Valence states of atoms and their conversions

1984 ◽  
Vol 49 (5) ◽  
pp. 1247-1261 ◽  
Author(s):  
Jaroslav Koča ◽  
Milan Kratochvíl ◽  
Milan Kunz ◽  
Vladimír Kvasnička
Keyword(s):  
Chemical Reactions ◽  
Computer Assisted ◽  
Efficient Tool ◽  
Common Features ◽  
Systematic Application ◽  
Organic Syntheses ◽  
Valence States ◽  
Algebraic Formalism

The algebraic formalism for the description of valence states of atoms and their interconversions is elaborated. It offers a possibility to construct and trace mechanistic paths of chemical reactions, the problem of which is of great importance in computer-assisted organic syntheses. Its systematic application gives exhaustive lists of possible mechanistic paths, and furthermore, very efficient tool to classify chemical reactions and look for their common features.

Reaction of Tropone with a Homopyrrole. The Result of a Computer-Assisted Search for Unique Chemical Reactions

1988 ◽  
Vol 27 (11) ◽  
pp. 1558-1559 ◽  
Author(s):  
Dietmar Forstmeyer ◽  
Johannes Bauer ◽  
Eric Fontain ◽  
Rainer Herges ◽  
Rudolf Herrmann ◽  
...  
Keyword(s):  
Chemical Reactions ◽  
Computer Assisted ◽  
Unique Chemical

scholarly journals DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions

2020 ◽  
Author(s):  
Filipp Nikitin ◽  
Olexandr Isayev ◽  
Vadim Strijov
Keyword(s):  
Neural Network ◽  
Chemical Reactions ◽  
Computer Assisted ◽  
Excellent Performance ◽  
Reaction Prediction ◽  
Latent Vector ◽  
Atom Mapping ◽  
Proposed Model ◽  
Disconnected Graphs ◽  
Disconnected Graph

<p>Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP). We formulate a reaction prediction problem in terms of node-classification in a disconnected graph of source molecules and generalize a graph convolution neural network for disconnected graphs. Here we demonstrate that our approach can successfully predict reaction outcome and atom-mapping during a chemical transformation. A set of experiments using the USPTO dataset demonstrates excellent performance and interpretability of the proposed model. Implicitly learned latent vector representation of chemical reactions strongly correlates with the class of the chemical reaction. Reactions with similar templates group together in the latent vector space.</p>

scholarly journals Application of the Microwave Technique in Continuous Flow Processing of Organophosphorus Chemical Reactions

Materials ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 788 ◽  
Author(s):  
Erika Bálint ◽  
Ádám Tajti ◽  
György Keglevich
Keyword(s):  
Chemical Reactions ◽  
Special Interest ◽  
Continuous Flow ◽  
Food Industry ◽  
Scale Up ◽  
Organic Reactions ◽  
Materials Chemistry ◽  
Efficient Tool ◽  
Microwave Technique

The microwave (MW) technique is an efficient tool in the realization of organic reactions, as well as in the analytical field and in the food industry. The continuous flow approach is of special interest as a promising way to scale-up MW-assisted syntheses. Besides summarizing the batch precedents, this review focuses on the utilization of the MW technique in the continuous-flow realization of organophosphorus transformations. The advantages of the continuous flow technique against the batch accomplishment are also shown. A few materials chemistry-related applications are also mentioned.

Computer-assisted synthetic analysis. Selection of protective groups for multistep organic syntheses.

1985 ◽  
Vol 50 (11) ◽  
pp. 1920-1927 ◽  
Author(s):  
E. J. Corey ◽  
Alan K. Long ◽  
Theodora W. Greene ◽  
John W. Miller
Keyword(s):  
Computer Assisted ◽  
Organic Syntheses ◽  
Protective Groups ◽  
Selection Of

scholarly journals DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions

2020 ◽  
Author(s):  
Filipp Nikitin ◽  
Olexandr Isayev ◽  
Vadim Strijov
Keyword(s):  
Neural Network ◽  
Chemical Reactions ◽  
Computer Assisted ◽  
Reaction Prediction ◽  
Latent Vector ◽  
Atom Mapping ◽  
Proposed Model ◽  
Unsupervised Approach ◽  
Disconnected Graphs ◽  
Disconnected Graph

Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP). We formulate a reaction prediction problem in terms of node-classification in a disconnected graph of source molecules and generalize a graph convolution neural network for disconnected graphs. Here we demonstrate that our approach can successfully predict reaction outcome and atom-mapping during a chemical transformation. A set of experiments using the USPTO dataset demonstrates excellent performance and interpretability of the proposed model. Our model uses an unsupervised approach to atom-mapping and bridges the gap between data-driven and traditional rule-based methods. Implicitly learned latent vector representation of chemical reactions strongly correlates with the class of the chemical reaction. Reactions with similar templates group together in the latent vector space.

Sign in / Sign up

Export Citation Format

Share Document