Automatic reaction mapping and reaction center detection

Chen, William Lingran; Chen, David Z.; Taylor, Keith T.

doi:10.1002/wcms.1140

Cited by 77 publications

(103 citation statements)

References 63 publications

(147 reference statements)

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…Also, any rule-based expert system that automatically extracts reaction rules from the reaction dataset depend heavily on accurate atom-mapping to describe the correspondence between the reactant and product atoms, which is itself a non-trivial problem. 55 The seq2seq model does not require atom-mapped reaction examples for training.…”

Section: Discussionmentioning

confidence: 99%

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

et al. 2017

View full text Add to dashboard Cite

We describe a fully data driven model that learns to perform a retrosynthetic reaction prediction task, which is treated as a sequence-to-sequence mapping problem. The end-to-end trained model has an encoder–decoder architecture that consists of two recurrent neural networks, which has previously shown great success in solving other sequence-to-sequence prediction tasks such as machine translation. The model is trained on 50,000 experimental reaction examples from the United States patent literature, which span 10 broad reaction types that are commonly used by medicinal chemists. We find that our model performs comparably with a rule-based expert system baseline model, and also overcomes certain limitations associated with rule-based expert systems and with any machine learning approach that contains a rule-based expert system component. Our model provides an important first step toward solving the challenging problem of computational retrosynthetic analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

et al. 2017

View full text Add to dashboard Cite

show abstract

“…17 Albeit sturdy, these methods rely heavily on pre-defined atom mapping to map atoms in the reactants to atoms in the product, which is still a nontrivial problem. [18][19] Besides, commonly used tools to identify the atom-mapping are themselves based on databases of expert rules and templates, which seems to get stuck in an infinite loop. 20 At any rate, templatebased models have the limitation that they cannot infer reactions outside the chemical space covered by the template's libraries, and thus are restrained from discovering novel chemistry.…”

Section: Introductionmentioning

confidence: 99%

Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks

Zheng

Rao²,

Zhang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Synthesis planning is the process of recursively decomposing target molecules into available precursors. Computer-aided retrosynthesis can potentially assist chemists in designing synthetic routes, but at present it is cumbersome and provides results of dissatisfactory quality. In this study, we develop a template-free self-corrected retrosynthesis predictor (SCROP) to perform a retrosynthesis prediction task trained by using the Transformer neural network architecture. In the method, the retrosynthesis planning is converted as a machine translation problem between molecular linear notations of reactants and the products. Coupled with a neural network-based syntax corrector, our method achieves an accuracy of 59.0% on a standard benchmark dataset, which increases >21% over other deep learning methods, and >6% over template-based methods. More importantly, our method shows an accuracy 1.7 times higher than other state-of-the-art methods for compounds not appearing in the training set.

show abstract

“…The problem becomes much more difficult when node correspondences are unknown, as is the case e.g. in the atom-mapping problem reviewed in [4]. A classical combinatorial formulation of the latter problem is to find the largest graph G that is isomorphic to a subgraph of each of two given input graphs G 1 and G 2 .…”

Section: Introductionmentioning

confidence: 99%

Spectral classes of regular, random, and empirical graphs

Jost

Liu

et al. 2016

Linear Algebra and its Applications

View full text Add to dashboard Cite

We define a (pseudo-)distance between graphs based on the spectrum of the normalized Laplacian, which is easy to compute or to estimate numerically. It can therefore serve as a rough classification of large empirical graphs into families that share the same asymptotic behavior of the spectrum so that the distance of two graphs from the same family is bounded by O(1/n) in terms of size n of their vertex sets. Numerical experiments demonstrate that the spectral distance provides a practically useful measure of graph dissimilarity.

show abstract

Automatic reaction mapping and reaction center detection

Cited by 77 publications

References 63 publications

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks

Spectral classes of regular, random, and empirical graphs

Contact Info

Product

Resources

About