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

TL;DR

This paper introduces a unified deep-learning framework that combines reaction representation learning and molecule generation, leveraging chemical knowledge and inductive biases to produce high-quality, synthesizable drug-like molecules, advancing reaction-based applications.

Contribution

The paper proposes a novel pretraining framework inspired by organic chemistry mechanisms that unifies reaction understanding and molecule generation tasks, achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on downstream tasks

Generates high-quality, synthesizable drug-like molecules

Overcomes limitations of template-based molecule generation

Abstract

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.