菜单
Use P2Rank to locate binding pockets in the input protein. Unless specified by the user, prioritize using fpocket.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | molclaw-p2rank |
| description | Use P2Rank to locate binding pockets in the input protein. Unless specified by the user, prioritize using fpocket. |
| license | MIT license |
| metadata | {"skill-author":"PJLab"} |
The description of tool pred_pocket_prank.
Use P2Rank to predict ligand binding pockets in the input protein.
Args:
pdb_file_path (str): Path to the protein structure file (PDB format)
Return:
status (str): success/error
msg (str): message
pred_pockets (List[dict]): List of dict, each containing pocket confidence and center position information. The first pocket (pred_pockets[0]) has the highest score and is usually used for molecular docking.
--site_id (str): Pocket id
--probability (float): Predicted confidence score (0~1) of the pocket
--center_x (float): Center X of the pocket
--center_y (float): Center Y of the pocket
--center_z (float): Center Z of the pocket
How to use tool pred_pocket_prank :
response = await client.session.call_tool(
"pred_pocket_prank",
arguments={
"pdb_file_path": pdb_file_path
}
)
result = client.parse_result(response)
pred_pockets = result["pred_pockets"]
When P2Rank pocket dimensions are used for downstream docking, enforce a minimum of 25.0 Å per dimension. If any dimension is less than 25 Å, override to 25.0 Å.
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.