Comprehensive Stereochemical Models for Selectivity Prediction in Diverse Chiral Phosphate-Catalyzed Reaction Space

ACS Catalysis ◽  
2021 ◽  
Vol 11 (19) ◽  
pp. 11897-11905
Author(s):  
Ali Shoja ◽  
Jianyu Zhai ◽  
Jolene P. Reid
Keyword(s):  
Reaction Space

Aluminum Siting in the ZSM-22 and Theta-1 Zeolites Revisited: A QM/MM Study

2008 ◽  
Vol 73 (6-7) ◽  
pp. 909-920 ◽  
Author(s):  
Stepan Sklenak ◽  
Jiří Dědeček ◽  
Chengbin Li ◽  
Fei Gao ◽  
Bavornpon Jansang ◽  
...  
Keyword(s):  
Experimental Data ◽  
Chemical Shift ◽  
Nearest Neighbor ◽  
Membered Ring ◽  
Mas Nmr ◽  
Isotropic Chemical Shift ◽  
Reaction Space ◽  
Ring Channel ◽  
T1 And T2 ◽  
Nmr Signals

The Al siting in the silicon rich ZSM-22 and Theta-1 zeolites of the TON structure was investigated analyzing already published 27Al 3Q MAS NMR experimental data using QM/MM calculations. The results of our computations show that Al atoms can be located in 6 framework T positions because the two eightfold sites (T1 and T2) split into four fourfold T sites after an Al/Si substitution. The observed resonance at 55.5 ppm corresponds to the T4 site which is predominantly occupied by Al. This site is not located on the surface of the TON ten-membered ring channel and thus the protonic sites related with the majority of Al atoms in the TON structure exhibit a significantly limited reaction space. The 27Al NMR signals centered at 57.6 and 58.7 ppm correspond to either the T2 and T3 sites, respectively, or only to T2. The T2 and T3 sites accommodate some 40% and up to 10%, respectively, of Al while the T1 site is unoccupied by Al. Isotropic shifts of 61.1 and 61.6 ppm were calculated for Al atoms located in the T1-1 and T1-2 sites, respectively. The effect of a silanol "nest" as a next-next-nearest neighbor on the 27Al isotropic chemical shift of Al located in the T4 site is calculated to be less than 1 ppm.

scholarly journals Mapping the Space of Chemical Reactions using Attention-Based Neural Networks

2020 ◽  
Author(s):  
Philippe Schwaller ◽  
Daniel Probst ◽  
Alain C. Vaucher ◽  
Vishnu H Nair ◽  
David Kreutter ◽  
...  
Keyword(s):  
Neural Networks ◽  
Reaction Center ◽  
Chemical Reactions ◽  
Chemical Reaction ◽  
Classification Accuracy ◽  
Similarity Searching ◽  
Reaction Space ◽  
Fine Grained ◽  
Visual Clustering ◽  
Better Than

<div><div><div><p>Organic reactions are usually assigned to classes grouping reactions with similar reagents and mechanisms. Reaction classes facilitate communication of complex concepts and efficient navigation through chemical reaction space. However, the classification process is a tedious task, requiring the identification of the corresponding reaction class template via annotation of the number of molecules in the reactions, the reaction center and the distinction between reactants and reagents. In this work, we show that transformer-based models can infer reaction classes from non-annotated, simple text-based representations of chemical reactions. Our best model reaches a classification accuracy of 98.2%. We also show that the learned representations can be used as reaction fingerprints which capture fine-grained differences between reaction classes better than traditional reaction fingerprints. The unprecedented insights into chemical reaction space enabled by our learned fingerprints is illustrated by an interactive reaction atlas providing visual clustering and similarity searching. </p><p><br></p><p>Code: https://github.com/rxn4chemistry/rxnfp</p><p>Tutorials: https://rxn4chemistry.github.io/rxnfp/</p><p>Interactive reaction atlas: https://rxn4chemistry.github.io/rxnfp//tmaps/tmap_ft_10k.html</p></div></div></div>

scholarly journals Machine learning in chemical reaction space

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Sina Stocker ◽  
Gábor Csányi ◽  
Karsten Reuter ◽  
Johannes T. Margraf
Keyword(s):  
Machine Learning ◽  
Chemical Reaction ◽  
Organic Molecules ◽  
Methane Combustion ◽  
Open Shell ◽  
Reaction Space ◽  
Multiple Reactions ◽  
Reaction Energies ◽  
Important Basis ◽  
Modern Machine

