A biclustering algorithm for binary matrices based on penalized Bernoulli likelihood

Handle URI:
http://hdl.handle.net/10754/597220
Title:
A biclustering algorithm for binary matrices based on penalized Bernoulli likelihood
Authors:
Lee, Seokho; Huang, Jianhua Z.
Abstract:
We propose a new biclustering method for binary data matrices using the maximum penalized Bernoulli likelihood estimation. Our method applies a multi-layer model defined on the logits of the success probabilities, where each layer represents a simple bicluster structure and the combination of multiple layers is able to reveal complicated, multiple biclusters. The method allows for non-pure biclusters, and can simultaneously identify the 1-prevalent blocks and 0-prevalent blocks. A computationally efficient algorithm is developed and guidelines are provided for specifying the tuning parameters, including initial values of model parameters, the number of layers, and the penalty parameters. Missing-data imputation can be handled in the EM framework. The method is tested using synthetic and real datasets and shows good performance. © 2013 Springer Science+Business Media New York.
Citation:
Lee S, Huang JZ (2013) A biclustering algorithm for binary matrices based on penalized Bernoulli likelihood. Stat Comput 24: 429–441. Available: http://dx.doi.org/10.1007/s11222-013-9379-3.
Publisher:
Springer Science + Business Media
Journal:
Statistics and Computing
KAUST Grant Number:
KUS-CI-016-04
Issue Date:
31-Jan-2013
DOI:
10.1007/s11222-013-9379-3
Type:
Article
ISSN:
0960-3174; 1573-1375
Sponsors:
The authors would like to thank the editor, the associate editor, and two reviewers for helpful comments. Dr. Lan Zhou carefully read the paper and gave many useful suggestions for improving the writing. Lee’s work was supported by Basic Science Research Program through the National Research Foundation (NRF) of Korea (2011-0011608). Huang’s work was partially supported by NCI (CA57030), NSF (DMS-0907170, DMS-1007618, DMS-1208952), and King Abdullah University of Science and Technology (KUS-CI-016-04).
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorLee, Seokhoen
dc.contributor.authorHuang, Jianhua Z.en
dc.date.accessioned2016-02-25T12:28:14Zen
dc.date.available2016-02-25T12:28:14Zen
dc.date.issued2013-01-31en
dc.identifier.citationLee S, Huang JZ (2013) A biclustering algorithm for binary matrices based on penalized Bernoulli likelihood. Stat Comput 24: 429–441. Available: http://dx.doi.org/10.1007/s11222-013-9379-3.en
dc.identifier.issn0960-3174en
dc.identifier.issn1573-1375en
dc.identifier.doi10.1007/s11222-013-9379-3en
dc.identifier.urihttp://hdl.handle.net/10754/597220en
dc.description.abstractWe propose a new biclustering method for binary data matrices using the maximum penalized Bernoulli likelihood estimation. Our method applies a multi-layer model defined on the logits of the success probabilities, where each layer represents a simple bicluster structure and the combination of multiple layers is able to reveal complicated, multiple biclusters. The method allows for non-pure biclusters, and can simultaneously identify the 1-prevalent blocks and 0-prevalent blocks. A computationally efficient algorithm is developed and guidelines are provided for specifying the tuning parameters, including initial values of model parameters, the number of layers, and the penalty parameters. Missing-data imputation can be handled in the EM framework. The method is tested using synthetic and real datasets and shows good performance. © 2013 Springer Science+Business Media New York.en
dc.description.sponsorshipThe authors would like to thank the editor, the associate editor, and two reviewers for helpful comments. Dr. Lan Zhou carefully read the paper and gave many useful suggestions for improving the writing. Lee’s work was supported by Basic Science Research Program through the National Research Foundation (NRF) of Korea (2011-0011608). Huang’s work was partially supported by NCI (CA57030), NSF (DMS-0907170, DMS-1007618, DMS-1208952), and King Abdullah University of Science and Technology (KUS-CI-016-04).en
dc.publisherSpringer Science + Business Mediaen
dc.subjectBiclusteringen
dc.subjectBinary dataen
dc.subjectPenalized likelihooden
dc.subjectPrincipal component analysisen
dc.titleA biclustering algorithm for binary matrices based on penalized Bernoulli likelihooden
dc.typeArticleen
dc.identifier.journalStatistics and Computingen
dc.contributor.institutionHankuk University of Foreign Studies, Seoul, South Koreaen
dc.contributor.institutionTexas A and M University, College Station, United Statesen
kaust.grant.numberKUS-CI-016-04en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.