Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-Based Drug Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Kangyu, Zhang, Kai, Tan, Jiale, Chen, Xuehan, Lu, Yingzhou, Zhang, Zaixi, Sun, Lichao, Zitnik, Marinka, Fu, Tianfan, Liang, Zhiding
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915742339825664
author Zheng, Kangyu
Zhang, Kai
Tan, Jiale
Chen, Xuehan
Lu, Yingzhou
Zhang, Zaixi
Sun, Lichao
Zitnik, Marinka
Fu, Tianfan
Liang, Zhiding
author_facet Zheng, Kangyu
Zhang, Kai
Tan, Jiale
Chen, Xuehan
Lu, Yingzhou
Zhang, Zaixi
Sun, Lichao
Zitnik, Marinka
Fu, Tianfan
Liang, Zhiding
contents 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 fifteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules and their docking affinities and poses 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. Our evaluation reveals distinct patterns across model categories. 3D structure-based models excel in binding affinities but show inconsistencies in chemical validity and pose quality. 1D models demonstrate reliable performance in standard molecular metrics but rarely achieve optimal binding affinities. 2D models offer balanced performance, maintaining high chemical validity while achieving moderate binding scores. Through detailed analysis across multiple protein targets, we identify key improvement areas for each model category, providing insights for researchers to combine strengths of different approaches while addressing their limitations. All the code that are used for benchmarking is available in https://github.com/zkysfls/2025-sbdd-benchmark
format Preprint
id arxiv_https___arxiv_org_abs_2601_14283
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-Based Drug Design
Zheng, Kangyu
Zhang, Kai
Tan, Jiale
Chen, Xuehan
Lu, Yingzhou
Zhang, Zaixi
Sun, Lichao
Zitnik, Marinka
Fu, Tianfan
Liang, Zhiding
Machine Learning
Artificial Intelligence
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 fifteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules and their docking affinities and poses 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. Our evaluation reveals distinct patterns across model categories. 3D structure-based models excel in binding affinities but show inconsistencies in chemical validity and pose quality. 1D models demonstrate reliable performance in standard molecular metrics but rarely achieve optimal binding affinities. 2D models offer balanced performance, maintaining high chemical validity while achieving moderate binding scores. Through detailed analysis across multiple protein targets, we identify key improvement areas for each model category, providing insights for researchers to combine strengths of different approaches while addressing their limitations. All the code that are used for benchmarking is available in https://github.com/zkysfls/2025-sbdd-benchmark
title Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-Based Drug Design
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.14283