Bio Biomart Queries

pip install pybiomart pandas
# R:
# BiocManager::install('biomaRt')

from pybiomart import Server
server = Server(host='http://www.ensembl.org')
print(server.marts)                                          # list marts
mart = server['ENSEMBL_MART_ENSEMBL']
print(mart.datasets)                                         # list datasets (species)
ds = mart['hsapiens_gene_ensembl']
print(ds.attributes)                                         # list attributes
print(ds.filters)                                            # list filters

from pybiomart import Server
import pandas as pd

server = Server(host='http://www.ensembl.org')
mart = server['ENSEMBL_MART_ENSEMBL']
ds = mart['hsapiens_gene_ensembl']

ensembl_ids = ['ENSG00000139618', 'ENSG00000141510', 'ENSG00000171862']  # ...up to 5K+

df = ds.query(
    attributes=['ensembl_gene_id', 'external_gene_name', 'hgnc_id',
                'refseq_mrna', 'uniprotswissprot'],
    filters={'ensembl_gene_id': ensembl_ids},
)
print(df.head())
# One row per (gene, cross-ref) pair; genes with multiple RefSeq mRNAs get multiple rows.

df = ds.query(
    attributes=['ensembl_gene_id', 'external_gene_name', 'chromosome_name',
                'start_position', 'end_position', 'strand', 'biotype'],
    filters={'chromosome_name': '17', 'biotype': 'protein_coding'},
)
print(f'{len(df)} protein-coding genes on chr17')

df = ds.query(
    attributes=['ensembl_gene_id', 'external_gene_name',
                'mmusculus_homolog_ensembl_gene', 'mmusculus_homolog_orthology_type',
                'drerio_homolog_ensembl_gene', 'drerio_homolog_orthology_type'],
    filters={'chromosome_name': '17'},
)
# pybiomart columns use the mart display names, which can vary across releases.
# Resolve column names defensively rather than hardcoding strings:
mouse_type_col = next(c for c in df.columns if 'Mouse' in c and 'type' in c)
zebra_type_col = next(c for c in df.columns if 'Zebrafish' in c and 'type' in c)
df_one2one = df[(df[mouse_type_col] == 'ortholog_one2one') &
                (df[zebra_type_col] == 'ortholog_one2one')]
print(f'{len(df_one2one)} 1:1 orthologs across all three species on chr17')

df = ds.query(
    attributes=['ensembl_gene_id', 'external_gene_name',
                'go_id', 'name_1006', 'namespace_1003'],
    filters={'external_gene_name': ['TP53', 'BRCA1', 'MYC', 'EGFR']},
)
# Long format: one row per (gene, GO term) pair

# Reference: Bioconductor biomaRt 2.58+ | Verify API if version differs
library(biomaRt)

# Pin to release 110 for reproducibility
ensembl <- useEnsembl(biomart='genes', dataset='hsapiens_gene_ensembl', version=110)

# Or via host URL (for older or specific assemblies)
# ensembl <- useMart('ENSEMBL_MART_ENSEMBL',
#                     dataset='hsapiens_gene_ensembl',
#                     host='https://nov2020.archive.ensembl.org')

df <- getBM(
    attributes = c('ensembl_gene_id', 'external_gene_name', 'entrezgene_id',
                   'uniprotswissprot', 'refseq_mrna'),
    filters = 'ensembl_gene_id',
    values = c('ENSG00000139618', 'ENSG00000141510'),
    mart = ensembl
)
head(df)

# What attributes are available?
attrs = ds.attributes
ortho_attrs = [a for a in attrs if 'homolog' in a]
print(f'{len(ortho_attrs)} ortholog attributes; first 5: {ortho_attrs[:5]}')

# What filters?
filts = ds.filters
chrom_filts = [f for f in filts if 'chrom' in f]