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

arXiv: https://arxiv.org/abs/2406.03403 · HTML: https://mlsanity.com/paper/2406.03403/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [Optimization of Molecules via Deep Reinforcement Learning](https://mlsanity.com/paper/1810.08678/) (2018)
- [Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets](https://mlsanity.com/paper/2205.07249/) (2022)
- [A 3D Generative Model for Structure-Based Drug Design](https://mlsanity.com/paper/2203.10446/) (2022)
- [MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design](https://mlsanity.com/paper/2203.14500/) (2022)
- [Accelerating high-throughput virtual screening through molecular pool-based active learning](https://mlsanity.com/paper/2012.07127/) (2020)
- [Differentiable Scaffolding Tree for Molecular Optimization](https://mlsanity.com/paper/2109.10469/) (2021)
- [MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization](https://mlsanity.com/paper/2010.02318/) (2020)
- [HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data](https://mlsanity.com/paper/2102.04252/) (2021)
- [ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?](https://mlsanity.com/paper/1708.08227/) (2017)
- [Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations](https://mlsanity.com/paper/2012.09712/) (2020)
- [Uncertainty Quantification on Clinical Trial Outcome Prediction](https://mlsanity.com/paper/2401.03482/) (2024)

## Built on by (most cited first, 7 of 7)

- [D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models](https://mlsanity.com/paper/2406.13035/) (2024)
- [Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS](https://mlsanity.com/paper/2507.05557/) (2025)
- [3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery](https://mlsanity.com/paper/2502.05107/) (2025)
- [Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-Based Drug Design](https://mlsanity.com/paper/2601.14283/) (2026)
- [CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation](https://mlsanity.com/paper/2604.11483/) (2026)
- [DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning](https://mlsanity.com/paper/2410.02023/) (2024)
- [TransDiffSBDD: Causality-Aware Multi-Modal Structure-Based Drug Design](https://mlsanity.com/paper/2503.20913/) (2025)

## Abstract (arXiv)

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.