Predicting chemical reactions with a neural network

1991 ◽  
pp. 392-398
Author(s):  
David W. Elrod ◽  
Gerry M. Maggiora ◽  
Robert G. Trenary
Keyword(s):  
Neural Network ◽  
Chemical Reactions

scholarly journals Discovery of Novel Chemical Reactions by Deep Generative Recurrent Neural Network

2020 ◽  
Author(s):  
William Bort ◽  
Igor I. Baskin ◽  
Pavel Sidorov ◽  
Gilles Marcou ◽  
Dragos Horvath ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Chemical Reactions ◽  
Recurrent Neural Network ◽  
Coupling Reactions ◽  
Two Dimensional ◽  
Topographic Map ◽  
Latent Space ◽  
The Given ◽  
Condensed Graph Of Reaction

Here, we report an application of Artificial Intelligence techniques to generate novel chemical reactions of the given type. A sequence-to-sequence autoencoder was trained on the USPTO reaction database. Each reaction was converted into a single Condensed Graph of Reaction (CGR), followed by their translation into on-purpose developed SMILES/GGR text strings. The autoencoder latent space was visualized on the two-dimensional generative topographic map, from which some zones populated by Suzuki coupling reactions were targeted. These served for the generation of novel reactions by sampling the latent space points and decoding them to SMILES/CGR.<br>

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 Predicting Potentially Hazardous Chemical Reactions Using Explainable Neural Network

2021 ◽  
Author(s):  
Juhwan Kim ◽  
Geun Ho Gu ◽  
Juhwan Noh ◽  
Seongun Kim ◽  
Suji Gim ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Investigation ◽  
Chemical Reactions ◽  
Laboratory Safety ◽  
Reaction Conditions ◽  
Hazardous Chemical ◽  
Critical Task

Predicting potentially dangerous chemical reactions is a critical task for the laboratory safety. However, traditional experimental investigation of reaction conditions for the possible hazardous or explosive byproducts entails substantial time...

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.

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 An Artificial Intelligence that Discovers Unpredictable Chemical Reactions

2020 ◽  
Author(s):  
Dario Caramelli ◽  
Jaroslaw Granda ◽  
Dario Cambié ◽  
Hessam Mehr ◽  
Alon Henson ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Chemical Reactions ◽  
Multicomponent Reaction ◽  
Cascade Reaction ◽  
One Pot ◽  
Single Substrate ◽  
Set Up

<p><b>We present an artificial intelligence, built to autonomously explore chemical reactions in the laboratory using deep learning. The reactions are performed automatically, analysed online, and the data is processed using a convolutional neural network (CNN) trained on a small reaction dataset to assess the reactivity of reaction mixtures. The network can be used to predict the reactivity of an unknown dataset, meaning that the system is able to abstract the reactivity assignment regardless the identity of the starting materials. The system was set up with 15 inputs that were combined in 1018 reactions, the analysis of which lead to the discovery of a ‘multi-step, single-substrate’ cascade reaction and a new mode of reactivity for methylene isocyanides. <i>p</i>-Toluenesulfonylmethyl isocyanide (TosMIC) in presence of an activator reacts consuming six equivalents of itself to yield a trimeric product in high (unoptimized) yield (47%) with formation of five new C-C bonds involving <i>sp</i>-<i>sp<sup>2</sup></i> and <i>sp</i>-<i>sp<sup>3</sup></i> carbon centres. A cheminformatics analysis reveals that this transformation is both highly unpredictable and able to generate an increase in complexity like a one-pot multicomponent reaction.</b></p>

scholarly journals Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Jinzhe Zeng ◽  
Liqun Cao ◽  
Mingyuan Xu ◽  
Tong Zhu ◽  
John Z. H. Zhang
Keyword(s):  
Neural Network ◽  
Molecular Dynamics ◽  
Chemical Reactions ◽  
Chemical Reaction ◽  
Molecular Species ◽  
Md Simulation ◽  
Dynamics Simulation ◽  
Reaction Pathways ◽  
Complex Reaction ◽  
Reaction Processes

Abstract Combustion is a complex chemical system which involves thousands of chemical reactions and generates hundreds of molecular species and radicals during the process. In this work, a neural network-based molecular dynamics (MD) simulation is carried out to simulate the benchmark combustion of methane. During MD simulation, detailed reaction processes leading to the creation of specific molecular species including various intermediate radicals and the products are intimately revealed and characterized. Overall, a total of 798 different chemical reactions were recorded and some new chemical reaction pathways were discovered. We believe that the present work heralds the dawn of a new era in which neural network-based reactive MD simulation can be practically applied to simulating important complex reaction systems at ab initio level, which provides atomic-level understanding of chemical reaction processes as well as discovery of new reaction pathways at an unprecedented level of detail beyond what laboratory experiments could accomplish.

scholarly journals An Artificial Intelligence that Discovers Unpredictable Chemical Reactions

2020 ◽  
Author(s):  
Dario Caramelli ◽  
Jaroslaw Granda ◽  
Dario Cambié ◽  
Hessam Mehr ◽  
Alon Henson ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Chemical Reactions ◽  
Multicomponent Reaction ◽  
Cascade Reaction ◽  
One Pot ◽  
Single Substrate ◽  
Set Up

<p><b>We present an artificial intelligence, built to autonomously explore chemical reactions in the laboratory using deep learning. The reactions are performed automatically, analysed online, and the data is processed using a convolutional neural network (CNN) trained on a small reaction dataset to assess the reactivity of reaction mixtures. The network can be used to predict the reactivity of an unknown dataset, meaning that the system is able to abstract the reactivity assignment regardless the identity of the starting materials. The system was set up with 15 inputs that were combined in 1018 reactions, the analysis of which lead to the discovery of a ‘multi-step, single-substrate’ cascade reaction and a new mode of reactivity for methylene isocyanides. <i>p</i>-Toluenesulfonylmethyl isocyanide (TosMIC) in presence of an activator reacts consuming six equivalents of itself to yield a trimeric product in high (unoptimized) yield (47%) with formation of five new C-C bonds involving <i>sp</i>-<i>sp<sup>2</sup></i> and <i>sp</i>-<i>sp<sup>3</sup></i> carbon centres. A cheminformatics analysis reveals that this transformation is both highly unpredictable and able to generate an increase in complexity like a one-pot multicomponent reaction.</b></p>

scholarly journals A Reactivity First Approach to Autonomous Discovery of New Chemistry

2021 ◽  
Author(s):  
Dario Caramelli ◽  
Jaroslaw Granda ◽  
Hessam Mehr ◽  
Dario Cambié ◽  
Alon Henson ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Chemical Reactions ◽  
Neural Network Model ◽  
Photochemical Reaction ◽  
Cascade Reaction ◽  
High Yield ◽  
Discovery System ◽  
Single Substrate ◽  
Autonomous Discovery

<p></p><p></p><p>We present a robotic chemical discovery system capable of learning the generalized notion of reactivity using a neural network model that can abstract the reactivity from the identity of the reagents. The system is controlled using an algorithm that works in conjunction with this learned knowledge, the robot was able to autonomously explore a large number of potential reactions and assess the reactivity of mixtures, including unknown datasets, regardless the identity of the starting materials. The system identified a range of chemical reactions and products, some of which were well-known, some new but predictable from known pathways, but also some unpredictable reactions that yielded new molecules. The search was done within a budget of 15 inputs combined in 1018 reactions, which allowed us not only to discover a new photochemical reaction, but also a new reactivity mode for a well-known reagent (<i>p</i>-toluenesulfonylmethyl isocyanide, TosMIC). This involved the reaction of six equivalents of TosMIC in a ‘multi-step, single-substrate’ cascade reaction yielding a trimeric product in high yield (47% unoptimized) with formation of five new C-C bonds involving <i>sp</i>-<i>sp<sup>2</sup></i> and <i>sp</i>-<i>sp<sup>3</sup></i> carbon centres. Analysis reveals that this transformation is intrinsically unpredictable, demonstrating the possibility of reactivity-first robotic discovery of unknown reaction methodologies without requiring human input.</p><br><p></p><p></p>

Sign in / Sign up

Export Citation Format

Share Document