def _map_and_cluster_reads(self):
if self.verbose:
print('{:_^79}'.format(' Mapping reads to clustered genes '),
flush=True)
minimap_prefix = 'minimap'
self._minimap_reads_to_all_ref_seqs(self.clusters_tsv,
self.all_ref_seqs_fasta,
self.reads_1,
self.reads_2,
minimap_prefix,
verbose=self.verbose)
if self.verbose:
print('Finished mapping\n')
print('{:_^79}'.format(' Generating clusters '), flush=True)
self.cluster_to_rep, self.cluster_read_counts, self.cluster_base_counts, self.insert_hist, self.proper_pairs = self._load_minimap_files(
minimap_prefix, self.insert_hist_bin)
self.cluster_to_dir = {
x: os.path.join(self.tmp_dir, x)
for x in self.cluster_to_rep
}
reads_file_for_read_store = minimap_prefix + '.reads'
if len(self.cluster_read_counts):
if self.verbose:
filehandle = sys.stdout
else:
filehandle = None
self.read_store = read_store.ReadStore(reads_file_for_read_store,
os.path.join(
self.outdir,
'read_store'),
log_fh=filehandle)
os.unlink(reads_file_for_read_store)
if self.clean:
for suffix in [
'cluster2representative', 'clusterCounts',
'insertHistogram', 'properPairs'
]:
filename = minimap_prefix + '.' + suffix
try:
os.unlink(filename)
except:
pass
if self.verbose:
print('Found', self.proper_pairs, 'proper read pairs from minimap')
print('Total clusters to perform local assemblies:',
len(self.cluster_to_dir),
flush=True)
def test_get_reads_fq_interleave(self):
'''Test get_reads fastq interleaved'''
infile = os.path.join(data_dir, 'read_store_test_get_reads.in')
expected = os.path.join(data_dir,
'read_store_test_get_reads.expected.reads.fq')
outprefix = 'tmp.read_store_test_get_reads'
reads = outprefix + '.reads_1.fq'
rstore = read_store.ReadStore(infile, outprefix)
got_reads, got_bases = rstore.get_reads('cluster2', reads)
self.assertEqual(6, got_reads)
self.assertEqual(24, got_bases)
self.assertTrue(filecmp.cmp(expected, reads))
os.unlink(outprefix + '.gz')
os.unlink(outprefix + '.gz.tbi')
os.unlink(reads)
def test_clean(self):
'''Test clean'''
infile = os.path.join(data_dir, 'read_store_test_clean.in')
outprefix = 'tmp.read_store_test_clean'
self.assertFalse(os.path.exists(outprefix))
self.assertFalse(os.path.exists(outprefix + '.gz'))
self.assertFalse(os.path.exists(outprefix + '.gz.tbi'))
rstore = read_store.ReadStore(infile, outprefix)
self.assertFalse(os.path.exists(outprefix))
self.assertTrue(os.path.exists(outprefix + '.gz'))
self.assertTrue(os.path.exists(outprefix + '.gz.tbi'))
rstore.clean()
self.assertFalse(os.path.exists(outprefix))
self.assertFalse(os.path.exists(outprefix + '.gz'))
self.assertFalse(os.path.exists(outprefix + '.gz.tbi'))
def _test_run(self):
'''test run'''
rstore_infile = os.path.join(data_dir, 'read_filter_test_run.in.read_store')
ref_fasta = os.path.join(data_dir, 'read_filter_test_run.in.ref.fa')
expected_reads1 = os.path.join(data_dir, 'read_filter_test_run.expected.reads_1.fq')
expected_reads2 = os.path.join(data_dir, 'read_filter_test_run.expected.reads_2.fq')
tmp_rstore_prefix = 'tmp.filter_test_run.read_store'
tmp_reads1 = 'tmp.filter_test_run.reads_1.fq'
tmp_reads2 = 'tmp.filter_test_run.reads_2.fq'
rstore = read_store.ReadStore(rstore_infile, tmp_rstore_prefix)
rfilter = read_filter.ReadFilter(rstore, ref_fasta, '1', sys.stdout)
got_reads, got_bases = rfilter.run(tmp_reads1, tmp_reads2)
self.assertEqual(12, got_reads)
self.assertEqual(912, got_bases)
self.assertTrue(filecmp.cmp(expected_reads1, tmp_reads1, shallow=False))
self.assertTrue(filecmp.cmp(expected_reads2, tmp_reads2, shallow=False))
os.unlink(tmp_reads1)
os.unlink(tmp_reads2)
rstore.clean()
def test_get_reads_fq_pair(self):
'''Test get_reads fastq pair'''
infile = os.path.join(data_dir, 'read_store_test_get_reads.in')
expected1 = os.path.join(
data_dir, 'read_store_test_get_reads.expected.reads_1.fq')
expected2 = os.path.join(
data_dir, 'read_store_test_get_reads.expected.reads_2.fq')
outprefix = 'tmp.read_store_test_get_reads'
reads1 = outprefix + '.reads_1.fq'
reads2 = outprefix + '.reads_2.fq'
rstore = read_store.ReadStore(infile, outprefix)
got_reads, got_bases = rstore.get_reads('cluster2',
reads1,
out2=reads2)
self.assertEqual(6, got_reads)
self.assertEqual(24, got_bases)
self.assertTrue(filecmp.cmp(expected1, reads1))
self.assertTrue(filecmp.cmp(expected2, reads2))
os.unlink(outprefix + '.gz')
os.unlink(outprefix + '.gz.tbi')
os.unlink(reads1)
os.unlink(reads2)
def test_get_reads_subset(self):
'''Test get_reads subset'''
infile = os.path.join(data_dir, 'read_store_test_get_reads.in')
expected1 = os.path.join(
data_dir, 'read_store_test_get_reads.expected.reads_subset.1.fq')
expected2 = os.path.join(
data_dir, 'read_store_test_get_reads.expected.reads_subset.2.fq')
wanted_ids = {1, 11}
outprefix = 'tmp.read_store_test_get_reads'
reads1 = outprefix + '.reads_1.fq'
reads2 = outprefix + '.reads_2.fq'
rstore = read_store.ReadStore(infile, outprefix)
got_reads, got_bases = rstore.get_reads('cluster2',
reads1,
out2=reads2,
wanted_ids=wanted_ids)
self.assertEqual(4, got_reads)
self.assertEqual(16, got_bases)
self.assertTrue(filecmp.cmp(expected1, reads1))
self.assertTrue(filecmp.cmp(expected2, reads2))
os.unlink(outprefix + '.gz')
os.unlink(outprefix + '.gz.tbi')
os.unlink(reads1)
os.unlink(reads2)
