A statistical model for unwarping of 1-D

C.A. Glasbey, L. Vali, J. Gustafsson

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

A statistical model is proposed which relates density profiles in 1-D electrophoresis gels, such as those produced by pulsed-field gel electrophoresis (PFGE), to databases of profiles of known genotypes. The warp in each gel lane is described by a trend that is linear in its parameters plus a first-order autoregressive process, and density differences are modelled by a mixture of two normal distributions. Maximum likelihood estimates are computed efficiently by a recursive algorithm that alternates between dynamic time warping to align individual lanes and generalised-least-squares regression to ensure that the warp is smooth between lanes. The method, illustrated using PFGE of Escherichia coli O157 strains, automatically unwarps and classifies gel lanes, and facilitates manual identification of new genotypes
Original languageEnglish
Pages (from-to)4327-4242
Number of pages6
JournalElectrophoresis
Volume26
Issue number22
DOIs
Publication statusPublished - 2005

Fingerprint

Statistical Models
Pulsed Field Gel Electrophoresis
Gels
Electrophoresis
Genotype
Likelihood Functions
Escherichia coli O157
Normal Distribution
Least-Squares Analysis
Databases
Normal distribution
Escherichia coli
Maximum likelihood

Keywords

  • autoregressive process
  • Pulsed-field gel electrophoresis
  • mixture distribution
  • image warping
  • dynamic programming

Cite this

Glasbey, C. A., Vali, L., & Gustafsson, J. (2005). A statistical model for unwarping of 1-D. Electrophoresis, 26(22), 4327-4242. https://doi.org/10.1002/elps.200500365
Glasbey, C.A. ; Vali, L. ; Gustafsson, J. / A statistical model for unwarping of 1-D. In: Electrophoresis. 2005 ; Vol. 26, No. 22. pp. 4327-4242.
@article{fd6f083ed5d7440fadcabab27d2054d9,
title = "A statistical model for unwarping of 1-D",
abstract = "A statistical model is proposed which relates density profiles in 1-D electrophoresis gels, such as those produced by pulsed-field gel electrophoresis (PFGE), to databases of profiles of known genotypes. The warp in each gel lane is described by a trend that is linear in its parameters plus a first-order autoregressive process, and density differences are modelled by a mixture of two normal distributions. Maximum likelihood estimates are computed efficiently by a recursive algorithm that alternates between dynamic time warping to align individual lanes and generalised-least-squares regression to ensure that the warp is smooth between lanes. The method, illustrated using PFGE of Escherichia coli O157 strains, automatically unwarps and classifies gel lanes, and facilitates manual identification of new genotypes",
keywords = "autoregressive process, Pulsed-field gel electrophoresis, mixture distribution, image warping, dynamic programming",
author = "C.A. Glasbey and L. Vali and J. Gustafsson",
note = "[1] Vali, L., Wisely, K. A., Pearce, M. C., Turner, E. J., Knight, H. I., Smith, A. W., Amyes, S. G. B., Appl. Environ. Microbiol. 2004, 70, 5947–5954. [2] Barrett, T. J., Lior, H., Green, J. H., Khakharia, R., Wells, J. G., Bell, B. P., Greene, K. D., Lewis, J., Griffin, P. M., J. Clin. Microbiol. 1994, 32, 3013–3017. [3] Goutom, R. K., J. Clin. Microbiol. 1997, 35, 2977–2980. [4] Skovgaard, I. M., Jensen, K., Sondergaard, I., Electrophoresis 1995, 16, 1385–1389. [5] Glasbey, C. A., Horgan, G. W., Image Analysis for the Biological Sciences, Wiley, Chichester 1995. [6] Glasbey, C. A., Mardia, K. V., J. Appl. Stat. 1998 25, 155– 171. [7] Glasbey, C. A., Mardia, K. V., J. R. Stat. Soc. B 2001, 63, 465–514. [8] Glasbey, C. A., Young, M. J., Appl. Stat. 2002, 51, 209–221. [9] Hastie, T. J., Tibshirani, R. J., Generalized Additive Models, Chapman and Hall, London 1990. [10] Bellman, R., Dynamic Programming, Princeton University Press, Princeton 1957. [11] Sakoe, H., Chiba, S., IEEE T. Acous. Speech. 1978, 26, 43– 49. [12] Burr, D. J., IEEE T. Pattern Anal. 1983, 5, 554–559. [13] MacDonald, I. L., Zucchini, W., Hidden Markov and Other Models for Discrete-Valued Time Series, Chapman and Hall, London 1997. [14] Dowsey, A. W., Dunn, M. J., Yang, G.-Z., Proteomics 2003, 3, 1567–1596.",
year = "2005",
doi = "10.1002/elps.200500365",
language = "English",
volume = "26",
pages = "4327--4242",
journal = "Electrophoresis",
issn = "0173-0835",
number = "22",

}

Glasbey, CA, Vali, L & Gustafsson, J 2005, 'A statistical model for unwarping of 1-D', Electrophoresis, vol. 26, no. 22, pp. 4327-4242. https://doi.org/10.1002/elps.200500365

A statistical model for unwarping of 1-D. / Glasbey, C.A.; Vali, L.; Gustafsson, J.

