database-lookup

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Database Lookup

数据库查询

You have access to 78 public databases through their REST APIs. Your job is to figure out which database(s) are relevant to the user's question, query them, and return the raw JSON results along with which databases you used.

你可以通过REST API访问78个公共数据库。你的任务是确定哪些数据库与用户的问题相关，查询这些数据库，并返回原始JSON结果以及你使用的数据库信息。

Core Workflow

核心工作流程

Understand the query — What is the user looking for? A compound? A gene? A pathway? A patent? Expression data? An economic indicator? This determines which database(s) to hit.
Select database(s) — Use the database selection guide below. When in doubt, search multiple databases — it's better to cast a wide net than to miss relevant data.
Read the reference file — Each database has a reference file in
```
references/
```
with endpoint details, query formats, and example calls. Read the relevant file(s) before making API calls.
Make the API call(s) — See the Making API Calls section below for which HTTP fetch tool to use on your platform.
Return results — Always return:
- The raw JSON response from each database
- A list of databases queried with the specific endpoints used
- If a query returned no results, say so explicitly rather than omitting it

理解查询需求 — 用户要查找什么？化合物？基因？通路？专利？表达数据？经济指标？这将决定要调用哪些数据库。
选择数据库 — 使用下方的数据库选择指南。不确定时，可搜索多个数据库——宁可扩大范围也不要遗漏相关数据。
查阅参考文件 — 每个数据库在
```
references/
```
目录下都有一个参考文件，包含端点详情、查询格式和调用示例。在调用API前请阅读相关文件。
调用API — 请查看下方的「API调用方法」部分，了解你所在平台应使用的HTTP获取工具。
返回结果 — 请始终返回：
- 每个数据库的原始JSON响应
- 已查询数据库列表及使用的具体端点
- 如果查询无结果，请明确说明，不要省略

Database Selection Guide

数据库选择指南

Match the user's intent to the right database(s). Many queries benefit from hitting multiple databases.

将用户的需求与合适的数据库匹配。许多查询需要调用多个数据库才能得到全面结果。

Physics & Astronomy

物理与天文学

User is asking about...	Primary database(s)	Also consider
Near-Earth objects, asteroids	NASA (NeoWs)	—
Mars rover images	NASA (Mars Rover Photos)	—
Exoplanets, orbital parameters	NASA Exoplanet Archive	—
Astronomical objects by name/coordinates	SIMBAD	SDSS
Galaxy/star spectra, photometry	SDSS	SIMBAD
Physical constants	NIST	—
Atomic spectra, spectral lines	NIST (ASD)	—

用户查询内容	首选数据库	备选数据库
近地天体、小行星	NASA (NeoWs)	—
火星探测器图像	NASA (Mars Rover Photos)	—
系外行星、轨道参数	NASA Exoplanet Archive	—
按名称/坐标查询天文对象	SIMBAD	SDSS
星系/恒星光谱、光度测量	SDSS	SIMBAD
物理常数	NIST	—
原子光谱、谱线	NIST (ASD)	—

Earth & Environmental Sciences

地球与环境科学

User is asking about...	Primary database(s)	Also consider
Earthquakes, seismic events	USGS Earthquakes	—
Water data, streamflow, groundwater	USGS Water Services	—
Weather (current, forecast, historical)	OpenWeatherMap	NOAA
Climate data, historical weather stations	NOAA (CDO)	—
Air quality, toxic releases	EPA (Envirofacts)	—

用户查询内容	首选数据库	备选数据库
地震、地震事件	USGS Earthquakes	—
水文数据、河流流量、地下水	USGS Water Services	—
天气（实时、预报、历史）	OpenWeatherMap	NOAA
气候数据、历史气象站	NOAA (CDO)	—
空气质量、有毒物质排放	EPA (Envirofacts)	—

Chemistry & Drugs

化学与药物学

User is asking about...	Primary database(s)	Also consider
Chemical compounds, molecules	PubChem	ChEMBL
Molecular properties (weight, formula, SMILES)	PubChem	—
Drug synonyms, CAS numbers	PubChem (synonyms)	DrugBank
Bioactivity data, IC50, binding assays	ChEMBL	BindingDB, PubChem
Drug binding affinities (Ki, IC50, Kd)	ChEMBL, BindingDB	PubChem
Drug-target interactions	ChEMBL, DrugBank	BindingDB, Open Targets
Ligands for a protein target (by UniProt)	BindingDB	ChEMBL
Target identification from compound structure	BindingDB (SMILES similarity)	ChEMBL
Drug labels, adverse events, recalls	FDA (OpenFDA)	DailyMed
Drug labels (structured product labels)	DailyMed	FDA (OpenFDA)
Drug pharmacology, indications	DrugBank	FDA
Chemical cross-referencing	PubChem (xrefs)	ChEMBL
Commercially available compounds for screening	ZINC	PubChem
Similarity/substructure search (purchasable)	ZINC	PubChem, ChEMBL
Drug-like compound libraries, building blocks	ZINC	—
FDA-approved drug structures	ZINC (fda subset)	PubChem, FDA
Compound purchasability, vendor catalogs	ZINC	—