Abstract Chemical compound space refers to the vast set of all possible chemical compounds, estimated to contain 1060 molecules. While intractable as a whole, modern machine learning (ML) is increasingly capable of accurately predicting molecular properties in important subsets. Here, we therefore engage in the ML-driven study of even larger reaction space. Central to chemistry as a science of transformations, this space contains all possible chemical reactions. As an important basis for ‘reactive’ ML, we establish a first-principles database (Rad-6) containing closed and open-shell organic molecules, along with an associated database of chemical reaction energies (Rad-6-RE). We show that the special topology of reaction spaces, with central hub molecules involved in multiple reactions, requires a modification of existing compound space ML-concepts. Showcased by the application to methane combustion, we demonstrate that the learned reaction energies offer a non-empirical route to rationally extract reduced reaction networks for detailed microkinetic analyses.

scholarly journals The Levinthal Problem in Amyloid Aggregation: Identification of Good Coordinates in a Flat Reaction Space

2017 ◽  
Vol 112 (3) ◽  
pp. 198a
Author(s):  
Zhiguang Jia ◽  
Jianhan Chen ◽  
Jeremy D. Schmit
Keyword(s):  
Amyloid Aggregation ◽  
Reaction Space

Growth of Large-Area Graphene Single Crystals in Confined Reaction Space with Diffusion-Driven Chemical Vapor Deposition

2015 ◽  
Vol 27 (18) ◽  
pp. 6249-6258 ◽  
Author(s):  
Chiao-Chen Chen ◽  
Chia-Jung Kuo ◽  
Chun-Da Liao ◽  
Chin-Fu Chang ◽  
Chi-Ang Tseng ◽  
...  
Keyword(s):  
Chemical Vapor Deposition ◽  
Single Crystals ◽  
Vapor Deposition ◽  
Chemical Vapor ◽  
Large Area ◽  
Reaction Space

scholarly journals Exploring Chemical Reaction Space With Reaction Difference Fingerprints and Parametric t-SNE

2021 ◽  
Author(s):  
Mikhail Andronov ◽  
Maxim Fedorov ◽  
Sergey Sosnin
Keyword(s):  
Neural Network ◽  
Chemical Reaction ◽  
Deep Neural Network ◽  
Visual Representations ◽  
Dimensional Manifold ◽  
Reaction Space ◽  
Large Databases ◽  
Global Reaction ◽  
Low Dimensional ◽  
Low Dimensional Manifold

<div>Humans prefer visual representations for the analysis of large databases. In this work, we suggest a method for the visualization of the chemical reaction space. Our technique uses the t-SNE approach that is parameterized by a deep neural network (parametric t-SNE). We demonstrated that the parametric t-SNE combined with reaction difference fingerprints can provide a tool for the projection of chemical reactions onto a low-dimensional manifold for easy exploration of reaction space. We showed that the global reaction landscape, been projected onto a 2D plane, corresponds well with already known reaction types. The application of a pretrained parametric t-SNE model to new reactions allows chemists to study these reactions on a global reaction space. We validated the feasibility of this approach for two marketed drugs: darunavir and oseltamivir. We believe that our method can help explore reaction space and inspire chemists to find new reactions and synthetic ways. </div><div><br></div>

scholarly journals Mapping the Space of Chemical Reactions using Attention-Based Neural Networks

2020 ◽  
Author(s):  
Philippe Schwaller ◽  
Daniel Probst ◽  
Alain C. Vaucher ◽  
Vishnu H Nair ◽  
David Kreutter ◽  
...  
Keyword(s):  
Neural Networks ◽  
Reaction Center ◽  
Chemical Reactions ◽  
Chemical Reaction ◽  
Classification Accuracy ◽  
Similarity Searching ◽  
Reaction Space ◽  
Fine Grained ◽  
Visual Clustering ◽  
Better Than

<div><div><div><p>Organic reactions are usually assigned to classes grouping reactions with similar reagents and mechanisms. Reaction classes facilitate communication of complex concepts and efficient navigation through chemical reaction space. However, the classification process is a tedious task, requiring the identification of the corresponding reaction class template via annotation of the number of molecules in the reactions, the reaction center and the distinction between reactants and reagents. In this work, we show that transformer-based models can infer reaction classes from non-annotated, simple text-based representations of chemical reactions. Our best model reaches a classification accuracy of 98.2%. We also show that the learned representations can be used as reaction fingerprints which capture fine-grained differences between reaction classes better than traditional reaction fingerprints. The unprecedented insights into chemical reaction space enabled by our learned fingerprints is illustrated by an interactive reaction atlas providing visual clustering and similarity searching. </p><p><br></p><p>Code: https://github.com/rxn4chemistry/rxnfp</p><p>Tutorials: https://rxn4chemistry.github.io/rxnfp/</p><p>Interactive reaction atlas: https://rxn4chemistry.github.io/rxnfp//tmaps/tmap_ft_10k.html</p></div></div></div>

Sign in / Sign up

Export Citation Format

Share Document