UniGEM: A Unified Approach to Generation and Property Prediction for Molecules

TL;DR

UniGEM introduces a novel unified model that simultaneously improves molecular generation and property prediction by employing a two-phase generative process and innovative training strategies, demonstrating superior performance and broad applicability.

Contribution

It is the first model to successfully integrate molecular generation and property prediction with a two-phase process and enhanced training strategies.

Findings

Significant improvements in molecular generation quality.

Enhanced accuracy in property prediction tasks.

Theoretical analysis supports the model's effectiveness.

Abstract

Molecular generation and molecular property prediction are both crucial for drug discovery, but they are often developed independently. Inspired by recent studies, which demonstrate that diffusion model, a prominent generative approach, can learn meaningful data representations that enhance predictive tasks, we explore the potential for developing a unified generative model in the molecular domain that effectively addresses both molecular generation and property prediction tasks. However, the integration of these tasks is challenging due to inherent inconsistencies, making simple multi-task learning ineffective. To address this, we propose UniGEM, the first unified model to successfully integrate molecular generation and property prediction, delivering superior performance in both tasks. Our key innovation lies in a novel two-phase generative process, where predictive tasks are activated in the later stages, after the molecular scaffold is formed. We further enhance task balance through innovative training strategies. Rigorous theoretical analysis and comprehensive experiments demonstrate our significant improvements in both tasks. The principles behind UniGEM hold promise for broader applications, including natural language processing and computer vision.