用户查询内容	首选数据库	备选数据库
化学化合物、分子	PubChem	ChEMBL
分子属性（分子量、分子式、SMILES）	PubChem	—
药物同义词、CAS号	PubChem (synonyms)	DrugBank
生物活性数据、IC50、结合实验	ChEMBL	BindingDB、PubChem
药物结合亲和力（Ki、IC50、Kd）	ChEMBL、BindingDB	PubChem
药物-靶点相互作用	ChEMBL、DrugBank	BindingDB、Open Targets
蛋白靶点的配体（通过UniProt）	BindingDB	ChEMBL
从化合物结构识别靶点	BindingDB (SMILES相似度)	ChEMBL
药物标签、不良反应、召回信息	FDA (OpenFDA)	DailyMed
药物标签（结构化产品标签）	DailyMed	FDA (OpenFDA)
药物药理学、适应症	DrugBank	FDA
化学交叉引用	PubChem (xrefs)	ChEMBL
可商业购买的筛选化合物	ZINC	PubChem
相似度/子结构搜索（可购买）	ZINC	PubChem、ChEMBL
类药化合物库、合成砌块	ZINC	—
FDA批准药物结构	ZINC (fda子集)	PubChem、FDA
化合物可购买性、供应商目录	ZINC	—

Materials Science & Crystallography

材料科学与晶体学

User is asking about...	Primary database(s)	Also consider
Materials by formula or elements	Materials Project	COD
Band gap, electronic structure	Materials Project	—
Crystal structures, CIF files	COD	Materials Project
Elastic/mechanical properties	Materials Project	—
Formation energy, thermodynamics	Materials Project	—
Cell parameters, space groups	COD	Materials Project

用户查询内容	首选数据库	备选数据库
按分子式或元素查询材料	Materials Project	COD
带隙、电子结构	Materials Project	—
晶体结构、CIF文件	COD	Materials Project
弹性/力学性能	Materials Project	—
形成能、热力学	Materials Project	—
晶胞参数、空间群	COD	Materials Project

Biology & Genomics

生物学与基因组学

User is asking about...	Primary database(s)	Also consider
Biological pathways	Reactome, KEGG	—
What pathways a gene/protein is in	Reactome (mapping), KEGG	—
Enzyme kinetics, catalytic activity	BRENDA	KEGG
Metabolomics studies, metabolite profiles	Metabolomics Workbench	PubChem
m/z or exact mass lookup	Metabolomics Workbench (moverz/exactmass)	PubChem
Protein sequence, function, annotation	UniProt	Ensembl
Protein-protein interactions	STRING	BioGRID
Gene information, genomic location	NCBI Gene	Ensembl
Genome sequences, variants, transcripts	Ensembl	NCBI Gene
Gene expression datasets	GEO (NCBI E-utilities)	—
Gene expression across tissues	GTEx	Human Protein Atlas
Gene expression signatures (CMap/L1000)	LINCS L1000	GEO
Gene set enrichment vs GEO	RummaGEO	GEO
Protein sequences (NCBI)	NCBI Protein	UniProt
Taxonomic classification	NCBI Taxonomy	—
SNP/variant data (dbSNP)	dbSNP	ClinVar, gnomAD
Population variant frequencies	gnomAD	dbSNP
Sequencing run metadata	SRA	ENA, GEO
Nucleotide sequences (European archive)	ENA	SRA, NCBI Gene
Genome assemblies, raw reads (European)	ENA	SRA, Ensembl
Cross-references from sequence accessions	ENA (xref)	NCBI Gene, UniProt
Genome annotations, tracks	UCSC Genome Browser	Ensembl
3D protein structures (experimental)	PDB (RCSB)	EMDB
3D protein structures (predicted)	AlphaFold DB	PDB
EM maps, cryo-EM structures	EMDB	PDB
Protein families, domains	InterPro	UniProt
Chemical entities (biological)	ChEBI	PubChem
Protein/genetic interactions	BioGRID	STRING
Gene function annotations (GO terms)	QuickGO	Gene Ontology
Regulatory elements, ChIP-seq, ATAC-seq	ENCODE	—
TF binding profiles/motifs	JASPAR	ENCODE
Protein expression across tissues	Human Protein Atlas	UniProt
Single-cell atlas projects	Human Cell Atlas	—
Proteomics datasets	PRIDE	—
Mouse gene data	MouseMine	NCBI Gene
Plasmid repository	Addgene	—

Organism/species matters. Most biology databases cover multiple organisms. If the user's query is about a specific organism, pass it explicitly — don't assume human. Common patterns: Ensembl uses

{species}

in the URL path (e.g.

homo_sapiens

), STRING/BioGRID/QuickGO use NCBI taxon IDs (

species=9606

for human,

for mouse), UniProt uses

organism_id:9606

in search queries, KEGG uses organism codes (

hsa

mmu

). GTEx and Human Protein Atlas are human-only. Check the reference file for each database's specific parameter.

