def test_get_from_taxonomy_db(self):
"""EUtils access from taxonomy database should work"""
#note: this is more fragile than the nucleotide databases
g = EUtils(db='taxonomy', rettype='Brief', retmode='text')
ids = '9606[taxid] OR 28901[taxid]'
result = sorted(g[ids].read().splitlines())
self.assertEqual(result, ['H**o sapiens', 'Salmonella enterica'])
def test_get_list(self):
"""EUtils access of a list should work"""
g = EUtils(db='protein', rettype='gp')
result = g['NP_003320', 'NP_003321', 'NP_003322'].read()
lines = result.splitlines()
is_locus = lambda x: x.startswith('LOCUS')
loci = filter(is_locus, lines)
self.assertEqual(len(loci), 3)
def test_get_slice(self):
"""EUtils access of a slice should work"""
g = EUtils(db='protein', rettype='gp', retmax=1)
result = g['NP_003320':'NP_003322'].read()
lines = result.splitlines()
is_locus = lambda x: x.startswith('LOCUS')
loci = filter(is_locus, lines)
self.assertEqual(len(loci), 3)
#EUtils access of a slice should work, while limiting
#the esearch term length
g = EUtils(db='protein', rettype='gp', retmax=1, url_limit=2)
result = g['NP_003320':'NP_003322'].read()
lines = result.splitlines()
is_locus = lambda x: x.startswith('LOCUS')
loci = filter(is_locus, lines)
self.assertEqual(len(loci), 3)
def test_query_max_recs_gt_retmax(self):
"""EUtils should stop query at max_recs when max_recs > retmax"""
g = EUtils(db='protein',
rettype='gi',
max_recs=5,
DEBUG=False,
retmax=3)
result = g['h**o[organism] AND myh7'].read().splitlines()
self.assertEqual(len(result), 5)
def test_get_from_taxonomy_db(self):
"""EUtils access from taxonomy database should work"""
#note: this is more fragile than the nucleotide databases
g = EUtils(db='taxonomy', rettype='xml', retmode='xml')
ids = '9606[taxid] OR 28901[taxid]'
fh = StringIO()
fh.write(g[ids].read())
fh.seek(0)
data = parse_taxonomy_using_elementtree_xml_parse(fh)
result = sorted([item['ScientificName'] for item in data])
self.assertEqual(result, ['H**o sapiens', 'Salmonella enterica'])
def test_parse_taxonomy_using_elementtree_xml_parse(self):
"""parse_taxonomy_using_elementtree_xml_parse should return taxonomy associated information"""
g = EUtils(db='taxonomy', rettype='xml', retmode='xml')
ids = '28901[taxid]'
fh = StringIO()
fh.write(g[ids].read())
fh.seek(0)
data = parse_taxonomy_using_elementtree_xml_parse(fh)[0]
obs = (data['Lineage'],data['TaxId'],data['ScientificName'],\
data['Rank'])
exp = ('cellular organisms; Bacteria; Proteobacteria; Gammaproteobacteria; Enterobacteriales; Enterobacteriaceae; Salmonella',\
'28901','Salmonella enterica','species')
self.assertEqual(obs, exp)
def fetch_seq(gid,gb_fn):
e = EUtils(db="nucleotide", rettype="gb")
outfile = open(gb_fn,'w')
outfile.write(e[gid].read())
outfile.close()
def test_query_retmax(self):
"""EUtils should join results taken retmax at a time"""
g = EUtils(db='protein', rettype='gi', retmax=3, DEBUG=False)
result = g['h**o[organism] AND myh7'].read().splitlines()
assert len(result) > 1
assert '83304912' in result #gi of human myh7
def test_query(self):
"""EUtils access via a query should work"""
g = EUtils(db='protein', rettype='gi', retmax=100)
result = g['h**o[organism] AND erf1[ti]'].read().splitlines()
assert '5499721' in result #gi of human eRF1
def test_simple_get(self):
"""EUtils simple access of an item should work"""
g = EUtils(db='protein', rettype='gp')
result = g['NP_003320'].read()
assert result.startswith('LOCUS')
assert 'NP_003320' in result
#!/usr/bin/env python
# taken from http://pycogent.sourceforge.net/
from cogent.db.ncbi import EUtils
db = EUtils(db="protein", rettype="gp")
query = '"VWf"[gene] AND h**o[orgn]'
records = db[query].readlines()
import re
from cogent.parse.genbank import RichGenbankParser
parser = RichGenbankParser(records)
acc2seq = {}
rows = []
for accession, seq in parser:
if len(seq) < 2800:
continue
species = seq.Info.species.split()
seq_name = "%s.%s" % (species[0][0] + species[1][:3], accession)
acc2seq[seq_name] = seq
print acc2seq
from cogent import LoadSeqs
seqs = LoadSeqs(data=acc2seq, aligned=False)
sh = seqs.NamedSeqs['Hsap.P04275']
print sh.toFasta()
print sh.Info.taxonomy
