Exploring Identifiability in Hybrid Models of Cell Signaling Pathways
Resumo
Various processes, including growth, proliferation, migration, and death, mediate the activity of a cell. To better understand these processes, dynamic modeling can be a helpful tool. First-principle modeling provides interpretability, while data-driven modeling can offer predictive performance using models such as neural network, however at the expense of the understanding of the underlying biological processes. A hybrid model that combines both approaches might mitigate the limitations of each of them alone; nevertheless, to this end one needs to tackle issues such as model calibration and identifiability. In this paper, we report a methodology to address these challenges that makes use of a universal differential equation (UDE)-based hybrid modeling, were a partially known, ODE-based, first-principle model is combined with a feedforward neural network-based, data-driven model. We used a synthetic signaling network composed of 38 chemical species and 51 reactions to generate simulated time series for those species, and then defined twelve of those reactions as a partially known first-principle model. A UDE system was defined with this latter and it was calibrated with the data simulated with the whole network. Initial results showed that this approach could identify the missing communication of the partially-known first-principle model with the remainder of the network. Therefore, we expect that this type of hybrid modeling might become a powerful tool to assist in the investigation of underlying mechanisms in cellular systems.
Referências
Balci, H., et al.: Newt: a comprehensive web-based tool for viewing, constructing and analyzing biological maps. Bioinformatics. 37(10), 1475–1477 (2020). https://doi.org/10.1093/bioinformatics/btaa850
Bangi, M.S.F., et al.: Physics-informed neural networks for hybrid modeling of lab-scale batch fermentation for beta-carotene production using saccharomyces cerevisiae. Chem. Eng. Res. Des. 179, 415–423 (2022). https://doi.org/10.1016/j.cherd.2022.01.041
Engelhardt, B., et al.: A Bayesian approach to estimating hidden variables as well as missing and wrong molecular interactions in ordinary differential equation-based mathematical models. J. R. Soc. Interface 14(131), 20170332 (2017). https://doi.org/10.1098/rsif.2017.0332
Fröhlich, F., et al.: Mechanistic model of MAPK signaling reveals how allostery and rewiring contribute to drug resistance. Mol. Syst. Biol. 19(2), e10988 (2023). https://doi.org/10.15252/msb.202210988
Gabor, A., et al.: Cell-to-cell and type-to-type heterogeneity of signaling networks: insights from the crowd. Mol. Syst. Biol. 17(10), e10402 (2021). https://doi.org/10.15252/msb.202110402
Glass, D.S., et al.: Nonlinear delay differential equations and their application to modeling biological network motifs. Nat. Commun. 12(1), 1788 (2021). https://doi.org/10.1038/s41467-021-21700-8
Hidalgo, M.R., et al.: Models of cell signaling uncover molecular mechanisms of high-risk neuroblastoma and predict disease outcome. Biol. Direct 13(1), 16 (2018). https://doi.org/10.1186/s13062-018-0219-4
Joo, J.D.: The use of intra-cellular signaling pathways in anesthesiology and pain medicine field. Korean J. Anesthesiol. 57(3), 277–283 (2009). https://doi.org/10.4097/kjae.2009.57.3.277
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. ArXiv Preprint ArXiv:1412.6980 (2014). https://doi.org/10.48550/arXiv.1412.6980
Le Novère, N., et al.: The systems biology graphical notation. Nat. Biotechnol. 27(8), 735–741 (2009). https://doi.org/10.1038/nbt.1558
Lee, D., et al.: Development of a hybrid model for a partially known intracellular signaling pathway through correction term estimation and neural network modeling. PLoS Comput. Biol. 16(12), 1–31 (2020). https://doi.org/10.1371/journal.pcbi.1008472
Lee, D., et al.: A hybrid mechanistic data-driven approach for modeling uncertain intracellular signaling pathways. In: 2021 American Control Conference (ACC), pp. 1903–1908 (2021). https://doi.org/10.23919/ACC50511.2021.9483352
Ma, Y., et al.: A comparison of automatic differentiation and continuous sensitivity analysis for derivatives of differential equation solutions. In: 2021 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1–9 (2021). https://doi.org/10.1109/HPEC49654.2021.9622796
Pal, A.: Lux: Explicit parameterization of deep neural networks in Julia (2022). https://github.com/avik-pal/Lux.jl/
Rackauckas, C., Nie, Q.: Differentialequations.jl-a performant and feature-rich ecosystem for solving differential equations in Julia. J. Open Res. Softw. 5(1), 15 (2017). https://doi.org/10.5334/jors.151
Rackauckas, C., et al.: Universal differential equations for scientific machine learning (2021). https://doi.org/10.48550/arXiv.2001.04385
Reis, M.S., et al.: An interdisciplinary approach for designing kinetic models of the RAS/MAPK signaling pathway. In: Methods in Molecular Biology Special Edition on Kinase Signaling Networks, pp. 455–474. Humana Press, New York (2017). https://doi.org/10.1007/978-1-4939-7154-1_28
Santana, V.V., et al.: Efficient hybrid modeling and sorption model discovery for non-linear advection-diffusion-sorption systems: a systematic scientific machine learning approach. ArXiv Preprint ArXiv:2303.13555 (2023). https://doi.org/10.48550/arXiv.2303.13555
Scheithauer, G., Nocedal, J., Wright, S.J.: Numerical Optimization. Springer Series In Operations Research and Financial Engineering, 2nd edn. Springer, New York (1999)
