ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction

TL;DR

ReLM is a novel framework that combines language models with graph neural networks to improve chemical reaction prediction accuracy, especially in challenging real-world and out-of-distribution scenarios.

Contribution

The paper introduces ReLM, integrating language models with GNNs and confidence scoring to enhance chemical reaction prediction beyond existing methods.

Findings

ReLM outperforms state-of-the-art GNN methods on multiple datasets.

ReLM shows significant improvements in out-of-distribution predictions.

Confidence scores help assess prediction reliability effectively.

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.