Change-point modelling in biological sequences via the bayesian adaptive independent sampler

Georgy Sofronov

Change-point modelling in biological sequences via the bayesian adaptive independent sampler

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

Abstract

The change-point problem arises in wide variety of fields, including biomedical signal processing, speech and image processing, seismology, industry (e.g., fault detection) and financial mathematics. Multiple change-point models are also important in many biological applications and,particularly, in analysis of biomolecular sequences. We model genome sequences as a multiple change-point process, that is, a process in which the sequential data are separated into segments by an unknown number of change-points, with each segment supposed to have been generated by a different process. The parameters of the model are estimated by Adaptive Independent Samplers, which are adaptive Markov chain Monte Carlo methods based on the Independent Metropolis-Hastings algorithm. We discuss results of numerical experiments comparing different computing schemes.

Original language	English
Title of host publication	Computer communication and management
Subtitle of host publication	selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011), May 2-3, Sydney Australia
Editors	Zhang Ting
Place of Publication	Sydney
Publisher	IACSIT Press
Pages	122-126
Number of pages	5
ISBN (Print)	9789810886363
Publication status	Published - 2011
Event	International Conference on Telecommunication Technology and Applications - Sydney Duration: 2 May 2011 → 3 May 2011

Publication series

Name	International Proceedings of Computer Science and Information Technology
Publisher	IACSIT Press
ISSN (Print)	2010-460X

Conference

Conference	International Conference on Telecommunication Technology and Applications
City	Sydney
Period	2/05/11 → 3/05/11

Keywords

Markov chain Monte Carlo
adaptive methods
multiple change-point problem
comparative genomics

Cite this

Sofronov, G. (2011). Change-point modelling in biological sequences via the bayesian adaptive independent sampler. In Z. Ting (Ed.), Computer communication and management: selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011), May 2-3, Sydney Australia (pp. 122-126). (International Proceedings of Computer Science and Information Technology). IACSIT Press.

Sofronov, Georgy. / Change-point modelling in biological sequences via the bayesian adaptive independent sampler. Computer communication and management: selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011), May 2-3, Sydney Australia. editor / Zhang Ting. Sydney : IACSIT Press, 2011. pp. 122-126 (International Proceedings of Computer Science and Information Technology).

@inproceedings{9ec0232c496246e79fc444dd7d51160d,

title = "Change-point modelling in biological sequences via the bayesian adaptive independent sampler",

abstract = "The change-point problem arises in wide variety of fields, including biomedical signal processing, speech and image processing, seismology, industry (e.g., fault detection) and financial mathematics. Multiple change-point models are also important in many biological applications and,particularly, in analysis of biomolecular sequences. We model genome sequences as a multiple change-point process, that is, a process in which the sequential data are separated into segments by an unknown number of change-points, with each segment supposed to have been generated by a different process. The parameters of the model are estimated by Adaptive Independent Samplers, which are adaptive Markov chain Monte Carlo methods based on the Independent Metropolis-Hastings algorithm. We discuss results of numerical experiments comparing different computing schemes.",

keywords = "Markov chain Monte Carlo, adaptive methods, multiple change-point problem, comparative genomics",

author = "Georgy Sofronov",

year = "2011",

language = "English",

isbn = "9789810886363",

series = "International Proceedings of Computer Science and Information Technology",

publisher = "IACSIT Press",

pages = "122--126",

editor = "Zhang Ting",

booktitle = "Computer communication and management",

note = "International Conference on Telecommunication Technology and Applications ; Conference date: 02-05-2011 Through 03-05-2011",

}

Sofronov, G 2011, Change-point modelling in biological sequences via the bayesian adaptive independent sampler. in Z Ting (ed.), Computer communication and management: selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011), May 2-3, Sydney Australia. International Proceedings of Computer Science and Information Technology, IACSIT Press, Sydney, pp. 122-126, International Conference on Telecommunication Technology and Applications, Sydney, 2/05/11.

Change-point modelling in biological sequences via the bayesian adaptive independent sampler. / Sofronov, Georgy.

Computer communication and management: selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011), May 2-3, Sydney Australia. ed. / Zhang Ting. Sydney : IACSIT Press, 2011. p. 122-126 (International Proceedings of Computer Science and Information Technology).

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

TY - GEN

T1 - Change-point modelling in biological sequences via the bayesian adaptive independent sampler

AU - Sofronov, Georgy

PY - 2011

Y1 - 2011

N2 - The change-point problem arises in wide variety of fields, including biomedical signal processing, speech and image processing, seismology, industry (e.g., fault detection) and financial mathematics. Multiple change-point models are also important in many biological applications and,particularly, in analysis of biomolecular sequences. We model genome sequences as a multiple change-point process, that is, a process in which the sequential data are separated into segments by an unknown number of change-points, with each segment supposed to have been generated by a different process. The parameters of the model are estimated by Adaptive Independent Samplers, which are adaptive Markov chain Monte Carlo methods based on the Independent Metropolis-Hastings algorithm. We discuss results of numerical experiments comparing different computing schemes.

AB - The change-point problem arises in wide variety of fields, including biomedical signal processing, speech and image processing, seismology, industry (e.g., fault detection) and financial mathematics. Multiple change-point models are also important in many biological applications and,particularly, in analysis of biomolecular sequences. We model genome sequences as a multiple change-point process, that is, a process in which the sequential data are separated into segments by an unknown number of change-points, with each segment supposed to have been generated by a different process. The parameters of the model are estimated by Adaptive Independent Samplers, which are adaptive Markov chain Monte Carlo methods based on the Independent Metropolis-Hastings algorithm. We discuss results of numerical experiments comparing different computing schemes.

KW - Markov chain Monte Carlo

KW - adaptive methods

KW - multiple change-point problem

KW - comparative genomics

M3 - Conference proceeding contribution

SN - 9789810886363

T3 - International Proceedings of Computer Science and Information Technology

SP - 122

EP - 126

BT - Computer communication and management

A2 - Ting, Zhang

PB - IACSIT Press

CY - Sydney

T2 - International Conference on Telecommunication Technology and Applications

Y2 - 2 May 2011 through 3 May 2011

ER -

Sofronov G. Change-point modelling in biological sequences via the bayesian adaptive independent sampler. In Ting Z, editor, Computer communication and management: selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011), May 2-3, Sydney Australia. Sydney: IACSIT Press. 2011. p. 122-126. (International Proceedings of Computer Science and Information Technology).

Change-point modelling in biological sequences via the bayesian adaptive independent sampler

Abstract

Publication series

Conference

Keywords

Fingerprint

Cite this