RetroXpert: Decompose Retrosynthesis Prediction like a Chemist
This addresses the need for more interpretable and efficient retrosynthesis prediction tools for chemists and researchers in organic synthesis, representing a novel method rather than an incremental improvement.
The paper tackled the problem of automating retrosynthesis prediction in organic synthesis planning by proposing a template-free algorithm that decomposes the process into two interpretable steps, resulting in a model that outperforms state-of-the-art baselines by a significant margin and provides chemically reasonable interpretations.
Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate or assist in the retrosynthesis analysis, various retrosynthesis prediction algorithms have been proposed. However, most of them are cumbersome and lack interpretability about their predictions. In this paper, we devise a novel template-free algorithm for automatic retrosynthetic expansion inspired by how chemists approach retrosynthesis prediction. Our method disassembles retrosynthesis into two steps: i) identify the potential reaction center of the target molecule through a novel graph neural network and generate intermediate synthons, and ii) generate the reactants associated with synthons via a robust reactant generation model. While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.