def test_general():
s = BioMart()
#s.registry()
s.datasets("ensembl")
s.version("ensembl")
s.attributes("oanatinus_gene_ensembl")
s.filters("oanatinus_gene_ensembl")
s.configuration("oanatinus_gene_ensembl")
xmlq = """<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE Query>
<Query virtualSchemaName = "default" formatter = "TSV" header = "0" uniqueRows = "0" count = "" datasetConfigVersion = "0.6" >
<Dataset name = "pathway" interface = "default" >
<Filter name = "referencepeptidesequence_uniprot_id_list" value = "P43403"/>
<Attribute name = "stableidentifier_identifier" />
<Attribute name = "pathway_db_id" />
</Dataset>
</Query>
"""
s.query(s._xml_example)
# build own xml using the proper functions
s.add_dataset_to_xml("protein")
s.get_xml()
def get_attributes(dataset):
bm = BioMart(verbose=False)
attributes = bm.attributes(dataset)
attr_dicts = [{"Attribute": k, "Description": v[0]}
for k, v in attributes.items()]
return pd.DataFrame.from_dict(attr_dicts)
def id_map_ensembl(to_annotation, version, species, psm_protein_id):
'''
:param to_annotation: target identifier annotation (i.e. uniprot_swissprot)
:param version: Database version
:param species: Full species name
:param psm_protein_id: list of IDs to be converted
:return: BioMart results
'''
# If species is in plantsDB, execute plants adjusted function
if species == "arabidopsis_thaliana":
result = id_map_ensembl_plants(to_annotation, version, species,
psm_protein_id)
return result
else:
#adjust UniProt xml annotation for BioMart version >87
if int(version) > 87 and "uniprot" in to_annotation:
to_annotation = to_annotation.replace('_', '')
#create connection
query_string = _id_in_xml_query_(psm_protein_id)
version = _get_ensembl_archive_(version, species)
dataset = _get_ensembl_dataset_(species)
biomart = BioMart(host=version)
#add filters
biomart.add_dataset_to_xml(dataset)
biomart.add_filter_to_xml(to_annotation, query_string)
#add attributs
biomart.add_attribute_to_xml("ensembl_transcript_id")
biomart.add_attribute_to_xml("transcript_start")
biomart.add_attribute_to_xml("transcript_end")
biomart.add_attribute_to_xml(to_annotation)
attributes = biomart.attributes(dataset)
#execute query
xml_query = biomart.get_xml()
tmp_result = biomart.query(xml_query)
if len(tmp_result) == 1:
print "ERROR: could not convert ID's trough BioMart, " \
"Please check whether Ensembl version/species were correctly supplied"
tmp_result = tmp_result.split("\n")
result = []
if tmp_result != []:
for i in tmp_result:
i = i.split("\t")
if i[0] != "":
result.append([i[0], (int(i[2]) - int(i[1])), i[3]])
else:
result.append(i)
return result
def retrieve_data_from_biomart(version, species, transcript_id,
three_frame_translation):
'''
:param version: Database version
:param species: Full species name
:param transcript_id: list of transcript IDs
:return: BioMart results
'''
#create connection
tr_query = _id_in_xml_query_(transcript_id)
version = _get_ensembl_archive_(version, species)
dataset = _get_ensembl_dataset_(species)
biomart = BioMart(host=version)
#add filters
biomart.add_dataset_to_xml(dataset)
biomart.add_filter_to_xml("ensembl_transcript_id", tr_query)
#add attributes
biomart.add_attribute_to_xml('ensembl_transcript_id')
biomart.add_attribute_to_xml("chromosome_name")
biomart.add_attribute_to_xml("strand")
if three_frame_translation == "Y":
biomart.add_attribute_to_xml("cdna")
else:
biomart.add_attribute_to_xml("coding")
attributes = biomart.attributes(dataset)
#execute query
xml_query = biomart.get_xml()
# create bypass for plants database
if species == "arabidopsis_thaliana":
xml_query = xml_query.replace('virtualSchemaName = "default"',
'virtualSchemaName = "plants_mart_30"')
result = biomart.query(xml_query)
result = result.split("\n")
return result
def retrieve_data_from_biomart(version,species,transcript_id,three_frame_translation):
'''
:param version: Database version
:param species: Full species name
:param transcript_id: list of transcript IDs
:return: BioMart results
'''
#create connection
tr_query=_id_in_xml_query_(transcript_id)
version=_get_ensembl_archive_(version,species)
dataset=_get_ensembl_dataset_(species)
biomart = BioMart(host=version)
#add filters
biomart.add_dataset_to_xml(dataset)
biomart.add_filter_to_xml("ensembl_transcript_id",tr_query)
#add attributes
biomart.add_attribute_to_xml('ensembl_transcript_id')
biomart.add_attribute_to_xml("chromosome_name")
biomart.add_attribute_to_xml("strand")
if three_frame_translation=="Y":
biomart.add_attribute_to_xml("cdna")
else:
biomart.add_attribute_to_xml("coding")
attributes=biomart.attributes(dataset)
#execute query
xml_query=biomart.get_xml()
# create bypass for plants database
if species=="arabidopsis_thaliana":
xml_query=xml_query.replace('virtualSchemaName = "default"','virtualSchemaName = "plants_mart_30"')
result=biomart.query(xml_query)
result=result.split("\n")
return result
def id_map_ensembl(to_annotation,version,species,psm_protein_id):
'''
:param to_annotation: target identifier annotation (i.e. uniprot_swissprot)
:param version: Database version
:param species: Full species name
:param psm_protein_id: list of IDs to be converted
:return: BioMart results
'''
# If species is in plantsDB, execute plants adjusted function
if species=="arabidopsis_thaliana":
result=id_map_ensembl_plants(to_annotation,version,species,psm_protein_id)
return result
else:
#create connection
query_string=_id_in_xml_query_(psm_protein_id)
version=_get_ensembl_archive_(version,species)
dataset=_get_ensembl_dataset_(species)
biomart = BioMart(host=version)
#add filters
biomart.add_dataset_to_xml(dataset)
biomart.add_filter_to_xml(to_annotation,query_string)
#add attributs
biomart.add_attribute_to_xml("ensembl_transcript_id")
biomart.add_attribute_to_xml("transcript_length")
biomart.add_attribute_to_xml("uniprot_sptrembl")
attributes=biomart.attributes(dataset)
#execute query
xml_query=biomart.get_xml()
result=biomart.query(xml_query)
result=result.split("\n")
return result
