Verified:GitHub

diffdock

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

1|Updated Mar 12, 2026

Search Tags:#bioinformatics #virtual screening #drug discovery #molecular docking #cheminformatics #protein-ligand interaction

Ready to run

npx skills add https://github.com/yf8578/clawomics --skill diffdock-yf8578

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: diffdock
Source: https://github.com/yf8578/clawomics/tree/main/skills/diffdock
Command: npx skills add https://github.com/yf8578/clawomics --skill diffdock-yf8578

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 understanding biological interactions.

Core Features & Use Cases

Predict Binding Poses: Generates 3D structures of ligand-protein interactions.
Virtual Screening: Screens large libraries of compounds to identify potential drug candidates.
Confidence Scoring: Provides scores to assess the reliability of predictions.
Use Case: A researcher wants to find new potential inhibitors for a specific cancer-related protein. They can use this Skill to dock thousands of small molecules against the protein's active site and identify the most promising candidates for further experimental testing.

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 structure-based drug design?▼

You can predict protein-ligand binding poses by using diffusion models to generate 3D structures of ligand-protein interactions directly from PDB files or protein sequences.

Can I run virtual screening campaigns to dock thousands of small molecules against a protein?▼

Yes, you can run virtual screening campaigns using batch processing to dock large libraries of small molecules against a protein active site and identify promising drug candidates.

Do I need PyTorch with CUDA and RDKit to perform molecular docking?▼

Yes, full molecular docking functionality requires PyTorch with CUDA, RDKit, and ESM to run the underlying diffusion models for protein-ligand interaction prediction.

How does confidence scoring work for molecular docking predictions?▼

Confidence scoring assesses the reliability of predicted protein-ligand binding poses by providing scores that help evaluate the quality of the 3D ligand-protein interaction structures.

What is the best way to dock a specific ligand SMILES string to a protein PDB file?▼

The best way to dock a specific ligand is to provide the SMILES string and the protein PDB file as inputs, allowing the diffusion model to predict their binding pose.