Skip to main content

Deep Abstractions of Chemical Reaction Networks

  • Conference paper
  • First Online:
Computational Methods in Systems Biology (CMSB 2018)

Part of the book series: Lecture Notes in Computer Science ((LNBI,volume 11095))

Included in the following conference series:


Multi-scale modeling of biological systems, for instance of tissues composed of millions of cells, are extremely demanding to simulate, even resorting to High Performance Computing (HPC) facilities, particularly when each cell is described by a detailed model of some intra-cellular pathways and cells are coupled and interacting at the tissue level. Model abstraction can play a crucial role in this setting, by providing simpler models of intra-cellular dynamics that are much faster to simulate so to scale better the analysis at the tissue level. Abstractions themselves can be very challenging to build ab-initio. A more viable strategy is to learn them from single cell simulation data.

In this paper, we explore this direction, constructing abstract models of chemical reaction networks in terms of Discrete Time Markov Chains on a continuous space, learning transition kernels using deep neural networks. This allows us to obtain accurate simulations, greatly reducing the computational burden.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
USD 49.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others


  1. 1.

    A node is said to be hidden if it does not belong to the input or the output layer. A layer is, roughly, a collection of nodes at the same depth level with respect to the input layer. A layer composed of hidden nodes is called hidden layer.

  2. 2.

    Rectified Linear Unit: \(f(x)=\max \{0, x\}\), cfr. [12].

  3. 3.

    We generated training and validation sets with the same number of datapoints. A t each epoch, we subsample from these sets without replacement (until the whole dataset has been consumed) to have a finer control on overfitting using early stopping regularization.

  4. 4.

    As in the SIR case, training set and validation set have the same number of datapoints, and we subsample without replacement at each epoch to have a finer control on overfitting using early stopping regularization.


  1. Gillespie, D.T.: Exact stochastic simulation of coupled chemical reactions. J. Phys. Chem. 81(25), 2340–2361 (1977). (Visited 28 Nov 11 2013)

    Article  Google Scholar 

  2. Bishop, C.M.: Mixture density networks. Technical report NCRG/94/004. Neural Computing Research Group, Aston University (1994)

    Google Scholar 

  3. LeCun, Y.A., Bottou, L., Orr, G.B., Müller, K.-R.: Efficient BackProp. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 9–48. Springer, Heidelberg (2012).

    Chapter  Google Scholar 

  4. Hochreiter, S., et al.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J.F. (eds.) A Field Guide to Dynamical Recurrent Neural Networks. IEEE Press (2001)

    Google Scholar 

  5. Christopher, M.: Pattern Recognition and Machine Learning. Springer, New York (2006)

    MATH  Google Scholar 

  6. Cao, Y., Gillespie, D.T., Petzold, L.R.: Efficient step size selection for the tau-leaping simulation method. J. Chem. Phys. 124(4), 044109 (2006).

    Article  Google Scholar 

  7. Cao, Y., Petzold, L.: Accuracy limitations and the measurement of errors in the stochastic simulation of chemically reacting systems. J. Comput. Phys. 212(1), 6–24 (2006).

    Article  MathSciNet  MATH  Google Scholar 

  8. Wilkinson, D.J.: Stochastic Modelling for Systems Biology. Chapman & Hall, Boca Raton (2006)

    MATH  Google Scholar 

  9. Pahle, J.: Biochemical simulations: stochastic, approximate stochastic and hybrid approaches. Brief. Bioinform. 10(1), 53–64 (2008).

    Article  Google Scholar 

  10. Greenwood, P.E., Gordillo, L.F.: Stochastic epidemic modeling. In: Chowell, G., Hyman, J.M., Bettencourt, L.M.A., Castillo-Chavez, C. (eds.) Mathematical and Statistical Estimation Approaches in Epidemiology, pp. 31–52. Springer, Dordrecht (2009).

    Chapter  Google Scholar 

  11. Deisboeck, T.S., et al.: Multiscale cancer modeling. Annu. Rev. Biomed. Eng. 13(1), 127–155 (2011). ISSN 1523-9829, 1545-4274.

  12. Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, vol. 15, pp. 315–323 (2011).

  13. Liu, B., Hsu, D., Thiagarajan, P.S.: Probabilistic approximations of ODEs based bio-pathway dynamics. Theor. Comput. Sci. 412, 2188–2206 (2011)

    Article  MathSciNet  Google Scholar 

  14. Sanft, K.R.: StochKit2: software for discrete stochastic simulation of biochemical systems with events. Bioinformatics 27(17), 2457–2458 (2011).

    Article  Google Scholar 

  15. Bernhardsson, E., Freider, E.: Luigi (2012).

  16. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014).

  17. Srivastava, N.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  18. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software:

  19. Bodei, C.: On the impact of discreteness and abstractions on modelling noise in gene regulatory networks. Comput. Biol. Chem. 56, 98–108 (2015).

    Article  Google Scholar 

  20. Chollet, F., et al.: Keras (2015).

  21. He, K., et al.: Deep residual learning for image recognition, December 2015.

  22. Abel, J.H., et al.: GillesPy: a Python package for stochastic model building and simulation. In: IEEE, September 2016, pp. 35–38 (2016).

  23. Goodfellow, I., Bengio, Y., Courvilleet, A.: Deep Learning. MIT Press, Cambridge (2016).

    MATH  Google Scholar 

  24. Michaelides, M., Hillston, J., Sanguinetti, G.: Statistical abstraction for multi-scale spatio-temporal systems. In: Quantitative Evaluation of Systems, QEST 2017, pp. 243–258 (2017).

  25. Palaniappan, S.K., et al.: Abstracting the dynamics of biological pathways using information theory: a case study of apoptosis pathway. Bioinformatics (2017). ISSN 1367-4803, 1460-2059,

  26. Schnoerr, D., Sanguinetti, G., Grima, R.: Approximation and inference methods for stochastic biochemical kinetics - a tutorial review. J. Phys. A: Math. Theor. 50(9), 093001 (2017). ISSN 1751-8113, 1751-8121, Visited 20 Apr 2017

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Luca Bortolussi .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bortolussi, L., Palmieri, L. (2018). Deep Abstractions of Chemical Reaction Networks. In: Češka, M., Šafránek, D. (eds) Computational Methods in Systems Biology. CMSB 2018. Lecture Notes in Computer Science(), vol 11095. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-99428-4

  • Online ISBN: 978-3-319-99429-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics