations include sufficient statistics, variable preselection, hash tables and calling a linear algebra library. We present experiments with very high dimensional microarray data sets to predict cancer survival time. We discuss encouraging findings, identifying specific genes likely to predict the survival time for brain cancer patients. We also show our DBMS-based algorithm is orders of magnitude faster than the R statistical package. Our work shows a DBMS is a promising platform to analyze microarray data.

KW - Algorithms

KW - DBMS

KW - MCMC

KW - Microarray

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=84889587726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889587726&partnerID=8YFLogxK

U2 - 10.1145/2512089.2512094

DO - 10.1145/2512089.2512094

M3 - Conference contribution

AN - SCOPUS:84889587726

SN - 9781450324199

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 17

EP - 18

BT - DTMBIO 2013 - Proceedings of the 7th International Workshop on Data and Text Mining in Biomedical Informatics, Co-located with CIKM 2013

T2 - 7th ACM International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO 2013, in Conjunction with the 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013

Y2 - 1 November 2013 through 1 November 2013

ER -

Bayesian variable selection for linear regression in high dimensional microarray data

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this