Discovery of Novel Chemical Reactions by Deep Generative Recurrent Neural Network

Bort, William; Baskin, Igor I.; Сидоров, П. И.; Marcou, Gilles; Horvath, Dragos; Madzhidov, Timur; Varnek, Alexandre; Gimadiev, Timur; Nugmanov, Ramil; Mukanov, Artem

doi:10.26434/chemrxiv.11635929

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the meantime, the large amount of accumulated chemical knowledge has become a suitable resource for deep learning. In the past decade, data-driven deep learning models based on the statistical learning of a vast number of existing reactions have been applied to retrosynthesis, reaction condition recommendation, generation of novel reactions, and forward-reaction prediction 3,4 . For forward-reaction predictions, there exist graphical convolutional neural networks 5,6 and simplified molecular-input line-entry system (SMILES)-based sequence-to-sequence (seq2seq) models 7,8 that take the SMILES of reactants and reagents as the input language and output the products as the translated language.…”

Section: Introductionmentioning

confidence: 99%

Reproducing the invention of a named reaction: zero-shot prediction of unseen chemical reactions

Wang²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

While state-of-art models can predict reactions through the transfer learning of thousands of samples with the same reaction types as those of the reactions to predict, how to prepare such models to predict "unseen" reactions remain an unanswered question. We aim to study the Transformer model's ability to predict "unseen" reactions following "zero-shot reaction prediction (ZSRP)", a concept derived from zero-shot learning and zero-shot translation. We reproduce the human invention of the Chan-Lam coupling reaction where the inventor was inspired by the Suzuki reaction when improving Barton's bismuth arylation reaction. After being fine-tuned with the samples from these two "existing" reactions, the USPTO-trained Transformer can predict "unseen" Chan-Lam coupling reactions with 55.7% top-1 accuracy. Our model also mimics the later stage of the history of this reaction, where the initial case of this reaction was generalized to more reactants and reagents via the "one-shot/few-shot reaction prediction (OSRP/FSRP)" approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Reproducing the invention of a named reaction: zero-shot prediction of unseen chemical reactions

Wang²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…19 It was also recently used to visualize chemical reactions embedded into the latent space of a generative variational autoencoder. 20 The t-SNE method was used to explore the structure of bioactive organic molecules datasets. 21 In this paper, we describe the application of the parametric t-SNE method to explore chemical reaction space.…”

Section: Introductionmentioning

confidence: 99%

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

Andronov¹,

Fedorov²,

Sosnin

2021

Preprint

View full text Add to dashboard Cite

<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 could 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 in 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 to explore reaction space and will inspire chemists to find new reactions and synthetic ways. </div><div><br></div>

show abstract

“…This has created an urgent need for automated solutions to extract information from patents in order to expedite the work of synthetic chemists ( Lowe and Mayfield, 2020 ). Furthermore, these databases allow for the discovery of new chemical and synthetic pathways ( Wang et al, 2001 ; Bort et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Identifying Chemical Reactions and Their Associated Attributes in Patents

Mahendran

Gurdin

Lewinski

et al. 2021

Front. Res. Metr. Anal.

View full text Add to dashboard Cite

Chemical patents are an essential source of information about novel chemicals and chemical reactions. However, with the increasing volume of such patents, mining information about these chemicals and chemical reactions has become a time-intensive and laborious endeavor. In this study, we present a system to extract chemical reaction events from patents automatically. Our approach consists of two steps: 1) named entity recognition (NER)—the automatic identification of chemical reaction parameters from the corresponding text, and 2) event extraction (EE)—the automatic classifying and linking of entities based on their relationships to each other. For our NER system, we evaluate bidirectional long short-term memory (BiLSTM)-based and bidirectional encoder representations from transformer (BERT)-based methods. For our EE system, we evaluate BERT-based, convolutional neural network (CNN)-based, and rule-based methods. We evaluate our NER and EE components independently and as an end-to-end system, reporting the precision, recall, and F1 score. Our results show that the BiLSTM-based method performed best at identifying the entities, and the CNN-based method performed best at extracting events.

show abstract

Discovery of Novel Chemical Reactions by Deep Generative Recurrent Neural Network

Cited by 4 publications

References 0 publications

Reproducing the invention of a named reaction: zero-shot prediction of unseen chemical reactions

Reproducing the invention of a named reaction: zero-shot prediction of unseen chemical reactions

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

Identifying Chemical Reactions and Their Associated Attributes in Patents

Contact Info

Product

Resources

About