Application of adaptive-network-based fuzzy inference systems to the parameter optimization of a biochemical rule-based model.

In this study, the binding of allergens to antibody-receptor complexes was investigated. This process is important in understanding the allergic response. A BioNetGen model that simulates this process, combined with a novel method for encoding steric effects via the optimization of the cutoff distance and the rule binding rate, was previously developed. These parameters were optimized by fitting the model output to the output of a 3D simulation that explicitly represents molecular geometry. In this work, the parameters for the BioNetGen model were optimized using an adaptive-network-based fuzzy inference system in order to predict the rule rate and cutoff distance given a residual-sum-of-squares value or a probability distribution. The fuzzy systems were constructed using fuzzy c-means clustering with existing data from BioNetGen model parameter scans used as the training data. Fuzzy systems with various input data and number of clusters were created and tested. Their performance was analyzed with regard to the effective optimization of the rule-based model. The study found that the fuzzy system that uses a residual-sum-of-squares value as the input value performs acceptably well. However, the performance of the fuzzy systems that use probabilities as their input values performed inconsistently in the tests and need further development. This methodology could potentially be modified for use in fitting other biological models.