skills.rest
RamanEbrahimi
RamanEbrahimiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

diffdock

Predicts 3D protein-ligand binding poses from PDB files and SMILES strings.

3|Updated Apr 17, 2026
Search Tags:#deep learning#virtual screening#molecular docking#structure-based drug design#protein-ligand interactions
One-click install
npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill diffdock-ramanebrahimi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: diffdock
Source: https://github.com/RamanEbrahimi/raman-marketplace/tree/main/plugins/agentic-research/skills/scientific-skills/diffdock
Command: npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill diffdock-ramanebrahimi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the challenge of predicting 3D protein-ligand binding poses, crucial for structure-based drug discovery and chemical biology.

Core Features & Use Cases

  • Predict Binding Poses: Accurately predict the 3D structure of small molecule ligands in protein targets.
  • Supports Multiple Inputs: Handles protein structures (PDB files) or sequences (via ESMFold), and diverse ligand inputs (SMILES, SDF, MOL2).
  • Confidence Scores: Generates confidence scores to assess prediction reliability.
  • Batch Processing: Perform virtual screening campaigns for multiple protein-ligand pairs.
  • Use Case: For a given PDB file and SMILES string, the Skill predicts the binding pose and generates confidence scores, facilitating structure-based drug design.

Quick Start

Use the diffdock skill to predict the binding pose of a ligand to a protein. Provide a PDB file and a SMILES string, and specify the output directory for results.

Frequently Asked Questions about diffdock

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

FAQPage Schema
How do I predict 3D protein-ligand binding poses for structure-based drug discovery?▼

To predict 3D protein-ligand binding poses, provide a protein PDB file and a ligand SMILES string. The system generates predicted binding poses and confidence scores to facilitate structure-based drug discovery and virtual screening.

What input formats are supported for molecular docking predictions?▼

Molecular docking predictions support protein structures as PDB files or sequences via ESMFold. Ligands can be input using SMILES strings, SDF, or MOL2 formats to generate 3D binding poses.

Do I need a CUDA-capable GPU to run deep learning virtual screening campaigns?▼

Yes, a CUDA-capable GPU is required for efficient processing when running deep learning virtual screening campaigns. The prediction system relies on these GPUs to handle the underlying models effectively.

Can I use protein sequences instead of PDB files for protein-ligand interaction predictions?▼

Yes, you can use protein sequences for protein-ligand interaction predictions. The system utilizes ESMFold to generate the necessary protein structures from sequences when PDB files are unavailable.

How do I assess the reliability of predicted small molecule binding poses?▼

You assess the reliability of predicted small molecule binding poses using generated confidence scores. These scores accompany the 3D binding pose outputs to help evaluate prediction reliability for virtual screening.

Related Skills

Explore More Software Engineering Skills→
biomaps-infrabiomaps-infra

bio-diffdock

Predict molecular docking poses for protein-ligand interactions using diffusion models.

Official
Advanced
SologaSologa
1

diffdock

Predict 3D ligand-protein binding poses from PDB files using diffusion models.

Community
Advanced
ovachieverovachiever
52

diffdock

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

Community
Advanced
Yezez9Yezez9

diffdock

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

Community
Advanced