Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables

TL;DR

This paper introduces RetroDVCAE, a novel sequence-based model using discrete latent variables and Gumbel-Softmax to generate diverse reactant sets for single-step retrosynthesis, improving reaction diversity over existing methods.

Contribution

The work presents RetroDVCAE, a new approach integrating conditional variational autoencoders with discrete latent variables to enhance diversity in retrosynthesis predictions.

Findings

RetroDVCAE outperforms state-of-the-art models on benchmark datasets.

The model effectively captures multi-modal reaction distributions.

It generates diverse reactant candidates for a given product.

Abstract

Single-step retrosynthesis is the cornerstone of retrosynthesis planning, which is a crucial task for computer-aided drug discovery. The goal of single-step retrosynthesis is to identify the possible reactants that lead to the synthesis of the target product in one reaction. By representing organic molecules as canonical strings, existing sequence-based retrosynthetic methods treat the product-to-reactant retrosynthesis as a sequence-to-sequence translation problem. However, most of them struggle to identify diverse chemical reactions for a desired product due to the deterministic inference, which contradicts the fact that many compounds can be synthesized through various reaction types with different sets of reactants. In this work, we aim to increase reaction diversity and generate various reactants using discrete latent variables. We propose a novel sequence-based approach, namely RetroDVCAE, which incorporates conditional variational autoencoders into single-step retrosynthesis and associates discrete latent variables with the generation process. Specifically, RetroDVCAE uses the Gumbel-Softmax distribution to approximate the categorical distribution over potential reactions and generates multiple sets of reactants with the variational decoder. Experiments demonstrate that RetroDVCAE outperforms state-of-the-art baselines on both benchmark dataset and homemade dataset. Both quantitative and qualitative results show that RetroDVCAE can model the multi-modal distribution over reaction types and produce diverse reactant candidates.