def test_string_reversecomplement():
logging.info(sys._getframe().f_code.co_name)
s1 = seqan.StringDNA5('AANNGG')
rc = s1.reversecomplement()
print rc
print str(rc)
assert seqan.StringDNA5('CCNNTT') == rc
del s1
assert seqan.StringDNA5('CCNNTT') == rc
def test_strings():
logging.info(sys._getframe().f_code.co_name)
_num_bases, sequences, ids = seqan.readFastaDNA5(fasta_file('dm01r.fasta'))
logging.info('Size of DNA5 alphabet %d', seqan.DNA5.valueSize )
logging.info('Size of DNA alphabet %d', seqan.DNA.valueSize )
logging.info('Length of sequence %s %d', ids[3], len(sequences[3]))
logging.info('Tenth base of sequence %s %s', ids[2], sequences[2].value(9))
logging.info('Infix of sequence %s %s', ids[2], sequences[2].infix(9, 14))
_s5 = seqan.StringDNA5('ACGTACGTACGTACGT')
s4 = seqan.StringDNA('ACGTACGTACGTACGT')
s = s4
infix = s.infix(3, 9)
slice_ = s[3:9]
logging.info('Infix %s', infix)
logging.info(type(infix))
logging.info('Slice %s', slice_)
logging.info(type(slice_))
# check object lifetimes are respected
del s
logging.info('Infix %s', infix)
logging.info('Slice %s', slice_)
#
# Check iteration using __getitem__ works correctly
#
s = sequences[0]
chars = set()
for i, c in enumerate(s):
if i >= len(s):
assert False
chars.add(c)
assert len(chars) <= 4
assert i == len(s) - 1
s5 = seqan.StringDNA5('NACGTNNACGTNACGTNACGT')
print s5[0] == 'N'
assert s5[0] == 'N'
print s5[0] != 'G'
assert s5[0] != 'G'
print s5[1] != 'N'
assert s5[1] != 'N'
print s5[1] == 'A'
assert s5[1] == 'A'
print 'N' == s5[0]
assert 'N' == s5[0]
print 'G' != s5[0]
assert 'G' != s5[0]
print 'N' != s5[1]
assert 'N' != s5[1]
print 'A' == s5[1]
assert 'A' == s5[1]
def test_small_index():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
sequences = seqan.StringDNA5Set()
sequences.appendValue(seqan.StringDNA5('A'))
index = IndexDNA5(sequences)
del sequences
_i = index.TopDownIterator(index)
def test_index_as_strings_custodian():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
sequences = seqan.StringDNA5Set()
sequences.appendValue(seqan.StringDNA5('ACG'))
index = IndexDNA5(sequences)
del sequences
i = index.TopDownIterator(index)
assert i.goDown('A')
def test_string_set_iteration():
logging.info(sys._getframe().f_code.co_name)
stringset = seqan.StringDNA5Set()
stringset.appendValue(seqan.StringDNA5('ACGTACGTACGTNNN'))
i = iter(stringset)
try:
while True:
logging.info(len(i.next()))
except StopIteration:
pass
map(len, stringset)
def _test_empty_index():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
sequences = seqan.StringDNA5Set()
sequences.appendValue(seqan.StringDNA5())
index = IndexDNA5(sequences)
logging.info('Creating top-down')
i = index.topdown()
1 / 0 # going down causes SEGV
logging.info('Going down "A"')
assert not i.goDown('A')
def test_split_sequence():
logger.info(sys._getframe().f_code.co_name)
result = list(split_sequence(seqan.StringDNA5('NNACNGANGGN')))
assert result[0] == 'AC', result[0]
assert result[1] == 'GA', result[1]
assert result[2] == 'GG', result[2]
assert 3 == len(result)
result = list(split_sequence('ACGTNNNNAAGG'))
assert result[0] == 'ACGT', result[0]
assert result[1] == 'AAGG', result[1]
assert 2 == len(result)
def test_go_down():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
sequences = seqan.StringDNA5Set()
for seq in (
'ACGT',
'AAAA',
'GGGG',
'AC',
):
sequences.appendValue(seqan.StringDNA5(seq))
index = IndexDNA5(sequences)
for expected_occs, texts in (
(2, (seqan.StringDNA5('AC'), 'AC')),
(1, (seqan.DNA5('T'), 'T', seqan.StringDNA5('T'))),
(6, (seqan.DNA5('A'), 'A', seqan.StringDNA5('A'))),
):
for text in texts:
logging.info('Trying %s: %s', type(text).__name__, text)
it = index.TopDownIterator(index)
assert it.goDown(text)
for occ in it.occurrences:
logging.info('Occurrence for %s: %s', text, occ)
assert expected_occs == len(it.occurrences)
def test_long_edges():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
sequences = seqan.StringDNA5Set()
for seq in (
'AA',
'AC',
'AG',
'ATACCGGTT',
):
sequences.appendValue(seqan.StringDNA5(seq))
index = IndexDNA5(sequences)
it = index.topdown()
assert it.goDown('A')
assert 'A' == it.representative
assert it.goDown('T')
logging.debug('%s: %s', IndexDNA5.__name__, it.representative)
assert 'ATACCGGTT' == it.representative
it = index.topdown()
assert it.goDown('AT')
logging.debug('%s: %s', IndexDNA5.__name__, it.representative)
assert 'ATACCGGTT' == it.representative
def test_string_set_append():
logging.info(sys._getframe().f_code.co_name)
stringset = seqan.StringDNA5Set()
stringset.appendValue(seqan.StringDNA5('ACGTACGTACGTNNN'))