Diffdock

This is a diffusion-based deep learning tool for molecular docking that predicts 3D binding poses of ligands to protein targets. You'd use it for structure-based drug design when you need to know where a molecule binds, not how strongly it binds. It handles PDB files or protein sequences via ESMFold, works with SMILES or structure files, and can process single complexes or batch virtual screening campaigns. The confidence scores tell you how certain the model is about the pose, not binding affinity, so you'll want to pair it with GNINA or MM/GBSA for affinity estimates. GPU recommended since it's 10-100x faster than CPU. First run takes a few minutes to pre-compute lookup tables.

skills.sh installs: 262
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill diffdock --agent claude-code

Installs into .claude/skills of the current project.

Files

DiffDock: Molecular Docking with Diffusion Models

Overview

DiffDock is a diffusion-based deep learning tool for molecular docking that predicts 3D binding poses of small molecule ligands to protein targets. It represents the state-of-the-art in computational docking, crucial for structure-based drug discovery and chemical biology.

Core Capabilities:

Predict ligand binding poses with high accuracy using deep learning
Support protein structures (PDB files) or sequences (via ESMFold)
Process single complexes or batch virtual screening campaigns
Generate confidence scores to assess prediction reliability
Handle diverse ligand inputs (SMILES, SDF, MOL2)

Key Distinction: DiffDock predicts binding poses (3D structure) and confidence (prediction certainty), NOT binding affinity (ΔG, Kd). Always combine with scoring functions (GNINA, MM/GBSA) for affinity assessment.