def test_build_index():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(
fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
show_shallow_tree(index.TopDownIterator(index))
def test_index_text():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
assert len(index.text) == len(_ids)
assert len(index.text[0]) == len(sequences[0])
def test_property_map():
_num_bases, sequences, _ids = seqan.readFastaDNA5(fasta_file('dm01r.fasta'))
logging.info('Building index')
index = seqan.IndexStringDNA5SetESA(sequences)
logging.info('Creating property map of length %d', len(index))
property_map = [None] * (2 * len(index))
def set_properties(i):
property_map[i.value.id] = i.representative, i.numOccurrences
if i.goDown():
while True:
set_properties(copy(i))
if not i.goRight():
break
def show_properties(i):
if len(i.representative) < 3:
logging.info('%-2s : %5d', *property_map[i.value.id])
if i.goDown():
while True:
show_properties(copy(i))
if not i.goRight():
break
logging.info('Setting properties')
set_properties(index.TopDownIterator(index))
logging.info('Showing properties')
show_properties(index.TopDownIterator(index))
def test_index_text():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(
fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
assert len(index.text) == len(_ids)
assert len(index.text[0]) == len(sequences[0])
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_read_fasta():
filename = fasta_file('dm01r.fasta')
logging.info('Reading %s', filename)
num_bases, sequences, ids = seqan.readFastaDNA5(filename)
logging.info('Read %d bases in %d sequences', num_bases, len(sequences))
assert 4 == len(sequences), len(sequences)
for _id, seq in zip(ids, sequences):
assert 1500 == len(seq)
logging.info('%5d bases in %s', len(seq), _id)
map(len, sequences)
def test_infix_comparison():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
i = index.TopDownIterator(index)
assert i.goDown('A')
assert i.goDown('T')
assert i.goDown('C')
assert 'ATC' == i.representative, i.representative
def test_read_fasta():
filename = fasta_file('dm01r.fasta')
logging.info('Reading %s', filename)
num_bases, sequences, ids = seqan.readFastaDNA5(filename)
logging.info('Read %d bases in %d sequences', num_bases, len(sequences))
assert 4 == len(sequences), len(sequences)
for _id, seq in zip(ids, sequences):
assert 1500 == len(seq)
logging.info('%5d bases in %s', len(seq), _id)
map(len, sequences)
def test_infix_comparison():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(
fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
i = index.TopDownIterator(index)
assert i.goDown('A')
assert i.goDown('T')
assert i.goDown('C')
assert 'ATC' == i.representative, i.representative
def test_save_load_index():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
tmpdir = tempfile.mkdtemp(suffix='test-index-save')
filename = os.path.join(tmpdir, 'index.saved')
index.save(filename)
index2 = IndexDNA5.load(filename)
i = index2.topdown()
assert i.goDown('A')
text = index2.text
print text[0][:4]
def read_sequences(fasta):
# Read and reverse the sequences
num_bases, seqs_dna5, _ids = seqan.readFastaDNA5(fasta, reverse=True)
for _id, seq in zip(_ids, seqs_dna5):
logger.info('%s: %d bases', _id, len(seq))
logger.info('Read %d bases in total', num_bases)
# Split the sequences into their known portions
seqs_dna4 = seqan.StringDNASet()
for seq in chain.from_iterable(imap(split_sequence, seqs_dna5)):
logger.info(seq)
seqs_dna4.appendValue(seqan.StringDNA(seq))
logger.info('Split %d sequences with %d possibly ambiguous bases into %d sections totalling %d unambiguous bases',
len(seqs_dna5), num_bases, len(seqs_dna4), sum(imap(len, seqs_dna4)))
def test_save_load_index():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(
fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
tmpdir = tempfile.mkdtemp(suffix='test-index-save')
filename = os.path.join(tmpdir, 'index.saved')
index.save(filename)
index2 = IndexDNA5.load(filename)
i = index2.topdown()
assert i.goDown('A')
text = index2.text
print text[0][:4]
def read_sequences(fasta):
# Read and reverse the sequences
num_bases, seqs_dna5, _ids = seqan.readFastaDNA5(fasta, reverse=True)
for _id, seq in zip(_ids, seqs_dna5):
logger.info('%s: %d bases', _id, len(seq))
logger.info('Read %d bases in total', num_bases)
# Split the sequences into their known portions
seqs_dna4 = seqan.StringDNASet()
for seq in chain.from_iterable(imap(split_sequence, seqs_dna5)):
logger.info(seq)
seqs_dna4.appendValue(seqan.StringDNA(seq))
logger.info(
'Split %d sequences with %d possibly ambiguous bases into %d sections totalling %d unambiguous bases',
len(seqs_dna5), num_bases, len(seqs_dna4), sum(imap(len, seqs_dna4)))
def test_build_index():
logging.info(sys._getframe().f_code.co_name)
for IndexDNA5 in IndexesDNA5:
_num_bases, sequences, _ids = seqan.readFastaDNA5(fasta_file('dm01r.fasta'))
index = IndexDNA5(sequences)
show_shallow_tree(index.TopDownIterator(index))