Federated Discrete Denoising Diffusion Model for Molecular Generation with OpenFL

TL;DR

This paper introduces a federated discrete denoising diffusion model for molecular generation, enabling privacy-preserving collaborative training across decentralized data sources, and achieves comparable results to centralized models.

Contribution

It presents a novel federated diffusion model for molecular generation trained with OpenFL, addressing data privacy issues in drug discovery.

Findings

Federated model matches centralized model performance in molecule validity and uniqueness.

Demonstrates federated learning's utility in privacy-sensitive drug design.

OpenFL framework effectively supports collaborative molecular generation.

Abstract

Generating unique molecules with biochemically desired properties to serve as viable drug candidates is a difficult task that requires specialized domain expertise. In recent years, diffusion models have shown promising results in accelerating the drug design process through AI-driven molecular generation. However, training these models requires massive amounts of data, which are often isolated in proprietary silos. OpenFL is a federated learning framework that enables privacy-preserving collaborative training across these decentralized data sites. In this work, we present a federated discrete denoising diffusion model that was trained using OpenFL. The federated model achieves comparable performance with a model trained on centralized data when evaluating the uniqueness and validity of the generated molecules. This demonstrates the utility of federated learning in the drug design process. OpenFL is available at: https://github.com/securefederatedai/openfl