Classification of Biochemical Pathway Robustness with Neural Networks for Graphs

Dynamical properties of biochemical pathways are often assessed by performing numerical (ODE-based) or stochastic simulations. These methods are often computationally very expensive and require reliable quantitative parameters, such as kinetic constants and initial concentrations, to be available. Biochemical pathways are often represented as graphs, in which nodes and edges give a qualitative description of the modeled reactions, while node and edge labels provide quantitative details such as kinetic and stoichiometric parameters. In this paper we propose the use of a neural network for graphs to predict dynamical properties of biochemical pathways by relying only on the structure of their graph representation (expressed in terms of Petri nets). We test our new methodology on a dataset of 706 pathways downloaded from the BioModels database, focusing on the dynamical property of concentration robustness. The proposed model allows us to predict robustness directly from the pathway structure, by avoiding the burden of performing numerical or stochastic simulations. Moreover, once trained, the model could be applied to predicting robustness properties for pathways in which quantitative parameters are not available.