Abstract
Biochemical networks are of great practical importance. The interaction of biological compounds in cells has been enforced to a proper understanding by the numerous bioinformatics projects, which contributed to a vast amount of biological information. The construction of biochemical systems (systems of chemical reactions), which include both topology and kinetic constants of the chemical reactions, is NP-hard and is a well-studied system biology problem. In this paper, we propose a hybrid architecture, which combines genetic programming and simulated annealing in order to generate and optimize both the topology (the network) and the reaction rates of a biochemical system. Simulations and analysis of an artificial model and three real models (two models and the noisy version of one of them) show promising results for the proposed method.
Similar content being viewed by others
References
Aarts E, Korst J, Michiels W (1989) Simulated annealing and Boltzmann machines: a stochastic approach to combinatorial optimization and neural computing. Wiley, New York, pp 188–202
Breitling R, Gilbert D, Heiner M, Orton R (2008) A structured approach for engineering of biochemical network models, illustrated for signalling pathways. Brief Bioinform 9(5):402–404
Calder M, Gilmore S, Hillston J (2004) Modelling the influence of RKIP on the ERK signalling pathway using the stochastic process algebra PEPA. In: Priami C et al (eds) Transactions on computational systems biology. Springer, Berlin, pp 1–23
Elliot W, Elliot D (2002) Biochemistry and molecular biology, 2nd edn. Oxford University Press, Oxford
Fogel G, Corne D (2003) Evolutionary computation in bioinformatics. Morgan Kaufmann, Los Altos, pp 256–276
Heaton JT (2008) Introduction to neural networks with java. Heaton Research Inc., Chesterfield, pp 245–266
Heiner M, Donaldson R, Gilbert D (2010) Petri nets for systems biology, symbolic systems biology: theory and methods. Jones & Bartlett Learning, Woods Hole, pp 61–97
Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220(4598):671–680
Kitagawa J, Iba H (2002) Identifying metabolic pathways and gene regulation networks with evolutionary algorithms. In: Fogel G, Corne D (eds) Evolutionary computation in bioinformatics. Elsevier, Amsterdam
Klingmueller U, Bergelson S, Hsiao JG, Lodish HF (1996) Multiple tyrosine residues in the cytosolic domain of the erythropoietin receptor promote activation of STAT5. Proc Natl Acad Sci USA 93:8324–8328 (JAK-STAT)
Kwang-Hyun C et al (2003) Mathematical modeling of the influence of RKIP on the ERK signaling pathway. In: Priami C (ed) Computational methods in systems biology (CMSB). LNCS, vol 2602. Springer, Berlin, Heidelberg, pp 127–141
Oltean M, Grosan C (2003) A Comparison of several linear genetic programming techniques. Complex Syst 14(4):285–313
Oltean M, Grosan C, Diosan L, Mihaila C (2009) Genetic programming with linear representation: a survey. Int J Artif Intell Tools 18(2):197–238
Rausanu S, Grosan C, Wu Z, Parvu O, Gilbert D (2013) Evolving biochemical systems. In: IEEE congress on evolutionary computation, IEEE CS, pp 1602–1609
Sakamoto E, Iba H (2000) Inferring a system of differential equations for a gene regulatory network by using genetic programming. In: Proceedings of the IEEE congress on evolutionary computation, IEEE Service Center, Piscataway, NJ
Voet D, Voet J, Pratt CW (2006) Fundamentals of biochemistry: life at the molecular level. Wiley, New York
Swameye I, Muller TG, Timmer J, Sandra O, Klingmuller U (2003) Identification of nucleocytoplasmic cycling as a remote sensor in cellular signaling by databased modelling. Proc Natl Acad Sci USA 100(3):1028–1033
Yeung K, Janosch P, McFerran B, Rose DW, Mischak H, Sedivy JM, Kolch W (2000) Mechanism of suppression of the Raf/MEK/extracellular signal regulated kinase pathway by the Raf kinase inhibitor protein. Mol Cell Biol 20(9):3079–3085
Yeung K, Seitz T, Li S, Janosch P, McFerran B, Kaiser C, Fee F, Katsanakis KD, Rose DW, Mischak H, Sedivy JM, Kolch W (1999) Suppression of Raf-1 kinase activity and MAP kinase signaling by RKIP. Nature 401:173–177
Wu Z, Grosan C, Gilbert D (2013) Empirical study of computational intelligence strategies for biochemical systems modelling. In: Nature inspired cooperative strategies for optimization (NICSO). Studies in computational intelligence, vol 512. Springer International Publishing, Switzerland, pp 245–260
Wu Z, Yang S, Gilbert D (2012) A hybrid approach to piece-wise modelling of biochemical systems. In: 12th international conference on parallel problem solving from nature, LNCS 7491/2012, pp 519–528
http://www-dssz.informatik.tu-cottbus.de/DSSZ/Software/Snoopy
Acknowledgments
S. Rausanu acknowledges support from ISDC Romania and C. Grosan acknowledges support from the Romanian National Authority for Scientific Research, CNDI–UEFISCDI, Project No. PN-II-PT-PCCA-2011-3.2-0917.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rausanu, S., Grosan, C., Wu, Z. et al. Computational models for inferring biochemical networks. Neural Comput & Applic 26, 299–311 (2015). https://doi.org/10.1007/s00521-014-1617-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1617-x