Molclaw Drug Likeness

Molecular Drug-likeness Metrics Calculation

Note:

• Local files are not directly accessible by the server. Please upload them to the server using molclaw-file-transfer before execution.
• For PDB file inputs, it is recommended to preprocess them using molclaw-pdbfixer before execution.
• Please refer to skill molclaw-scp-server to complete tool invocation.

The description of tool calculatemoldrug_chemistry.

Compute key drug-likeness metrics for each SMILES.
Args:
    smiles_list (List[str]): List of input SMILES strings, (e.g., ["N[C@@H](Cc1ccc(O)cc1)C(=O)O", "CC(C)C1=CC=CC=C1"])
Return:
    status (str): success/error
    msg (str): message
    metrics (List[dict]): List of dict, each containing feature keys.
        --smiles (str): A SMILES string of smiles_list
        --qed (float): Quantitative Estimate of Drug-likeness (QED) score
        --lipinski_rule_of_5_violations (int): Number of violations of Lipinski's Rule of Five

How to use tool calculatemoldrug_chemistry :

response = await client.session.call_tool(
    "calculate_mol_drug_chemistry",
    arguments={
        "smiles_list": smiles_list
    }
)
result = client.parse_result(response)
druglikeness_metrics = result["metrics"]

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: InternScience
• Source: InternScience/MolClaw
• License: MIT

Install and usage instructions live in the source repository linked above.