def test_topology_genbank(self):
"""Check GenBank LOCUS line parsing."""
# This is a bit low level, but can test pasing the LOCUS line only
tests = [
("LOCUS U00096", None, None, None),
# This example is actually fungal, accession U49845 from Saccharomyces cerevisiae:
("LOCUS SCU49845 5028 bp DNA PLN 21-JUN-1999",
None, "DNA", "PLN"),
("LOCUS AB070938 6497 bp DNA linear BCT 11-OCT-2001",
"linear", "DNA", "BCT"),
("LOCUS NC_005816 9609 bp DNA circular BCT 21-JUL-2008",
"circular", "DNA", "BCT"),
("LOCUS SCX3_BUTOC 64 aa linear INV 16-OCT-2001",
"linear", None, "INV"),
]
for (line, topo, mol_type, div) in tests:
scanner = Scanner.GenBankScanner()
consumer = GenBank._FeatureConsumer(1, GenBank.FeatureValueCleaner)
scanner._feed_first_line(consumer, line)
t = consumer.data.annotations.get('topology', None)
self.assertEqual(
t, topo, "Wrong topology %r not %r from %r" % (t, topo, line))
mt = consumer.data.annotations.get('molecule_type', None)
self.assertEqual(
mt, mol_type,
"Wrong molecule_type %r not %r from %r" % (mt, mol_type, line))
d = consumer.data.annotations.get('data_file_division', None)
self.assertEqual(
d, div, "Wrong division %r not %r from %r" % (d, div, line))
def test_topology_genbank(self):
"""Check GenBank LOCUS line parsing."""
# This is a bit low level, but can test pasing the LOCUS line only
tests = [
("LOCUS U00096",
None, None, None, None),
# This example is actually fungal, accession U49845 from Saccharomyces cerevisiae:
("LOCUS SCU49845 5028 bp DNA PLN 21-JUN-1999",
None, "DNA", "PLN", None),
("LOCUS AB070938 6497 bp DNA linear BCT 11-OCT-2001",
"linear", "DNA", "BCT", None),
("LOCUS NC_005816 9609 bp DNA circular BCT 21-JUL-2008",
"circular", "DNA", "BCT", None),
("LOCUS SCX3_BUTOC 64 aa linear INV 16-OCT-2001",
"linear", None, "INV", None),
("LOCUS pEH010 5743 bp DNA circular",
"circular", "DNA", None, [BiopythonParserWarning]),
# This is a test of the format > 80 chars long
("LOCUS AZZZAA02123456789 1000000000 bp DNA linear PRI 15-OCT-2018",
"linear", "DNA", "PRI", None)
]
for (line, topo, mol_type, div, warning_list) in tests:
with warnings.catch_warnings(record=True) as caught:
warnings.simplefilter("always")
scanner = Scanner.GenBankScanner()
consumer = GenBank._FeatureConsumer(1, GenBank.FeatureValueCleaner)
scanner._feed_first_line(consumer, line)
t = consumer.data.annotations.get('topology', None)
self.assertEqual(t, topo,
"Wrong topology %r not %r from %r" % (t, topo, line))
mt = consumer.data.annotations.get('molecule_type', None)
self.assertEqual(mt, mol_type,
"Wrong molecule_type %r not %r from %r" %
(mt, mol_type, line))
d = consumer.data.annotations.get('data_file_division', None)
self.assertEqual(d, div,
"Wrong division %r not %r from %r" % (d, div, line))
if warning_list is None:
self.assertEqual(len(caught), 0)
else:
self.assertEqual(len(caught), len(warning_list))
for i, warning_class in enumerate(warning_list):
self.assertEqual(caught[i].category, warning_class)
class GenBankScannerTests(unittest.TestCase):
"""GenBank Scanner tests, test parsing gbk and embl files."""
gb_s = Scanner.GenBankScanner()
def gb_to_l_cds_f(self, filename, tags2id=None):
"""Gb file to Seq list parse CDS features."""
with open(filename) as handle:
if tags2id:
l_cds_f = list(self.gb_s.parse_cds_features(handle, tags2id=tags2id))
else:
l_cds_f = list(self.gb_s.parse_cds_features(handle))
return l_cds_f
def gb_to_l_r(self, filename, do_features=False):
"""Gb file to Seq list parse records."""
with open(filename) as handle:
l_gb_r = list(self.gb_s.parse_records(handle, do_features=do_features))
return l_gb_r
def test_genbank_cds_interaction(self):
"""Test CDS interaction, parse CDS features on gb(k) files."""
