What inputs does the DiffDock skill require?

It requires a protein target (provided as a PDB file or amino acid sequence) and a ligand (provided as a SMILES string or structural file like SDF/MOL2).

What is DiffDock used for?

DiffDock is a deep learning tool used to predict the 3D binding pose—the specific position and orientation—of a small molecule ligand within a protein's binding site.

Is DiffDock suitable for protein-protein docking?

No, this skill is specifically designed for small molecule ligands. For protein-protein interactions, specialized tools like DiffDock-PP or AlphaFold-Multimer are required.

Can I run DiffDock on a CPU?

While technically possible, a GPU is strongly recommended as it provides a 10-100x speedup, making practical molecular docking and virtual screening feasible.

Does DiffDock predict binding affinity?

No, DiffDock focuses on structural pose and confidence scores. It should be combined with scoring functions like GNINA or MM/GBSA for affinity (ΔG) or binding strength prediction.

DiffDock Molecular Docking

Name: DiffDock Molecular Docking
Author: Microck

byMicrock

•

Ciencia de Datos y ML

Predicts high-accuracy 3D binding poses of small molecule ligands to protein targets using state-of-the-art diffusion models.

Acerca de

DiffDock is a specialized computational chemistry skill for Claude Code that enables researchers to perform diffusion-based molecular docking. It automates the complex workflow of predicting how a drug-like molecule binds to a specific protein, supporting both single-complex analysis and large-scale virtual screening. By generating detailed 3D coordinates and reliability confidence scores, it facilitates structure-based drug discovery and lead optimization directly within the development environment, bridging the gap between AI-driven modeling and structural biology.

Características Principales

Support for multiple input formats including PDB files, SMILES strings, and protein sequences.
Predict 3D ligand-protein binding poses using diffusion-based deep learning.
Automated batch processing for large-scale virtual screening campaigns.
81 GitHub stars
Generation of reliability confidence scores for pose prediction assessment.
Seamless integration with scoring functions like GNINA and MM/GBSA.

Casos de Uso

Predicting binding sites for novel protein targets.
Screening compound libraries against specific receptor models.
Structure-based drug design and lead optimization.

Acerca de

Características Principales

Support for multiple input formats including PDB files, SMILES strings, and protein sequences.
Predict 3D ligand-protein binding poses using diffusion-based deep learning.
Automated batch processing for large-scale virtual screening campaigns.
81 GitHub stars
Generation of reliability confidence scores for pose prediction assessment.
Seamless integration with scoring functions like GNINA and MM/GBSA.

Casos de Uso

Predicting binding sites for novel protein targets.
Screening compound libraries against specific receptor models.
Structure-based drug design and lead optimization.