def get_mgi_to_ensembl_map():
return dict(
biomart.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=['mgi_id', 'ensembl_gene_id'],
)
)
def get_all_ensembl_names():
"@return: All ensembl names."
from biopsy.identifiers.biomart import quick_query
logging.info("Querying Ensembl biomart for all mouse genes' names")
return dict(
quick_query(dataset='mmusculus_gene_ensembl',
attributes=('ensembl_gene_id', 'external_gene_id')))
def genes_for_go_id(go_id):
import biopsy.identifiers.biomart as B
for row in B.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=['ensembl_gene_id'],
filters=[('go', go_id)],
):
yield row[0]
def genes_for_go_id(go_id):
import biopsy.identifiers.biomart as B
for row in B.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=['ensembl_gene_id'],
filters=[('go', go_id)],
):
yield row[0]
def entrez_to_ensembl():
import biopsy.identifiers.biomart as B
return dict(
B.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=['entrezgene', 'ensembl_gene_id'],
filters=()
)
)
def transcripts_to_genes():
import biopsy.identifiers.biomart as B
return dict(
B.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=['ensembl_transcript_id', 'ensembl_gene_id'],
filters=()
)
)
def get_all_ensembl_names():
"@return: All ensembl names."
from biopsy.identifiers.biomart import quick_query
logging.info("Querying Ensembl biomart for all mouse genes' names")
return dict(
quick_query(
dataset='mmusculus_gene_ensembl',
attributes=('ensembl_gene_id', 'external_gene_id')
)
)
def go_ids_for_genes(genes):
import biopsy.identifiers.biomart as B
for row in B.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=[
'ensembl_gene_id',
#'go_cellular_component_id',
'go_biological_process_id',
#'go_molecular_function_id'
],
filters=[('ensembl_gene_id', ','.join(genes))],
):
yield row
def go_ids_for_genes(genes):
import biopsy.identifiers.biomart as B
for row in B.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=[
'ensembl_gene_id',
#'go_cellular_component_id',
'go_biological_process_id',
#'go_molecular_function_id'
],
filters=[('ensembl_gene_id', ','.join(genes))],
):
yield row
def get_all_ensembl_go_annotations():
"@return: A map from ensembl genes to sets of go annotations."
import biopsy.identifiers.biomart as biomart
logging.info('Querying Ensembl biomart for all GO annotations')
result = cookbook.DictOfLists()
for id_attr, evidence_attr in [
('go_biological_process_id', 'go_biological_process_linkage_type'),
('go_cellular_component_id', 'go_cellular_component_linkage_type'),
('go_molecular_function_id', 'go_molecular_function_linkage_type'),
]:
for row in biomart.quick_query(
dataset='mmusculus_gene_ensembl',
attributes=['ensembl_gene_id', id_attr, evidence_attr]
):
if row[2] not in options.go_evidence_codes_to_ignore and row[1]:
result[row[0]].append(row[1])
logging.info('Found %d go annotations', sum(len(v) for v in result.values()))
return result
def transcripts_to_genes():
import biopsy.identifiers.biomart as B
return dict(
B.quick_query(dataset='mmusculus_gene_ensembl',
attributes=['ensembl_transcript_id', 'ensembl_gene_id'],
filters=()))
def get_rat_mouse_orthologs():
from biopsy.identifiers.biomart import quick_query
logging.info('Getting rat mouse orthologs from Ensembl')
result = dict(quick_query(dataset='rnorvegicus_gene_ensembl', attributes=['ensembl_gene_id', 'mouse_ensembl_gene']))
logging.info('Mapped %d rat genes to mouse', len(result))
return result