Abstract
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.
This work is supported by the Universitá di Pisa under the “PRA – Progetti di Ricerca di Ateneo” (Institutional Research Grants) - Project no. PRA_2020-2021_26 “Metodi Informatici Integrati per la Biomedica”.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
BioModels: https://www.ebi.ac.uk/biomodels/.
- 2.
This definition of layer is adapted from the Deep Learning literature, where a layer is a parameterized function applied to an input, whose parameters are learned from data [11].
- 3.
A function f on an input set x is invariant with respect to a permutation \(\pi \) iff \(f(x) = f(\pi (x))\). Note that, in the case of DGNs, the input set x is a set of node embeddings.
- 4.
A hop is defined as the shortest unweighted path between two nodes.
- 5.
May 2019.
- 6.
The DOT graph description language specification, available at: https://graphviz.gitlab.io/_pages/doc/info/lang.html.
- 7.
The concentration values obtained at the end of the simulation are considered as steady state values also in the cases in which the timeout has been reached.
References
Bacciu, D., Errica, F., Micheli, A., Podda, M.: A gentle introduction to deep learning for graphs. Neural Netw. 129, 203–221 (2020). https://doi.org/10.1016/j.neunet.2020.06.006
Bianucci, A., Micheli, A., Sperduti, A., Starita, A.: Application of cascade correlation networks for structures to chemistry. Appl. Intell. 12, 117–147 (2000). https://doi.org/10.1023/A:1008368105614
Bove, P., Micheli, A., Milazzo, P., Podda, M.: Prediction of dynamical properties of biochemical pathways with graph neural networks. In: Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3 BIOINFORMATICS, pp. 32–43. INSTICC, SciTePress (2020). https://doi.org/10.5220/0008964700320043
Duvenaud, D.K., et al.: Convolutional networks on graphs for learning molecular fingerprints. Adv. Neural. Inf. Process. Syst. 28, 2224–2232 (2015)
Fages, F., Soliman, S.: From reaction models to influence graphs and back: a theorem. In: Fisher, J. (ed.) FMSB 2008. LNCS, vol. 5054, pp. 90–102. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-68413-8_7
Frasconi, P., Gori, M., Sperduti, A.: A general framework for adaptive processing of data structures. IEEE Trans. Neural Netw. 9(5), 768–86 (1998). A publication of the IEEE Neural Networks Council
Funahashi, A., Morohashi, M., Kitano, H., Tanimura, N.: CellDesigner: a process diagram editor for gene-regulatory and biochemical networks. Biosilico 1(5), 159–162 (2003)
Gilbert, D., Heiner, M., Lehrack, S.: A unifying framework for modelling and analysing biochemical pathways using Petri nets. In: Calder, M., Gilmore, S. (eds.) CMSB 2007. LNCS, vol. 4695, pp. 200–216. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-75140-3_14
Gillespie, D.T.: Exact stochastic simulation of coupled chemical reactions. J. Phys. Chem. 81(25), 2340–2361 (1977)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. The MIT Press, Cambridge (2016)
Gori, R., Milazzo, P., Nasti, L.: Towards an efficient verification method for monotonicity properties of chemical reaction networks. In: Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS, pp. 250–257. INSTICC, SciTePress (2019). https://doi.org/10.5220/0007522002500257
Hammer, B., Micheli, A., Sperduti, A.: Universal approximation capability of cascade correlation for structures. Neural Comput. 17(5), 1109–1159 (2005)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, New York (2001). https://doi.org/10.1007/978-0-387-21606-5
Haykin, S.S.: Neural Networks and Learning Machines, 3rd edn. Pearson Education, London (2009)
Hucka, M., et al.: The systems biology markup language (SBML): language specification for level 3 version 2 core. J. Integr. Bioinform. 15(1) (2018). https://doi.org/10.1515/jib-2017-0081. Article no. 20170081
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, ICML 2015, vol. 37, pp. 448–456. JMLR.org (2015)
