Predicting protein-ligand binding sites using deep convolutional neural network

Deep Site and Docking Pose (DSDP) is a blind docking strategy accelerated by GPUs, developed by Gao Group. For the site prediction part, several modifications are introduced to PUResNet program. The pose sampling part is similar as AutoDock Vina combined with a number of modifications.

Identification of Protein-Ligand Binding Sites using dipolar EPR data

Subpocket-based fingerprint for kinase pocket comparison

Ligand Binding Site detection using Deep Learning

MaSIF- Molecular surface interaction fingerprints. Geometric deep learning to decipher patterns in molecular surfaces.

P2Rank: Protein-ligand binding site prediction from protein structure based on machine learning.

fpocket is a very fast open source protein pocket detection algorithm based on Voronoi tessellation. The platform is suited for the scientific community willing to develop new scoring functions and extract pocket descriptors on a large scale level. fpocket is distributed as free open source software.

A Molecular Topography MultiToolkit designed to simplify and streamline the detection, analysis, and characterization of protein pockets, cavities, channels, and binding sites.

[NeurIPS2025 Spotlight 🔥 ] Official implementation of "UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection"

Predict protein-ligand and catalytic pockets and perform molecular docking of a specific ligand to each predicted pocket.

Prediction of binding residues for metal ions, nucleic acids, and small molecules.

IF-SitePred is a method for predicting ligand-binding sites on protein structures. It first generates an embedding for each residue of the protein using the ESM-IF1 (inverse folding) model, then performs point cloud clustering to identify binding site centers.

Prediction of ligand binding site