Materials and methods Second part of glycolysis experimental data. Experimental data of PGAM, ENO and PPDK activities and pathway flux (J obs) are obtained from plots of a previous study 8. The free online software WebPlotDigitizer (Version 4.1, https ://autom eris.io/WebPl otDig itize r/) is used to extract data from plots. These data are available in Tables S1 and S2. Artificial neural networks (ANNs). ANNs functioning mimics that of biological neurons, the networks consist of many layers allowing input reception and processing and output delivery. This technique can be used for solving classification or regression problems 18. To build the second part of glycolysis in ANNs, different types of software are employed: RStudio (Version 1.1.456), an open-source integrated development environment for R 19 and two packages: NeuralNet (Version 1.44.2) and Nnet (Version 7.3-12) 20,21. Complex pathway SImulator (COPASI) metabolic networks. A first metabolic network of the studied pathway was kindly provided by the authors of a previous study 8. This model is developed on GEPASI 22 , an old software for metabolic pathway modeling, replaced by COPASI since 2002. The second part of the glycolysis is also modeled by using the open source software called COPASI (Version 4.24) 23. This software is used for metabolic network design, analysis and optimization. The resulting metabolic networks are based on the use of enzyme properties (kinetic parameters and mechanism-based rate equations). Ethics approval and consent to participate. Not applicable. Methodology Black-white-and grey-box approach procedure. To conduct the present study, a specific methodol