Automatic kinetic model generation and selection based on concentration versus time curves

Nagy, Tibor; Tóth, János; Ladics, Tamás

doi:10.1002/kin.21335

Cited by 5 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Symbolic regression and sparse regression can produce physically interpretable kinetic models with known candidate pathways. However, such candidate pathways can only be proposed for a few relatively simple systems because of the curse of dimensionality, as the possible interactions among species increase dramatically with the number of species . For example, the number of possible reaction pathways scales with the fourth power of the number of species if we only consider the possible reactions involving two species in the reactants and two species in the products.…”

Section: Introductionmentioning

confidence: 99%

Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network

Deng

2021

J. Phys. Chem. A

View full text Add to dashboard Cite

The inference of chemical reaction networks is an important task in understanding the chemical processes in life sciences and environment. Yet, only a few reaction systems are well-understood due to a large number of important reaction pathways involved but still unknown. Revealing unknown reaction pathways is an important task for scientific discovery that takes decades and requires lots of expert knowledge. This work presents a neural network approach for discovering unknown reaction pathways from concentration time series data. The neural network denoted as Chemical Reaction Neural Network (CRNN), is designed to be equivalent to chemical reaction networks by following the fundamental physics laws of the Law of Mass Action and Arrhenius Law. The CRNN is physically interpretable, and its weights correspond to the reaction pathways and rate constants of the chemical reaction network. Then, inferencing the reaction pathways and the rate constants are accomplished by training the equivalent CRNN via stochastic gradient descent. The approach precludes the need for expert knowledge in proposing candidate reactions, such that the inference is autonomous and applicable to new systems for which there is no existing empirical knowledge to propose reaction pathways. The physical interpretability also makes the CRNN not only capable of fitting the data for a given system but also developing knowledge of unknown pathways that could be generalized to similar chemical systems. Finally, the approach is applied to several chemical systems in chemical engineering and biochemistry to demonstrate its robustness and generality.

show abstract

Section: Introductionmentioning

confidence: 99%

Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network

Deng

2021

J. Phys. Chem. A

View full text Add to dashboard Cite

show abstract

“…In [15], the authors presented an approach to infer the stoichiometric subspace of a chemical reaction network from steady-state concentration data profiles, which is then cast as a series of MILP. In [16], some chemically reasonable requirements were considered such as the mass conservation and the principle of detailed balance. The deep neural networks (DNNs) were applied to extract the chemical reaction rate information in [17,18], but the weights are difficult to interpret physically.…”

Section: Introductionmentioning

confidence: 99%

Data-driven discovery of multiscale chemical reactions governed by the law of mass action

Huang,

Zhou,

Yong

2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a data-driven method to discover multiscale chemical reactions governed by the law of mass action. First, we use a single matrix to represent the stoichiometric coefficients for both the reactants and products in a system without catalysis reactions. The negative entries in the matrix denote the stoichiometric coefficients for the reactants and the positive ones for the products. Second, we find that the conventional optimization methods usually get stuck in the local minima and could not find the true solution in learning the multiscale chemical reactions. To overcome this difficulty, we propose a partial-parameters-freezing (PPF) technique to progressively determine the network parameters by using the fact that the stoichiometric coefficients are integers. With such a technique, the dimension of the searching space is gradually reduced in the training process and the global mimina can be eventually obtained. Several numerical experiments including the classical Michaelis-Menten kinetics and the hydrogen oxidation reactions verify the good performance of our algorithm in learning the multiscale chemical reactions. The code is available at https://github.com/JuntaoHuang/multiscale-chemical-reaction.

show abstract

Data-driven discovery of multiscale chemical reactions governed by the law of mass action

Huang

Zhou

Yong

2022

Journal of Computational Physics

View full text Add to dashboard Cite

Automatic kinetic model generation and selection based on concentration versus time curves

Cited by 5 publications

References 54 publications

Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network

Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network

Data-driven discovery of multiscale chemical reactions governed by the law of mass action

Data-driven discovery of multiscale chemical reactions governed by the law of mass action

Contact Info

Product

Resources

About