article

Modeling of gene regulatory networks with hybrid differential evolution and particle swarm optimization

Authors:

Ganesh K. Venayagamoorthy,

Donald C. Wunsch, IIAuthors Info & Claims

Neural Networks, Volume 20, Issue 8

Pages 917 - 927

https://doi.org/10.1016/j.neunet.2007.07.002

Published: 01 October 2007 Publication History

Abstract

In the last decade, recurrent neural networks (RNNs) have attracted more efforts in inferring genetic regulatory networks (GRNs), using time series gene expression data from microarray experiments. This is critically important for revealing fundamental cellular processes, investigating gene functions, and understanding their relations. However, RNNs are well known for training difficulty. Traditional gradient descent-based methods are easily stuck in local minima and the computation of the derivatives is also not always possible. Here, the performance of three evolutionary-swarm computation technology-based methods, known as differential evolution (DE), particle swarm optimization (PSO), and the hybrid of DE and PSO (DEPSO), in training RNNs is investigated. Furthermore, the gene networks are reconstructed via the identification of the gene interactions, which are explained through corresponding connection weight matrices. The experimental results on two data sets studied in this paper demonstrate that the DEPSO algorithm performs better in RNN training. Also, the RNN-based model can provide meaningful insight in capturing the nonlinear dynamics of genetic networks and revealing genetic regulatory interactions.

References

[1]

A Bayesian framework for the analysis of microarray expression data: Regularized t-test and statistical inferences of gene changes. Bioinformatics. v17. 509-519.

[2]

Analyzing time series gene expression data. Bioinformatics. v20 i16. 2493-2503.

[3]

Hybrid PSO-EA algorithm for training feedforward and recurrent neural networks for challenging problems. In: Wang, F., Liu, D. (Eds.), Computational intelligence: Theory and application, World Scientific Publishing, Hackensack, NJ.

[4]

Modeling and simulation of genetic regulatory systems: A literature review. Journal of Computational Biology. v9. 67-103.

[5]

delValle, Y., Venayagamoorthy, G., Mohagheghi, S., Hernandez, J., & Harley, R. (2007). Particle swarm optimization: Basic concepts, variants and applications in power systems. IEEE Transactions on Evolutionary Computation, in press (

[6]

D'haeseleer, P. (2000). Reconstructing gene network from large scale gene expression data. Dissertation. University of New Mexico

[7]

Genetic network inference: From co-expression clustering to reverse engineering. Bioinformatics. v16 i8. 707-726.

[8]

D'haeseleer, P., Wen, X., Fuhrman, S., & Somogyi, R. (1999). Linear modeling of mRNA expression levels during CNS development and injury. In Proceedings of the pacific symposium biocomputing (pp. 41-52)

[9]

Doctor, S., Venayagamoorthy, G., & Gudise, V. (2004). Optimal PSO for collective robotic search applications. In Proceedings of congress on evolutionary computation 2004 (pp. 1390-1395)

[10]

Eberhart, R., & Shi, Y. (2001). Particle swarm optimization: Developments, applications and recourses. In Proceedings of the 2001 congress on evolutionary computation (pp. 81-86)

[11]

DNA arrays for analysis of gene expression. Methods Enzymol. v303. 179-205.

[12]

Computational intelligence: An introduction. John Wiley, Chichester.

[13]

Feoktistov, V., & Janaqi, S. (2004). Generalization of the strategies in differential evolution. In Proceedings of 18th international parallel and distributed processing symposium (pp. 165-170)

[14]

An introduction to simulated evolutionary optimization. IEEE Transactions on Neural Networks. v5 i1. 3-14.

[15]

Using Bayesian networks to analyze expression data. Journal of Computational Biology. v7. 601-620.

[16]

Gudise, V., & Venayagamoorthy, G. (2003). Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks. In Proceedings of the 2003 IEEE swarm intelligence symposium (pp. 110-117)

[17]

Hallinan, J., & Jackway, P. (2005). Network motifs, feedback loops and the dynamics of genetic regulatory networks. In Proceedings of the IEEE symposium on computational intelligence in bioinformatics and computational biology (pp. 1-7)

[18]

Neural networks: A comprehensive foundation. 2nd ed. Prentice Hall, Upper Saddle River, NJ.

