Abstract
In this paper, a special-purpose qualitative model learning (QML) system using an immune-inspired algorithm is proposed to qualitatively reconstruct biological pathways. We choose a real-world application, the detoxification pathway of Methylglyoxal (MG), as a case study. First a converter is implemented to convert possible pathways to qualitative models. Then a general learning strategy is presented. To improve the scalability of the proposed QML system and make it adapt to future more complicated pathways, a modified clonal selection algorithm (CLONALG) is employed as the search strategy. The performance of this immune-inspired approach is compared with those of exhaustive search and two backtracking algorithms. The experimental results indicate that this immune-inspired approach can significantly improve the search efficiency when dealing with some complicated pathways with large-scale search spaces.
Similar content being viewed by others
Notes
This quantitative model has not been published yet. So it will not be presented in this paper.
Data obtained by Prof. Ian Booth’s research group at Aberdeen University.
Note that Eq. 5 is an arbitrary example given, and it is not relevant to the MG model.
Note we use the word “may” is because CLONALG is a randomised algorithm, although several successful experiments performed in previous work showed that CLONALG did improve the scalability of QML when learning these particular problems, it is not completely safe to say that CLONALG can improve the scalability of QML for learning any other problems in general. In addition, even for the previous successful experiments, when conditions and configurations of the problems are changed, we might get negative results. In summary, we cannot guarantee that CLONALG always (statistically) performs better than the deterministic algorithms in any conditions for any problem.
References
Bruce AM (2007) Jmorven: a framework for parallel non-constructive qualitative reasoning and fuzzy interval simulation. PhD thesis, Department of Computing Science, University of Aberdeen, Aberdeen
Bruce AM, Coghill GM (2005) Parallel fuzzy qualitative reasoning. In: Proceedings of the 19th international workshop on qualitative reasoning, Graz, Austria, pp 110–116
Coghill GM (1996) Mycroft: a framework for constraint based fuzzy qualitative reasoning. PhD thesis, Heriot-Watt University, Edinburgh
Coghill GM, Srinivasan A, King RD (2008) Qualitative system identification from imperfect data. J Artif Intell Res 32:825–877
Cooper R (1984) Metabolism of methylglyoxal in microorganisms. Annu Rev Microbiol 38:49–68
Cutello V, Narzisi G, Nicosia G, Pavone M (2005) An immunological algorithm for global numerical optimization. In: Artificial evolution, lecture notes in computer science, vol 3871. Springer, Lille, pp 284–295
de Almeida C, Ozyamak E, Miller S, de Moura A, Booth I, Grebogi C (2008) Modelling of methylglyoxal detoxification pathway in enteric bacteria. In: Abstract book of the 9th international conference on systems biology, Gǒteborg, p 170
de Castro LN, Timmis J (2002) An artificial immune network for multimodal function optimization. In: Proceedings of IEEE congress on evolutionary computation (CEC’02). IEEE Press, New York, pp 674–699
de Castro LN, Von Zuben FJ (2002) Learning and optimization using the clonal selection principle. In: IEEE transactions on evolutionary computation, special issue on artificial immune systems, vol 6. IEEE Press, New York, pp 239–251
Ferguson GP, Totemeyer S, MacLean MJ, Booth IR (1998) Methylglyoxal production in bacteria: suicide or survival? Arch Microbiol 170(4):209–218
Forbus KD (1997) Qualitative reasoning. In: Tucker AB (ed) The computer science and engineering handbook. CRC Press, Boca Raton, pp 715–733
Hau DT, Coiera EW (1993) Learning qualitative models of dynamic systems. Mach Learn 26:177–211
King RD, Garrett SM, Coghill GM (2005) On the use of qualitative reasoning to simulate and identify metabolic pathways. Bioinformatics 21(9):2017–2026
Kitano H (2002) Systems biology: a brief overview. Science 295(5560):1662–1664
Klipp E, Herwig R, Kowald A, Wierling C, Lehrach H (2005a) Systems biology in practice: concepts, implementation and application. Wiley-VCH, Weinheim
Klipp E, Nordlander B, Krűger R, Gennemark P, Hohmann S (2005b) Integrative model of the response of yeast to osmotic shock. Nat Biotechnol 23:975–982
Kuipers B (1989) Modeling and simulation with incomplete knowledge. Automatica 25(4):571–585
Kuipers B (1994) Qualitative reasoning: modeling and simulation with incomplete knowledge. MIT Press, Cambridge
Ljung L (1999) System identification—theory for the user, 2nd edn. Prentice Hall, Upper Saddle River
MacLean MJ, Ness LS, Ferguson GP, Booth IR (1998) The role of glyoxalase I in the detoxification of methylglyoxal and in the activation of the kefb k+ efflux system in Escherichia coli. Mol Microbiol 27(3):563–571
Michaelis L, Menten M (1913) Die kinetik der invertinwirkung. Biochem Z 49:333–369
Pang W (2009) Qml-morven: a framework for learning qualitative models. PhD thesis, University of Aberdeen, Aberdeen
Pang W, Coghill GM (2007a) Advanced experiments for learning qualitative compartment models. In: The 21st international workshop on qualitative reasoning, Aberystwyth, UK, pp 109–117
Pang W, Coghill GM (2007b) Modified clonal selection algorithm for learning qualitative compartmental models of metabolic systems. In: Thierens D (ed) Genetic and evolutionary computation conference (GECCO07). ACM Press, New York, pp 2887–2894
Richards BL, Kraan I, Kuipers B (1992) Automatic abduction of qualitative models. In: Proceedings of the national conference on artificial intelligence. AAAI, San Jose, pp 723–728
Say ACC, Kuru S (1996) Qualitative system identification: deriving structure from behavior. Artif Intell 83:75–141
Shen Q (1991) Fuzzy qualitative simulation and diagnosis of continuous dynamic systems. PhD thesis, Heriot-Watt University, Edinburgh
Shen Q, Leitch R (1993) Fuzzy qualitative simulation. IEEE Trans Syst Man Cybern 23(4):1038–1061
Varsek A (1991) Qualitative model evolution. In: Mylopoulos J, Reiter R (eds) Proceedings of the 12th international joint conference on artificial intelligence, vol 2. Sydney, Australia, pp 1311–1316
Wiegand M (1991) Constructive qualitative simulation of continuous dynamic systems. PhD thesis, Heriot-Watt University, Edinburgh
Acknowledgments
The authors would like to thank Dr Alessandro P.S. de Moura, Camilla de Almeida and Prof. Celso Grebogi for their suggestions about the modelling issues. We also thank Prof. Ian Booth and his research group for their explanations of the Detoxification Pathway of Methylglyoxal. WP and GMC are supported by the CRISP project (Combinatorial Responses In Stress Pathways) funded by the BBSRC (BB/F00513X/1) under the Systems Approaches to Biological Research (SABR) Initiative. WP is supported by the National Natural Science Foundation of China under grant No. 60703025, 60803052, 60873146, 60973092, 60903097; the Science-Technology Development Project from Jilin Province of China under Grant No. 20090116. WP is also partially supported by the National Engineering Laboratory for Druggable Gene and Protein Screening at Northeast Normal University, China.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Pang, W., Coghill, G.M. An immune-inspired approach to qualitative system identification of biological pathways. Nat Comput 10, 189–207 (2011). https://doi.org/10.1007/s11047-010-9212-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11047-010-9212-2