Realistic molecule optimization on a learned graph manifold

TL;DR

This paper introduces a hybrid molecule optimization method combining learned graph distributions with the Metropolis algorithm, resulting in more realistic molecules and improved performance over recent baselines.

Contribution

It proposes the learned realism sampling (LRS) approach that enhances molecule realism during optimization by integrating a learned dataset distribution with the Metropolis algorithm.

Findings

LRS produces more realistic molecules than previous methods.

LRS outperforms recent baselines in molecule optimization tasks.

The hybrid approach effectively balances realism and optimization quality.

Abstract

Deep learning based molecular graph generation and optimization has recently been attracting attention due to its great potential for de novo drug design. On the one hand, recent models are able to efficiently learn a given graph distribution, and many approaches have proven very effective to produce a molecule that maximizes a given score. On the other hand, it was shown by previous studies that generated optimized molecules are often unrealistic, even with the inclusion of mechanics to enforce similarity to a dataset of real drug molecules. In this work we use a hybrid approach, where the dataset distribution is learned using an autoregressive model while the score optimization is done using the Metropolis algorithm, biased toward the learned distribution. We show that the resulting method, that we call learned realism sampling (LRS), produces empirically more realistic molecules and outperforms all recent baselines in the task of molecule optimization with similarity constraints.