def main():
# ------ Parse Command line ------
parser = _build_option_parser()
(opts, args) = parser.parse_args(sys.argv[1:])
if args:
parser.error("Unparsable arguments: %s " % args)
seqs = opts.reader.read(opts.fin)
if opts.trans_seg:
seqs = SeqList([mask_low_complexity(s) for s in seqs])
if opts.subsample is not None:
from random import random
frac = opts.subsample
ss = []
for s in seqs:
if random() < frac:
ss.append(s)
seqs = SeqList(ss)
if opts.reverse:
seqs = SeqList([s.reverse() for s in seqs])
if opts.complement:
seqs = SeqList([Seq(s, alphabet=nucleic_alphabet) for s in seqs])
seqs = SeqList([s.complement() for s in seqs])
opts.writer.write(opts.fout, seqs)
def test_tally(self):
# 1234567890123456789012345678
s0 = Seq("ACTTT", nucleic_alphabet)
s1 = Seq("ACCCC", nucleic_alphabet)
s2 = Seq("GGGG", nucleic_alphabet)
seqs = SeqList([s0, s1, s2], nucleic_alphabet)
counts = seqs.tally()
assert counts == [2, 5, 4, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
seqs = SeqList(
[Seq("AAACD", nucleic_alphabet),
Seq("AAACD", nucleic_alphabet)])
self.assertRaises(ValueError, seqs.tally)
def test_repr(self):
s0 = Seq("ACGTURYBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s1 = Seq("ACGTURYSWKMBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s2 = Seq("ACGTURSWKMBDHVNACGTURKMBDHVN", nucleic_alphabet)
seqs = SeqList([s0, s1, s2])
repr(seqs)
def test_create(self):
# 1234567890123456789012345678
s0 = Seq("ACGTURYBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s1 = Seq("ACGTURYSWKMBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s2 = Seq("ACGTURSWKMBDHVNACGTURKMBDHVN", nucleic_alphabet)
seqs = SeqList([s0, s1, s2])
self.assertEqual(len(seqs), 3)
def test_profile(self):
a = Alphabet("ABCD")
s0 = Seq("ABCDD", a)
s1 = Seq("AAAAD", a)
s2 = Seq("AAABD", a)
s3 = Seq("AAACD", a)
seqs = SeqList([s0, s1, s2, s3], a)
tally = seqs.profile()
self.assertEqual(list(tally[0]), [4, 0, 0, 0])
self.assertEqual(list(tally[1]), [3, 1, 0, 0])
self.assertEqual(list(tally[2]), [3, 0, 1, 0])
self.assertEqual(list(tally[3]), [1, 1, 1, 1])
self.assertEqual(list(tally[4]), [0, 0, 0, 4])
self.assertEqual(tally[4, 'D'], 4)
seqs = SeqList([Seq("AAACD", a), Seq("AAACDA", a)], a)
self.assertRaises(ValueError, seqs.profile)
seqs = SeqList([Seq("AAACD", a), Seq("AAACD", a)])
self.assertRaises(ValueError, seqs.profile)
def test_create_annotated(self):
s0 = Seq("ACGTURYBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s1 = Seq("ACGTURYSWKMBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s2 = Seq("ACGTURSWKMBDHVNACGTURKMBDHVN", nucleic_alphabet)
seqs = SeqList([s0, s1, s2],
alphabet=nucleic_alphabet,
name="alsdf",
description='a')
self.assertEqual(seqs.name, 'alsdf')
self.assertEqual(seqs.description, 'a')
self.assertEqual(seqs.alphabet, nucleic_alphabet)
def test_ords(self):
s0 = Seq("ACGTURYBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s1 = Seq("ACGTURYSDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s2 = Seq("ACGTURSWKMBDHVNACGTURKMBDHVN", nucleic_alphabet)
seqs = SeqList([s0, s1, s2], nucleic_alphabet)
seqs.ords()
# self.assertEqual( a.shape, (3, 28) )
# Fails if seqs are of different lengths
# FIXME?
# s3 = Seq("ACGTUR", nucleic_alphabet )
# seqs2 = SeqList( [ s0,s1,s3,s2], nucleic_alphabet)
# self.assertRaises(ValueError, seqs2.ords )
# Use a different alphabet
seqs.ords(nucleic_alphabet)
# No alphabet
seqs3 = SeqList([s0, s1, s2])
seqs3.ords(alphabet=Alphabet("ABC"))
# Fail if no alphabet
self.assertRaises(ValueError, seqs3.ords)
def test_create_empty(self):
s0 = Seq("ACGTURYBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s1 = Seq("ACGTURYSWKMBDHVNACGTURYSWKMBDHVN", nucleic_alphabet)
s2 = Seq("ACGTURSWKMBDHVNACGTURKMBDHVN", nucleic_alphabet)
seqs = SeqList()
seqs.append(s0)
seqs.extend((s1, s2))
self.assertEqual(len(seqs), 3)
self.assertEqual(type(seqs), SeqList)
def test_isaligned(self):
a = Alphabet("ABCD")
s0 = Seq("ABCDD", a)
s1 = Seq("AAAAD", a)
s2 = Seq("AAABD", a)
s3 = Seq("AAACD", a)
seqs = SeqList([s0, s1, s2, s3], a)
assert seqs.isaligned()
seqs = SeqList([s0, s1, s2, s3], Alphabet("ABCDE"))
assert not seqs.isaligned()