Combining multi-target regression deep neural networks and kinetic modeling to predict relative fluxes in reaction systems

DOI10.1016/J.IC.2021.104798MaRDI QIDQ2051826zbMATH OpenOpenAlexFDO

Authors Lucrezia Patruno, Francesco Craighero, Davide Maspero, Alex Graudenzi, Chiara Damiani

Publication date 25 November 2021

Published in Information and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ic.2021.104798

zbMATH Keywords

deep neural networksmetabolic fluxesmetabolomicsMonte Carlo samplingODE-based modelling

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Recommendations

• Automated deep abstractions for stochastic chemical reaction networks
• Deep abstractions of chemical reaction networks
• Metabolic P system flux regulation by artificial neural networks
• Diverse metabolic model parameters generate similar methionine cycle dynamics
• Inference of chemical reaction networks based on concentration profiles using an optimization framework

Cites work

• Applied predictive modeling
• Automatic Selection of Methods for Solving Stiff and Nonstiff Systems of Ordinary Differential Equations
• Deep learning
• Scikit-learn: machine learning in Python

Cited in

(3)

• Automated deep abstractions for stochastic chemical reaction networks
• Combining artificial neural networks and experimental design to prediction of kinetic rate constants
• Regression prediction of coupling reaction yield based on attention-driven convolutional neural network

Describes a project that uses

Uses Software

• Keras
• AppliedPredictiveModeling
• Scikit

This page was built for publication: Combining multi-target regression deep neural networks and kinetic modeling to predict relative fluxes in reaction systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2051826)