Parameter estimation for robust HMM analysis of ChIP-chip data
<p>Abstract</p> <p>Background</p> <p>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 a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2008-08-01
|
| Series: | BMC Bioinformatics |
| Online Access: | http://www.biomedcentral.com/1471-2105/9/343 |
| _version_ | 1811297387119902720 |
|---|---|
| author | Humburg Peter Bulger David Stone Glenn |
| author_facet | Humburg Peter Bulger David Stone Glenn |
| author_sort | Humburg Peter |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>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 <it>ad hoc</it>. 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.</p> <p>Results</p> <p>Here we develop a hidden Markov model for the analysis of chromatin structure ChIP-chip tiling array data, using <it>t </it>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.</p> <p>Conclusion</p> <p>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 <it>ad hoc </it>estimates. The resulting hidden Markov model outperforms established methods like TileMap in the context of histone modification studies.</p> |
| first_indexed | 2024-04-13T06:03:28Z |
| format | Article |
| id | doaj.art-a141bfba397841dfa26d97476e1ba5ac |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-13T06:03:28Z |
| publishDate | 2008-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-a141bfba397841dfa26d97476e1ba5ac2022-12-22T02:59:21ZengBMCBMC Bioinformatics1471-21052008-08-019134310.1186/1471-2105-9-343Parameter estimation for robust HMM analysis of ChIP-chip dataHumburg PeterBulger DavidStone Glenn<p>Abstract</p> <p>Background</p> <p>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 <it>ad hoc</it>. 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.</p> <p>Results</p> <p>Here we develop a hidden Markov model for the analysis of chromatin structure ChIP-chip tiling array data, using <it>t </it>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.</p> <p>Conclusion</p> <p>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 <it>ad hoc </it>estimates. The resulting hidden Markov model outperforms established methods like TileMap in the context of histone modification studies.</p>http://www.biomedcentral.com/1471-2105/9/343 |
| spellingShingle | Humburg Peter Bulger David Stone Glenn Parameter estimation for robust HMM analysis of ChIP-chip data BMC Bioinformatics |
| title | Parameter estimation for robust HMM analysis of ChIP-chip data |
| title_full | Parameter estimation for robust HMM analysis of ChIP-chip data |
| title_fullStr | Parameter estimation for robust HMM analysis of ChIP-chip data |
| title_full_unstemmed | Parameter estimation for robust HMM analysis of ChIP-chip data |
| title_short | Parameter estimation for robust HMM analysis of ChIP-chip data |
| title_sort | parameter estimation for robust hmm analysis of chip chip data |
| url | http://www.biomedcentral.com/1471-2105/9/343 |
| work_keys_str_mv | AT humburgpeter parameterestimationforrobusthmmanalysisofchipchipdata AT bulgerdavid parameterestimationforrobusthmmanalysisofchipchipdata AT stoneglenn parameterestimationforrobusthmmanalysisofchipchipdata |