Prediction of regulatory elements in mammalian genomes using chromatin signatures

Kyoung-Jae Won; Iouri Chepelev; Bing Ren; Wei Wang

doi:10.1186/1471-2105-9-547

Prediction of regulatory elements in mammalian genomes using chromatin signatures

Kyoung-Jae Won, Iouri Chepelev, Bing Ren, Wei Wang

Functional genomics

71 Citationer (Scopus)

Abstract

BACKGROUND: Recent genomic scale survey of epigenetic states in the mammalian genomes has shown that promoters and enhancers are correlated with distinct chromatin signatures, providing a pragmatic way for systematic mapping of these regulatory elements in the genome. With rapid accumulation of chromatin modification profiles in the genome of various organisms and cell types, this chromatin based approach promises to uncover many new regulatory elements, but computational methods to effectively extract information from these datasets are still limited.

RESULTS: We present here a supervised learning method to predict promoters and enhancers based on their unique chromatin modification signatures. We trained Hidden Markov models (HMMs) on the histone modification data for known promoters and enhancers, and then used the trained HMMs to identify promoter or enhancer like sequences in the human genome. Using a simulated annealing (SA) procedure, we searched for the most informative combination and the optimal window size of histone marks.

CONCLUSION: Compared with the previous methods, the HMM method can capture the complex patterns of histone modifications particularly from the weak signals. Cross validation and scanning the ENCODE regions showed that our method outperforms the previous profile-based method in mapping promoters and enhancers. We also showed that including more histone marks can further boost the performance of our method. This observation suggests that the HMM is robust and is capable of integrating information from multiple histone marks. To further demonstrate the usefulness of our method, we applied it to analyzing genome wide ChIP-Seq data in three mouse cell lines and correctly predicted active and inactive promoters with positive predictive values of more than 80%. The software is available at http://http:/nash.ucsd.edu/chromatin.tar.gz.

Originalsprog	Engelsk
Tidsskrift	BMC Bioinformatics
Vol/bind	9
Sider (fra-til)	547
ISSN	1471-2105
DOI	https://doi.org/10.1186/1471-2105-9-547
Status	Udgivet - 18 dec. 2008

Adgang til dokumentet

10.1186/1471-2105-9-547

Citationsformater

@article{44fafb00b9824f13b3758d349e797472,

title = "Prediction of regulatory elements in mammalian genomes using chromatin signatures",

abstract = "BACKGROUND: Recent genomic scale survey of epigenetic states in the mammalian genomes has shown that promoters and enhancers are correlated with distinct chromatin signatures, providing a pragmatic way for systematic mapping of these regulatory elements in the genome. With rapid accumulation of chromatin modification profiles in the genome of various organisms and cell types, this chromatin based approach promises to uncover many new regulatory elements, but computational methods to effectively extract information from these datasets are still limited.RESULTS: We present here a supervised learning method to predict promoters and enhancers based on their unique chromatin modification signatures. We trained Hidden Markov models (HMMs) on the histone modification data for known promoters and enhancers, and then used the trained HMMs to identify promoter or enhancer like sequences in the human genome. Using a simulated annealing (SA) procedure, we searched for the most informative combination and the optimal window size of histone marks.CONCLUSION: Compared with the previous methods, the HMM method can capture the complex patterns of histone modifications particularly from the weak signals. Cross validation and scanning the ENCODE regions showed that our method outperforms the previous profile-based method in mapping promoters and enhancers. We also showed that including more histone marks can further boost the performance of our method. This observation suggests that the HMM is robust and is capable of integrating information from multiple histone marks. To further demonstrate the usefulness of our method, we applied it to analyzing genome wide ChIP-Seq data in three mouse cell lines and correctly predicted active and inactive promoters with positive predictive values of more than 80%. The software is available at http://http:/nash.ucsd.edu/chromatin.tar.gz.",

keywords = "Animals, Chromatin/genetics, Computational Biology/methods, Genome, Histones/genetics, Humans, Markov Chains, Promoter Regions, Genetic, Regulatory Sequences, Nucleic Acid/genetics",

author = "Kyoung-Jae Won and Iouri Chepelev and Bing Ren and Wei Wang",

year = "2008",

month = dec,

day = "18",

doi = "10.1186/1471-2105-9-547",

language = "English",

volume = "9",

pages = "547",

journal = "B M C Bioinformatics",

issn = "1471-2105",

publisher = "BioMed Central Ltd.",

}

TY - JOUR

T1 - Prediction of regulatory elements in mammalian genomes using chromatin signatures

