Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?

TL;DR

This paper benchmarks sixteen structure-based drug design models across different algorithmic types, revealing that 1D/2D methods can be competitive with 3D approaches and highlighting AutoGrow4's superior optimization performance.

Contribution

It provides the first comprehensive cross-algorithm benchmark for SBDD models, comparing their pharmaceutical and docking performance.

Findings

1D/2D methods are competitive with 3D methods.

AutoGrow4 outperforms other models in optimization.

Different algorithms have unique advantages and trade-offs.

Abstract

Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper, to fill the gap, we establish a benchmark to evaluate the performance of sixteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules and their docking affinities with specified target proteins. We highlight the unique advantages of each algorithmic approach and offer recommendations for the design of future SBDD models. We emphasize that 1D/2D ligand-centric drug design methods can be used in SBDD by treating the docking function as a black-box oracle, which is typically neglected. The empirical results show that 1D/2D methods achieve competitive performance compared with 3D-based methods that use the 3D structure of the target protein explicitly. Also, AutoGrow4, a 2D molecular graph-based genetic algorithm, dominates SBDD in terms of optimization ability. The relevant code is available in https://github.com/zkysfls/2024-sbdd-benchmark.