Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems

Zhouyi Xu, Xiaodong Cai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The weighted stochastic simulation algorithm (wSSA) recently developed by Kuwahara and Mura and the refined wSSA proposed by Gillespie et al. based on the importance sampling technique open the door for efficient estimation of the probability of rare events in biochemical reaction systems. However, both the wSSA and the refined wSSA do not provide a systematic method for selecting the values of importance sampling parameters but require some initial guessing for those values. In this paper, we develop a systematic method for selecting the values of importance sampling parameters for the wSSA. Numerical results demonstrate that our parameter selection method can substantially improve the performance of the wSSA in terms of simulation efficiency and accuracy.

Original languageEnglish
Title of host publication2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010
DOIs
StatePublished - Dec 1 2010
Event2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010 - Cold Spring Harbor, NY, United States
Duration: Nov 10 2010Nov 12 2010

Other

Other2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010
CountryUnited States
CityCold Spring Harbor, NY
Period11/10/1011/12/10

Fingerprint

Importance sampling

Keywords

  • Biochemical reaction system
  • Rare event
  • Stochastic simulation

ASJC Scopus subject areas

  • Genetics
  • Signal Processing

Cite this

Xu, Z., & Cai, X. (2010). Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems. In 2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010 [5719686] https://doi.org/10.1109/GENSIPS.2010.5719686

Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems. / Xu, Zhouyi; Cai, Xiaodong.

2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010. 2010. 5719686.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xu, Z & Cai, X 2010, Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems. in 2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010., 5719686, 2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010, Cold Spring Harbor, NY, United States, 11/10/10. https://doi.org/10.1109/GENSIPS.2010.5719686
Xu Z, Cai X. Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems. In 2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010. 2010. 5719686 https://doi.org/10.1109/GENSIPS.2010.5719686
Xu, Zhouyi ; Cai, Xiaodong. / Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems. 2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010. 2010.
@inproceedings{cc8ad0904aa14160a3c82e11750e34db,
title = "Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems",
abstract = "The weighted stochastic simulation algorithm (wSSA) recently developed by Kuwahara and Mura and the refined wSSA proposed by Gillespie et al. based on the importance sampling technique open the door for efficient estimation of the probability of rare events in biochemical reaction systems. However, both the wSSA and the refined wSSA do not provide a systematic method for selecting the values of importance sampling parameters but require some initial guessing for those values. In this paper, we develop a systematic method for selecting the values of importance sampling parameters for the wSSA. Numerical results demonstrate that our parameter selection method can substantially improve the performance of the wSSA in terms of simulation efficiency and accuracy.",
keywords = "Biochemical reaction system, Rare event, Stochastic simulation",
author = "Zhouyi Xu and Xiaodong Cai",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/GENSIPS.2010.5719686",
language = "English",
isbn = "9781612847924",
booktitle = "2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010",

}

TY - GEN

T1 - Importance sampling method for efficient estimation of the probability of rare events in biochemical reaction systems

AU - Xu, Zhouyi

AU - Cai, Xiaodong

PY - 2010/12/1

Y1 - 2010/12/1

N2 - The weighted stochastic simulation algorithm (wSSA) recently developed by Kuwahara and Mura and the refined wSSA proposed by Gillespie et al. based on the importance sampling technique open the door for efficient estimation of the probability of rare events in biochemical reaction systems. However, both the wSSA and the refined wSSA do not provide a systematic method for selecting the values of importance sampling parameters but require some initial guessing for those values. In this paper, we develop a systematic method for selecting the values of importance sampling parameters for the wSSA. Numerical results demonstrate that our parameter selection method can substantially improve the performance of the wSSA in terms of simulation efficiency and accuracy.

AB - The weighted stochastic simulation algorithm (wSSA) recently developed by Kuwahara and Mura and the refined wSSA proposed by Gillespie et al. based on the importance sampling technique open the door for efficient estimation of the probability of rare events in biochemical reaction systems. However, both the wSSA and the refined wSSA do not provide a systematic method for selecting the values of importance sampling parameters but require some initial guessing for those values. In this paper, we develop a systematic method for selecting the values of importance sampling parameters for the wSSA. Numerical results demonstrate that our parameter selection method can substantially improve the performance of the wSSA in terms of simulation efficiency and accuracy.

KW - Biochemical reaction system

KW - Rare event

KW - Stochastic simulation

UR - http://www.scopus.com/inward/record.url?scp=79952800776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952800776&partnerID=8YFLogxK

U2 - 10.1109/GENSIPS.2010.5719686

DO - 10.1109/GENSIPS.2010.5719686

M3 - Conference contribution

SN - 9781612847924

BT - 2010 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2010

ER -