Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting

TL;DR

This paper introduces a probabilistic generative model using an energy-based approach in latent space for molecule design, combined with a gradual distribution shifting algorithm to generate molecules with desired properties, demonstrating strong experimental results.

Contribution

The paper proposes a novel latent space energy-based model and a gradual distribution shifting algorithm for targeted molecule generation, advancing drug discovery methods.

Findings

Effective generation of molecules with desired properties

Strong performance on various molecule design tasks

Successful application of energy-based models in latent space

Abstract

Generation of molecules with desired chemical and biological properties such as high drug-likeness, high binding affinity to target proteins, is critical for drug discovery. In this paper, we propose a probabilistic generative model to capture the joint distribution of molecules and their properties. Our model assumes an energy-based model (EBM) in the latent space. Conditional on the latent vector, the molecule and its properties are modeled by a molecule generation model and a property regression model respectively. To search for molecules with desired properties, we propose a sampling with gradual distribution shifting (SGDS) algorithm, so that after learning the model initially on the training data of existing molecules and their properties, the proposed algorithm gradually shifts the model distribution towards the region supported by molecules with desired values of properties. Our experiments show that our method achieves very strong performances on various molecule design tasks.