What question did this study set out to answer?

The aim is to accurately predict protein-ligand binding sites to aid in drug discovery processes.

February 22, 2026Journal of Chemical Information and Modeling0 citationsOpen Access

SwinSite: 3D Structure-Based Prediction of Protein–Ligand Binding Sites Using a Combined Vision Transformer and Convolution Model

DKDongwoo KimSeoul National University JKJunsu KoSeoul National University

Key Points

The aim is to accurately predict protein-ligand binding sites to aid in drug discovery processes.
Developed a hybrid architecture combining 3D convolutional neural networks and vision transformers.
Voxelized protein structures into 3D grids focusing on surface residues.
Utilized local feature extraction and hierarchical self-attention mechanisms.
SwinSite consistently outperformed existing CNN- and GNN-based methods.
Demonstrated enhanced robustness and generalization across multiple benchmark datasets.

Abstract

Accurate identification of protein–ligand binding sites is an essential step in structure-based drug discovery. Herein, we present SwinSite, a deep learning framework that leverages a hybrid architecture combining 3D convolutional neural networks and hierarchical vision transformer modules to predict ligand binding sites based on a 3D structure of a target protein. SwinSite encodes spatial information by voxelizing a protein structure into 3D grids centered around surface residues, allowing for a detailed spatial representation of the protein’s surface environment. By combining local feature extraction with hierarchical self-attention via shifted windows, SwinSite effectively captures both fine-grained geometric features and long-range dependencies. Evaluations on multiple benchmark data sets demonstrate that SwinSite outperforms existing CNN- and GNN-based ligand binding site detection methods consistently, highlighting its robustness and generalization ability.

问 AI

Bookmark

View Full Paper