ワンクリックで
molclaw-prolif-docking
ProLIF docking-pose analysis skill for batch interaction fingerprints and interaction count summaries.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
ProLIF docking-pose analysis skill for batch interaction fingerprints and interaction count summaries.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
Generate entirely new drug-like molecules from scratch without any starting molecule, using REINVENT4's de novo prior.
| name | molclaw-prolif-docking |
| description | ProLIF docking-pose analysis skill for batch interaction fingerprints and interaction count summaries. |
| license | MIT license |
| metadata | {"skill-author":"PJLab"} |
[!NOTE] Local files are not directly accessible by the server. Please upload them to the server using
drugsda-file-transferbefore execution. For PDB file inputs, it is recommended to preprocess them usingdrugsda-fix_pdbbefore execution.
Batch-analyze multiple docking-generated binding poses and produce interaction fingerprints or interaction count summaries. Use this skill to screen binding modes and evaluate docking result quality.
| Parameter | Source Guidance |
|---|---|
protein_path | Generated by structure retrieval/prediction tools (e.g., retrieve_protein_structure_by_*, pred_protein_structure_esmfold, chai1_predict) or a PDB fixed by fix_pdb |
ligand_paths | Generated by docking tools (e.g., molecule_docking_quickvina, hdock_tool, run_karmadock_screening) as pose files (.sdf/.mol2/.pdbqt) |
ligand_format | Must match the upstream docking output format: sdf, mol2, or pdbqt |
template_smiles | Required when ligand_format is pdbqt to provide ligand chemistry reference |
prolif_dockingSummarize docking poses with ProLIF and return a CSV of interaction fingerprints plus summary metrics.
Args:
protein_path (str): Path to the receptor protein structure.
ligand_paths (List[str]): List of ligand pose files.
ligand_format (str): Ligand format identifier (e.g., 'sdf', 'mol2', 'pdbqt').
template_smiles (str|None): Optional template SMILES; required when ligand_format is 'pdbqt'.
interactions (List[str]|None): Optional interaction types to compute.
count (bool): If True, compute interaction counts instead of fingerprints. Default: False.
vicinity_cutoff (float|None): Optional distance cutoff for vicinity interactions.
params_json (str|None): Optional JSON parameter file path for ProLIF interaction settings.
Return:
status (str): 'success' or 'error'.
msg (str): Human-readable summary or error message.
command (str): The executed command label ('docking').
output_dir (str|None): Run-specific directory under tool_result/prolif_result.
output_file (str|None): Path to the produced CSV summary file.
n_frames (int|None): Number of processed frames where applicable.
n_interactions (int|None): Number of interaction columns in output.
frequent_interactions (List[dict]|None): High-frequency interactions (>30%) with keys 'interaction' and 'frequency'.
result_summary (dict|None): Full summary dictionary from the wrapper.
prolif_dockingresponse = await client.session.call_tool(
"prolif_docking",
arguments={
"protein_path": "relative/path/to/receptor.pdb",
"ligand_paths": [
"relative/path/to/pose1.sdf",
"relative/path/to/pose2.sdf"
],
"ligand_format": "sdf",
"interactions": ["Hydrophobic", "HBDonor"]
}
)
result = client.parse_result(response)
key_output = result["output_file"]
# 1) Main mode
{
"protein_path": "relative/path/to/receptor.pdb",
"ligand_paths": [
"relative/path/to/docking_poses.sdf"
],
"ligand_format": "sdf"
}
# 2) Variant mode
{
"protein_path": "relative/path/to/receptor.pdb",
"ligand_paths": [
"relative/path/to/pose1.pdbqt",
"relative/path/to/pose2.pdbqt"
],
"ligand_format": "pdbqt",
"template_smiles": "CCO",
"count": True,
"vicinity_cutoff": 4.0
}
ProLIF reports residue identifiers using the numbering of the input PDB file. If the PDB was generated by a prediction tool (ESMFold, Boltz-2, Chai-1), these numbers are tool-internal sequential numbers (1, 2, 3...) — NOT UniProt numbers.
Before interpreting ProLIF results when the task references specific residues (e.g., "confirm Met793 interaction"):
molclaw-residue-mapper to build a mapping table.Common catastrophic error: ProLIF reports "HBDonor at MET76" from a Boltz-2 structure. Agent searches for "MET793" in ProLIF output, does not find it, and concludes "Met793 interaction is absent." In reality, MET76 (Boltz-2 internal) IS Met793 (UniProt). Use residue_mapper with query="tool:76" to verify.
After ProLIF analysis, download ALL visualization outputs (interaction heatmaps, frequency barplots, etc.) from the output directory using server_file_to_base64. These are Category A files essential for result communication and user verification.