Iooss, B., Lemaître, P.: A review on global sensitivity analysis methods. In: Dellino, G., Meloni, C. (eds.) Uncertainty Management in Simulation-Optimization of Complex Systems. ORSIS, vol. 59, pp. 101–122. Springer, Boston, MA (2015). https://doi.org/10.1007/978-1-4899-7547-8_5
Janocha, K., Czarnecki, W.: On loss functions for deep neural networks in classification. Schedae Informaticae 25, 49–59 (2017)
Karp, P.D., Paley, S.M.: Representations of metabolic knowledge: pathways. In: ISMB, vol. 2, pp. 203–211 (1994)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations, ICLR (2015)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, ICLR (2017)
Kitano, H.: Biological robustness. Nat. Rev. Genet. 5(11), 826 (2004)
Kitano, H.: Towards a theory of biological robustness. Mol. Syst. Biol. 3(1), 137 (2007)
Larhlimi, A., Blachon, S., Selbig, J., Nikoloski, Z.: Robustness of metabolic networks: a review of existing definitions. Biosystems 106(1), 1–8 (2011)
Le Novere, N., et al.: BioModels database: a free, centralized database of curated, published, quantitative kinetic models of biochemical and cellular systems. Nucleic Acids Res. 34(suppl\(\_\)1), D689–D691 (2006)
Le Novere, N., et al.: The systems biology graphical notation. Nat. Biotechnol. 27(8), 735 (2009)
Li, C., et al.: BioModels database: an enhanced, curated and annotated resource for published quantitative kinetic models. BMC Syst. Biol. 4 (2010). https://doi.org/10.1186/1752-0509-4-92. Article no. 92
Micheli, A.: Neural network for graphs: a contextual constructive approach. IEEE Trans. Neural Netw. 20(3), 498–511 (2009)
Micheli, A., Sona, D., Sperduti, A.: Contextual processing of structured data by recursive cascade correlation. IEEE Trans. Neural Netw. 15, 1396–1410 (2004)
Nasti, L., Gori, R., Milazzo, P.: Formalizing a notion of concentration robustness for biochemical networks. In: Mazzara, M., Ober, I., Salaün, G. (eds.) STAF 2018. LNCS, vol. 11176, pp. 81–97. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04771-9_8
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: Proceedings of the 33rd International Conference on Machine Learning, vol. 48, pp. 2014–2023 (2016)
Peterson, J.L.: Petri nets. ACM Comput. Surv. (CSUR) 9(3), 223–252 (1977)
Reddy, V.N., Mavrovouniotis, M.L., Liebman, M.N., et al.: Petri net representations in metabolic pathways. In: ISMB, vol. 93, pp. 328–336 (1993)
Rizk, A., Batt, G., Fages, F., Soliman, S.: A general computational method for robustness analysis with applications to synthetic gene networks. Bioinformatics 25(12), i169–i178 (2009)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2009)
Shinar, G., Feinberg, M.: Structural sources of robustness in biochemical reaction networks. Science 327(5971), 1389–1391 (2010)
Sivakumar, K.C., Dhanesh, S.B., Shobana, S., James, J., Mundayoor, S.: A systems biology approach to model neural stem cell regulation by Notch, Shh, Wnt, and EGF signaling pathways. Omics: J. Integr. Biol. 15(10), 729–737 (2011)
Somogyi, E.T., et al.: libRoadRunner: a high performance SBML simulation and analysis library. Bioinformatics 31(20), 3315–3321 (2015)
Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Trans. Neural Netw. 8(3), 714–735 (1997)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Zi, Z.: Sensitivity analysis approaches applied to systems biology models. IET Syst. Biol. 5(6), 336–346 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Podda, M., Bove, P., Micheli, A., Milazzo, P. (2021). Classification of Biochemical Pathway Robustness with Neural Networks for Graphs. In: Ye, X., et al. Biomedical Engineering Systems and Technologies. BIOSTEC 2020. Communications in Computer and Information Science, vol 1400. Springer, Cham. https://doi.org/10.1007/978-3-030-72379-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-72379-8_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72378-1
Online ISBN: 978-3-030-72379-8
eBook Packages: Computer ScienceComputer Science (R0)