def runTest(self):
parser = naivetrack.TrackParser(chromosome_list=self.chromosome_list)
parser.register_handle(self.file)
parser.set_maximum_chromosome_size(500000)
sample_filter = naivetrack.SampleFilter()
sample_filter.add_frequency_filter("__qual__", 0.1)
provider = naivetrack.apply_filters(parser, filters=[sample_filter])
entry = provider.next()
self.assertEqual(entry.position.coordinate, 1)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(entry.position.get_chromosome(), 'chr1')
self.assertEqual(len(parser.buffer), 1)
self.assertEqual(len(entry.alleles), 2)
self.assertEqual(entry.alleles[0].sequence, 'G')
self.assertEqual(entry.alleles[0].depth, 1)
self.assertEqual(entry.alleles[0].quality, 40)
self.assertEqual(entry.alleles[1].sequence, 'T')
self.assertEqual(entry.alleles[1].depth, 1)
self.assertEqual(entry.alleles[1].quality, 55)
self.assertEqual(entry.statistics.number_of_alleles, 2)
self.assertEqual(entry.statistics.depth, 2)
self.assertEqual(entry.statistics.quality, 95)
def runTest(self):
parser = naivetrack.TrackParser(chromosome_list=self.chromosome_list)
parser.register_handle(self.file)
parser.set_maximum_chromosome_size(500000)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 1)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(entry.position.get_chromosome(), 'chr1')
self.assertEqual(len(parser.buffer), 1)
self.assertEqual(len(entry.alleles), 1)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20000)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(entry.position.get_chromosome(), 'chr1')
self.assertEqual(len(parser.buffer), 2)
self.assertEqual(len(entry.alleles), 1)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20001)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(entry.position.get_chromosome(), 'chr1')
self.assertEqual(len(parser.buffer), 2)
self.assertEqual(len(entry.alleles), 1)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20001)
self.assertEqual(entry.position.sequence, 'G')
self.assertEqual(entry.position.get_chromosome(), 'chr2')
self.assertEqual(len(parser.buffer), 1)
self.assertEqual(len(entry.alleles), 1)
# end of file
self.assertRaises(StopIteration, parser.next)
def runTest(self):
parser = naivetrack.TrackParser(chromosome_list=self.chromosome_list)
parser.register_handle(self.file_a)
parser.register_handle(self.file_b)
parser.set_maximum_chromosome_size(500000)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 1)
self.assertEqual(entry.statistics.number_of_alleles, 1)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(len(parser.buffer), 2)
# second position
entry = parser.next()
self.assertEqual(entry.position.coordinate, 3)
self.assertEqual(entry.statistics.number_of_alleles, 1)
self.assertEqual(entry.position.sequence, 'T')
# third position merged 2 entries
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20000)
self.assertEqual(entry.statistics.number_of_alleles, 2)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(len(parser.buffer), 2)
# fourth position
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20001)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(len(parser.buffer), 2)
# fifth position
entry = parser.next()
self.assertEqual(entry.position.coordinate, 200000)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(len(parser.buffer), 1)
# sixt position: next chromosome test
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20001)
self.assertEqual(entry.position.sequence, 'G')
self.assertEqual(entry.position.get_chromosome(), 'chr2')
self.assertEqual(len(parser.buffer), 1)
# sixt position: next chromosome test
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20001)
self.assertEqual(entry.position.sequence, 'G')
self.assertEqual(entry.position.get_chromosome(), 'chr3')
self.assertEqual(len(parser.buffer), 1)
# end of file
self.assertRaises(StopIteration, parser.next)
def runTest(self):
summarize = naivetrack.SummarizeEntries()
summarize_with_strand = naivetrack.SummarizeEntries()
