A Transformer Model for Retrosynthesis

Карпов, П. А.; Godin, Guillaume; Tetko, Igor V.

doi:10.26434/chemrxiv.8058464

Cited by 19 publications

(30 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…et al, 2017] and LSTM+Attention [Liu et al, 2017]. Note that the results of vanilla Transformer are based on our own experiments since the results reported by previous works [Zheng et al, 2019;Lin et al, 2019;Karpov et al, 2019;Lee et al, 2019] are different from each other. Actually, their results are closed to the results of our implementation.…”

Section: Settingsmentioning

confidence: 82%

“…Moreover, without the constraint of fixed templates, they have the potential of discovering novel synthetic routes. The most related work to ours are [Zheng et al, 2019] [Lin et al, 2019Karpov et al, 2019;Lee et al, 2019] that apply Transformer to retrosynthesis prediction.…”

Section: Related Workmentioning

confidence: 99%

“…Dataset Splitting. Previous works [Liu et al, 2017;Zheng et al, 2019;Karpov et al, 2019] follow a specific split strategy with 40,029, 5,004 and 5,004 reactions for training, validation and testing, and we keep the same. Implementation Details.…”

Section: Settingsmentioning

confidence: 99%

“…Based on this idea, [Liu et al, 2017] first applied LSTM with attention mechanism in retrosynthesis prediction and achieved comparable performance. Whereafter, many works [Karpov et al, 2019;Zheng et al, 2019;Lin et al, 2019;Lee et al, 2019] tried to employ Transformer [Vaswani et al, 2017], a more powerful Sequence-to-Sequence(Seq2Seq) model, to improve prediction accuracy in retrosynthesis. However, these methods just utilize the sequential representations of the molecule, while ignoring the natural topological connections between atoms within the molecule.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Molecular Graph Enhanced Transformer for Retrosynthesis Prediction

Mao

Zhao

et al. 2020

Preprint

View full text Add to dashboard Cite

With massive possible synthetic routes in chemistry, retrosynthesis prediction is still a challenge for researchers. Recently, retrosynthesis prediction is formulated as a Machine Translation (MT) task. Namely, since each molecule can be represented as a Simplified Molecular-Input Line-Entry System (SMILES) string, the process of retrosynthesis is analogized to a process of language translation from the product to reactants. However, the MT models that applied on SMILES data usually ignore the information of natural atomic connections and the topology of molecules. To make more chemically plausible constrains on the atom representation learning for better performance, in this paper, we propose a Graph Enhanced Transformer (GET) framework, which adopts both the sequential and graphical information of molecules. Four different GET designs are proposed, which fuse the SMILES representations with atom embeddings learned from our improved Graph Neural Network (GNN). Empirical results show that our model significantly outperforms the vanilla Transformer model in test accuracy.

show abstract

Section: Settingsmentioning

confidence: 82%

Section: Related Workmentioning

confidence: 99%

Section: Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Molecular Graph Enhanced Transformer for Retrosynthesis Prediction

Mao

Zhao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The method has benefited from the recent progress in the neural machine translation field where the Transformer architecture demonstrated state-of-the-art results [34]. Recently the Transformer also exhibited very promising results in predicting the products of chemical reaction and retrosynthesis [56,57]. One of the key features of the Transformer is self-attention layers.…”

Section: The Transformer Applicability To Drug Generation Taskmentioning

confidence: 99%

Transformer neural network for protein-specific de novo drug generation as a machine translation problem

Grechishnikova

2019

Preprint

View full text Add to dashboard Cite

Drug discovery for the protein target is a very laborious, long and costly process. Machine learning approaches, and deep generative networks in particular, can substantially reduce development time and costs. However, the majority of methods imply prior knowledge of protein binders, their physicochemical characteristics or three-dimensional structure of the protein. The method proposed in this work generates novel molecules with predicted ability to bind target protein relying on its amino acid sequence only. We consider target specific de novo drug design as a translational problem between amino acid "language" and SMILE (Simplified Molecular Input Line Entry System) representation of the molecule. To tackle this problem, we apply Transformer neural network architecture, the state-of-the-art approach in sequence transduction tasks. The Transformer is based on a self-attention technique which allows capturing long-range dependencies between items in sequence. The model generates realistic diverse compounds with structural novelty. The computed physicochemical properties and common metrics used in drug discovery fall within the plausible drug-like range of values.Most of the deep learning models for molecule generation are based on recurrent neural network (RNN). RNN is commonly used for modeling sequence data. The main feature of RNN allowing it to work with sequential data is the ability to make use of information from preceding steps. RNN can reveal links between distant elements of a sequence [8]. Unfortunately, RNNs suffer from the problem of vanishing gradients which significantly limits the ability to work with long sequences.

show abstract

Structure–Activity Relationship Prediction‐Based Synthesis and Cytotoxicity Evaluation against the HEp‐2 Laryngeal Carcinoma Cell of Isoflavone–Cytisine Mannich Bases

Mrug,

Hodyna,

Metelytsia

et al. 2023

Chemistry & Biodiversity

View full text Add to dashboard Cite

QSAR analysis of previously synthesized and nature‐inspired virtual isoflavone‐cytisine hybrids against the HEp‐2 laryngeal carcinoma cell lines was performed using the OCHEM web platform. The validation of the models using an external test set proved that the models can be used to predict the activity of newly designed compounds such as 8‐cytisinylmethyl derivatives of 5,7‐ and 6,7‐dihydroxyisoflavones. The synthetic procedure for selective aminomethylation of 5,7‐dihydroxyisoflavones with cytisine was developed. In vitro testing identified compound 7 f with cisplatin‐level cytotoxicity against HEp‐2 cell lines and compound 10 which was twice active than cisplatin after 72 h of incubation.

show abstract

A Transformer Model for Retrosynthesis

Cited by 19 publications

References 0 publications

Molecular Graph Enhanced Transformer for Retrosynthesis Prediction

Molecular Graph Enhanced Transformer for Retrosynthesis Prediction

Transformer neural network for protein-specific de novo drug generation as a machine translation problem

Structure–Activity Relationship Prediction‐Based Synthesis and Cytotoxicity Evaluation against the HEp‐2 Laryngeal Carcinoma Cell of Isoflavone–Cytisine Mannich Bases

Contact Info

Product

Resources

About