skills.rest
galeep
galeepCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

diffdock

Predict 3D binding poses and confidence scores for protein-ligand interactions.

Updated May 17, 2026
Search Tags:#drug discovery#molecular docking#diffusion models#computational chemistry#protein-ligand interactions
One-click install
npx skills add https://github.com/galeep/plugin-place --skill diffdock-galeep
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: diffdock
Source: https://github.com/galeep/plugin-place/tree/main/plugins/sci-cheminformatics-drug-discovery/skills/diffdock
Command: npx skills add https://github.com/galeep/plugin-place --skill diffdock-galeep

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, torch_geometric, rdkit, esm, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

DiffDock predicts the 3D binding poses of small molecule ligands to protein targets and provides confidence scores to assess prediction reliability, which is crucial for structure-based drug discovery and chemical biology.

Core Features & Use Cases

  • Molecular Docking: Predicts the 3D structure of ligands in the binding site of a protein target.
  • Confidence Scoring: Generates confidence scores for each predicted binding pose.
  • Use Case: Imagine you have a protein target and a small molecule ligand. Use this Skill to predict the binding pose and evaluate the reliability of the prediction.

Quick Start

Run the diffdock skill with the following command: diffdock -p protein.pdb -l ligand.sdf -o results/

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 using diffusion models?▼

Predict protein-ligand binding poses using diffusion models by providing a protein PDB file and ligand SDF file. The system outputs 3D binding structures and confidence scores for structure-based drug discovery and computational chemistry.

What do I need to run molecular docking predictions with deep learning?▼

To run molecular docking predictions with deep learning, you need a GPU-supported computational environment and dependencies like PyTorch, TorchGeometric, RDKit, and ESM. You also need protein and ligand structure files for input.

Can I evaluate the reliability of predicted ligand binding poses?▼

You can evaluate the reliability of predicted ligand binding poses using generated confidence scores. These scores assess prediction reliability, which is crucial for molecular design and chemical biology applications.

How does diffusion-based molecular docking compare to traditional computational chemistry methods?▼

Diffusion-based molecular docking uses generative deep learning to predict 3D binding structures, unlike traditional computational chemistry methods. This approach provides confidence scores to assess prediction reliability for small molecule ligands.

What is the best way to run molecular docking for structure-based drug discovery?▼

The best way to run molecular docking for structure-based drug discovery is to execute the command with your protein PDB and ligand SDF files, directing the output to a results directory to retrieve predicted 3D binding poses.

Related Skills

Explore More Software Engineering Skills→
ovachieverovachiever
52

diffdock

Predict protein-ligand docking poses and confidence scores from PDB structures or sequences.

Community
Advanced
tassiovaletassiovale
13

diffdock

Predict 3D binding poses and confidence scores for small-molecule ligands against protein targets using DiffDock software.

Community
Advanced
jonnabiojonnabio
6

diffdock

Predict binding poses and confidence scores for protein-ligand interactions.

Community
Advanced
pradyumnasagarpradyumnasagar
6

docking-rescoring

Predict and score protein-ligand binding affinities with machine learning and docking.

Community
Advanced