MolEBM: Molecule Generation and Design by Latent Space Energy-Based Modeling

Deqian Kong, Bo Pang, Tian Han, Ying Nian Wu

Keywords: molecule design, energy-based model

TL;DR: We propose a probabilistic generative model to model molecule and molecular properties jointly and naturally achieve molecule design by posterior sampling conditional on desired properties.

Abstract: Generation of molecules with desired chemical and biological properties such as high drug-likeness, high binding affinity to target proteins, is critical in 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. Given the latent vector sampled from the latent space EBM, both molecules and molecular properties are conditionally sampled via a top-down molecule generator model and a property regression model respectively. The EBM in a low dimensional latent space allows our model to capture complex chemical rules implicitly but efficiently and effectively. Due to the joint modeling with chemical properties, molecule design can be conveniently and naturally achieved by conditional sampling from our learned model given desired properties, in both single-objective and multi-objective optimization settings. The latent space EBM, top-down molecule generator, and property regression model are learned jointly by maximum likelihood, while optimization of properties is accomplished by gradual shifting of the model distribution towards the region supported by molecules with high property values. Our experiments show that our model outperforms state-of-the-art models on various molecule design tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )