A graph-convolutional neural network for addressing small-scale reaction prediction.

We describe a graph-convolutional neural network (GCN) model, the reaction prediction capabilities of which are as potent as those of the transformer model based on sufficient data, and we adopt the Baeyer-Villiger oxidation reaction to explore their performance differences based on limited data. The top-1 accuracy of the GCN model (90.4%) is higher than that of the transformer model (58.4%).

Chemistry Computer Science Medicine

View graph Source

Paper

Full text

A graph-convolutional neural network for addressing small-scale reaction prediction.

Semantic Scholar · Chemistry · 2021

Abstract

We describe a graph-convolutional neural network (GCN) model, the reaction prediction capabilities of which are as potent as those of the transformer model based on sufficient data, and we adopt the Baeyer-Villiger oxidation reaction to explore their performance differences based on limited data. The top-1 accuracy of the GCN model (90.4%) is higher than that of the transformer model (58.4%).

Source of record · Semantic Scholar

Similar papers

Prediction and Interpretable Visualization of Retrosynthetic Reactions Using Graph Convolutional NetworksShoichi Ishida, Kei Terayama, R. Kojima et al.2019 · Journal of Chemical Information and Modeling · 67 citations In Library

Machine Learning of Reaction Properties via Learned Representations of the Condensed Graph of ReactionEsther Heid, W. Green2021 · Journal of Chemical Information and Modeling · 118 citations In Library

Chemical Graph-Based Transformer Models for Yield Prediction of High-Throughput Cross-Coupling Reaction DatasetsAkinori Sato, Ryosuke Asahara, Tomoyuki Miyao2024 · ACS Omega · 7 citations In Library

Graph Transformation Policy Network for Chemical Reaction PredictionKien Do, T. Tran, S. Venkatesh2018 · Knowledge Discovery and Data Mining · 178 citations In Library

Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction ConditionsSerim Ryou, Michael R. Maser, Alexander Cui et al.2020 · arXiv.org · 6 citations In Library

Graph transformer-convolution network for graph classificationLI Cheng-zong, Rui Zhai, Fang Zuo et al.2021 In Library

Graph Neural Networks for Predicting Chemical Reaction PerformanceMandana Saebi, B. Nan, John E. Herr et al.2021 · ChemRxiv · 6 citations In Library

A Graph Convolution-Transformer Neural Network for Drug-Target Interaction PredictionTianjun Wang, Xin Liu2022 · ICBBT · 1 citation In Library

A deep learning framework for accurate reaction prediction and its application on high-throughput experimentation dataBaiqing Li, Shimin Su, Chan Zhu et al.2023 · Journal of Cheminformatics · 40 citations In Library

Property Prediction of Molecules in Graph Convolutional Neural Network ExpansionMei-re Meng, Zhiqiang Wei, Zhuguo Li et al.2019 · 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS) · 13 citations In Library

Source of record

Semantic Scholar

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal