A system of recurrent neural networks for modularising, parameterising and dynamic analysis of cell signalling networks. (March 2017)

• Record Type: Journal Article
• Authors: Samarasinghe, S.; Ling, H.
• Is Part Of: Bio systems. Volume 153/154(2017)
• Page Start: 6
• Page End: 25
• Publication Date: 2017-03
• Subjects: Recurrent neural networks -- Cell signalling networks -- Model decomposition -- Modularisation -- Cell cycle -- G1/S transition; Biological systems -- Periodicals; Biology -- Periodicals; Biology -- Periodicals; Evolution -- Periodicals; Biologie -- Périodiques; Évolution -- Périodiques; 570
• DOI: 10.1016/j.biosystems.2017.01.001
• Languages: English
• ISSNs: 0303-2647

Abstract

Highlights: Successfully extends our previously published continuous time recurrent neural network (RNN) approach to modularise large cell signalling networks. Transforms a large ODE system into a flexible RNN system. Estimates a large number of parameters through iterative learning in modules and reveals crucial parameters supported by biology. Easily and efficiently produces accurate continuous systems dynamics comparable to the ODE system. Modifies the RNN system to receive large, more experimentally realistic, data and still produce fine temporal dynamics as in the original RNN and the ODE system. Abstract: In this paper, we show how to extend our previously proposed novel continuous time Recurrent Neural Networks (RNN) approach that retains the advantage of continuous dynamics offered by Ordinary Differential Equations (ODE) while enabling parameter estimation through adaptation, to larger signalling networks using a modular approach. Specifically, the signalling network is decomposed into several sub-models based on important temporal events in the network. Each sub-model is represented by the proposed RNN and trained using data generated from the corresponding ODE model. Trained sub-models are assembled into a whole system RNN which is then subjected to systems dynamics and sensitivity analyses. The concept is illustrated by application to G1/S transition in cell cycle using Iwamoto et al. (2008) ODE model. We decomposed the G1/S network into 3 sub-models: (i) E2F transcription factor release; (ii) E2F and CycE positive feedback loop for elevating cyclin levels; and (iii) E2F and CycA negative feedback to degrade E2F. The trained sub-models accurately represented system dynamics and parameters were in good agreement with the ODE model. The whole system RNN however revealed couple of parameters contributing to compounding errors due to feedback and required refinement to sub-model 2. These related to the reversible reaction between CycE/CDK2 and p27, its inhibitor. The revised whole system RNN model very accurately matched dynamics of the ODE system. Local sensitivity analysis of the whole system model further revealed the most dominant influence of the above two parameters in perturbing G1/S transition, giving support to a recent hypothesis that the release of inhibitor p27 from Cyc/CDK complex triggers cell cycle stage transition. To make the model useful in a practical setting, we modified each RNN sub-model with a time relay switch to facilitate larger interval input data (≈ 20 min) (original model used data for 30 s or less) and retrained them that produced parameters and protein concentrations similar to the original RNN system. Results thus demonstrated the reliability of the proposed RNN method for modelling relatively large networks by modularisation for practical settings. Advantages of the method are its ability to represent accurate continuous system dynamics and ease of: parameter estimation through training with data from a practical setting, model analysis (40% faster than ODE), fine tuning parameters when more data are available, sub-model extension when new elements and/or interactions come to light and model expansion with addition of sub-models.