[19]

Sensitivity and specificity of inferring genetic regulatory interactions from microarray experiments with dynamic Bayesian networks. Bioinformatics. v19 i17. 2271-2282.

[20]

Jaeger, H. (2002). A tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the echo state network approach. GMD report 159. German National Research Center for Information Technology

[21]

A hybrid of genetic algorithm and particle swarm optimization for recurrent network design. IEEE Transaction on Systems, Man, and Cybernetics, Part B. v34 i2. 997-1006.

[22]

The origins of order: Self-organization and selection in evolution. Oxford University Press, New York, NY.

[23]

Discovering gene networks with a neural-genetic hybrid. IEEE/ACM Transactions on Computational Biology and Bioinformatics. v2 i3. 231-242.

[24]

Swarm intelligence. Academic Press, San Diego, CA.

[25]

A field guide to dynamical recurrent networks. IEEE Press, New York, NY.

[26]

Gene regulation: A eukaryotic perspective. 5th ed. Taylor & Francis Ltd, New York, NY.

[27]

Liang, S., Fuhrman, S., & Somogyi, R. (1998). Reveal: A general reverse engineering algorithm for inference of genetic network architectures. In Proceedings of the pacific symposium biocomputing (pp. 18-29)

[28]

High density synthetic oligonucleotide arrays. Nature Genetics. v21. 20-24.

[29]

Analyzing microarray gene expression data. John Wiley & Sons, Hoboken, NJ.

[30]

From co-expression to co-regulation: An approach to inferring transcriptional regulation among gene classes from large-scale expression data. In: Solla, S., Leen, T., Müller, K. (Eds.), Advances in neural information processing systems, Vol. 12. MIT Press, Cambridge, MA. pp. 928-934.

[31]

Murphy, K., & Mian, S. (1999). Modeling gene expression data using dynamic Bayesian networks. Technical report. Berkeley: Computer Science Division, University of California

[32]

Regulation of gene expression. Human Press, Totowa, NJ.

[33]

Gene networks inference using dynamic Bayesian networks. Bioinformatics. v19 iSuppl. 2. ii138-ii148.

[34]

Differential evolution: A practical approach to global optimization. Springer-Verlag, Berlin.

[35]

Assigning numbers to the arrows: Parameterizing a gene regulation network by using accurate expression kinetics. Proceedings of the National Academic Sciences USA. v99 i16. 10555-10560.

[36]

Quantitative monitoring of gene expression patterns with a complementary DNA microarray. Science. v270 i5235. 467-470.

[37]

Settles, M., Rodebaugh, B., & Soule, T. (2003). Comparison of genetic algorithm and particle swarm optimizer when evolving a recurrent neural network. In Proceedings of the genetic and evolutionary computation conference 2003 (pp. 148-149)

[38]

From Boolean to probabilistic Boolean networks as models of genetic regulatory networks. Proceedings of the IEEE. v90 i11. 1778-1792.

[39]

Evaluating functional network inference using simulations of complex biological systems. Bioinformatics. v18 iSuppl. 1. S216-S224.

[40]

Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization. v11. 341-359.

[41]

Estimating gene networks from gene expression data by combining Bayesian network model with promoter element detection. Bioinformatics. v19 iSuppl. 2. ii227-ii236.

[42]

van Someren, E., Wessels, L., & Reinders, M. (2000). Linear modeling of genetic networks from experimental data. In Proceedings of the 8th international conference on intelligent systems for molecular biology (pp. 355-366)

[43]

van Someren, E., Wessels, L., & Reinders, M. (2001). Genetic network models: A comparative study. In Proceedings of SPIE, micro-arrays: Optical technologies and informatics (pp. 236-247)

[44]

van Someren, E., Wessels, L., Reinders, M., & Backer, E. (2001). Robust genetic network modeling by adding noisy data. In Proceedings of the 2001 IEEE-EURASIP workshop on nonlinear signal and image processing

[45]

Neural network model of gene expression. FASEB Journal. v15. 846-854.