AU - Won, Kyoung-Jae

AU - Chepelev, Iouri

AU - Ren, Bing

AU - Wang, Wei

PY - 2008/12/18

Y1 - 2008/12/18

N2 - BACKGROUND: Recent genomic scale survey of epigenetic states in the mammalian genomes has shown that promoters and enhancers are correlated with distinct chromatin signatures, providing a pragmatic way for systematic mapping of these regulatory elements in the genome. With rapid accumulation of chromatin modification profiles in the genome of various organisms and cell types, this chromatin based approach promises to uncover many new regulatory elements, but computational methods to effectively extract information from these datasets are still limited.RESULTS: We present here a supervised learning method to predict promoters and enhancers based on their unique chromatin modification signatures. We trained Hidden Markov models (HMMs) on the histone modification data for known promoters and enhancers, and then used the trained HMMs to identify promoter or enhancer like sequences in the human genome. Using a simulated annealing (SA) procedure, we searched for the most informative combination and the optimal window size of histone marks.CONCLUSION: Compared with the previous methods, the HMM method can capture the complex patterns of histone modifications particularly from the weak signals. Cross validation and scanning the ENCODE regions showed that our method outperforms the previous profile-based method in mapping promoters and enhancers. We also showed that including more histone marks can further boost the performance of our method. This observation suggests that the HMM is robust and is capable of integrating information from multiple histone marks. To further demonstrate the usefulness of our method, we applied it to analyzing genome wide ChIP-Seq data in three mouse cell lines and correctly predicted active and inactive promoters with positive predictive values of more than 80%. The software is available at http://http:/nash.ucsd.edu/chromatin.tar.gz.

AB - BACKGROUND: Recent genomic scale survey of epigenetic states in the mammalian genomes has shown that promoters and enhancers are correlated with distinct chromatin signatures, providing a pragmatic way for systematic mapping of these regulatory elements in the genome. With rapid accumulation of chromatin modification profiles in the genome of various organisms and cell types, this chromatin based approach promises to uncover many new regulatory elements, but computational methods to effectively extract information from these datasets are still limited.RESULTS: We present here a supervised learning method to predict promoters and enhancers based on their unique chromatin modification signatures. We trained Hidden Markov models (HMMs) on the histone modification data for known promoters and enhancers, and then used the trained HMMs to identify promoter or enhancer like sequences in the human genome. Using a simulated annealing (SA) procedure, we searched for the most informative combination and the optimal window size of histone marks.CONCLUSION: Compared with the previous methods, the HMM method can capture the complex patterns of histone modifications particularly from the weak signals. Cross validation and scanning the ENCODE regions showed that our method outperforms the previous profile-based method in mapping promoters and enhancers. We also showed that including more histone marks can further boost the performance of our method. This observation suggests that the HMM is robust and is capable of integrating information from multiple histone marks. To further demonstrate the usefulness of our method, we applied it to analyzing genome wide ChIP-Seq data in three mouse cell lines and correctly predicted active and inactive promoters with positive predictive values of more than 80%. The software is available at http://http:/nash.ucsd.edu/chromatin.tar.gz.

KW - Animals

KW - Chromatin/genetics

KW - Computational Biology/methods

KW - Genome

KW - Histones/genetics

KW - Humans

KW - Markov Chains

KW - Promoter Regions, Genetic

KW - Regulatory Sequences, Nucleic Acid/genetics

U2 - 10.1186/1471-2105-9-547

DO - 10.1186/1471-2105-9-547

M3 - Journal article

C2 - 19094206

SN - 1471-2105

VL - 9

SP - 547

JO - B M C Bioinformatics

JF - B M C Bioinformatics

ER -

Prediction of regulatory elements in mammalian genomes using chromatin signatures

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater