def __init__(self, filename=None):
self._hgnc_service = HGNC()
if filename == None:
self.alldata = self.load_all_hgnc()
self.df = self.build_dataframe()
else:
self.read_csv(filename)
def _lookup_hgnc_id(self):
hgnc_web = HGNC()
hgnc = hgnc_web.fetch('hgnc_id', self.external_id)
if hgnc['response']['numFound'] == 1:
self.name = hgnc['response']['docs'][0]['symbol']
self.description = hgnc['response']['docs'][0]['name']
# Get synonyms if requested.
if self.get_synonyms:
for item in hgnc['response']['docs'][0]['alias_symbol']:
self.synonyms.append(item)
elif hgnc['response']['numFound'] == 0:
self.error = "No results found when querying HGNC for {}".format(
self.external_id)
return self
def __init__(self, filename=None):
self._hgnc_service = HGNC()
if filename == None:
self.alldata = self.load_all_hgnc()
self.df = self.build_dataframe()
else:
self.read_csv(filename)
class HGNCMapper(object):
hgnc_dblink = ['EC','Ensembl', 'EntrezGene', 'GDB', 'GENATLAS',
'GeneCards', 'GeneTests', 'GoPubmed', 'H-InvDB', 'HCDM', 'HCOP',
'HGNC', 'HORDE', 'IMGT_GENE_DB', 'INTERFIL', 'IUPHAR', 'KZNF',
'MEROPS', 'Nucleotide', 'OMIM', 'PubMed', 'RefSeq', 'Rfam',
'Treefam', 'UniProt', 'Vega', 'miRNA', 'snoRNABase']
def __init__(self, filename=None):
self._hgnc_service = HGNC()
if filename == None:
self.alldata = self.load_all_hgnc()
self.df = self.build_dataframe()
else:
self.read_csv(filename)
def load_all_hgnc(self):
"""keys are unique Gene names"""
print("Fetching the data from HGNC first. May take a few minutes"),
alldata = self._hgnc_service.mapping_all()
print("done")
return alldata
def build_dataframe(self):
# simplify to get a dictionary of dictionary
data = {k1:{k2:v2['xkey'] for k2,v2 in self.alldata[k1].iteritems()} for k1 in self.alldata.keys()}
dfdata = pd.DataFrame(data)
dfdata = dfdata.transpose()
# rename to tag with "HGNC"
dfdata.columns = [this + "__HGNC_mapping" for this in dfdata.columns]
print("a dataframe was built using HGNC data set and saved in attributes self._df_hgnc")
return dfdata
def add_sequence_to_nodes(n: str, d: Dict[str, Any]):
"""
Maps UniProt ACC to UniProt ID. Retrieves sequence from UniProt and adds it to the node as a feature
:param n: Graph node.
:type n: str
:param d: Graph attribute dictionary.
:type d: Dict[str, Any]
"""
h = HGNC(verbose=False)
u = UniProt(verbose=False)
d["uniprot_ids"] = h.fetch(
"symbol", d["protein_id"])["response"]["docs"][0]["uniprot_ids"]
# Todo these API calls should probably be batched
# Todo mapping with bioservices to support other protein IDs?
for id in d["uniprot_ids"]:
d[f"sequence_{id}"] = u.get_fasta_sequence(id)
def kegg_to_hugo(genes, species='hsa'):
"""
Converts all KEGG names to HGNC
Parameters
----------
genes : list
species : str
Returns
-------
dict
"""
prefix = species + ':'
hugo = HGNC(verbose=True)
hugo_dict = {}
not_found = set()
for i in genes:
tmp_name = i.lstrip(prefix)
mapping = hugo.search(tmp_name)
if 'response' in mapping:
response = mapping['response']
if 'numFound' in response:
if response['numFound'] == 0:
not_found.add(i)
continue
elif response['numFound'] == 1:
docs = response['docs'][0]
hugo_dict[i] = docs['symbol']
continue
else:
if 'symbol' in response['docs'][0]:
hugo_dict[i] = response['docs'][0]['symbol']
else:
not_found.add(i)
if not_found != 0:
print("{} not found after HGNC mapping".format(len(not_found)))
print("{} ".format(not_found))
return hugo_dict, not_found
def kegg_to_hugo(genes, species='hsa'):
"""
Converts all KEGG names to HGNC
Parameters
----------
genes : list
species : str
Returns
-------
dict
"""
prefix = species + ':'
hugo = HGNC(verbose=True)
hugo_dict = {}
not_found = set()
for i in genes:
tmp_name = i.lstrip(prefix)
mapping = hugo.search(tmp_name)
if 'response' in mapping:
response = mapping['response']
if 'numFound' in response:
if response['numFound'] == 0:
not_found.add(i)
continue
elif response['numFound'] == 1:
docs = response['docs'][0]
hugo_dict[i] = docs['symbol']
continue
else:
if 'symbol' in response['docs'][0]:
hugo_dict[i] = response['docs'][0]['symbol']
else:
not_found.add(i)
if not_found != 0:
print("{} not found after HGNC mapping".format(len(not_found)))
