← 返回 Skills 市场
98
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install chembl-query
功能描述
Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based s...
使用说明 (SKILL.md)
ChEMBL Query
Query ChEMBL database for bioactivity data on drug-like compounds.
When to Use
- Find compounds active against a protein target (target-based search)
- Get bioactivity profile for a molecule (molecule-based search)
- Find drugs for a disease indication (indication-based search)
Workflow
Use Case 1: Target-Based Compound Search
Find compounds with activity against a protein target.
from open_biomed.tools.tool_registry import TOOLS
tool = TOOLS["chembl_query"]
# Search by target name
results, _ = tool.run(
query_type="target",
target_name="EGFR",
standard_type="IC50",
standard_value_lte=100, # nM
limit=20
)
# Or search by UniProt ID
results, _ = tool.run(
query_type="target",
uniprot_id="P00533",
standard_type="IC50",
limit=20
)
Use Case 2: Molecule Bioactivity Profile
Get all known targets and activity data for a compound.
# Search by molecule name
results, _ = tool.run(
query_type="molecule",
molecule_name="imatinib",
limit=50
)
# Or search by SMILES
results, _ = tool.run(
query_type="molecule",
smiles="CC(=O)Oc1ccccc1C(=O)O",
limit=20
)
# Or search by ChEMBL ID
results, _ = tool.run(
query_type="molecule",
chembl_id="CHEMBL25",
limit=20
)
Use Case 3: Disease/Indication-Based Drug Search
Find drugs studied for a specific disease.
# Find all drugs for diabetes
results, _ = tool.run(
query_type="indication",
disease="diabetes",
limit=50
)
# Filter for approved drugs only (max_phase=4)
results, _ = tool.run(
query_type="indication",
disease="diabetes",
max_phase=4, # Approved drugs only
limit=20
)
Expected Outputs
| Query Type | Output Fields |
|---|---|
| Target | molecule_chembl_id, molecule_name, target_chembl_id, target_name, standard_type, standard_value, standard_units, pchembl_value |
| Molecule | molecule_chembl_id, molecule_name, target_chembl_id, target_name, target_organism, standard_type, standard_value, standard_units, pchembl_value |
| Indication | molecule_chembl_id, molecule_name, indication, max_phase_for_ind, phase_description |
Score Interpretation
Activity Values
| pChEMBL Value | IC50/Ki Approx | Interpretation |
|---|---|---|
| > 9 | \x3C 1 nM | Extremely potent |
| 8-9 | 1-10 nM | Very potent |
| 7-8 | 10-100 nM | Potent |
| 6-7 | 100 nM - 1 uM | Moderately active |
| 5-6 | 1-10 uM | Weakly active |
| \x3C 5 | > 10 uM | Inactive |
Clinical Phase
| Phase | Description |
|---|---|
| 0 | Preclinical |
| 1 | Phase I (safety) |
| 2 | Phase II (efficacy) |
| 3 | Phase III (large-scale) |
| 4 | Approved |
Parameters
| Parameter | Type | Description |
|---|---|---|
query_type |
str | "target", "molecule", or "indication" |
target_name |
str | Target name (e.g., "EGFR", "BACE1") |
uniprot_id |
str | UniProt accession (e.g., "P00533") |
molecule_name |
str | Molecule name (e.g., "aspirin") |
smiles |
str | SMILES string |
chembl_id |
str | ChEMBL ID (e.g., "CHEMBL25") |
disease |
str | Disease name (e.g., "diabetes") |
standard_type |
str | Activity type (e.g., "IC50", "Ki", "EC50") |
standard_value_lte |
float | Max activity value (nM) |
max_phase |
int | Minimum clinical phase (0-4) |
limit |
int | Max results (default: 50) |
Error Handling
| Error | Solution |
|---|---|
| Target not found | Try alternative names or UniProt ID |
| No activity data | Target may not have curated bioactivity data |
| Molecule not found | Verify SMILES or try molecule name |
| No indication results | Try simpler disease terms (e.g., "neoplasm" instead of "cancer") |
| Timeout | Reduce limit parameter |
Available Tools
| Tool Name | Purpose |
|---|---|
chembl_query |
Unified ChEMBL query interface |
See examples/basic_example.py for complete runnable examples.
安全使用建议
This skill appears coherent and implements what it claims: queries to the public ChEMBL API with example usage. Before installing, verify you trust the skill author and the surrounding OpenBioMed runtime (TOOLS registry and the implementation of tool.run), since network requests will occur at runtime. No credentials are required, but if you plan to run this in an environment with sensitive data, review the actual runtime implementation that performs the HTTP calls to ensure it only queries ChEMBL endpoints and does not log or transmit local secrets. Also be aware of ChEMBL rate limits when running large queries.
功能分析
Type: OpenClaw Skill
Name: chembl-query
Version: 1.0.0
The chembl-query skill bundle is a legitimate tool for querying the official ChEMBL bioinformatics database (ebi.ac.uk). The documentation in SKILL.md and references/api_endpoints.md accurately describes the tool's purpose for drug discovery research, and the example script (examples/basic_example.py) demonstrates standard usage without any signs of malicious intent, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
Name and description describe querying ChEMBL for bioactivity/indication data. The skill requests no credentials or special binaries and includes example code and API endpoint docs pointing at the official EBI ChEMBL API (https://www.ebi.ac.uk/chembl/api/data). All requested resources are proportional to that purpose.
Instruction Scope
SKILL.md contains focused instructions and example calls for three query types (target, molecule, indication). It references only the ChEMBL endpoints in references/api_endpoints.md and example usage via the tool registry. There are no instructions to read unrelated local files, exfiltrate data, or call unexpected endpoints.
Install Mechanism
No install spec is provided (instruction-only plus example files). No downloads, archives, or third-party install sources are present. The included Python example is self-contained and only depends on the surrounding OpenBioMed tool registry at runtime.
Credentials
The skill declares no required environment variables or credentials, which is appropriate because ChEMBL is a public API that does not require API keys. No other apparent sensitive configuration is requested.
Persistence & Privilege
Flags show always:false and normal autonomous invocation allowed (disable-model-invocation:false), which is typical. The skill does not request persistent system-wide privileges or modify other skills' configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install chembl-query - 安装完成后，直接呼叫该 Skill 的名称或使用
/chembl-query触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of chembl-query skill.
- Enables querying the ChEMBL database for drug bioactivity data.
- Supports target-based, molecule-based, and indication-based searches.
- Provides clear output fields and interpretation guides for activity and clinical phases.
- Detailed usage instructions and error handling included.
元数据
常见问题
ChEMBL Query 是什么？
Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based s... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 98 次。
如何安装 ChEMBL Query？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install chembl-query」即可一键安装，无需额外配置。
ChEMBL Query 是免费的吗？
是的，ChEMBL Query 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
ChEMBL Query 支持哪些平台？
ChEMBL Query 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 ChEMBL Query？
由 HollyYa（@hollyya）开发并维护，当前版本 v1.0.0。
推荐 Skills