summarize_with_strand.add_filter(2, "forward", "__quality_f__",
"__depth_f__")
parser = naivetrack.TrackParser(chromosome_list=self.chromosome_list)
parser.register_handle(self.file)
parser.set_maximum_chromosome_size(500000)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 1)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(entry.position.get_chromosome(), 'chr1')
self.assertEqual(len(entry.alleles), 4)
dsum = summarize(entry)
self.assertEqual(dsum['T']['X']['__quality__'], 20)
self.assertEqual(dsum['T']['X']['__depth__'], 10)
self.assertEqual(dsum['G']['X']['__quality__'], 40)
self.assertEqual(dsum['G']['X']['__depth__'], 4)
self.assertEqual(dsum['G']['Y']['__quality__'], 200)
self.assertEqual(dsum['G']['Y']['__depth__'], 20)
strandsum = summarize_with_strand(entry)
self.assertEqual(strandsum['T']['X']['__quality__'], 20)
self.assertEqual(strandsum['T']['X']['__quality_f__'], 20)
self.assertEqual(strandsum['T']['X']['__depth__'], 10)
self.assertEqual(strandsum['T']['X']['__depth_f__'], 10)
self.assertEqual(strandsum['G']['X']['__quality__'], 40)
self.assertEqual(strandsum['G']['X']['__quality_f__'], 20)
self.assertEqual(strandsum['G']['X']['__depth__'], 4)
self.assertEqual(strandsum['G']['X']['__depth_f__'], 1)
self.assertEqual(strandsum['G']['Y']['__quality__'], 200)
self.assertEqual(strandsum['G']['Y']['__quality_f__'], 200)
self.assertEqual(strandsum['G']['Y']['__depth__'], 20)
self.assertEqual(strandsum['G']['Y']['__depth_f__'], 20)
entry = parser.next()
self.assertEqual(entry.position.coordinate, 20000)
self.assertEqual(entry.position.sequence, 'T')
self.assertEqual(entry.position.get_chromosome(), 'chr1')
self.assertEqual(len(entry.alleles), 1)
# end of file
self.assertRaises(StopIteration, parser.next)
def main():
"""Perform the main program loop."""
# prepare data parsing
chromosome_list = []
provider = naivetrack.TrackParser(chromosome_list=chromosome_list)
provider.set_maximum_chromosome_size(3000000000)
# prepare the filter
fltr = naivetrack.SampleFilter()
fout = sys.stdout
# parse the commandline options
shortopt = "i:o:h"
longopt = [
"input=", "output=", "help", "minimum-quality=",
"maximum-quality=", "minimum-quality-frequency=",
"maximum-quality-frequency=", "minimum-depth=", "maximum-depth=",
"remove-N", "no-reference", "minimum-depth-frequency=",
"maximum-depth-frequency="
]
try:
opts, _ = getopt.getopt(sys.argv[1:], shortopt, longopt)
for opt, ans in opts:
if opt in ("-i", "--input"):
if ans != "-":
provider.register_handle(
open(os.path.abspath(ans), 'r'))
else:
provider.register_handle(sys.stdin)
elif opt in ("-o", "--output"):
fout = open(ans, 'w')
elif opt == "--minimum-quality":
fltr.add_value_filter('__qual__', lowerbound=int(ans))
elif opt == "--maximum-quality":
fltr.add_value_filter('__qual__', upperbound=int(ans))
elif opt == "--minimum-quality-frequency":
fltr.add_frequency_filter('__qual__',
lowerbound=float(ans))
elif opt == "--maximum-quality-frequency":
fltr.add_frequency_filter('__qual__',
upperbound=float(ans))
elif opt == "--minimum-depth":
fltr.add_value_filter('__depth__', lowerbound=int(ans))
elif opt == "--maximum-depth":
fltr.add_value_filter('__depth__', upperbound=int(ans))
elif opt == "--minimum-depth-frequency":
fltr.add_frequency_filter('__depth__',
lowerbound=float(ans))
elif opt == "--maximum-depth-frequency":
fltr.add_frequency_filter('__depth__',
upperbound=float(ans))
elif opt == "--remove-N":
fltr.remove_N_alleles = True
elif opt == "--no-reference":
fltr.remove_all_reference = True
elif opt in ('-h', "--help"):
usage("Help was asked", error=0)
except getopt.GetoptError as err:
usage(str(err), error=101)
# register filters
if fltr.n_filters_defined() > 0:
provider = naivetrack.apply_filters(provider=provider,
filters=[fltr])
# prepare the output writer
outwriter = table.VariantWriter(fout, chromosome_list)
# process the variants
naivetrack_to_annoinput(provider, writer=outwriter)
del outwriter