medical-4

Single-step retrosynthesis

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in single-step-retrosynthesis-4

Trend

Dataset

Best Model

Actions

USPTO-50k

Libraries

i

Use these libraries to find single-step-retrosynthesis-4 models and implementations

Datasets

USPTO-50k

Subtasks

No subtasks available.

Most implemented papers

Retrosynthesis Prediction with Conditional Graph Logic Network

Connor W. Coley, H. Dai, Le Song, Chengtao Li, Bo Dai•Sun Jan 05 2020

The Conditional Graph Logic Network is proposed, a conditional graphical model built upon graph neural networks that learns when rules from reaction templates should be applied, implicitly considering whether the resulting reaction would be both chemically feasible and strategic.

218

Content

0

Paper Graph

State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis

I. Tetko, Pavel Karpov, Ruud Van Deursen, G. Godin•Wed Mar 04 2020

It is demonstrated that applying augmentation techniques to the SMILE representation of target data significantly improves the quality of the reaction predictions.

346 0

Paper Graph

Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits

Stanislaw Jastrzebski, Mikolaj Sacha, Mikolaj Blaz, Piotr Byrski, Pawel Wlodarczyk-Pruszynski•Fri Jun 26 2020

It is argued that representing the reaction as a sequence of edits enables MEGAN to efficiently explore the space of plausible chemical reactions, maintaining the flexibility of modeling the reaction in an end-to-end fashion and achieving state-of-the-art accuracy in standard benchmarks.

178 0

Paper Graph

Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction

Sepp Hochreiter, Marwin H. S. Segler, G. Klambauer, Philipp Seidl, Philipp Renz, N. Dyubankova, Paulo Neves, Jonas Verhoeven, J. Wegner•Tue Apr 06 2021

This study model single-step retrosynthesis in a template-based approach using modern Hopfield networks (MHNs) to associate different modalities, reaction templates and molecules, which allows the model to leverage structural information about reaction templates.

17 0

Paper Graph

Dual-view Molecule Pre-training

Tao Qin, Tie-Yan Liu, Wen-gang Zhou, Houqiang Li, Jinhua Zhu, Yingce Xia•Wed Jun 16 2021

This work proposes to leverage both the representations and design a new pre-training algorithm, dual-view molecule pre- training (briefly, DMP), that can effectively combine the strengths of both types of molecule representations.

55 0

Paper Graph

RetroPrime: A Diverse, Plausible and Transformer-based Method for Single-Step Retrosynthesis Predictions

Xiaorui Wang, Yuquan Li, Huanxiang Liu, X. Yao, J. Qiu, Guangyong Chen, B. Liao, Chang-Yu Hsieh•Tue Apr 20 2021

This work proposes a single-step template-free and Transformer-based method dubbed RetroPrime, integrating chemists’ retrosynthetic strategy of decomposing a molecule into synthons then generating reactants by attaching leaving groups.

122 0

Paper Graph

Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global Attention

Shuan Chen, Yousung Jung•Wed Aug 04 2021

A local retrosynthesis framework called LocalRetro is proposed, motivated by the chemical intuition that the molecular changes occur mostly locally during the chemical reactions, and shows a promising 89.5 and 99.2% round-trip accuracy at top-1 and top-5 predictions for the USPTO-50K dataset containing 50 016 reactions.

173 0

Paper Graph

Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction

Connor W. Coley, Zhengkai Tu•Mon Oct 18 2021

A novel Graph2SMILES model that combines the power of Transformer models for text generation with the permutation invariance of molecular graph encoders that mitigates the need for input data augmentation is described.

134 0

Paper Graph

Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks

Sepp Hochreiter, Marwin H. S. Segler, G. Klambauer, Philipp Seidl, Philipp Renz, N. Dyubankova, Paulo Neves, Jonas Verhoeven, J. Wegner•Fri Jan 14 2022

A template-based single-step retrosynthesis model based on Modern Hopfield Networks is introduced, which learn an encoding of both molecules and reaction templates in order to predict the relevance of templates for a given molecule.

81 0

Paper Graph

RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction

P. Zhao, Chan Lu, Yang Yu, Junzhou Huang, Chao-chao Yan•Sun Dec 19 2021

This work proposes an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates and can produce novel templates for 15 USPTO-50K test reactions that are not covered by training templates.

32 0

Paper Graph

Adding a benchmark result helps the community track progress.