Bridging the Gap between Chemical Reaction Pretraining and Conditional Molecule Generation with a Unified Model

Chemical reactions are the fundamental building blocks of drug design and organic chemistry research. In recent years, there has been a growing need for a large-scale deep-learning framework that can efficiently capture the basic rules of chemical reactions. In this paper, we have proposed a unified framework that addresses both the reaction representation learning and molecule generation tasks, which allows for a more holistic approach. Inspired by the organic chemistry mechanism, we develop a novel pretraining framework that enables us to incorporate inductive biases into the model. Our framework achieves state-of-the-art results on challenging downstream tasks. By possessing chemical knowledge, our generative framework overcome the limitations of current molecule generation models that rely on a small number of reaction templates. In the extensive experiments, our model generates synthesizable drug-like structures of high quality. Overall, our work presents a significant step toward a large-scale deep-learning framework for a variety of reaction-based applications. Deep learning models have found applications across a multitude of scientific research domains [1-3]. Pretraining frameworks [4, 5] facilitate the seamless integration of new tasks, thereby expediting the modeling process, especially for scenarios with limited labeled data. Chemical reactions are the foundation of drug design and organic chemistry studies. Currently, data-mining works [6, 7] have enabled deep learning models to be applied to chemical reactions. Based on these data, there have been plenty of data-driven works that intend to delve into the representation learning of chemical reactions. Representation learning refers to automatically learning useful features from the data, which can then be used for various downstream tasks [8]. In earlier works, traditional molecular fingerprints were applied directly for reaction representations[9, 10]. Inspired by natural language processing (NLP) methods, researchers also applied attention-based network[11, 12] or contrastive learning techniques[13, 14] in chemical reaction pretraining networks. These representations have been tested on classification tasks[15] or regression tasks[16]. However, these methods ignore the fundamental theories in organic chemistry, which limits their performance. For example, electronic effects and inductive effects will be ignored if bonds or atoms outside the reactive centers are masked [13]. Except for reaction classification tasks, molecule generation based on chemical reactions is also an important application. This branch of models has been proven to be capable of generating synthetically accessible molecules.[17-20]. Earlier works always applied a step-wise template-based molecule generation strategy.