用户查询内容	首选数据库	备选数据库
生物通路	Reactome、KEGG	—
基因/蛋白参与的通路	Reactome (mapping)、KEGG	—
酶动力学、催化活性	BRENDA	KEGG
代谢组学研究、代谢物谱	Metabolomics Workbench	PubChem
m/z或精确质量查询	Metabolomics Workbench (moverz/exactmass)	PubChem
蛋白序列、功能、注释	UniProt	Ensembl
蛋白-蛋白相互作用	STRING	BioGRID
基因信息、基因组位置	NCBI Gene	Ensembl
基因组序列、变异体、转录本	Ensembl	NCBI Gene
基因表达数据集	GEO (NCBI E-utilities)	—
跨组织基因表达	GTEx	Human Protein Atlas
基因表达特征（CMap/L1000）	LINCS L1000	GEO
基因集富集分析 vs GEO	RummaGEO	GEO
蛋白序列（NCBI）	NCBI Protein	UniProt
分类学分类	NCBI Taxonomy	—
SNP/变异体数据（dbSNP）	dbSNP	ClinVar、gnomAD
群体变异频率	gnomAD	dbSNP
测序运行元数据	SRA	ENA、GEO
核苷酸序列（欧洲存档）	ENA	SRA、NCBI Gene
基因组组装、原始测序读段（欧洲）	ENA	SRA、Ensembl
序列登录号的交叉引用	ENA (xref)	NCBI Gene、UniProt
基因组注释、轨道数据	UCSC Genome Browser	Ensembl
3D蛋白结构（实验）	PDB (RCSB)	EMDB
3D蛋白结构（预测）	AlphaFold DB	PDB
EM图谱、冷冻电镜结构	EMDB	PDB
蛋白家族、结构域	InterPro	UniProt
生物相关化学实体	ChEBI	PubChem
蛋白/基因相互作用	BioGRID	STRING
基因功能注释（GO术语）	QuickGO	Gene Ontology
调控元件、ChIP-seq、ATAC-seq	ENCODE	—
TF结合谱/基序	JASPAR	ENCODE
跨组织蛋白表达	Human Protein Atlas	UniProt
单细胞图谱项目	Human Cell Atlas	—
蛋白质组学数据集	PRIDE	—
小鼠基因数据	MouseMine	NCBI Gene
质粒库	Addgene	—

物种至关重要。大多数生物学数据库涵盖多个物种。如果用户的查询针对特定物种，请明确传入该物种参数——不要默认是人类。常见规则：Ensembl在URL路径中使用

{species}

（例如

homo_sapiens

），STRING/BioGRID/QuickGO使用NCBI分类ID（人类为

species=9606

，小鼠为

），UniProt在搜索查询中使用

organism_id:9606

，KEGG使用物种代码（人类

hsa

，小鼠

mmu

）。GTEx和Human Protein Atlas仅支持人类。请查阅每个数据库的参考文件了解具体参数。

Disease & Clinical

疾病与临床医学

User is asking about...	Primary database(s)	Also consider
Somatic mutations in cancer	COSMIC	Open Targets, cBioPortal
Cancer genomics (TCGA)	GDC (TCGA)	COSMIC, cBioPortal
Cancer study mutations, CNA, expression	cBioPortal	GDC (TCGA), COSMIC
Tumor clinical data (survival, staging)	cBioPortal	GDC (TCGA)
Drug-target-disease associations	Open Targets	ChEMBL
Gene-disease associations	DisGeNET	Open Targets, Monarch
Mendelian disease-gene relationships	OMIM	NCBI Gene
Variant clinical significance	ClinVar (NCBI)	OMIM
GWAS SNP-trait associations	GWAS Catalog	—
Disease-phenotype-gene links	Monarch Initiative	HPO
Phenotype ontology, HPO terms	HPO	Monarch
Pharmacogenomics, drug-gene interactions	ClinPGx (PharmGKB)	DrugBank
Clinical trials for a drug/disease	ClinicalTrials.gov	FDA
Disease-related expression data	GEO	Open Targets

用户查询内容	首选数据库	备选数据库
癌症体细胞突变	COSMIC	Open Targets、cBioPortal
癌症基因组学（TCGA）	GDC (TCGA)	COSMIC、cBioPortal
癌症研究突变、拷贝数变异、表达	cBioPortal	GDC (TCGA)、COSMIC
肿瘤临床数据（生存、分期）	cBioPortal	GDC (TCGA)
药物-靶点-疾病关联	Open Targets	ChEMBL
基因-疾病关联	DisGeNET	Open Targets、Monarch
孟德尔疾病-基因关系	OMIM	NCBI Gene
变异体临床意义	ClinVar (NCBI)	OMIM
GWAS SNP-性状关联	GWAS Catalog	—
疾病-表型-基因关联	Monarch Initiative	HPO
表型本体、HPO术语	HPO	Monarch
药物基因组学、药物-基因相互作用	ClinPGx (PharmGKB)	DrugBank
药物/疾病相关临床试验	ClinicalTrials.gov	FDA
疾病相关表达数据	GEO	Open Targets

Patents & Regulatory

专利与监管

User is asking about...	Primary database(s)	Also consider
Patents by keyword or technology	USPTO (PatentsView)	—
Patents by inventor or assignee	USPTO (PatentsView)	—
Patent prosecution status	USPTO (PEDS)	—
Trademark lookup	USPTO (TSDR)	—
SEC company filings, 10-K, 10-Q	SEC EDGAR	—

用户查询内容	首选数据库	备选数据库
按关键词或技术查询专利	USPTO (PatentsView)	—
按发明人或受让人查询专利	USPTO (PatentsView)	—
专利审查状态	USPTO (PEDS)	—
商标查询	USPTO (TSDR)	—
SEC公司文件、10-K、10-Q	SEC EDGAR	—

Economics & Finance

经济与金融

User is asking about...	Primary database(s)	Also consider
US economic time series (GDP, CPI, rates)	FRED	BEA
Employment, wages, labor statistics	BLS	FRED
GDP, national accounts	BEA	FRED, World Bank
International development indicators	World Bank	FRED
Interest rates, money supply	Federal Reserve	FRED
Euro exchange rates, ECB monetary stats	ECB	—
US debt, yield curves, fiscal data	US Treasury	FRED
Stock prices, forex, crypto	Alpha Vantage	—
Statistical data across many topics	Data Commons	—

用户查询内容	首选数据库	备选数据库
美国经济时间序列（GDP、CPI、利率）	FRED	BEA
就业、工资、劳工统计	BLS	FRED
GDP、国民账户	BEA	FRED、World Bank
国际发展指标	World Bank	FRED
利率、货币供应量	Federal Reserve	FRED
欧元汇率、ECB货币统计	ECB	—
美国债务、收益率曲线、财政数据	US Treasury	FRED
股票价格、外汇、加密货币	Alpha Vantage	—
多领域统计数据	Data Commons	—

Social Sciences & Demographics

社会科学与人口统计学

User is asking about...	Primary database(s)	Also consider
US population, housing, income data	US Census	Data Commons
EU statistics (economy, trade, health)	Eurostat	World Bank
Global health indicators (mortality, disease)	WHO GHO	World Bank

用户查询内容	首选数据库	备选数据库
美国人口、住房、收入数据	US Census	Data Commons
欧盟统计数据（经济、贸易、健康）	Eurostat	World Bank
全球健康指标（死亡率、疾病）	WHO GHO	World Bank

Cross-domain queries

跨领域查询

User is asking about...	Primary database(s)	Also consider
Everything about a compound	PubChem + ChEMBL + DrugBank	BindingDB, ZINC, Reactome, FDA
Everything about a gene	NCBI Gene + UniProt + Ensembl	Reactome, STRING, COSMIC, cBioPortal, ENA
Everything about a variant	dbSNP + ClinVar + gnomAD	GWAS Catalog, COSMIC, cBioPortal
Drug target pathways	ChEMBL + Reactome	Open Targets, GEO
Prior art for a chemical invention	USPTO + PubChem	ChEMBL
Everything about a material	Materials Project + COD	—
US economic overview	FRED + BLS + BEA	Federal Reserve

When the user's query spans multiple domains (e.g. "what do we know about aspirin" or "find everything about BRCA1"), query all relevant databases in parallel.

用户查询内容	首选数据库	备选数据库
某化合物的所有信息	PubChem + ChEMBL + DrugBank	BindingDB、ZINC、Reactome、FDA
某基因的所有信息	NCBI Gene + UniProt + Ensembl	Reactome、STRING、COSMIC、cBioPortal、ENA
某变异体的所有信息	dbSNP + ClinVar + gnomAD	GWAS Catalog、COSMIC、cBioPortal
药物靶点通路	ChEMBL + Reactome	Open Targets、GEO
化学发明的现有技术	USPTO + PubChem	ChEMBL
某材料的所有信息	Materials Project + COD	—
美国经济概况	FRED + BLS + BEA	Federal Reserve

当用户的查询跨多个领域时（例如“我们对阿司匹林了解多少”或“查找BRCA1的所有信息”），请并行查询所有相关数据库。

Common Identifier Formats

常见标识符格式

Different databases use different identifier systems. If a query fails, the identifier format may be wrong. Here's a quick reference:

Identifier	Format	Example	Used by
UniProt accession	`P#####` or `Q#####`	`P04637` (TP53)	UniProt, STRING, AlphaFold, Reactome mapping
Ensembl gene ID	`ENSG###########`	`ENSG00000141510`	Ensembl, Open Targets, GTEx
NCBI Gene ID	Integer	`7157` (TP53)	NCBI Gene, GEO, DisGeNET, HPO
HGNC ID	`HGNC:#####`	`HGNC:11998`	Monarch
PubChem CID	Integer	`2244` (aspirin)	PubChem
ZINC ID	`ZINC` + 15 digits	`ZINC000000000053` (aspirin)	ZINC
ENA Project	`PRJEB` + digits	`PRJEB40665`	ENA
ENA Run	`ERR` + digits	`ERR1234567`	ENA
ENA Experiment	`ERX` + digits	`ERX1234567`	ENA
ENA Sample	`ERS` + digits	`ERS1234567`	ENA
ChEMBL ID	`CHEMBL####`	`CHEMBL25` (aspirin)	ChEMBL
Reactome stable ID	`R-HSA-######`	`R-HSA-109581`	Reactome
HP term	`HP:#######`	`HP:0001250` (seizure)	HPO (URL-encode colon as %3A)
MONDO disease	`MONDO:#######`	`MONDO:0007947`	Monarch
GO term	`GO:#######`	`GO:0008150`	QuickGO, Gene Ontology
dbSNP rsID	`rs########`	`rs334`	dbSNP, GWAS Catalog, gnomAD
GENCODE ID	`ENSG###.##` (versioned)	`ENSG00000139618.17`	GTEx (requires version suffix)

不同数据库使用不同的标识符系统。如果查询失败，可能是标识符格式错误。以下是快速参考：

标识符	格式	示例	使用数据库
UniProt登录号	`P#####` 或 `Q#####`	`P04637` （TP53）	UniProt、STRING、AlphaFold、Reactome mapping
Ensembl基因ID	`ENSG###########`	`ENSG00000141510`	Ensembl、Open Targets、GTEx
NCBI基因ID	整数	`7157` （TP53）	NCBI Gene、GEO、DisGeNET、HPO
HGNC ID	`HGNC:#####`	`HGNC:11998`	Monarch
PubChem CID	整数	`2244` （阿司匹林）	PubChem
ZINC ID	`ZINC` +15位数字	`ZINC000000000053` （阿司匹林）	ZINC
ENA项目ID	`PRJEB` +数字	`PRJEB40665`	ENA
ENA运行ID	`ERR` +数字	`ERR1234567`	ENA
ENA实验ID	`ERX` +数字	`ERX1234567`	ENA
ENA样本ID	`ERS` +数字	`ERS1234567`	ENA
ChEMBL ID	`CHEMBL####`	`CHEMBL25` （阿司匹林）	ChEMBL
Reactome稳定ID	`R-HSA-######`	`R-HSA-109581`	Reactome
HP术语	`HP:#######`	`HP:0001250` （癫痫发作）	HPO（需将冒号URL编码为%3A）
MONDO疾病ID	`MONDO:#######`	`MONDO:0007947`	Monarch
GO术语	`GO:#######`	`GO:0008150`	QuickGO、Gene Ontology
dbSNP rsID	`rs########`	`rs334`	dbSNP、GWAS Catalog、gnomAD
GENCODE ID	`ENSG###.##` （带版本号）	`ENSG00000139618.17`	GTEx（需要版本后缀）

Identifier Resolution

标识符转换

When a database doesn't recognize an identifier, convert it using these workflows:

Genes: Symbol (e.g. "TP53") → look up in NCBI Gene (esearch by symbol) → get NCBI Gene ID → convert to Ensembl ID via Ensembl

/xrefs/symbol/homo_sapiens/{symbol}

, or to UniProt accession via UniProt search (

gene_exact:{symbol} AND organism_id:9606

Compounds: Name → PubChem

/compound/name/{name}/cids/JSON

→ get CID → convert to ChEMBL ID via UniChem or ChEMBL molecule search. If name lookup fails, try SMILES, InChIKey, or CAS number.

Variants: rsID (e.g. "rs334") works directly in dbSNP, ClinVar, GWAS Catalog, gnomAD. For genomic coordinates, use Ensembl VEP to get consequence annotations and linked rsIDs.

Diseases: Name → Open Targets or Monarch search → get EFO or MONDO ID → use in downstream queries.

当数据库无法识别某个标识符时，请使用以下流程进行转换：

基因：符号（例如“TP53”）→ 在NCBI Gene中查找（通过符号搜索）→ 获取NCBI基因ID → 通过Ensembl的

/xrefs/symbol/homo_sapiens/{symbol}

转换为Ensembl ID，或通过UniProt搜索（

gene_exact:{symbol} AND organism_id:9606

）转换为UniProt登录号。

化合物：名称 → PubChem的

/compound/name/{name}/cids/JSON

→ 获取CID → 通过UniChem或ChEMBL分子搜索转换为ChEMBL ID。如果名称查找失败，尝试SMILES、InChIKey或CAS号。

变异体：rsID（例如“rs334”）可直接在dbSNP、ClinVar、GWAS Catalog、gnomAD中使用。对于基因组坐标，使用Ensembl VEP获取后果注释和关联的rsID。

疾病：名称 → Open Targets或Monarch搜索 → 获取EFO或MONDO ID → 用于后续查询。

POST-Only APIs

仅支持POST的API

These databases require HTTP POST and will not work with WebFetch (GET-only). Use

curl

via your platform's shell tool instead:

Database	Why POST needed	Example
Open Targets	GraphQL endpoint	`curl -X POST -H "Content-Type: application/json" -d '{"query":"..."}' https://api.platform.opentargets.org/api/v4/graphql`
gnomAD	GraphQL endpoint	`curl -X POST -H "Content-Type: application/json" -d '{"query":"..."}' https://gnomad.broadinstitute.org/api`
RummaGEO	POST-only enrichment	`curl -X POST -H "Content-Type: application/json" -d '{"genes":["..."]}' https://rummageo.com/api/enrich`
GDC/TCGA	Complex filter queries	`curl -X POST -H "Content-Type: application/json" -d '{"filters":...}' https://api.gdc.cancer.gov/ssms`
SEC EDGAR	Requires User-Agent header	`curl -H "User-Agent: YourApp you@email.com" https://efts.sec.gov/LATEST/search-index?q=...`

以下数据库需要HTTP POST请求，无法使用WebFetch（仅支持GET）。请改用平台的shell工具执行

curl

命令：

数据库	需要POST的原因	示例
Open Targets	GraphQL端点	`curl -X POST -H "Content-Type: application/json" -d '{"query":"..."}' https://api.platform.opentargets.org/api/v4/graphql`
gnomAD	GraphQL端点	`curl -X POST -H "Content-Type: application/json" -d '{"query":"..."}' https://gnomad.broadinstitute.org/api`
RummaGEO	仅支持POST的富集分析	`curl -X POST -H "Content-Type: application/json" -d '{"genes":["..."]}' https://rummageo.com/api/enrich`
GDC/TCGA	复杂过滤查询	`curl -X POST -H "Content-Type: application/json" -d '{"filters":...}' https://api.gdc.cancer.gov/ssms`
SEC EDGAR	需要User-Agent头	`curl -H "User-Agent: YourApp you@email.com" https://efts.sec.gov/LATEST/search-index?q=...`

API Keys and Access Restrictions

API密钥与访问限制

Some databases require API keys or have access restrictions. When an API key is needed:

Check the current environment first — the key may already be exported as a shell environment variable (e.g.
```
$FRED_API_KEY
```
). Read it directly from the environment.
Fall back to
.env
— if the variable isn't in the environment, check the
```
.env
```
file in the current working directory.
If neither has it — proceed without the key (most APIs still work at lower rate limits) and tell the user which key is missing and how to get one.

部分数据库需要API密钥或有访问限制。当需要API密钥时：

先检查当前环境 — 密钥可能已作为shell环境变量导出（例如
```
$FRED_API_KEY
```
）。直接从环境中读取。
** fallback到.env文件** — 如果环境中没有该变量，请检查当前工作目录下的
```
.env
```
文件。
如果都没有 — 无需密钥继续操作（大多数API在低速率限制下仍可使用），并告知用户缺少哪个密钥以及如何获取。

Databases requiring API keys (free registration)

需要API密钥的数据库（免费注册）

Database	Env Variable	Registration URL
FRED	`FRED_API_KEY`	https://fred.stlouisfed.org/docs/api/api_key.html
BEA	`BEA_API_KEY`	https://apps.bea.gov/API/signup/
BLS	`BLS_API_KEY`	https://data.bls.gov/registrationEngine/
NCBI (GEO, Gene)	`NCBI_API_KEY`	https://www.ncbi.nlm.nih.gov/account/settings/
OpenFDA	`OPENFDA_API_KEY`	https://open.fda.gov/apis/authentication/
USPTO (PatentsView)	`PATENTSVIEW_API_KEY`	https://patentsview.org/apis/keyrequest
Data Commons	`DATACOMMONS_API_KEY`	Google Cloud Console
Materials Project	`MP_API_KEY`	https://materialsproject.org (free account)
NASA	`NASA_API_KEY`	https://api.nasa.gov (free, DEMO_KEY available)
NOAA (CDO)	`NOAA_API_KEY`	https://www.ncdc.noaa.gov/cdo-web/token
OpenWeatherMap	`OPENWEATHERMAP_API_KEY`	https://openweathermap.org/appid
OMIM	`OMIM_API_KEY`	https://omim.org/api (free academic)
BioGRID	`BIOGRID_API_KEY`	https://webservice.thebiogrid.org (free)
Alpha Vantage	`ALPHAVANTAGE_API_KEY`	https://www.alphavantage.co/support/#api-key
US Census	`CENSUS_API_KEY`	https://api.census.gov/data/key_signup.html
DisGeNET	`DISGENET_API_KEY`	https://www.disgenet.org (free academic)
Addgene	`ADDGENE_API_KEY`	https://www.addgene.org (free account)
LINCS L1000 (CLUE)	`CLUE_API_KEY`	https://clue.io (free academic)

These are all free to obtain. The APIs work without keys but have lower rate limits. Always try with a key first — if the env variable isn't set, proceed without the key and note in your response that rate limits may be lower.

数据库	环境变量	注册链接
FRED	`FRED_API_KEY`	https://fred.stlouisfed.org/docs/api/api_key.html
BEA	`BEA_API_KEY`	https://apps.bea.gov/API/signup/
BLS	`BLS_API_KEY`	https://data.bls.gov/registrationEngine/
NCBI (GEO, Gene)	`NCBI_API_KEY`	https://www.ncbi.nlm.nih.gov/account/settings/
OpenFDA	`OPENFDA_API_KEY`	https://open.fda.gov/apis/authentication/
USPTO (PatentsView)	`PATENTSVIEW_API_KEY`	https://patentsview.org/apis/keyrequest
Data Commons	`DATACOMMONS_API_KEY`	Google Cloud Console
Materials Project	`MP_API_KEY`	https://materialsproject.org（免费账户）
NASA	`NASA_API_KEY`	https://api.nasa.gov（免费，提供DEMO_KEY）
NOAA (CDO)	`NOAA_API_KEY`	https://www.ncdc.noaa.gov/cdo-web/token
OpenWeatherMap	`OPENWEATHERMAP_API_KEY`	https://openweathermap.org/appid
OMIM	`OMIM_API_KEY`	https://omim.org/api（免费学术使用）
BioGRID	`BIOGRID_API_KEY`	https://webservice.thebiogrid.org（免费）
Alpha Vantage	`ALPHAVANTAGE_API_KEY`	https://www.alphavantage.co/support/#api-key
US Census	`CENSUS_API_KEY`	https://api.census.gov/data/key_signup.html
DisGeNET	`DISGENET_API_KEY`	https://www.disgenet.org（免费学术使用）
Addgene	`ADDGENE_API_KEY`	https://www.addgene.org（免费账户）
LINCS L1000 (CLUE)	`CLUE_API_KEY`	https://clue.io（免费学术使用）