print("{} ".format(not_found))
return hugo_dict, not_found
def __init__(self, verbosity="INFO"):
super(Mapper, self).__init__(level=verbosity)
self.logging.info("Initialising the services")
self.logging.info("... uniprots")
self._uniprot_service = UniProt()
self.logging.info("... KEGG")
self._kegg_service = KeggParser(verbose=False)
self.logging.info("... HGNC")
self._hgnc_service = HGNC()
self.logging.info("... UniChem")
self._unichem_service = UniChem()
self.logging.info("...BioDBNet")
self._biodbnet = BioDBNet()
class HGNCMapper(object):
hgnc_dblink = [
'EC', 'Ensembl', 'EntrezGene', 'GDB', 'GENATLAS', 'GeneCards',
'GeneTests', 'GoPubmed', 'H-InvDB', 'HCDM', 'HCOP', 'HGNC', 'HORDE',
'IMGT_GENE_DB', 'INTERFIL', 'IUPHAR', 'KZNF', 'MEROPS', 'Nucleotide',
'OMIM', 'PubMed', 'RefSeq', 'Rfam', 'Treefam', 'UniProt', 'Vega',
'miRNA', 'snoRNABase'
]
def __init__(self, filename=None):
self._hgnc_service = HGNC()
if filename == None:
self.alldata = self.load_all_hgnc()
self.df = self.build_dataframe()
else:
self.read_csv(filename)
def load_all_hgnc(self):
"""keys are unique Gene names"""
print("Fetching the data from HGNC first. May take a few minutes"),
alldata = self._hgnc_service.mapping_all()
print("done")
return alldata
def build_dataframe(self):
# simplify to get a dictionary of dictionary
data = {
k1: {k2: v2['xkey']
for k2, v2 in self.alldata[k1].iteritems()}
for k1 in self.alldata.keys()
}
dfdata = pd.DataFrame(data)
dfdata = dfdata.transpose()
# rename to tag with "HGNC"
dfdata.columns = [this + "__HGNC_mapping" for this in dfdata.columns]
print(
"a dataframe was built using HGNC data set and saved in attributes self._df_hgnc"
)
return dfdata
def test_hgnc():
h = HGNC()
h.get_info()
h.fetch('symbol', 'ZNF3')
h.fetch('alias_name', 'A-kinase anchor protein, 350kDa')
h.search('BRAF')
h.search('symbol', 'ZNF*')
h.search('symbol', 'ZNF?')
h.search('symbol', 'ZNF*+AND+status:Approved')
h.search('symbol', 'ZNF3+OR+ZNF12')
h.search('symbol', 'ZNF*+NOT+status:Approved')
def __init__(self):
self.s = HGNC(verbose=False)
class test_hgnc():
def __init__(self):
self.s = HGNC(verbose=False)
@attr('skip')
def test_get_xml(self):
xml = self.s.get_xml("ZAP70")
xml = self.s.get_xml("ZAP70;INSR")
assert len(xml.findAll("gene")) == 2
self.s.get_xml("wrong")
@attr('skip')
def test_aliases(self):
assert self.s.get_aliases("ZAP70") == [u'ZAP-70', u'STD']
self.s.get_name("ZAP70")
self.s.get_chromosome("ZAP70")
self.s.get_previous_symbols("ZAP70")
self.s.get_withdrawn_symbols("ZAP70")
self.s.get_previous_names("ZAP70")
@attr('skip')
def test_xref(self):
assert self.s.get_xrefs("ZAP70")['UniProt']['xkey'] == 'P43403'
assert self.s.get_xrefs("ZAP70", "xml")['UniProt']['link'] == ['http://www.uniprot.org/uniprot/P43403.xml']
@attr('skip')
def test_lookfor(self):
self.s.lookfor("ZAP70")
@attr('skip')
def test_mapping(self):
value = "UniProt:P43403"
res = self.s.mapping(value)
res[0]['xlink:title'] == "ZAP70"
def test_hgnc():
h = HGNC()
h.get_info()
h.fetch("symbol", "ZNF3")
h.fetch("alias_name", "A-kinase anchor protein, 350kDa")
h.search("BRAF")
h.search("symbol", "ZNF*")
h.search("symbol", "ZNF?")
h.search("symbol", "ZNF*+AND+status:Approved")
h.search("symbol", "ZNF3+OR+ZNF12")
h.search("symbol", "ZNF*+NOT+status:Approved")
def __init__(self):
self.s = HGNC(verbose=False)
class test_hgnc():
def __init__(self):
self.s = HGNC(verbose=False)
def test_get_xml(self):
xml = self.s.get_xml("ZAP70")
xml = self.s.get_xml("ZAP70;INSR")
assert len(xml.findAll("gene")) == 2
self.s.get_xml("wrong")
def test_aliases(self):
assert self.s.get_aliases("ZAP70") == [u'ZAP-70', u'STD']
self.s.get_name("ZAP70")
self.s.get_chromosome("ZAP70")
self.s.get_previous_symbols("ZAP70")
self.s.get_withdrawn_symbols("ZAP70")
self.s.get_previous_names("ZAP70")
def test_xref(self):
assert self.s.get_xrefs("ZAP70")['UniProt']['xkey'] == 'P43403'
assert self.s.get_xrefs("ZAP70", "xml")['UniProt']['link'] == [
'http://www.uniprot.org/uniprot/P43403.xml'
]
def test_lookfor(self):
self.s.lookfor("ZAP70")
def test_mapping(self):
value = "UniProt:P43403"
res = self.s.mapping(value)
res['xlink:title'] == "ZAP70"