def test_contigset_consolidate(self):
#build set to merge
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
inFas = os.path.join(outdir, 'infile.fasta')
outFas1 = os.path.join(outdir, 'tempfile1.fasta')
outFas2 = os.path.join(outdir, 'tempfile2.fasta')
# copy fasta reference to hide fai and ensure FastaReader is used
backticks('cp {i} {o}'.format(
i=ReferenceSet(data.getXml(9)).toExternalFiles()[0],
o=inFas))
rs1 = ContigSet(inFas)
singletons = ['A.baumannii.1', 'A.odontolyticus.1']
double = 'B.cereus.1'
reader = rs1.resourceReaders()[0]
exp_double = rs1.get_contig(double)
exp_singles = [rs1.get_contig(name) for name in singletons]
# todo: modify the names first:
with FastaWriter(outFas1) as writer:
writer.writeRecord(exp_singles[0])
writer.writeRecord(exp_double.name + '_10_20', exp_double.sequence)
with FastaWriter(outFas2) as writer:
writer.writeRecord(exp_double.name + '_0_10',
exp_double.sequence + 'ATCGATCGATCG')
writer.writeRecord(exp_singles[1])
exp_double_seq = ''.join([exp_double.sequence,
'ATCGATCGATCG',
exp_double.sequence])
exp_single_seqs = [rec.sequence for rec in exp_singles]
acc_file = ContigSet(outFas1, outFas2)
acc_file.induceIndices()
log.debug(acc_file.toExternalFiles())
self.assertEqual(len(acc_file), 4)
self.assertEqual(len(list(acc_file)), 4)
acc_file.consolidate()
log.debug(acc_file.toExternalFiles())
# open acc and compare to exp
for name, seq in zip(singletons, exp_single_seqs):
self.assertEqual(acc_file.get_contig(name).sequence[:], seq)
self.assertEqual(acc_file.get_contig(double).sequence[:],
exp_double_seq)
self.assertEqual(len(acc_file._openReaders), 1)
self.assertEqual(len(acc_file.index), 3)
self.assertEqual(len(acc_file._indexMap), 3)
self.assertEqual(len(acc_file), 3)
self.assertEqual(len(list(acc_file)), 3)
# test merge:
acc1 = ContigSet(outFas1)
acc2 = ContigSet(outFas2)
acc3 = acc1 + acc2
def test_contigset_consolidate(self):
#build set to merge
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
inFas = os.path.join(outdir, 'infile.fasta')
outFas1 = os.path.join(outdir, 'tempfile1.fasta')
outFas2 = os.path.join(outdir, 'tempfile2.fasta')
# copy fasta reference to hide fai and ensure FastaReader is used
backticks('cp {i} {o}'.format(i=ReferenceSet(
data.getXml(9)).toExternalFiles()[0],
o=inFas))
rs1 = ContigSet(inFas)
singletons = ['A.baumannii.1', 'A.odontolyticus.1']
double = 'B.cereus.1'
reader = rs1.resourceReaders()[0]
exp_double = rs1.get_contig(double)
exp_singles = [rs1.get_contig(name) for name in singletons]
# todo: modify the names first:
with FastaWriter(outFas1) as writer:
writer.writeRecord(exp_singles[0])
writer.writeRecord(exp_double.name + '_10_20', exp_double.sequence)
with FastaWriter(outFas2) as writer:
writer.writeRecord(exp_double.name + '_0_10',
exp_double.sequence + 'ATCGATCGATCG')
writer.writeRecord(exp_singles[1])
exp_double_seq = ''.join(
[exp_double.sequence, 'ATCGATCGATCG', exp_double.sequence])
exp_single_seqs = [rec.sequence for rec in exp_singles]
acc_file = ContigSet(outFas1, outFas2)
acc_file.induceIndices()
log.debug(acc_file.toExternalFiles())
self.assertEqual(len(acc_file), 4)
self.assertEqual(len(list(acc_file)), 4)
acc_file.consolidate()
log.debug(acc_file.toExternalFiles())
# open acc and compare to exp
for name, seq in zip(singletons, exp_single_seqs):
self.assertEqual(acc_file.get_contig(name).sequence[:], seq)
self.assertEqual(
acc_file.get_contig(double).sequence[:], exp_double_seq)
self.assertEqual(len(acc_file._openReaders), 1)
self.assertEqual(len(acc_file.index), 3)
self.assertEqual(len(acc_file._indexMap), 3)
self.assertEqual(len(acc_file), 3)
self.assertEqual(len(list(acc_file)), 3)
# test merge:
acc1 = ContigSet(outFas1)
acc2 = ContigSet(outFas2)
acc3 = acc1 + acc2
def test_contigset_write(self):
fasta = upstreamData.getLambdaFasta()
ds = ContigSet(fasta)
assert isinstance(ds.resourceReaders()[0], IndexedFastaReader)
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
outfn = os.path.join(outdir, 'test.fasta')
w = FastaWriter(outfn)
for rec in ds:
w.writeRecord(rec)
w.close()
fas = FastaReader(outfn)
for rec in fas:
# make sure a __repr__ didn't slip through:
assert not rec.sequence.startswith('<')
def test_contigset_write(self):
fasta = upstreamData.getLambdaFasta()
ds = ContigSet(fasta)
self.assertTrue(isinstance(ds.resourceReaders()[0],
IndexedFastaReader))
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
outfn = os.path.join(outdir, 'test.fasta')
w = FastaWriter(outfn)
for rec in ds:
w.writeRecord(rec)
w.close()
fas = FastaReader(outfn)
for rec in fas:
# make sure a __repr__ didn't slip through:
self.assertFalse(rec.sequence.startswith('<'))
def test_len_fastq(self):
fn = ('/pbi/dept/secondary/siv/testdata/SA3-RS/'
'lambda/2590980/0008/Analysis_Results/'
'm141115_075238_ethan_c100699872550000001'
'823139203261572_s1_p0.1.subreads.fastq')
fq_out = tempfile.NamedTemporaryFile(suffix=".fastq").name
with open(fq_out, 'w') as fqh:
with open(fn, 'r') as fih:
for line in itertools.islice(fih, 24):
fqh.write(line)
cset = ContigSet(fq_out)
assert not cset.isIndexed
assert isinstance(cset.resourceReaders()[0], FastqReader)
assert sum(1 for _ in cset) == sum(1 for _ in FastqReader(fq_out))
assert sum(1 for _ in cset) == 6
def test_len_fastq(self):
fn = ('/pbi/dept/secondary/siv/testdata/SA3-RS/'
'lambda/2590980/0008/Analysis_Results/'
'm141115_075238_ethan_c100699872550000001'
'823139203261572_s1_p0.1.subreads.fastq')
fq_out = tempfile.NamedTemporaryFile(suffix=".fastq").name
with open(fq_out, 'w') as fqh:
with open(fn, 'r') as fih:
for line in itertools.islice(fih, 24):
fqh.write(line)
cset = ContigSet(fq_out)
self.assertFalse(cset.isIndexed)
self.assertTrue(isinstance(cset.resourceReaders()[0], FastqReader))
self.assertEqual(sum(1 for _ in cset),
sum(1 for _ in FastqReader(fq_out)))
self.assertEqual(sum(1 for _ in cset), 6)
