Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.14/137051
25 Visitors
27 Hits
0 Downloads
- Title
- Parameter estimation for robust HMM analysis of ChIP-chip data
- Related
- BMC bioinformatics, Vol. 9, No. 343, (2008), p.1-13
- DOI
- 10.1186/1471-2105-9-343
- Publisher
- BioMed Central
- Date
- 2008
- FoR/RFCD Code(s)
-
080100 Artificial Intelligence and Image Processing
060100 Biochemistry and Cell Biology
080200 Computation Theory and Mathematics
- Author/Creator
- Humburg, Peter
- Author/Creator
- Bulger, David
- Author/Creator
- Stone, Glenn
- Description
- Tiling arrays are an important tool for the study of transcriptional activity, protein-DNA interactions and chromatin structure on a genome-wide scale at high resolution. Although hidden Markov models have been used successfully to analyse tiling array data, parameter estimation for these models is typically ad hoc. Especially in the context of ChIP-chip experiments, no standard procedures exist to obtain parameter estimates from the data. Common methods for the calculation of maximum likelihood estimates such as the Baum-Welch algorithm or Viterbi training are rarely applied in the context of tiling array analysis. Results: Here we develop a hidden Markov model for the analysis of chromatin structure ChIP-chip tiling array data, using t emission distributions to increase robustness towards outliers. Maximum likelihood estimates are used for all model parameters. Two different approaches to parameter estimation are investigated and combined into an efficient procedure. Conclusion: We illustrate an efficient parameter estimation procedure that can be used for HMM based methods in general and leads to a clear increase in performance when compared to the use of ad hoc estimates. The resulting hidden Markov model outperforms established methods like TileMap in the context of histone modification studies.
- Description
- 13 page(s)
- Subject Keyword
- 080100 Artificial Intelligence and Image Processing
- Subject Keyword
- 060100 Biochemistry and Cell Biology
- Subject Keyword
- 080200 Computation Theory and Mathematics
- Subject Keyword
- hidden Markov model
- Subject Keyword
- Parameter estimation
- Subject Keyword
- ChIP-chip
- Resource Type
- journal article
- Organisation
- Macquarie University. Dept. of Statistics
- Identifier
- http://hdl.handle.net/1959.14/137051
- Identifier
- ISSN:1471-2105
- Identifier
- mq-rm-2007008464
- Language
- eng
- Rights
- This version is archived for private and non-commercial use under the terms of this BioMed Central open access license ("license") (see http://www.biomedcentral.com/info/about/license). The work is protected by copyright and/or other applicable law. Any use of the work other than as authorized under this license is prohibited. For further rights please check the terms of the license, or contact the publisher.
- Full Text
- Reviewed
-
-
