Improving Chemical Reaction Prediction with Unlabeled Data
Predicting products of organic chemical reactions is useful in chemical sciences, especially when one or more reactants are new organics. However, the performance of traditional learning models heavily relies on high-quality labeled data.
Yu Xie +4 more
doaj +1 more source
Bayesian chemical reaction neural network for autonomous kinetic uncertainty quantification
We develop Bayesian Chemical Reaction Neural Network (B-CRNN), a method to infer chemical reaction models and provide the associated uncertainty purely from data without prior knowledge of reaction templates.
Koenig, Benjamin C +7 more
core +1 more source
Robust Mechanism Discovery with Atom Conserving Chemical Reaction Neural Networks [PDF]
Chemical reaction neural networks (CRNNs) established as the state-of-the-art tool for autonomous mechanism discovery. While they encode some fundamental physical laws, mass- and atom conservation are still violated.
Felix, Döppel, Martin, Votsmeier
core +1 more source
Identification of functional differences in metabolic networks using comparative genomics and constraint-based models. [PDF]
Genome-scale network reconstructions are useful tools for understanding cellular metabolism, and comparisons of such reconstructions can provide insight into metabolic differences between organisms.
Joshua J Hamilton, Jennifer L Reed
doaj +1 more source
The Gompertz model revisited and modified using reaction networks: Mathematical analysis
In the present work we discuss the usage of the framework of chemical reaction networks for the construction of dynamical models and their mathematical analysis.
Svetoslav Marinov Markov
doaj +1 more source
Accelerating Reaction Network Explorations with Automated Reaction Template Extraction and Application [PDF]
Autonomously exploring chemical reaction networks with first-principles methods can generate vast data. Especially autonomous explorations without tight constraints risk getting trapped in regions of reaction networks that are not of interest.
Jan Patrick, Unsleber
core +1 more source
Challenges for Kinetics Predictions via Neural Network Potentials: A Wilkinson’s Catalyst Case
Ab initio kinetic studies are important to understand and design novel chemical reactions. While the Artificial Force Induced Reaction (AFIR) method provides a convenient and efficient framework for kinetic studies, accurate explorations of reaction path
Ruben Staub +4 more
doaj +1 more source
PNNARMA model: an alternative to phenomenological models in chemical reactors [PDF]
This paper is focused on the development of non-linear neural models able to provide appropriate predictions when acting as process simulators. Parallel identification models can be used for this purpose.
J.M. Zaldı́var +5 more
core +1 more source
Chemical reaction network knowledge graphs: the OntoRXN ontology [PDF]
: The organization and management of large amounts of data has become a major point in almost all areas of human knowledge. In this context, semantic approaches propose a structure for the target data, defining ontologies that state the types of entities
Bo, Carles +5 more
core +2 more sources
Persistence and stability of generalized ribosome flow models with time-varying transition rates.
In this paper some important qualitative dynamical properties of generalized ribosome flow models are studied. Ribosome flow models known from the literature are generalized by allowing an arbitrary directed network structure between compartments, and by
Mihály A Vághy, Gábor Szederkényi
doaj +1 more source

