菜单
Retrieve SMILES strings from PubChem database using compound names.
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
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.
Generate entirely new drug-like molecules from scratch without any starting molecule, using REINVENT4's de novo prior.
Run automated DiffDock protein-ligand docking and return confidence-based result summaries.
| name | molclaw-compound-retrieve |
| description | Retrieve SMILES strings from PubChem database using compound names. |
| license | MIT license |
| metadata | {"skill-author":"PJLab"} |
The description of tool retrieve_smiles_by_compoundname.
Retrieve SMILES strings from PubChem using compound names.
Args:
compound_names (List[str]): List of input compound names (e.g., ["aspirin", "caffeine"])
Return:
status (str): success/partial_success/error
msg (str): message
retrieve_smiles (List[dict]): List of dict, each containing the keys 'compound_name' and 'smiles'.
--compound_name (str): A compound name of compound_names
--smiles (str): The retrieved SMILES string, if it exists; otherwise, None.
How to use tool retrieve_smiles_by_compoundname :
response = await client.session.call_tool(
"retrieve_smiles_by_compoundname",
arguments={
"compound_names": compound_names
}
)
result = client.parse_result(response)
retrieve_smiles = result["retrieve_smiles"]