Predict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of the input molecules.
Predict binding affinity between target protein sequence and small molecule SMILES using Boltz-2.
Predict protein structures with Chai-1 from sequence or FASTA input and return model scoring summaries.
Chroma toolkit skill covering chroma_monomer for single-chain generation, chroma_complex for multi-chain assembly generation, and chroma_symmetry for symmetry-constrained protein design.
Retrieve SMILES strings from PubChem database using compound names.
[CURRENTLY UNAVAILABLE] DiffDock protein-ligand docking. This tool is not deployed on the current MCP server. Use molclaw-quickvina-docking or molclaw-karmadock-tool as alternatives.
| name | molclaw-denovo-sampling |
| description | Generate new molecules de novo. |
| license | MIT license |
| metadata | {"skill-author":"PJLab"} |
Note:
molclaw-file-transfer before execution.molclaw-pdbfixer before execution.molclaw-scp-server to complete tool invocation.The description of tool reinvent_denovo_sampling.
Generate new molecules de novo.
Args:
n (int): Number of molecules for sampling
lipinski (bool): Whether to apply Lipinski's rule of five filtering, default is True
filter_preset (str): Filter preset, options: ['none', 'minimal', 'default', 'strict', 'druglike', 'all'], default is 'druglike'
Return:
status (str): success/error
msg (str): message
save_smiles_file (str): Path to the saved SMILES file
output_smiles_list (List[str]): List of generated SMILES strings
How to use tool reinvent_denovo_sampling :
response = await client.session.call_tool(
"reinvent_denovo_sampling",
arguments={
"n": n,
"lipinski": True,
"filter_preset": filter_type
}
)
result = client.parse_result(response)
output_smiles_list = result["output_smiles_list"]