def test_parse_gg_summary_flat(self):
"""Parse the gg summary files from flat_files.py"""
exp = [GreengenesRecord({'prokMSA_id':'1', 'ncbi_acc_w_ver':'xyzf'}),
GreengenesRecord({'prokMSA_id':'25', 'ncbi_acc_w_ver':'abcd',
'country':'australia'}),
GreengenesRecord({'prokMSA_id':'50', 'ncbi_acc_w_ver':'223xx'})]
obs = list(parse_gg_summary_flat(StringIO(gg_summary)))
self.assertEqual(obs,exp)
def test_write_gg_record(self):
"""Writes a gg record"""
exp = sorted([
'BEGIN', 'prokmsa_id=123', 'gg_id=', 'hugenholtz_tax_string=',
'ncbi_acc_w_ver=xyz', 'ncbi_gi=333', 'n_pos_aligned=',
'n_pos_unaligned=', 'db_name=', 'gold_id=', 'decision=',
'prokmsaname=', 'isolation_source=', 'clone=foo', 'organism=',
'strain=', 'specific_host=', 'authors=', 'title=', 'pubmed=123',
'journal=', 'study_id=', 'submit_date=', 'country=',
'ncbi_tax_string=', 'silva_tax_string=', 'rdp_tax_string=',
'greengenes_tax_string=', 'non_acgt_percent=0.5',
'perc_ident_to_invariant_core=', 'small_gap_intrusions=',
'bellerophon=', 'bel3_div_ratio=', 'chim_slyr_a=', 'chim_slyr_b=',
'chim_slyr_a_tax=', 'chim_slyr_b_tax=', 'aligned_seq=',
'unaligned_seq=', 'END', ''
])
ggrec = GreengenesRecord({
'prokmsa_id': 123,
'ncbi_acc_w_ver': 'xyz',
'ncbi_gi': '333',
'pubmed': 123,
'clone': 'foo',
'non_acgt_percent': '0.5'
})
f = StringIO()
write_gg_record(f, ggrec)
f.seek(0)
obs = sorted(f.read().splitlines())
self.assertEqual(obs, exp)
def get_genbank_summary(r):
"""Get the gb summary data"""
rec = GreengenesRecord()
for f, m in parse_funs:
rec[f] = m(r)
return rec
def parse_gg_summary_flat(open_file):
"""Parse a flat greengenes summary file from flat_files"""
header_line = open_file.readline()
if not header_line.startswith('#'):
raise ValueError, "Missing the header!"
header = header_line[1:].strip().split('\t')
print "WARNING: NOT SETTING TYPES CURRENTLY"
for line in open_file:
record = GreengenesRecord()
for key, value in zip(header, line.strip().split('\t')):
record[key] = value
#record.setTypes()
yield record
def test_get_genbank_summary(self):
"""Get the summary!!"""
exp = GreengenesRecord({'ncbi_acc_w_ver':'AGIY01000001.1',
'ncbi_gi':'354825968',
'gold_id':'Gi05850',
'decision':'named_isolate',
'isolation_source':'anaerobic digested sludge',
'organism':'Methanolinea tarda NOBI-1',
'strain':'NOBI-1',
'prokmsaname':'Methanolinea tarda NOBI-1',
'specific_host':'Methanolinea tarda NOBI-1 ctg73, whole genome shotgun sequence.',
'authors':'Lucas,S., Han,J., Lapidus,A., Cheng,J.-F., Goodwin,L., Pitluck,S., Peters,L., Land,M.L., Hauser,L., Imachi,H., Sekiguchi,Y., Kamagata,Y., Cadillo-Quiroz,H., Zinder,S., Liu,W.T., Tamaki,H. and Woyke,T.J.',
'title':'The draft genome of Methanolinea tarda NOBI-1',
'submit_date':'31-OCT-2011',
'country':'Japan: Nagaoka',
#'NCBI_tax_id':'882090',
'ncbi_tax_string':'Archaea; Euryarchaeota; Methanomicrobia; Methanomicrobiales; Methanoregulaceae; Methanolinea'})
obs = get_genbank_summary(self.gb1)
self.assertEqual(obs,exp)
def setUp(self):
self.ggrecord = GreengenesRecord({'prokmsa_id':123})
