CASyM winter school of Systems Medicine took place between March 29th and April 1st 2017 in Ljubljana, Slovenia and is entitled »The 3rd SysBioMed hands-on tutorial: Systems Medicine Approaches in Personalized Medicine«
1Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
Introduction: Fuzzy modelling is an approach to cope with uncertain data . Models are built upon linguistic description, where for each linguistic variable its collection of fuzzy values and a membership functions are defined. A set of fuzzy rules has to be constructed to describe the relations between linguistic variables. Here we present an approach for automatic fuzzy model generation from known data.
Results: The signaling pathway of the MAPK is a phosphorylation cascade . The rules for a single phosphorylation cycle are automatically defined using a fuzzy c-means clustering algorithm. Here, data is firstly collected from a deterministic model. Experimental data could also be used. Data is generated by several runs of the deterministic model using different initial conditions. It needs to be resampled to be evenly distributed. The resampled data is then used as an input for the clustering algorithm. It is divided into three clusters that define the fuzzy rules. The so defined fuzzy model provides results that correspond to the expected system’s behaviour.
Conclusions: In order to construct a fuzzy model of the MAPK signaling pathway, the phosphorylation modules are sequentially bound to form a cascade. Since the fuzzy rules were generated generically, only small modifications of the modules are needed besides the definition of systems initial conditions. Namely, additional fitting of the membership functions is needed. For this purpose, general optimization approaches such as genetic algorithms and simulated annealing are used. The proposed approach can be thus efficiently applied to the reconstruction of computational models from the experimental data.
References: 1. J. Bordon, Modeliranje enostavnih bioloških preklopnih sistemov z uporabo mehke logike in razširjenih Petrijevih mrež, PhD dissertation, Univerza v Ljubljani (2017). 2. M. Kochańczyk et al., Relaxation oscillations and hierarchy of feedbacks in MAPK signaling, Sci Rep 7 (2017) 38244.
2006 - University of Ljubljana, Faculty of Medicine, Center for Functional Genomics and Bio-chips.