Zero Shot Molecular Generation via Similarity Kernels

TL;DR

This paper analyzes the score behavior in diffusion models for molecular generation and introduces SiMGen, a zero-shot method combining similarity kernels and pretrained force fields for controllable molecule design.

Contribution

The paper provides insights into the score dynamics in diffusion models and introduces SiMGen, a novel zero-shot molecular generation method using similarity kernels and pretrained descriptors.

Findings

Score resembles a restorative potential initially and a quantum-mechanical force at the end.

SiMGen enables zero-shot molecule generation without additional training.

The approach supports shape control and conditional generation.

Abstract

Generative modelling aims to accelerate the discovery of novel chemicals by directly proposing structures with desirable properties. Recently, score-based, or diffusion, generative models have significantly outperformed previous approaches. Key to their success is the close relationship between the score and physical force, allowing the use of powerful equivariant neural networks. However, the behaviour of the learnt score is not yet well understood. Here, we analyse the score by training an energy-based diffusion model for molecular generation. We find that during the generation the score resembles a restorative potential initially and a quantum-mechanical force at the end. In between the two endpoints, it exhibits special properties that enable the building of large molecules. Using insights from the trained model, we present Similarity-based Molecular Generation (SiMGen), a new method for zero shot molecular generation. SiMGen combines a time-dependent similarity kernel with descriptors from a pretrained machine learning force field to generate molecules without any further training. Our approach allows full control over the molecular shape through point cloud priors and supports conditional generation. We also release an interactive web tool that allows users to generate structures with SiMGen online (https://zndraw.icp.uni-stuttgart.de).