所有密钥均可免费获取。无密钥时API仍可使用，但速率限制较低。请优先尝试使用密钥——如果环境变量未设置，无需密钥继续操作，并在响应中注明速率限制可能较低。

Databases with paid or restricted access

付费或受限访问的数据库

Database	Restriction	Free alternative
DrugBank	Paid API license required	Use ChEMBL + PubChem + OpenFDA instead
COSMIC	Free academic registration required (JWT auth)	Use Open Targets for cancer mutation data
BRENDA	Free registration required (SOAP, not REST)	Use KEGG for enzyme/pathway data

When a database requires paid access or registration the user hasn't set up:

Fall back to a free alternative that can answer the same question
Tell the user which database you couldn't access, why, and what you used instead
If the user specifically requests a restricted database, explain the access requirements so they can set it up

数据库	限制	免费替代方案
DrugBank	需要付费API许可证	使用ChEMBL + PubChem + OpenFDA替代
COSMIC	需要免费学术注册（JWT认证）	使用Open Targets获取癌症突变数据
BRENDA	需要免费注册（SOAP，非REST）	使用KEGG获取酶/通路数据

当数据库需要付费访问或用户未完成注册时：

改用免费替代方案来回答相同问题
告知用户无法访问哪个数据库、原因以及你使用的替代方案
如果用户明确要求访问受限数据库，请说明访问要求以便他们进行设置

Loading API keys

加载API密钥

Step 1 — Check the current environment. The key may already be exported as a shell variable. For example, in Claude Code you can check with Bash:

echo $FRED_API_KEY

. If the variable is set and non-empty, use it.

Step 2 — Check
.env
file. If the environment variable isn't set, read

.env

from the current working directory. Format:

FRED_API_KEY=your_key_here
BEA_API_KEY=your_key_here

Step 3 — Proceed without. If neither source has the key, proceed without it (most APIs still work at lower rate limits) and mention this to the user.

步骤1 — 检查当前环境。密钥可能已作为shell变量导出。例如，在Claude Code中可通过Bash检查：

echo $FRED_API_KEY

。如果变量已设置且非空，请使用它。

步骤2 — 检查.env文件。如果环境变量未设置，请读取当前工作目录下的

.env

文件。格式：

FRED_API_KEY=your_key_here
BEA_API_KEY=your_key_here

步骤3 — 无需密钥继续。如果两个来源都没有密钥，无需密钥继续操作（大多数API在低速率限制下仍可使用），并向用户提及这一点。

Making API Calls

API调用方法

Use your environment's HTTP fetch tool to call REST endpoints. The tool name varies by platform:

Platform	HTTP Fetch Tool	Fallback
Claude Code	`WebFetch`	`curl` via Bash
Gemini CLI	`web_fetch`	`curl` via shell
Windsurf	`read_url_content`	`curl` via terminal
Cursor	No dedicated fetch tool	`curl` via `run_terminal_cmd`
Codex CLI	No dedicated fetch tool	`curl` via `shell`
Cline	No dedicated fetch tool	`curl` via `execute_command`

If you don't recognize your platform or the fetch tool fails, fall back to

curl

via whatever shell/terminal tool is available. Example:

bash

curl -s -H "Accept: application/json" "https://api.example.com/endpoint"

使用你所在环境的HTTP获取工具调用REST端点。工具名称因平台而异：

平台	HTTP获取工具	备选方案
Claude Code	`WebFetch`	通过Bash使用 `curl`
Gemini CLI	`web_fetch`	通过shell使用 `curl`
Windsurf	`read_url_content`	通过终端使用 `curl`
Cursor	无专用获取工具	通过 `run_terminal_cmd` 使用 `curl`
Codex CLI	无专用获取工具	通过 `shell` 使用 `curl`
Cline	无专用获取工具	通过 `execute_command` 使用 `curl`

如果你不认识自己的平台或获取工具失败，请改用可用的shell/终端工具执行

curl

。示例：

bash

curl -s -H "Accept: application/json" "https://api.example.com/endpoint"

Request guidelines

请求指南

Set
```
Accept: application/json
```
header where supported
URL-encode special characters in query parameters — SMILES strings (
```
/
```
,
```
#
```
,
```
=
```
,
```
@
```
), compound names with parentheses, and ontology terms with colons (
```
HP:0001250
```
→
```
HP%3A0001250
```
) are common sources of failures. With
```
curl
```
, use
```
--data-urlencode
```
for safety.
Parallel OK: When querying different databases (e.g., PubChem + ChEMBL + Reactome), run them in parallel — most APIs have generous rate limits.
Serialize requests to rate-limited APIs: NCBI APIs (Gene, GEO, Protein, Taxonomy, dbSNP, SRA) at 3 req/sec without key, 10 with key. Also watch: Ensembl (15 req/sec), BLS v1 (25 req/day without key), SEC EDGAR (10 req/sec), NOAA (5 req/sec with token).
If you get a rate-limit error (HTTP 429 or 503), wait briefly and retry once

