def parse(self):
# parse gene_info to represent the current valid entrez gene ids
eg_dict = dict([((EntrezGeneParser.resourceLocation, rec[1]), (self.encoding[rec[9]], uuid.uuid4())) \
for rec in csv.reader(gzip_to_text(self.gene_info), delimiter="\t", quotechar="\"") if rec[0] in ("9606", "10090", "10116")])
# parse gene_history to know which gene ids were discontinued
history_dict = dict([(rec[2], rec[1])
for rec in csv.reader(gzip_to_text(self.gene_history), delimiter="\t", quotechar="\"") if rec[0] in ("9606", "10090", "10116")])
history_dict = {k : self.__walk__(history_dict, k) for k in history_dict}
return (eg_dict, history_dict)
def parse(self):
# would like to have DictReader handle this, but need a way to
# deal with the special case of the first value beginning with
# a hashtag. i.e. #Format: <-- is NOT a column header.
column_headers = [
"tax_id",
"GeneID",
"status",
"RNA nucleotide accession.version",
"RNA nucleotide gi",
"protein accession.version",
"protein gi",
"genomic nucleotide accession.version",
"genomic nucleotide gi",
"start position on the genomic accession",
"end position on the genomic accession",
"orientation",
"assembly",
"mature peptide accession.version",
"mature peptide gi",
"Symbol",
]
g2a_reader = csv.DictReader(gzip_to_text(self._url), delimiter="\t", fieldnames=column_headers)
for row in g2a_reader:
if row["tax_id"] in ("9606", "10090", "10116"):
yield row
def parse(self):
column_headers = ['PubChem SID', 'Source', 'External ID', 'PubChem CID']
cid_reader = csv.DictReader(gzip_to_text(self.cid_file), delimiter='\t',
fieldnames=column_headers)
for row in cid_reader:
yield row
def parse(self):
reader = csv.DictReader(gzip_to_text(self._url),
delimiter='\t',
fieldnames=self.headers)
for row in reader:
if row['tax_id'] in ('9606', '10090', '10116'):
yield row
def parse(self):
reader = csv.DictReader(gzip_to_text(self._url),
delimiter='\t',
fieldnames=self.headers)
for row in reader:
if row['tax_id'] in ('9606', '10090', '10116'):
yield row
def parse(self):
# use iso-8859-1 as default encoding.
try:
reader = csv.DictReader(gzip_to_text(self._url), delimiter="\t")
except:
reader = csv.DictReader(open(self._url, "r", encoding="iso-8859-1"), delimiter="\t")
for row in reader:
yield row
def parse(self):
column_headers = ['pubchem_id', 'synonym']
pub_reader = csv.DictReader(gzip_to_text(self.pub_file), delimiter='\t',
fieldnames=column_headers)
with open(self.pub_file, 'r') as fp:
pub_reader = csv.DictReader(fp, delimiter='\t',
fieldnames=column_headers)
for row in pub_reader:
yield row
def parse(self):
# use iso-8859-1 as default encoding.
try:
reader = csv.DictReader(gzip_to_text(self._url), delimiter='\t')
except:
reader = csv.DictReader(open(self._url, "r",
encoding="iso-8859-1"),
delimiter='\t')
for row in reader:
yield row
def parse(self):
entrez_history_headers = ["tax_id", "GeneID", "Discontinued_GeneID",
"Discontinued_Symbol", "Discontinue_Date"]
# dictionary for base gene info
history_csvr = csv.DictReader(gzip_to_text(self.entrez_history),
delimiter='\t',
fieldnames=entrez_history_headers)
for row in history_csvr:
if row['tax_id'] in ("9606", "10090", "10116"):
yield row
def parse(self):
# columns for an Entrez gene info dataset.
entrez_info_headers = ['tax_id', 'GeneID', 'Symbol', 'LocusTag',
'Synonyms', 'dbXrefs', 'chromosome',
'map_location', 'description',
'type_of_gene',
'Symbol_from_nomenclature_authority',
'Full_name_from_nomenclature_authority',
'Nomenclature_status',
'Other_designations', 'Modification_date']
# dictionary for base gene info
info_csvr = csv.DictReader(gzip_to_text(self.entrez_info),
delimiter='\t',
fieldnames=entrez_info_headers)
for row in info_csvr:
if row['tax_id'] in ('9606', '10090', '10116'):
yield row
def parse(self):
# would like to have DictReader handle this, but need a way to
# deal with the special case of the first value beginning with
# a hashtag. i.e. #Format: <-- is NOT a column header.
column_headers = ['tax_id', 'GeneID', 'status',
'RNA nucleotide accession.version',
'RNA nucleotide gi', 'protein accession.version',
'protein gi', 'genomic nucleotide accession.version',
'genomic nucleotide gi',
'start position on the genomic accession',
'end position on the genomic accession',
'orientation', 'assembly',
'mature peptide accession.version',
'mature peptide gi', 'Symbol']
g2a_reader = csv.DictReader(gzip_to_text(self.gene2acc_file), delimiter='\t',
fieldnames=column_headers)
for row in g2a_reader:
yield row
def parse(self):
reader = csv.DictReader(gzip_to_text(self._url), delimiter="\t", fieldnames=self.headers)
for row in reader:
if row["tax_id"] in ("9606", "10090", "10116"):
yield row
