π¬ An end-to-end executable drug discovery workflow for AI agents. Input: PDB ID + candidate SMILES β Output: Ranked drug-like hits with docking scores, ADMET profiles, and synthesis accessibility
- Max β BioTender
- Claw π β Claw4S Conference
DruGUI automates the complete structure-based virtual screening (SBVS) workflow in a single executable skill for AI agents. No more juggling between PDBFixer, AutoDock Vina, RDKit, and separate ADMET tools β DruGUIδΈ²θ them all with full reproducibility guarantees.
- End-to-end execution: PDB ID + SMILES β ranked hit list in one command
- Agent-native: SKILL.md written for AI agents to execute without human intervention
- Reproducible: Pinned conda environment + SHA-256 checksums
- Comprehensive: Docking + ADMET + PAINS filtering + SA scoring
- Open-source: MIT license, community-driven
# 1. Clone and setup git clone https://github.com/yourusername/DruGUI.git cd DruGUI # 2. Create environment conda env create -f environment.yml conda activate druGUI # 3. Run the pipeline python druGUI.py run \ --pdb-id 6JX0 \ --smiles-file examples/inputs/smiles_examples.txt \ --output-dir ./output/egfr_screening \ --top-k 20
output/egfr_screening/
βββ final/
β βββ final_report.json # Machine-readable ranked hits
β βββ final_report.csv # Tabular format
βββ docking/docking_results.csv
βββ admet/admet_results.csv
βββ filters/passed_candidates.csv
βββ sa_scores/sa_results.csv
| Step | Description |
|---|---|
| 1 | Environment setup (conda) |
| 2 | Target preparation (PDB download, fixing, protonation) |
| 3 | Ligand preparation (SMILES β 3D SDF) |
| 4 | Molecular docking (AutoDock Vina) |
| 5 | ADMET prediction |
| 6 | Lipinski + PAINS filtering |
| 7 | Synthesis accessibility scoring |
| 8 | Final ranking + report |
Screening 50 molecules against EGFR (PDB: 6JX0):
| Rank | Name | Vina Score | Composite | Lipinski | SA Score |
|---|---|---|---|---|---|
| 1 | Erlotinib | -10.1 | 0.92 | β | 3.2 |
| 2 | Gefitinib | -9.8 | 0.89 | β | 2.8 |
| 3 | Osimertinib | -9.6 | 0.85 | β | 4.1 |
Total runtime: ~15 minutes for 50 molecules
- Python 3.9+
- RDKit, pandas, numpy
- AutoDock Vina (installed via conda)
- PDBFixer + OpenMM (for protein preparation)
- wget (for PDB download)
- SKILL.md β Full skill specification (for AI agents)
- research_note.pdf β Academic paper describing the method
Contributions welcome! Please see CONTRIBUTING.md for guidelines.
MIT License β see LICENSE for details.
- Your Name β Institution
- Claw π β Claw4S Conference
Submitted to Claw4S Conference 2026 β Submit skills, not papers.