[46]

Coarse-grained reverse engineering of genetic regulatory networks. Biosystems. v55. 129-136.

[47]

Modeling genetic regulatory dynamics in neural development. Journal of Computational Biology. v8. 429-442.

[48]

Weaver, D., Workman, C., & Stormo, G. (1999). Modeling regulatory networks with weight matrices. In Proceedings of the pacific symposium on biocomputing (pp. 112-123)

[49]

Backpropagation through time: What it does and how to do it. Proceedings of IEEE. v78 i10. 1550-1560.

[50]

Comparative evaluation of reverse engineering gene regulatory networks with relevance networks, graphical Gaussian models and Bayesian networks. Bioinformatics. v22 i20. 2523-2531.

[51]

Xu, R., Hu, X., & Wunsch, D., II (2004a). Inference of genetic regulatory networks from time series gene expression data. In Proceedings of international joint conference on neural networks (pp. 1215-1220)

[52]

Xu, R., Hu, X., & Wunsch, D., II (2004b). Inference of genetic regulatory networks with recurrent neural network models. In Proceedings of the 26th annual international conference of IEEE engineering in medicine and biology society (pp. 2905-2908)

[53]

A study of particle swarm optimization in gene regulatory networks inference. In: Wang, J., Yi, Z., Zurada, J., Lu, B., Yin, H. (Eds.), Advances in neural networks - ISNN 2006: Third international symposium on neural networks, Springer, Berlin, Heidelberg. pp. 648-653.

[54]

Survey of clustering algorithms. IEEE Transactions on Neural Networks. v16 i3. 645-678.

[55]

Xu, R., Wunsch, D., II, & Frank, R. (2007). Inference of genetic regulatory networks with recurrent neural network models using particle swarm optimization. IEEE Transactions on Computational Biology and Bioinformatics, in press (

[56]

Evolving artificial neural networks. Proceedings of the IEEE. v87 i9. 1423-1447.

[57]

Advances to Bayesian network inference for generating causal networks from observational biological data. Bioinformatics. v20 i18. 3594-3603.

[58]

Zhang, W., & Xie, X. (2003). DEPSO: Hybrid particle swarm with differential evolution operator. In Proceedings of IEEE international conference on systems, man, and cybernetics (pp. 3816-3821)

Cited By

Khan ADutta ASaha GPal R(2020)A Hybrid Methodology for the Reverse Engineering of Gene Regulatory Networks2020 IEEE Congress on Evolutionary Computation (CEC)10.1109/CEC48606.2020.9185866(1-8)Online publication date: 19-Jul-2020
https://dl.acm.org/doi/10.1109/CEC48606.2020.9185866
Liu LLiu J(2020)Reconstructing gene regulatory networks via memetic algorithm and LASSO based on recurrent neural networksSoft Computing - A Fusion of Foundations, Methodologies and Applications10.1007/s00500-019-04185-y24:6(4205-4221)Online publication date: 1-Mar-2020
https://dl.acm.org/doi/10.1007/s00500-019-04185-y
Chen ZKuo R(2019)Combining SOM and evolutionary computation algorithms for RBF neural network trainingJournal of Intelligent Manufacturing10.1007/s10845-017-1313-730:3(1137-1154)Online publication date: 1-Mar-2019
https://dl.acm.org/doi/10.1007/s10845-017-1313-7
Show More Cited By

Index Terms

Modeling of gene regulatory networks with hybrid differential evolution and particle swarm optimization
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches

Recommendations

Inference of Genetic Regulatory Networks with Recurrent Neural Network Models Using Particle Swarm Optimization

Genetic regulatory network inference is critically important for revealing fundamental cellular processes, investigating gene functions, and understanding their relations. The availability of time series gene expression data makes it possible to ...
Optimized neural network ensemble by combination of particle swarm optimization and differential evolution
ISNN'13: Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I

The Neural-Network Ensemble (NNE) is a very effective method where the outputs of separately trained neural networks are combined to perform the prediction. In this paper, we introduce the improved Neural Network Ensemble (INNE) in which each component ...
A recurrent fuzzy neural model of a gene regulatory network for knowledge extraction using differential evolution
CEC'09: Proceedings of the Eleventh conference on Congress on Evolutionary Computation

A gene regulatory network describes the influence of genes over others. This paper attempts to model gene regulatory network by a recurrent neural net with fuzzy membership distribution of weights. A cost function is designed to match the response of ...

