CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
Haitao Lin, Guojiang Zhao, Odin Zhang, Yufei Huang, Lirong Wu, Cheng Tan, Zicheng Liu, Zhifeng Gao, Stan Z. Li
Abstract
Structure-based drug design (SBDD) aims to generate potential drugs that can bind to a target protein and is greatly expedited by the aid of AI techniques in generative models. However, a lack of systematic understanding persists due to the diverse settings, complex implementation, difficult reproducibility, and task singularity. Firstly, the absence of standardization can lead to unfair comparisons and inconclusive insights. To address this dilemma, we propose CBGBench, a comprehensive benchmark for SBDD, that unifies the task as a generative graph completion, analogous to fill-in-the-blank of the 3D complex binding graph. By categorizing existing methods based on their attributes, CBGBench facilitates a modular and extensible framework that implements various cutting-edge methods. Secondly, a single de novo molecule generation task can hardly reflect their capabilities. To broaden the scope, we adapt these models to a range of tasks essential in drug design, considered sub-tasks within the graph fill-in-the-blank tasks. These tasks include the generative designation of de novo molecules, linkers, fragments, scaffolds, and sidechains, all conditioned on the structures of protein pockets. Our evaluations are conducted with fairness, encompassing comprehensive perspectives on interaction, chemical properties, geometry authenticity, and substructure validity. We further provide deep insights with analysis from empirical studies. Our results indicate that there is potential for further improvements on many tasks, with optimization in network architectures, and effective incorporation of chemical prior knowledge. Finally, to lower the barrier to entry and facilitate further developments in the field, we also provide a single codebase (https://github.com/EDAPINENUT/CBGBench) that unifies the discussed state-of-the-art models, data pre-processing, training, sampling, and evaluation.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
9 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- MoleBridge: Synthetic Space Projecting with Discrete Markov Bridges cites Denoising Diffusion Probabilistic Models
- UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design cites E(n) Equivariant Graph Neural Networks
- UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design cites Denoising Diffusion Probabilistic Models
- Score-Based Generative Modeling through Stochastic Differential Equations cites Denoising Diffusion Probabilistic Models
Cited by top-tier papers9
- Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom NumberJingyuan Zhou, Hao Qian, Shikui Tu, Lei XuNeurIPS 2025 · 11 citations
- MoleBridge: Synthetic Space Projecting with Discrete Markov BridgesRongchao Zhang, Yu Huang, Yongzhi Cao, Hanpin WangNeurIPS 2025 · 8 citations
- CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMsBowen Gao, Yanwen Huang, Yiqiao Liu, Wenxuan Xie et al.NeurIPS 2025 · 4 citations
- Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow NetworksKeyue Qiu, Yuxuan Song, Jie Yu, Hongbo Ma et al.ICML 2025
- UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder DesignXiangzhe Kong, Zishen Zhang, Ziting Zhang, Rui Jiao et al.ICML 2025
Builds on26
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- E(n) Equivariant Graph Neural NetworksVictor Garcia Satorras, Emiel Hoogeboom, Max WellingICML 2021 · 1,432 citations
- Score-Based Generative Modeling through Stochastic Differential EquationsYang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar et al.ICLR 2021 · 1,270 citations
- Learning from Protein Structure with Geometric Vector PerceptronsBowen Jing, Stephan Eismann, Patricia Suriana, Raphael John Lamarre Townshend et al.ICLR 2021 · 627 citations
Related papers
- Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient IntegrationSeungyeon Choi, Hwanhee Kim, Chihyun Park, Dahyeon Lee et al.NeurIPS 2025 · 4 citations
- A 3D Generative Model for Structure-Based Drug DesignShitong Luo, Jiaqi Guan, Jianzhu Ma, Jian PengNeurIPS 2021 · 302 citations
- Learning Subpocket Prototypes for Generalizable Structure-based Drug DesignZaixi Zhang, Qi LiuICML 2023 · 42 citations
- Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and ElaborationHaitao Lin, Yufei Huang, Odin Zhang, Yunfan Liu et al.NeurIPS 2023 · 51 citations
- Molecule Generation For Target Protein Binding with Structural MotifsZaixi Zhang, Yaosen Min, Shuxin Zheng, Qi LiuICLR 2023
