ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction
This work addresses a fundamental challenge in chemistry for researchers and practitioners, but it is incremental as it builds on existing GNN methods by integrating language models.
The paper tackles the problem of predicting chemical reactions, which is limited by insufficient training data and lack of textual information in conventional GNN-based methods, by proposing ReLM, a framework that leverages language models to assist GNNs, resulting in improved accuracy, especially in out-of-distribution settings.
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.