Comments

Information & Contributors

Information

Published In

cover image Neural Networks

Neural Networks Volume 20, Issue 8

October, 2007

80 pages

ISSN:0893-6080

Issue’s Table of Contents

Copyright © Elsevier Ltd © 2007.

Publisher

Elsevier Science Ltd.

United Kingdom

Publication History

Published: 01 October 2007

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

18
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 28 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Khan ADutta ASaha GPal R(2020)A Hybrid Methodology for the Reverse Engineering of Gene Regulatory Networks2020 IEEE Congress on Evolutionary Computation (CEC)10.1109/CEC48606.2020.9185866(1-8)Online publication date: 19-Jul-2020
https://dl.acm.org/doi/10.1109/CEC48606.2020.9185866
Liu LLiu J(2020)Reconstructing gene regulatory networks via memetic algorithm and LASSO based on recurrent neural networksSoft Computing - A Fusion of Foundations, Methodologies and Applications10.1007/s00500-019-04185-y24:6(4205-4221)Online publication date: 1-Mar-2020
https://dl.acm.org/doi/10.1007/s00500-019-04185-y
Chen ZKuo R(2019)Combining SOM and evolutionary computation algorithms for RBF neural network trainingJournal of Intelligent Manufacturing10.1007/s10845-017-1313-730:3(1137-1154)Online publication date: 1-Mar-2019
https://dl.acm.org/doi/10.1007/s10845-017-1313-7
Berrones AJiménez EAlcorta-García MAlmaguer FPeña B(2016)Parameter inference of general nonlinear dynamical models of gene regulatory networks from small and noisy time seriesNeurocomputing10.1016/j.neucom.2015.10.095175:PA(555-563)Online publication date: 29-Jan-2016
https://dl.acm.org/doi/10.1016/j.neucom.2015.10.095
Raza KAlam M(2016)Recurrent neural network based hybrid model for reconstructing gene regulatory networkComputational Biology and Chemistry10.1016/j.compbiolchem.2016.08.00264:C(322-334)Online publication date: 1-Oct-2016
https://dl.acm.org/doi/10.1016/j.compbiolchem.2016.08.002
Wu SWu C(2015)A bio-inspired optimization for inferring interactive networksExpert Systems with Applications: An International Journal10.1016/j.eswa.2014.11.03942:6(3253-3267)Online publication date: 15-Apr-2015
https://dl.acm.org/doi/10.1016/j.eswa.2014.11.039
Hui ZFei Y(2014)A Novel Fuzzy Clustering Recommendation Algorithm Based On PsoCybernetics and Information Technologies10.2478/cait-2014-004814:5(108-117)Online publication date: 1-Dec-2014
https://dl.acm.org/doi/10.2478/cait-2014-0048
Ling GGuan ZHe DLiao RZhang X(2014)Stability and bifurcation analysis of new coupled repressilators in genetic regulatory networks with delaysNeural Networks10.1016/j.neunet.2014.08.01260:C(222-231)Online publication date: 1-Dec-2014
https://dl.acm.org/doi/10.1016/j.neunet.2014.08.012
Fathi AMozaffari A(2014)Modeling a shape memory alloy actuator using an evolvable recursive black-box and hybrid heuristic algorithms inspired based on the annual migration of salmons in natureApplied Soft Computing10.1016/j.asoc.2013.03.01914(229-251)Online publication date: 1-Jan-2014
https://dl.acm.org/doi/10.1016/j.asoc.2013.03.019
Zhou YLi XGao L(2013)A differential evolution algorithm with intersect mutation operatorApplied Soft Computing10.1016/j.asoc.2012.08.01413:1(390-401)Online publication date: 1-Jan-2013
https://dl.acm.org/doi/10.1016/j.asoc.2012.08.014
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents