Bio Entrez Link

Version Compatibility

Reference examples tested with: BioPython 1.83+, Entrez Direct 21.0+

Before using code patterns, verify installed versions match. If versions differ:

• Python: pip show <package> then help(module.function) to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Entrez Link

Navigate between NCBI databases using Biopython's Entrez module (ELink utility).

"Find related records across NCBI databases" → Use ELink to discover cross-references (e.g., gene to protein, sequence to publication).

• Python: Entrez.elink(dbfrom=..., db=..., id=...) (BioPython)
• CLI: elink -db protein -target gene (Entrez Direct)

Required Setup

from Bio import Entrez

Entrez.email = 'your.email@example.com'  # Required by NCBI
Entrez.api_key = 'your_api_key'          # Optional, raises rate limit

Core Function

Entrez.elink() - Cross-Database Links

Find related records in the same or different databases.

# Find proteins linked to a gene
handle = Entrez.elink(dbfrom='gene', db='protein', id='672')
record = Entrez.read(handle)
handle.close()

# Extract linked IDs
linkset = record[0]
if linkset['LinkSetDb']:
    links = linkset['LinkSetDb'][0]['Link']
    protein_ids = [link['Id'] for link in links]
    print(f"Found {len(protein_ids)} linked proteins")

Key Parameters:

ELink Result Structure

record[0]                          # First linkset
record[0]['DbFrom']                # Source database
record[0]['IdList']                # Input IDs
record[0]['LinkSetDb']             # List of link results
record[0]['LinkSetDb'][0]['DbTo']  # Target database
record[0]['LinkSetDb'][0]['LinkName']  # Link name
record[0]['LinkSetDb'][0]['Link']  # List of linked records
record[0]['LinkSetDb'][0]['Link'][0]['Id']  # Linked ID

Common Link Paths

Gene to Other Databases

Nucleotide to Other Databases

Protein to Other Databases

PubMed Links

Code Patterns

Gene to Protein

from Bio import Entrez

Entrez.email = 'your.email@example.com'

def get_proteins_for_gene(gene_id):
    handle = Entrez.elink(dbfrom='gene', db='protein', id=gene_id, linkname='gene_protein_refseq')
    record = Entrez.read(handle)
    handle.close()

    if not record[0]['LinkSetDb']:
        return []
    return [link['Id'] for link in record[0]['LinkSetDb'][0]['Link']]

protein_ids = get_proteins_for_gene('672')  # BRCA1
print(f"RefSeq proteins: {protein_ids[:5]}")

Nucleotide to Gene

def get_gene_for_nucleotide(nuc_id):
    handle = Entrez.elink(dbfrom='nucleotide', db='gene', id=nuc_id)
    record = Entrez.read(handle)
    handle.close()

    if not record[0]['LinkSetDb']:
        return None
    return record[0]['LinkSetDb'][0]['Link'][0]['Id']

gene_id = get_gene_for_nucleotide('NM_007294')
print(f"Gene ID: {gene_id}")

Find Related PubMed Articles

def get_related_articles(pmid, max_results=10):
    handle = Entrez.elink(dbfrom='pubmed', db='pubmed', id=pmid, linkname='pubmed_pubmed')
    record = Entrez.read(handle)
    handle.close()

    if not record[0]['LinkSetDb']:
        return []
    links = record[0]['LinkSetDb'][0]['Link']
    return [link['Id'] for link in links[:max_results]]

related = get_related_articles('35412348')
print(f"Related articles: {related}")

Get All Available Links

def discover_links(db, record_id):
    handle = Entrez.elink(dbfrom=db, id=record_id, cmd='acheck')
    record = Entrez.read(handle)
    handle.close()

    links = {}
    for linkset in record[0].get('LinkSetDb', []):
        links[linkset['LinkName']] = linkset['DbTo']
    return links

available = discover_links('gene', '672')
for name, target in available.items():
    print(f"{name} -> {target}")

Navigate Gene -> Protein -> Structure

Goal: Traverse multiple NCBI databases to find 3D structures associated with a gene of interest.

Approach: Chain two ELink calls: first link from gene to RefSeq proteins, then link those protein IDs to the structure database.

def gene_to_structures(gene_id):
    # Gene to protein
    handle = Entrez.elink(dbfrom='gene', db='protein', id=gene_id, linkname='gene_protein_refseq')
    record = Entrez.read(handle)
    handle.close()

    if not record[0]['LinkSetDb']:
        return []
    protein_ids = [link['Id'] for link in record[0]['LinkSetDb'][0]['Link'][:5]]

    # Protein to structure
    handle = Entrez.elink(dbfrom='protein', db='structure', id=','.join(protein_ids))
    record = Entrez.read(handle)
    handle.close()

    structure_ids = []
    for linkset in record:
        if linkset['LinkSetDb']:
            structure_ids.extend([link['Id'] for link in linkset['LinkSetDb'][0]['Link']])
    return structure_ids

structures = gene_to_structures('672')
print(f"Structure IDs: {structures[:5]}")

Link Multiple IDs at Once

Goal: Find cross-database links for a batch of source IDs in a single API call.

Approach: Pass comma-joined IDs to ELink; the result contains one linkset per input ID, so iterate through the record list to map each source ID to its linked targets.

def batch_link(dbfrom, db, ids):
    if isinstance(ids, list):
        ids = ','.join(ids)

    handle = Entrez.elink(dbfrom=dbfrom, db=db, id=ids)
    record = Entrez.read(handle)
    handle.close()

    # Returns one linkset per input ID
    results = {}
    for linkset in record:
        source_id = linkset['IdList'][0]
        linked_ids = []
        if linkset['LinkSetDb']:
            linked_ids = [link['Id'] for link in linkset['LinkSetDb'][0]['Link']]
        results[source_id] = linked_ids
    return results

results = batch_link('gene', 'protein', ['672', '675', '7157'])
for gene, proteins in results.items():
    print(f"Gene {gene}: {len(proteins)} proteins")

Get Publications for a Sequence

def get_sequence_publications(accession):
    # First get the GI/UID
    handle = Entrez.esearch(db='nucleotide', term=f'{accession}[accn]')
    search = Entrez.read(handle)
    handle.close()

    if not search['IdList']:
        return []
    uid = search['IdList'][0]

    # Link to PubMed
    handle = Entrez.elink(dbfrom='nucleotide', db='pubmed', id=uid)
    record = Entrez.read(handle)
    handle.close()

    if not record[0]['LinkSetDb']:
        return []
    return [link['Id'] for link in record[0]['LinkSetDb'][0]['Link']]

pmids = get_sequence_publications('NM_007294')
print(f"PubMed IDs: {pmids[:5]}")

Link Commands

Common Errors

Decision Tree

Need to find related records?
├── Know what link you want?
│   └── Use elink with specific linkname
├── Discover what links exist?
│   └── Use elink with cmd='acheck'
├── Navigate to target database?
│   └── Use elink(dbfrom=X, db=Y, id=Z)
├── Find related records in same database?
│   └── Use elink(dbfrom=X, db=X) with neighbor
├── Chain multiple databases?
│   └── Call elink multiple times
└── Need the actual records?
    └── Use elink first, then efetch with IDs

Related Skills

• entrez-search - Search databases before linking
• entrez-fetch - Retrieve records after finding linked IDs
• batch-downloads - Download many linked records efficiently