Can I run DiffDock without a GPU?

While it can run on a CPU, a GPU is strongly recommended as it provides a 10-100x speedup, making practical docking tasks much more efficient.

What ligand formats are supported?

DiffDock supports ligands provided as SMILES strings or structure files in SDF and MOL2 formats.

Does DiffDock predict binding affinity (ΔG or Kd)?

No, DiffDock is designed to predict 3D binding poses and confidence scores. For affinity prediction, you should combine DiffDock results with scoring functions like GNINA or MM/GBSA.

Is it possible to dock ligands to a protein sequence without a PDB file?

Yes, DiffDock supports protein sequences by utilizing ESMFold to generate the necessary structural embeddings for docking.

Can DiffDock be used for protein-protein docking?

No, DiffDock is specifically optimized for small molecule ligands. For protein-protein docking, tools like AlphaFold-Multimer or DiffDock-PP are more appropriate.

DiffDock Molecular Docking

Name: DiffDock Molecular Docking
Author: pur3v4d3r

bypur3v4d3r

•

Ciencia de Datos y ML

Performs state-of-the-art diffusion-based molecular docking to predict 3D binding poses of ligands to protein targets.

DiffDock is a specialized scientific tool that leverages diffusion-based deep learning to predict accurate 3D binding orientations of small molecules within protein targets. It allows researchers to transition from chemical sequences (SMILES) or structural files (SDF/MOL2) to high-confidence binding poses, facilitating structure-based drug discovery and lead optimization directly within the Claude Code environment. By providing automated workflows for environment validation, single-complex docking, and batch virtual screening, it bridges the gap between raw biological data and actionable structural insights.

Características Principales

01Automated batch processing and virtual screening for large compound libraries

021 GitHub stars

03Support for both structural PDB files and amino acid sequences via ESMFold

04Advanced result analysis scripts for ranking and filtering docking outcomes

05Integrated confidence scoring to evaluate the reliability of predicted poses

06High-accuracy 3D ligand binding pose prediction using diffusion models

Casos de Uso

01Visualizing and analyzing protein-ligand interactions for lead optimization in drug design

02Predicting the binding orientation of potential drug candidates to specific protein pockets

03Running large-scale virtual screenings of compound libraries against therapeutic targets

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add pur3v4d3r/pur3-pkb-codebase diffdock

For use in Claude.ai and ChatGPT

Download Skill