How do I install the Drug Ligand Prep skill?

Run npx skillmds@latest add learningmatter-mit/drug-ligand-prep in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Drug Ligand Prep safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Drug Ligand Prep?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Drug Ligand Prep free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Drug Ligand Prep?

learningmatter-mit (@learningmatter-mit) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Drug Ligand Prep by learningmatter-mit

Name: Drug Ligand Prep
Rating: 4.2 (5 reviews)
Author: learningmatter-mit

File contents

Ligand Preparation

Goal

To prepare small-molecule ligands for molecular docking and downstream analysis by:

optionally enumerating relevant ligand ionization states and tautomers,
generating 3D conformers with RDKit ETKDG (via MCP),
minimizing with MMFF94/UFF (via MCP),
exporting a docking-ready PDBQT (AutoDock-Vina) and an optimized SDF (via MCP).

This skill combines script-based state enumeration with MCP-based 3D generation to ensure reproducibility.

Instructions

1. Enumerate States (Optional Batch Processing)

Use the script to process SMILES/SDF files and enumerate protonation/tautomer states. This outputs 2D SDFs.

# Env: drugdisc-agent
python .agents/skills/drug-ligand-prep/scripts/prepare_ligand.py \
  --smiles_file ligands.smi \
  --enumerate_protomers \
  --output_dir ligand_states/

2. Generate 3D Conformer and PDBQT (using MCP)

Use the mcp_drugdisc_convert_to_pdbqt tool to generate the final 3D docking input.

From a single SMILES:

mcp_drugdisc_convert_to_pdbqt(
    input_data="CC(=O)Oc1ccccc1C(=O)O",
    input_type="smiles",
    output_path="aspirin.pdbqt",
    num_confs=50
)

From an SDF (e.g. output of Step 1):

mcp_drugdisc_convert_to_pdbqt(
    input_data="ligand_states/ligand_001.sdf",
    input_type="sdf",
    output_path="ligand_001.pdbqt",
    num_confs=20
)

Examples

Prepare Ibuprofen

Enumerate inputs (if needed):

python .agents/skills/drug-ligand-prep/scripts/prepare_ligand.py \
  --smiles "CC(C)Cc1ccc(cc1)[C@@H](C)C(=O)O" \
  --name ibuprofen \
  --output_dir prep_stages/

Generate PDBQT:

mcp_drugdisc_convert_to_pdbqt(
    input_data="prep_stages/ibuprofen.sdf",
    input_type="sdf",
    output_path="prep_stages/ibuprofen.pdbqt",
    num_confs=50
)

Constraints

Environment: Requires drugdisc-agent.
3D/PDBQT: Delegated to mcp_drugdisc_convert_to_pdbqt (Meeko/RDKit).
State Enumeration: The script handles batch enumeration of protonation/tautomer states, but 3D generation is done by the MCP tool.

Author: Matthew Cox Contact: GitHub @mcox3406

---name: drug-ligand-prepdescription: Prepare small-molecule ligands for docking and analysis via optional state enumeration, 3D conformer generation, MMFF/UFF minimization, and export to SDF + AutoDock PDBQT.---# Ligand Preparation## GoalTo prepare small-molecule ligands for molecular docking and downstream analysis by:1) optionally enumerating relevant ligand ionization states and tautomers,2) generating 3D conformers with RDKit ETKDG (via MCP),3) minimizing with MMFF94/UFF (via MCP),4) exporting a docking-ready **PDBQT** (AutoDock-Vina) and an optimized **SDF** (via MCP).This skill combines script-based state enumeration with MCP-based 3D generation to ensure reproducibility.## Instructions### 1. Enumerate States (Optional Batch Processing)Use the script to process SMILES/SDF files and enumerate protonation/tautomer states. This outputs 2D SDFs.```bash# Env: drugdisc-agentpython .agents/skills/drug-ligand-prep/scripts/prepare_ligand.py \ --smiles_file ligands.smi \ --enumerate_protomers \ --output_dir ligand_states/```### 2. Generate 3D Conformer and PDBQT (using MCP)Use the `mcp_drugdisc_convert_to_pdbqt` tool to generate the final 3D docking input.**From a single SMILES:**```bashmcp_drugdisc_convert_to_pdbqt( input_data="CC(=O)Oc1ccccc1C(=O)O", input_type="smiles", output_path="aspirin.pdbqt", num_confs=50)```**From an SDF (e.g. output of Step 1):**```bashmcp_drugdisc_convert_to_pdbqt( input_data="ligand_states/ligand_001.sdf", input_type="sdf", output_path="ligand_001.pdbqt", num_confs=20)```## Examples### Prepare Ibuprofen1. Enumerate inputs (if needed): ```bash python .agents/skills/drug-ligand-prep/scripts/prepare_ligand.py \ --smiles "CC(C)Cc1ccc(cc1)[C@@H](C)C(=O)O" \ --name ibuprofen \ --output_dir prep_stages/ ```2. Generate PDBQT: ```bash mcp_drugdisc_convert_to_pdbqt( input_data="prep_stages/ibuprofen.sdf", input_type="sdf", output_path="prep_stages/ibuprofen.pdbqt", num_confs=50 ) ```## Constraints* **Environment**: Requires `drugdisc-agent`.* **3D/PDBQT**: Delegated to `mcp_drugdisc_convert_to_pdbqt` (Meeko/RDKit).* **State Enumeration**: The script handles batch enumeration of protonation/tautomer states, but 3D generation is done by the MCP tool.---**Author:** Matthew Cox**Contact:** [GitHub @mcox3406](https://github.com/mcox3406)

Frequently asked questions

Drug Ligand Prep