SpecLig: Energy-Guided Hierarchical Model for Target-Specific 3D Ligand Design
Authors:
Preprint
Abstract
Structure-based generative models often optimize single-target affinity with ignorance of specificity, resulting in the generation of high-affinity candidates that exhibit promiscuous binding across unrelated targets. This decoupling of affinity and specificity not only compromises therapeutic efficacy but also elevates off-target risks that constrain translational potential. Therefore, we introduce SpecLig, a unified structure-based framework that jointly generates small molecules and peptides with improved target affinity and specificity. SpecLig represents a complex as a block-based graph, combining a hierarchical SE(3)-equivariant variational autoencoder with an energy-guided geometric latent-diffusion model. Chemical priors derived from block–block contact statistics are explicitly incorporated, biasing generation towards pocket-complementary fragment combinations. We benchmark SpecLig on peptide and small-molecule tasks using standard public datasets and propose precision/breadth testing paradigms to quantify specificity. Across multiple evaluations, ligand candidates generated by SpecLig usually bind to the target pocket with high specificity and affinity while maintaining competitive advantages in other attributes. Ablations indicate that both hierarchical representation and energy guidance contribute to success. Finally, we present multiple real applications that demonstrate how SpecLig improves ligands in natural complexes to mitigate potential off-target risks. SpecLig, therefore, provides a practical route to prioritize higher-specificity designs for downstream experimental validation. The codes are available at: https://github.com/CQ-zhang-2016/SpecLig .Keywords
Funding Information
- National Science Foundation of China (T2541010)
- National Key R&D Program of China (2024YFF1207103)
- Beijing National Research Center For Information Science And Technology
This publication has 49 references indexed in Scilit:
- HelixDiff, a Score-Based Diffusion Model for Generating All-Atom α-Helical StructuresACS Central Science, 2024
- In silico off-target profiling for enhanced drug safety assessmentActa Pharmaceutica Sinica B, 2024
- Uni-Dock: GPU-Accelerated Docking Enables Ultralarge Virtual ScreeningJournal of Chemical Theory and Computation, 2023
- Advances and Challenges in De Novo Drug Design Using Three-Dimensional Deep Generative ModelsJournal of Chemical Information and Modeling, 2022
- Small molecules and their impact in drug discovery: A perspective on the occasion of the 125th anniversary of the Bayer Chemical Research LaboratoryDrug Discovery Today, 2022
- Three-Dimensional Convolutional Neural Networks and a Cross-Docked Data Set for Structure-Based Drug DesignJournal of Chemical Information and Modeling, 2020
- Cell penetrating peptides: A concise review with emphasis on biomedical applicationsBiomedicine & Pharmacotherapy, 2018
- ZINC 15 – Ligand Discovery for EveryoneJournal of Chemical Information and Modeling, 2015
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- Binding MOAD (Mother Of All Databases)Proteins: Structure, Function, and Bioinformatics, 2005