# Test parse CDS features on NC_000932.gb
l_cds_f = self.gb_to_l_cds_f("GenBank/NC_000932.gb")
# number of records, should be 85
self.assertEqual(len(l_cds_f), 85)
# Seq ID
self.assertEqual(l_cds_f[0].id, 'NP_051037.1')
self.assertEqual(l_cds_f[84].id, 'NP_051123.1')
# Test parse CDS features on NC_005816.gb, Tag to ID
l_cds_f = self.gb_to_l_cds_f("GenBank/NC_005816.gb",
tags2id=('gene', 'locus_tag', 'product'))
# number of records, should be 10
self.assertEqual(len(l_cds_f), 10)
# Seq ID
self.assertEqual(l_cds_f[0].id, '<unknown id>')
self.assertEqual(l_cds_f[0].name, 'YP_pPCP01')
# Test parse CDS features on NC_000932.gb and NC_005816.gb combined
l_cds_f1 = self.gb_to_l_cds_f("GenBank/NC_000932.gb",
tags2id=('gene', 'locus_tag', 'product'))
l_cds_f2 = self.gb_to_l_cds_f("GenBank/NC_005816.gb",
tags2id=('gene', 'locus_tag', 'product'))
l_cds_combined = l_cds_f1 + l_cds_f2
# number of records combined, should be 95
self.assertEqual(len(l_cds_combined), 95)
# Seq ID
self.assertEqual(l_cds_combined[0].id, 'rps12')
self.assertEqual(l_cds_combined[0].description, 'ribosomal protein S12')
self.assertEqual(l_cds_combined[94].id, '<unknown id>')
self.assertEqual(l_cds_combined[94].description, 'hypothetical protein')
def test_genbank_interaction(self):
"""Test GenBank records interaction on gbk files."""
# Test parse records, on NC_005816, do_features False
l_r = self.gb_to_l_r("GenBank/NC_005816.gb", do_features=False)
# number of records, should be 1
self.assertEqual(len(l_r), 1)
self.assertEqual(l_r[0].id, 'NC_005816.1')
self.assertEqual(l_r[0].name, 'NC_005816')
self.assertEqual(l_r[0].description, 'Yersinia pestis biovar '
'Microtus str. 91001 plasmid '
'pPCP1, complete sequence')
self.assertEqual(len(l_r[0].features), 0)
# Test parse records on NC_005816, do_features True
l_r = self.gb_to_l_r("GenBank/NC_005816.gb", do_features=True)
# number of records, should be 1
self.assertEqual(len(l_r), 1)
self.assertEqual(l_r[0].id, 'NC_005816.1')
self.assertEqual(l_r[0].name, 'NC_005816')
self.assertEqual(l_r[0].description, 'Yersinia pestis biovar '
'Microtus str. 91001 plasmid '
'pPCP1, complete sequence')
self.assertEqual(len(l_r[0].features), 41)
# Test parse records on "GenBank/NC_000932.gb", do_features False
l_r = self.gb_to_l_r("GenBank/NC_000932.gb", do_features=False)
# number of records, should be 1
self.assertEqual(len(l_r), 1)
self.assertEqual(l_r[0].id, 'NC_000932.1')
self.assertEqual(l_r[0].name, 'NC_000932')
self.assertEqual(l_r[0].description, 'Arabidopsis thaliana chloroplast, '
'complete genome')
self.assertEqual(len(l_r[0].features), 0)
# Test parse records on NC_000932, do_features True
l_r = self.gb_to_l_r("GenBank/NC_000932.gb", do_features=True)
# number of records, should be 1
self.assertEqual(len(l_r), 1)
self.assertEqual(l_r[0].id, 'NC_000932.1')
self.assertEqual(l_r[0].name, 'NC_000932')
self.assertEqual(l_r[0].description, 'Arabidopsis thaliana chloroplast, '
'complete genome')
self.assertEqual(len(l_r[0].features), 259)
def test_embl_cds_interaction(self):
"""Test EMBL CDS interaction, parse CDS features on embl files."""
embl_s = Scanner.EmblScanner()
# Test parse CDS features on embl_file
with open("EMBL/AE017046.embl") as handle_embl7046:
l_cds_f = list(embl_s.parse_cds_features(handle_embl7046))
# number of records, should be 10
self.assertEqual(len(l_cds_f), 10)
# Seq ID
self.assertEqual(l_cds_f[0].id, 'AAS58758.1')
self.assertEqual(l_cds_f[0].description, 'putative transposase')
def test_embl_record_interaction(self):
"""Test EMBL Record interaction on embl files."""
embl_s = Scanner.EmblScanner()
# Test parse records on embl_file
with open("EMBL/AE017046.embl") as handle_embl7046:
l_embl_r = list(embl_s.parse_records(handle_embl7046, do_features=True))
# number of records, should be 1
self.assertEqual(len(l_embl_r), 1)
self.assertEqual(l_embl_r[0].id, 'AE017046.1')
self.assertEqual(l_embl_r[0].description, 'Yersinia pestis biovar Microtus '
'str. 91001 plasmid pPCP1, complete '
'sequence.')
self.assertEqual(len(l_embl_r[0].features), 29)