支持的情况下设置
```
Accept: application/json
```
头
对查询参数中的特殊字符进行URL编码——SMILES字符串（
```
/
```
、
```
#
```
、
```
=
```
、
```
@
```
）、带括号的化合物名称和带冒号的本体术语（
```
HP:0001250
```
→
```
HP%3A0001250
```
）是常见的失败原因。使用
```
curl
```
时，为安全起见请使用
```
--data-urlencode
```
。
并行调用可行：查询不同数据库时（例如PubChem + ChEMBL + Reactome），可并行执行——大多数API的速率限制较为宽松。
对速率受限的API序列化请求：NCBI API（Gene、GEO、Protein、Taxonomy、dbSNP、SRA）无密钥时为3次/秒，有密钥时为10次/秒。此外注意：Ensembl（15次/秒）、BLS v1（无密钥时25次/天）、SEC EDGAR（10次/秒）、NOAA（有令牌时5次/秒）。
如果收到速率限制错误（HTTP 429或503），请稍作等待后重试一次

Error recovery

错误恢复

If an API returns an error or empty results:

Check the identifier format — use the Common Identifier Formats table above. A gene symbol may need to be converted to NCBI Gene ID or Ensembl ID first.
Try alternative identifiers — if a compound name fails in PubChem, try SMILES, InChIKey, or CID. If a gene symbol fails, try the NCBI Gene ID.
Try a different database — if one database is down or returns nothing, check the "Also consider" column in the selection guide for alternatives.
Report the failure — tell the user which database failed, the error, and what you tried instead.

如果API返回错误或空结果：

检查标识符格式 — 使用上方的常见标识符格式表。基因符号可能需要先转换为NCBI基因ID或Ensembl ID。
尝试替代标识符 — 如果化合物名称在PubChem中查找失败，尝试SMILES、InChIKey或CID。如果基因符号失败，尝试NCBI基因ID。
尝试其他数据库 — 如果某个数据库宕机或无结果，请查看选择指南中的“备选数据库”列寻找替代方案。
报告失败情况 — 告知用户哪个数据库失败、错误信息以及你尝试的替代方案。

Pagination

分页

Many APIs return paginated results — if you only read the first page, you may miss data. Common patterns:

Offset/Limit:
```
offset=0&limit=100
```
→ increment offset by limit for the next page (ChEMBL, FRED, NOAA, USGS, NCBI E-utilities, ENA, GDC, FDA)
Cursor-based: Response includes a
```
nextPageToken
```
or
```
cursor
```
value — pass it in the next request (ClinicalTrials.gov, UniProt)
Page number:
```
page=1&per_page=50
```
→ increment page (World Bank, cBioPortal, ZINC)

Check the reference file for each database's specific pagination parameters. If a response includes

total

totalCount

, or

next

and the number of returned results is less than the total, there are more pages.

For targeted lookups (single gene, single compound), the first page is usually sufficient. Paginate when the user needs comprehensive results (e.g., "all clinical trials for X" or "all known variants in gene Y").

许多API返回分页结果——如果你只读取第一页，可能会遗漏数据。常见模式：

偏移量/限制：
```
offset=0&limit=100
```
→ 每次将偏移量增加限制值获取下一页（ChEMBL、FRED、NOAA、USGS、NCBI E-utilities、ENA、GDC、FDA）
基于游标：响应包含
```
nextPageToken
```
或
```
cursor
```
值——将其传入下一次请求（ClinicalTrials.gov、UniProt）
页码：
```
page=1&per_page=50
```
→ 递增页码（World Bank、cBioPortal、ZINC）

请查阅每个数据库的参考文件了解具体分页参数。如果响应包含

total

、

totalCount

或

next

，且返回结果数小于总数，则存在更多页面。

对于针对性查询（单个基因、单个化合物），第一页通常足够。当用户需要全面结果时（例如“X的所有临床试验”或“基因Y的所有已知变异体”），请进行分页查询。

Output Format

输出格式

Structure your response like this:

undefined

请按以下结构组织响应：

undefined

Databases Queried

已查询数据库

PubChem — /compound/name/aspirin/property/...
Reactome — /search/query?query=aspirin

PubChem — /compound/name/aspirin/property/...
Reactome — /search/query?query=aspirin

Results

结果

PubChem

[raw JSON response]

[原始JSON响应]

Reactome

[raw JSON response]


If results are very large, present the most relevant portion and note that additional data is available. But default to showing the full raw JSON — the user asked for it.

[原始JSON响应]


如果结果非常大，请展示最相关的部分并注明还有更多数据可用。但默认情况下请展示完整的原始JSON——用户要求获取原始结果。

Adding New Databases

添加新数据库

This skill is designed to grow. Each database is a self-contained reference file in

references/

. To add a new database:

Create
```
references/<database-name>.md
```
following the same format as existing files
Add an entry to the database selection guide above
The reference file should include: base URL, key endpoints, query parameter formats, example calls, rate limits, and response structure

本工具支持扩展。每个数据库对应

references/

目录下一个独立的参考文件。添加新数据库的步骤：

按照现有文件格式创建
```
references/<database-name>.md
```
在上方的数据库选择指南中添加条目
参考文件应包含：基础URL、关键端点、查询参数格式、调用示例、速率限制和响应结构

Available Databases

可用数据库

Read the relevant reference file before making any API call.

调用任何API前请阅读相关参考文件。