Verified:GitHub

diffdock

Predict protein-ligand binding poses and confidence scores from PDB files or SMILES.

Updated Mar 10, 2026

Search Tags:#virtual screening #drug discovery #molecular docking #diffusion models #cheminformatics #protein-ligand binding

Ready to run

npx skills add https://github.com/Yezez9/Research-Agent --skill diffdock-yezez9

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: diffdock
Source: https://github.com/Yezez9/Research-Agent/tree/main/scientific-skills/diffdock
Command: npx skills add https://github.com/Yezez9/Research-Agent --skill diffdock-yezez9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the prediction of how small molecules (ligands) bind to proteins, a critical step in drug discovery and chemical biology, by leveraging advanced diffusion models.

Core Features & Use Cases

Molecular Docking: Predicts the 3D binding pose of ligands to protein targets with high accuracy.
Virtual Screening: Enables rapid screening of large compound libraries to identify potential drug candidates.
Structure-Based Drug Design: Assists in optimizing lead compounds by predicting their binding modes.
Use Case: A medicinal chemist needs to understand how a new drug candidate might bind to a target protein. They can use this Skill to generate plausible binding poses and assess their structural feasibility.

Quick Start

Use the diffdock skill to dock the ligand with SMILES 'CC(=O)Oc1ccccc1C(=O)O' to the protein structure 'protein.pdb'.

Frequently Asked Questions about diffdock

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I predict protein-ligand binding poses for virtual screening?▼

To predict protein-ligand binding poses for virtual screening, you provide a PDB file or protein sequence alongside a SMILES string for the ligand. The system outputs predicted 3D binding poses and confidence scores.

Can I use a SMILES string as ligand input for molecular docking?▼

Yes, you can use a SMILES string as ligand input for molecular docking. You can also supply ligand structure files. The protein target requires a PDB file or an amino acid sequence to run the prediction.

What is diffusion-based deep learning for structure-based drug design?▼

Diffusion-based deep learning for structure-based drug design is an approach that predicts 3D binding poses by modeling molecular movements. It automates pose generation to assist in optimizing lead compounds and assessing structural feasibility.

Does this protein-ligand docking approach work without external dependencies?▼

Yes, this protein-ligand docking approach works without external dependencies. The environment is self-contained, allowing you to process PDB files and SMILES strings directly to generate binding poses and confidence scores.

What is the best way to screen compound libraries for drug discovery?▼

The best way to screen compound libraries for drug discovery is using diffusion models to predict protein-ligand binding poses. This enables rapid virtual screening of large compound libraries to identify potential drug candidates.