uniprot

UniProt 数据库访问

注意：此技能直接使用 UniProt REST API。无需部署 Modal——所有操作都通过 HTTP 请求在本地运行。

获取序列

按登录号

# FASTA format
curl "https://rest.uniprot.org/uniprotkb/P00533.fasta"

# JSON format with annotations
curl "https://rest.uniprot.org/uniprotkb/P00533.json"

使用 Python

import requests

def get_uniprot_sequence(accession):
    """Fetch sequence from UniProt."""
    url = f"https://rest.uniprot.org/uniprotkb/{accession}.fasta"
    response = requests.get(url)
    if response.ok:
        lines = response.text.strip().split('\n')
        header = lines[0]
        sequence = ''.join(lines[1:])
        return header, sequence
    return None, None

获取注释

完整条目

def get_uniprot_entry(accession):
    """Fetch full UniProt entry as JSON."""
    url = f"https://rest.uniprot.org/uniprotkb/{accession}.json"
    response = requests.get(url)
    return response.json() if response.ok else None

entry = get_uniprot_entry("P00533")
print(f"Protein: {entry['proteinDescription']['recommendedName']['fullName']['value']}")

结构域边界

def get_domains(accession):
    """Extract domain annotations."""
    entry = get_uniprot_entry(accession)
    domains = []

    for feature in entry.get('features', []):
        if feature['type'] == 'Domain':
            domains.append({
                'name': feature.get('description', ''),
                'start': feature['location']['start']['value'],
                'end': feature['location']['end']['value']
            })

    return domains

# Example: EGFR domains
domains = get_domains("P00533")
# [{'name': 'Kinase', 'start': 712, 'end': 979}, ...]

搜索 UniProt

按基因名称

def search_uniprot(query, organism=None, limit=10):
    """Search UniProt by query."""
    url = "https://rest.uniprot.org/uniprotkb/search"
    params = {
        "query": query,
        "format": "json",
        "size": limit
    }
    if organism:
        params["query"] += f" AND organism_id:{organism}"

    response = requests.get(url, params=params)
    return response.json()['results']

# Search for human EGFR
results = search_uniprot("EGFR", organism=9606)

按序列相似性（BLAST）

# Use UniProt BLAST
# https://www.uniprot.org/blast

交叉引用

获取 PDB 结构

def get_pdb_references(accession):
    """Get PDB structures for UniProt entry."""
    entry = get_uniprot_entry(accession)
    pdbs = []

    for xref in entry.get('uniProtKBCrossReferences', []):
        if xref['database'] == 'PDB':
            pdbs.append({
                'pdb_id': xref['id'],
                'method': xref.get('properties', [{}])[0].get('value', ''),
                'chains': xref.get('properties', [{}])[1].get('value', '')
            })

    return pdbs

# Example: PDB structures for EGFR
pdbs = get_pdb_references("P00533")

常见用例

靶标选择

# 1. Find protein by name
results = search_uniprot("insulin receptor", organism=9606)

# 2. Get accession
accession = results[0]['primaryAccession']  # e.g., P06213

# 3. Get domains
domains = get_domains(accession)

# 4. Find PDB structure
pdbs = get_pdb_references(accession)

# 5. Download best structure for design

序列比对信息

def get_sequence_variants(accession):
    """Get natural variants from UniProt."""
    entry = get_uniprot_entry(accession)
    variants = []

    for feature in entry.get('features', []):
        if feature['type'] == 'Natural variant':
            variants.append({
                'position': feature['location']['start']['value'],
                'original': feature.get('alternativeSequence', {}).get('originalSequence', ''),
                'variant': feature.get('alternativeSequence', {}).get('alternativeSequences', [''])[0],
                'description': feature.get('description', '')
            })

    return variants

API 参考

端点	描述
/uniprotkb/{id}.fasta	FASTA 序列
/uniprotkb/{id}.json	完整条目 JSON
/uniprotkb/search	搜索条目
/uniprotkb/stream	批量下载

故障排除

未找到条目：检查登录号格式（例如，P00533） 速率限制：在请求之间添加延迟 大型下载：使用带分页的 stream 端点

---

下一步：使用 esm 获取嵌入，或使用 chai / boltz 获取结构。