In: Electrophoresis, Vol. 26, No. 22, 2005, p. 4327-4242.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A statistical model for unwarping of 1-D

AU - Glasbey, C.A.

AU - Vali, L.

AU - Gustafsson, J.

N1 - [1] Vali, L., Wisely, K. A., Pearce, M. C., Turner, E. J., Knight, H. I., Smith, A. W., Amyes, S. G. B., Appl. Environ. Microbiol. 2004, 70, 5947–5954. [2] Barrett, T. J., Lior, H., Green, J. H., Khakharia, R., Wells, J. G., Bell, B. P., Greene, K. D., Lewis, J., Griffin, P. M., J. Clin. Microbiol. 1994, 32, 3013–3017. [3] Goutom, R. K., J. Clin. Microbiol. 1997, 35, 2977–2980. [4] Skovgaard, I. M., Jensen, K., Sondergaard, I., Electrophoresis 1995, 16, 1385–1389. [5] Glasbey, C. A., Horgan, G. W., Image Analysis for the Biological Sciences, Wiley, Chichester 1995. [6] Glasbey, C. A., Mardia, K. V., J. Appl. Stat. 1998 25, 155– 171. [7] Glasbey, C. A., Mardia, K. V., J. R. Stat. Soc. B 2001, 63, 465–514. [8] Glasbey, C. A., Young, M. J., Appl. Stat. 2002, 51, 209–221. [9] Hastie, T. J., Tibshirani, R. J., Generalized Additive Models, Chapman and Hall, London 1990. [10] Bellman, R., Dynamic Programming, Princeton University Press, Princeton 1957. [11] Sakoe, H., Chiba, S., IEEE T. Acous. Speech. 1978, 26, 43– 49. [12] Burr, D. J., IEEE T. Pattern Anal. 1983, 5, 554–559. [13] MacDonald, I. L., Zucchini, W., Hidden Markov and Other Models for Discrete-Valued Time Series, Chapman and Hall, London 1997. [14] Dowsey, A. W., Dunn, M. J., Yang, G.-Z., Proteomics 2003, 3, 1567–1596.

PY - 2005

Y1 - 2005

N2 - A statistical model is proposed which relates density profiles in 1-D electrophoresis gels, such as those produced by pulsed-field gel electrophoresis (PFGE), to databases of profiles of known genotypes. The warp in each gel lane is described by a trend that is linear in its parameters plus a first-order autoregressive process, and density differences are modelled by a mixture of two normal distributions. Maximum likelihood estimates are computed efficiently by a recursive algorithm that alternates between dynamic time warping to align individual lanes and generalised-least-squares regression to ensure that the warp is smooth between lanes. The method, illustrated using PFGE of Escherichia coli O157 strains, automatically unwarps and classifies gel lanes, and facilitates manual identification of new genotypes

AB - A statistical model is proposed which relates density profiles in 1-D electrophoresis gels, such as those produced by pulsed-field gel electrophoresis (PFGE), to databases of profiles of known genotypes. The warp in each gel lane is described by a trend that is linear in its parameters plus a first-order autoregressive process, and density differences are modelled by a mixture of two normal distributions. Maximum likelihood estimates are computed efficiently by a recursive algorithm that alternates between dynamic time warping to align individual lanes and generalised-least-squares regression to ensure that the warp is smooth between lanes. The method, illustrated using PFGE of Escherichia coli O157 strains, automatically unwarps and classifies gel lanes, and facilitates manual identification of new genotypes

KW - autoregressive process

KW - Pulsed-field gel electrophoresis

KW - mixture distribution

KW - image warping

KW - dynamic programming

UR - http://dx.doi.org/10.1002/elps.200500365

U2 - 10.1002/elps.200500365

DO - 10.1002/elps.200500365

M3 - Article

VL - 26

SP - 4327

EP - 4242

JO - Electrophoresis

JF - Electrophoresis

SN - 0173-0835

IS - 22

ER -