Extended Modelling of Platelet Calcium Signaling by Combined Recurrent Neural Network and Partial Least Squares Analyses
Platelets play critical roles in hemostasis and thrombosis. The platelet activation process is driven by agonist-induced rises in cytosolic [Ca2+]i, where the patterns of Ca2+ responses are still incompletely understood. In this study, we developed a number of techniques to model the [Ca2+]i curves of platelets from a single blood donor. Using a fluorescence ratio probe, the platelets were stimulated with a panel of agonists, i.e. thrombin, collagen, or CRP under various conditions, preventing extracellular Ca2+ entry, secondary mediator effects or Ca2+ reuptake into intracellular stores. To analyze the data, we developed two non-linear models, a multilayer perceptron (MLP) network and an autoregressive network with exogenous inputs (NARX). The trained networks accurately predicted the platelet [Ca2+]i curves in the presence of combinations of agonists and inhibitors, with the NARX model achieving an R2 up to 0.64 for trend prediction of unforeseen data. In addition, we used the same dataset for construction of a partial least square (PLS) linear regression model, which estimated the explained variance of each input. The NARX model demonstrated that good fits could be obtained for the calcium curves modelled, whereas the PLS model gave useful interpretable information on the importance of each variable. These modelling results can be used for the development of novel platelet [Ca2+]i-inhibiting drugs.