ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction

Yaorui Shi, An Zhang, Enzhi Zhang, Zhiyuan Liu, Xiang Wang
10/20/2023
cs.LGcs.AI

Official code: syr-cn/ReLM (23 stars, last commit 2024-01-28).

Abstract

Predicting chemical reactions, a fundamental challenge in chemistry, involves forecasting the resulting products from a given reaction process. Conventional techniques, notably those employing Graph Neural Networks (GNNs), are often limited by insufficient training data and their inability to utilize textual information, undermining their applicability in real-world applications. In this work, we propose ReLM, a novel framework that leverages the chemical knowledge encoded in language models (LMs) to assist GNNs, thereby enhancing the accuracy of real-world chemical reaction predictions. To further enhance the model's robustness and interpretability, we incorporate the confidence score strategy, enabling the LMs to self-assess the reliability of their predictions. Our experimental results demonstrate that ReLM improves the performance of state-of-the-art GNN-based methods across various chemical reaction datasets, especially in out-of-distribution settings. Codes are available at https://github.com/syr-cn/ReLM.

View on arXivView PDF

Code Implementations(1)

syr-cn/ReLMOfficial100%

[EMNLP 2023] ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction.

232Shell, PythonOct 18, 20232 years ago

Similar Papers

log-RRIM: Yield Prediction via Local-to-global Reaction Representation Learning and Interaction Modeling

83% match1 repo82024

ReactionT5: a large-scale pre-trained model towards application of limited reaction data

81% match1 repo202023

Cross-Modal Learning for Chemistry Property Prediction: Large Language Models Meet Graph Machine Learning

80% match2024

Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective for Molecular Property Prediction

80% match1 repo42024

Learning Continuous Solvent Effects from Transient Flow Data: A Graph Neural Network Benchmark on Catechol Rearrangement

80% match2025

Beyond Chemical Language: A Multimodal Approach to Enhance Molecular Property Prediction

79% match2023

Cite this paper

@article{shi2023relm,
  title  = {ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction},
  author = {Yaorui Shi and An Zhang and Enzhi Zhang and Zhiyuan Liu and Xiang Wang},
  year   = {2023},
  eprint = {2310.13590},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.13590v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.13590.svg)](https://codeofpaper.com/paper/2310.13590)

Discussion