YuliaNuzhnenko Agent Skill: DiffDock AI Molecular Docking & Screening Skill
📌 Description
Runs DiffDock generative diffusion models for blind protein-ligand docking against AlphaFold structures and ranks candidates by confidence scores.
🤖 Agent Execution Protocol
When an AI Agent is tasked with diffdock-virtual-screener:
- Input Validation: Verify that the required input files or coordinates are supplied.
- Environment Check: Ensure dependencies (
DiffDock, PyTorch, RDKit, OpenBabel) are installed. - Execution: Run the protocol pipeline snippet below.
- Output Generation: Produce actionable Markdown/JSON summaries with publication figures.
💻 Protocol Code Snippet
# DiffDock Screening Protocol
python -m inference --protein_path protein.pdb --ligand_description ligand.sdf --out_dir docking_results/
📥 Input & Output Specifications
Input Contract
- Target Files: Valid input data matching domain formats.
- Parameters: Quality thresholds and cutoffs.
Output Contract
- Results Table: Structured summary dataframe or matrix.
- Visualization: Rendered SVG/PNG figures.
📄 License
Distributed under the MIT License. See LICENSE for details.