Text-guided multi-property molecular optimization with a diffusion language model

TL;DR

This paper introduces TransDLM, a diffusion language model guided by textual descriptions for multi-property molecular optimization, reducing errors from property predictors and improving molecule design in drug discovery.

Contribution

The paper presents a novel text-guided diffusion model that integrates chemical semantics to improve multi-property molecular optimization, addressing predictor errors and enhancing molecule quality.

Findings

Outperforms state-of-the-art methods in property enhancement

Maintains higher molecular structural similarity

Effectively balances structural retention and property optimization

Abstract

Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property predictors to guide iterative property optimization. However, learning all molecular samples in the vast chemical space is unrealistic for predictors. As a result, errors and noise are inevitably introduced during property prediction due to the nature of approximation. This leads to discrepancy accumulation, generalization reduction and suboptimal molecular candidates. In this paper, we propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM). TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby mitigating error propagation during diffusion process. By fusing physically and chemically detailed textual semantics with specialized molecular representations, TransDLM effectively integrates diverse information sources to guide precise optimization, which enhances the model's ability to balance structural retention and property enhancement. Additionally, the success of a case study further demonstrates TransDLM's ability to solve practical problems. Experimentally, our approach surpasses state-of-the-art methods in maintaining molecular structural similarity and enhancing chemical properties on the benchmark dataset.