Fragment-Masked Diffusion for Molecular Optimization

TL;DR

This paper introduces FMOP, a phenotypic drug discovery-based molecular optimization method using a diffusion model to generate new molecules with improved efficacy, achieving high success rates on large-scale datasets.

Contribution

Proposes a novel fragment-masked molecular optimization method based on phenotypic drug discovery and diffusion models, enhancing molecule generation without relying on target structures.

Findings

Optimization success rate of 95.4% on GDSCv2 dataset

Average efficacy increase of 7.5%

Effective and robust molecular optimization demonstrated

Abstract

Molecular optimization is a crucial aspect of drug discovery, aimed at refining molecular structures to enhance drug efficacy and minimize side effects, ultimately accelerating the overall drug development process. Many molecular optimization methods have been proposed, significantly advancing drug discovery. These methods primarily on understanding the specific drug target structures or their hypothesized roles in combating diseases. However, challenges such as a limited number of available targets and a difficulty capturing clear structures hinder innovative drug development. In contrast, phenotypic drug discovery (PDD) does not depend on clear target structures and can identify hits with novel and unbiased polypharmacology signatures. As a result, PDD-based molecular optimization can reduce potential safety risks while optimizing phenotypic activity, thereby increasing the likelihood of clinical success. Therefore, we propose a fragment-masked molecular optimization method based on PDD (FMOP). FMOP employs a regression-free diffusion model to conditionally optimize the molecular masked regions, effectively generating new molecules with similar scaffolds. On the large-scale drug response dataset GDSCv2, we optimize the potential molecules across all 985 cell lines. The overall experiments demonstrate that the in-silico optimization success rate reaches 95.4\%, with an average efficacy increase of 7.5\%. Additionally, we conduct extensive ablation and visualization experiments, confirming that FMOP is an effective and robust molecular optimization method. The code is available at: https://anonymous.4open.science/r/FMOP-98C2.