Predict protein-ligand binding poses and confidence scores from PDB and SMILES inputs.
npx skills add https://github.com/swaruplab/operon --skill diffdock-swaruplab
Please help me install this Agent Skill. Skill: diffdock Source: https://github.com/swaruplab/operon/tree/main/src-tauri/protocols/diffdock Command: npx skills add https://github.com/swaruplab/operon --skill diffdock-swaruplab
DiffDock provides reliable predictions of protein-ligand binding poses along with per-pose confidence scores, enabling faster and more trustworthy structure-based drug design workflows.
Provide a protein structure (PDB) and a ligand (SMILES or file), then run the inference with the default config to generate docking poses and confidence scores.
High-intent search queries and answers about installing and using this skill.
To predict protein-ligand binding poses, provide a protein PDB structure and ligand SMILES string as inputs. DiffDock uses diffusion models to generate 3D binding poses along with per-pose confidence scores for structure-based drug design.
Yes, you can run molecular docking using a protein sequence by leveraging ESMFold within the workflow. DiffDock supports protein sequence inputs, folding them into structures to enable binding pose prediction without requiring a pre-existing PDB file.
The best way to account for protein flexibility during molecular docking is using ensemble docking. DiffDock supports ensemble docking across multiple protein conformations, allowing you to generate reliable binding poses for flexible targets.
Yes, DiffDock works with RDKit and PyTorch for virtual screening workflows. It supports batch docking and integrates with downstream rescoring tools like GNINA or MM/GBSA to refine affinity estimations from generated poses.
A limitation of using diffusion models for structure-based drug design is that generated poses often require downstream validation. DiffDock provides confidence scores, but accurate affinity estimation typically requires additional rescoring with tools like GNINA or energy minimization.
You can configure inference parameters for batch molecular docking through YAML configurations. DiffDock allows you to adjust model inference settings, enabling efficient processing of multiple protein-ligand pairs for virtual screening workflows.
Yezez9Predict protein-ligand binding poses and confidence scores from PDB files or SMILES.
rubenslivPredict 3D protein-ligand binding poses and confidence scores with diffusion models.
sanand0Predict 3D binding poses of small molecules to protein targets using diffusion models.
ovachieverPredict protein-ligand docking poses and confidence scores from PDB structures or sequences.
