Root-aligned SMILES: a tight representation for chemical reaction prediction (2022-03-22T00:00:00.000000Z)

TL;DR

This article proposes the root-aligned SMILES (R-SMILES), which is a tightly aligned one-to-one mapping between the product and the reactant SMilES for more e-cient synthesis prediction and shows that it signiﬁcantly outperforms them all, demonstrating the superiority of the proposed method.

Abstract

Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis. A popular computational paradigm formulates synthesis prediction as a sequence-to-sequence translation problem, where the typical SMILES is adopted for molecule representations. However, the general-purpose SMILES neglects the characteristics of chemical reactions, where the molecular graph topology is largely unaltered from reactants to products, resulting in the suboptimal performance of SMILES if straightforwardly applied. In this article, we propose the root-aligned SMILES (R-SMILES), which specifies a tightly aligned one-to-one mapping between the product and the reactant SMILES for more efficient synthesis prediction. Due to the strict one-to-one mapping and reduced edit distance, the computational model is largely relieved from learning the complex syntax and dedicated to learning the chemical knowledge for reactions. We compare the proposed R-SMILES with various state-of-the-art baselines and show that it significantly outperforms them all, demonstrating the superiority of the proposed method.

Authors

Jie Song

5 papers

Mingli Song

2 papers

Zipeng Zhong

1 papers

TL;DR

Abstract

Authors

References55 items

Retrosynthetic reaction pathway prediction through neural machine translation of atomic environments

Masked Autoencoders Are Scalable Vision Learners

Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global Attention

Chemformer: a pre-trained transformer for computational chemistry

GTA: Graph Truncated Attention for Retrosynthesis

RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

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

Extraction of organic chemistry grammar from unsupervised learning of chemical reactions

Valid, Plausible, and Diverse Retrosynthesis Using Tied Two-Way Transformers with Latent Variables

Towards understanding retrosynthesis by energy-based models

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

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

Learning Graph Models for Retrosynthesis Prediction

RetroXpert: Decompose Retrosynthesis Prediction like a Chemist

A Graph to Graphs Framework for Retrosynthesis Prediction

A Bayesian algorithm for retrosynthesis

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

5分で分かる!? 有名論文ナナメ読み：Jacob Devlin et al. : BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding

Retrosynthesis Prediction with Conditional Graph Logic Network

Predicting Retrosynthetic Reactions Using Self-Corrected Transformer Neural Networks

Automatic Retrosynthetic Pathway Planning Using Template-free Models

A Transformer Model for Retrosynthesis

Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction

Computer-Assisted Retrosynthesis Based on Molecular Similarity

Graph Attention Networks

Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

Attention is All you Need

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction.

Modeling Relational Data with Graph Convolutional Networks

Linking the Neural Machine Translation and the Prediction of Organic Chemistry Reactions

What's What: The (Nearly) Definitive Guide to Reaction Role Assignment

Variational Autoencoder for Deep Learning of Images, Labels and Captions

Computer-Assisted Synthetic Planning: The End of the Beginning.

Get Your Atoms in Order - An Open-Source Implementation of a Novel and Robust Molecular Canonicalization Algorithm

Efficient Heuristics for Maximum Common Substructure Search

Towards a Universal SMILES representation - A standard method to generate canonical SMILES based on the InChI

Enantioselective synthesis of (R)-salmeterol employing an asymmetric Henry reaction as the key step

Investigations into the Suzuki–Miyaura coupling aiming at multikilogram synthesis of E2040 using (o-cyanophenyl)boronic esters

Computer-assisted synthesis and reaction planning in combinatorial chemistry

Palladium(0)-Catalyzed Cross-Coupling Reaction of Alkoxydiboron with Haloarenes: A Direct Procedure for Arylboronic Esters

SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules

LHASA—Logic and Heuristics Applied to Synthetic Analysis

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Articial Neural Networks and Machine Learning – ICANN

arXiv, DOI: 10.48550/ arXiv.1612.09529

The preparation of febuxo-stat by suzuki reaction

Design, Synthesis and Biological Evaluation of Novel Benzopyran Sulfonamide Derivatives as 5-HT6 Receptor Ligands

Designing an expert system for organic synthesis in expert systems application in chemistry

Cl)Cl O=C(O)C=C.C(Cl)C(Cl)(Cl)Cl O=C(O)C=C.OCC(Cl)(Cl)Cl O=C(=O)C=C.C(O)C(Cl)(Cl)Cl Canonicalize and Augmentation score C=CC(=O)OCC(Cl)C(Cl)(Cl)Cl C=CC=O

C=C)=O)(Cl)(Cl)Cl Beam Search C(Cl)(COC(C=C)=O)C(Cl)(Cl)Cl C(CO)(Cl)(Cl)Cl.C(C=C)=O

RDKit: Open-Source Chemin-formatics Software

C(CO)(Cl)(Cl)Cl.O=C(C=C)OO

Ring-forming reaction b 15.2 (-36%)

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names