Modelling gene expression time-series with radial basis function neural networks

Caria S. Möller-Levet; Hujun Yin; Kwang Hyun Cho; Olaf Wolkenhauer

doi:10.1109/IJCNN.2004.1380110

Modelling gene expression time-series with radial basis function neural networks

Caria S. Möller-Levet^*, Hujun Yin, Kwang Hyun Cho, Olaf Wolkenhauer

^*Corresponding author for this work

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

6 Scopus citations

Abstract

Gene expression time-series are discrete, noisy, short and usually unevenly sampled. Most existing methods used to compare expression profiles operate directly on the time points. While modelling the profiles can lead to more generalised, smooth characterisation of gene expressions. In this paper a Radial Basis Function neural network is employed to model gene expression time-series. The Orthogonal Least Square method, used for selection of centres, is further combined with a width optimisation scheme. The experiments on a number of expression datasets have shown the advantages of the approach in terms of generalisation and approximation. The results on known datasets have indeed coincided with biological interpretations.

Original language	English
Title of host publication	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Pages	1191-1195
Number of pages	5
DOIs	https://doi.org/10.1109/IJCNN.2004.1380110
State	Published - 2004
Externally published	Yes
Event	2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary Duration: 25 Jul 2004 → 29 Jul 2004

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	2
ISSN (Print)	1098-7576

Conference

Conference	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Country/Territory	Hungary
City	Budapest
Period	25/07/04 → 29/07/04

Access to Document

10.1109/IJCNN.2004.1380110

Cite this

Möller-Levet, C. S., Yin, H., Cho, K. H., & Wolkenhauer, O. (2004). Modelling gene expression time-series with radial basis function neural networks. In 2004 IEEE International Joint Conference on Neural Networks - Proceedings (pp. 1191-1195). (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 2). https://doi.org/10.1109/IJCNN.2004.1380110

@inproceedings{1b061f4ab463433785a2988d227c1d36,

title = "Modelling gene expression time-series with radial basis function neural networks",

abstract = "Gene expression time-series are discrete, noisy, short and usually unevenly sampled. Most existing methods used to compare expression profiles operate directly on the time points. While modelling the profiles can lead to more generalised, smooth characterisation of gene expressions. In this paper a Radial Basis Function neural network is employed to model gene expression time-series. The Orthogonal Least Square method, used for selection of centres, is further combined with a width optimisation scheme. The experiments on a number of expression datasets have shown the advantages of the approach in terms of generalisation and approximation. The results on known datasets have indeed coincided with biological interpretations.",

author = "M{\"o}ller-Levet, \{Caria S.\} and Hujun Yin and Cho, \{Kwang Hyun\} and Olaf Wolkenhauer",

year = "2004",

doi = "10.1109/IJCNN.2004.1380110",

language = "English",

isbn = "0780383591",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "1191--1195",

booktitle = "2004 IEEE International Joint Conference on Neural Networks - Proceedings",

note = "2004 IEEE International Joint Conference on Neural Networks - Proceedings ; Conference date: 25-07-2004 Through 29-07-2004",

}

Möller-Levet, CS, Yin, H, Cho, KH & Wolkenhauer, O 2004, Modelling gene expression time-series with radial basis function neural networks. in 2004 IEEE International Joint Conference on Neural Networks - Proceedings. IEEE International Conference on Neural Networks - Conference Proceedings, vol. 2, pp. 1191-1195, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 25/07/04. https://doi.org/10.1109/IJCNN.2004.1380110

Modelling gene expression time-series with radial basis function neural networks. / Möller-Levet, Caria S.; Yin, Hujun; Cho, Kwang Hyun et al.
2004 IEEE International Joint Conference on Neural Networks - Proceedings. 2004. p. 1191-1195 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 2).

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

TY - GEN

T1 - Modelling gene expression time-series with radial basis function neural networks

AU - Möller-Levet, Caria S.

AU - Yin, Hujun

AU - Cho, Kwang Hyun

AU - Wolkenhauer, Olaf

PY - 2004

Y1 - 2004

N2 - Gene expression time-series are discrete, noisy, short and usually unevenly sampled. Most existing methods used to compare expression profiles operate directly on the time points. While modelling the profiles can lead to more generalised, smooth characterisation of gene expressions. In this paper a Radial Basis Function neural network is employed to model gene expression time-series. The Orthogonal Least Square method, used for selection of centres, is further combined with a width optimisation scheme. The experiments on a number of expression datasets have shown the advantages of the approach in terms of generalisation and approximation. The results on known datasets have indeed coincided with biological interpretations.

AB - Gene expression time-series are discrete, noisy, short and usually unevenly sampled. Most existing methods used to compare expression profiles operate directly on the time points. While modelling the profiles can lead to more generalised, smooth characterisation of gene expressions. In this paper a Radial Basis Function neural network is employed to model gene expression time-series. The Orthogonal Least Square method, used for selection of centres, is further combined with a width optimisation scheme. The experiments on a number of expression datasets have shown the advantages of the approach in terms of generalisation and approximation. The results on known datasets have indeed coincided with biological interpretations.

UR - https://www.scopus.com/pages/publications/10944227262

U2 - 10.1109/IJCNN.2004.1380110

DO - 10.1109/IJCNN.2004.1380110

M3 - Conference contribution

AN - SCOPUS:10944227262

SN - 0780383591

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1191

EP - 1195

BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

T2 - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

Y2 - 25 July 2004 through 29 July 2004

ER -

Modelling gene expression time-series with radial basis function neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this