Abstract
This paper presents a novel approach towards showing how specific emergent multi-level behaviours in agent-based simulations (ABSs) can be quantified and used as the basis for inferring predictive models. First, we first show how behaviours at different levels can be specified and detected in a simulation using the complex event formalism. We then apply partial least squares regression to frequencies of these behaviours to infer models predicting the global behaviour of the system from lower-level behaviours. By comparing the mean predictive errors of models learned from different subsets of behavioural frequencies, we are also able to determine the relative importance of different types of behaviour and different resolutions. These methods are applied to ABSs of a novel agent-based model of cancer in the colonic crypt, with tumorigenesis as the global behaviour we wish to predict.
Similar content being viewed by others
Notes
The Singular Value Decomposition (SVD) is a widely used technique to decompose a matrix into several component matrices, exposing properties of the original matrix. Using the SVD, we can determine the rank of matrix, quantify the sensitivity of a linear system to numerical error, or obtain an optimal lower-rank approximation to the matrix.
References
Andreu P et al (2005). Crypt-restricted proliferation and commitment to the paneth cell lineage following APC loss in the mouse intestine. Development 132: 1443–1451.
Aoki M and Taketo M (2007). Adenomatous polyposis coli (apc): A multi-functional tumor suppressor gene. J Cell Sci 120: 3327–3335.
Bedau MA (2003). Downward causation and the autonomy of weak emergence. Principia 3: 5–50.
Boman BM et al (2004). Colonic crypt changes during adenoma development in familial adenomatous polypsis. Am J Pathol 165 (5): 1489–1498.
Bonabeau E and Dessalles JL (1997). Detection and emergence. Intellectica 2 (25): 85–94.
Boschetti F and Gray R (2007). Emergence and computability. Emergence: Complexity and Organisation 9: 120–130.
Chen CC, Nagl SB and Clack CD (2007). Specifying, detecting and analysing emergent behaviours in multi-level agent-based simulations. In: Wainer, G (ed.) Proceedings of the Summer Simulation Conference, Agent-directed simulation SCS.
Crutchfield JP (1994). The calculi of emergence: Computation, dynamics, and induction. Physica D 75: 11–54.
Deguet J, Demazeau Y and Magnin L (2006). Elements about the emergence issue—A survey of emergence definitions. ComPlexUs 3: 24–31.
Fodde R et al (1994). A targeted chain-termination mutation in the mouse apc gene results in multiple intestinal tumors. Proc Natl Acad Sci USA 91: 8969–8973.
Geladi P and Kowlaski BR (1985). Partial least-squares regression: A tutorial. Anal Chim Acta 185: 1–17.
Giles RH, van Es JH and Clevers H (2003). Caught up in a wnt storm: Wnt signaling in cancer. Biochim biophys acta 1653 (1): 1–24.
Gunji Y-P and Kamiura M (2004). Observational heterarchy enhancing active coupling. Physica D 198 (1–2): 74–105.
Gunji Y-P, Sasai K and Wakisaka S (2008). Abstract heterarchy: Time/state-scale re-entrant form. Biosystems 91 (1): 13–33.
Holland J (2000). Emergence—From Chaos to Order. Oxford University Press, Oxford.
Ilyas M (2005). Wnt signalling and the mechanistic basis of tumour development. J Pathol 205 (2): 130–144.
Krobath K et al (2007). Lack of adenomatous polposis coli protein correlates with a decrease in cell migration and overall changes in microtuble stability. Mol Biol Cell 18 (3): 910–918.
Kubik A (2003). Toward a formalization of emergence. Artif Life 9: 41–66.
Lamprecht SA and Lipkin M (2002). Migrating colonic crypt epithelial cells: Primary targets for transformation. Carcinogenesis 23 (11): 1777–1780.
Morrison SJ and Kimble J (2006). Asymmetric and symmetric stem-cell divisions in development and cancer. Nature 441 (7097): 1068–1074.
Oshima M et al (1995). Loss of apc heterozygosity and abnormal tissue binding in nascent intestinal polyps in mice carrying a truncated apc gene. Proc Natl Acad Sci USA 92: 4482–4486.
Pearl J (2000). Causality: Models, Reasoning and Inference. Cambridge University Press, Cambridge.
Pearson K (1901). On lines and planes of closest fit to systems of points in space. Philos Mag 2 (6): 559–572.
Rasmussen S et al (2001). Ansatz for dynamical hierarchies. Artif Life 7: 329–353.
Ryan A (2007). Emergence is coupled to scope, not level. Nonlinear Sci, Complexity 13 (2): 67–77.
Sansom OJ et al (2004). Loss of apc in vivo immediately perturbs wnt signalling, differentiation, and migration. Genes Dev 18: 1385–1390.
Williamson J (2007). Causality. In: Gabbay DM and Guenther F (eds). Handbook of Philosophical Logic. Springer: Dordrecht, The Netherlands, pp 89–120.
Acknowledgements
Chih-Chun Chen acknowledges the advisory support of Christopher D. Clack and Sylvia B. Nagl as part of a multi-disciplinary collaboration between the departments of Computer Science and Oncology at UCL. David R. Hardoon acknowledges financial support from the EPSRC project Le Strum, (http://www.lestrum.org.) EP-D063612-1 and from the EU project PinView, (http://www.pineview.eu.) FP7-216529.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Chen, CC., Hardoon, D. Learning from multi-level behaviours in agent-based simulations: a Systems Biology application. J Simulation 4, 196–203 (2010). https://doi.org/10.1057/jos.2009.30
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1057/jos.2009.30