Structure-Based Drug Design via 3D Molecular Generative Pre-training and Sampling

TL;DR

This paper introduces MolEdit3D, a 3D graph editing model for structure-based drug design that combines molecular generation with optimization, achieving state-of-the-art results in generating high-affinity ligands.

Contribution

It presents a novel 3D graph editing approach pre-trained on ligands and a target-guided self-learning strategy to enhance target-specific properties.

Findings

MolEdit3D outperforms existing methods on key metrics.

The model effectively captures target-dependent and independent properties.

Pre-training on abundant ligands improves generation quality.

Abstract

Structure-based drug design aims at generating high affinity ligands with prior knowledge of 3D target structures. Existing methods either use conditional generative model to learn the distribution of 3D ligands given target binding sites, or iteratively modify molecules to optimize a structure-based activity estimator. The former is highly constrained by data quantity and quality, which leaves optimization-based approaches more promising in practical scenario. However, existing optimization-based approaches choose to edit molecules in 2D space, and use molecular docking to estimate the activity using docking predicted 3D target-ligand complexes. The misalignment between the action space and the objective hinders the performance of these models, especially for those employ deep learning for acceleration. In this work, we propose MolEdit3D to combine 3D molecular generation with optimization frameworks. We develop a novel 3D graph editing model to generate molecules using fragments, and pre-train this model on abundant 3D ligands for learning target-independent properties. Then we employ a target-guided self-learning strategy to improve target-related properties using self-sampled molecules. MolEdit3D achieves state-of-the-art performance on majority of the evaluation metrics, and demonstrate strong capability of capturing both target-dependent and -independent properties.