def test_compare_seqs_nonequal(self):
seq1 = 'abcdefghi'
seq2 = 'jklmnopqr'
# 7 of 9 resiues used as standard setting in main program
self.assertFalse(sequence.compare_seqs(seq1, seq2, 7))
if re.search(rna_string,k):
rna_seq = seqdict.get(k).upper()
elif re.search(gen_string,k):
gen_seq = seqdict.get(k).upper()
else:
ref_seq = seqdict.get(k).upper()
# Need to find beginning and end of aligned region
i = 0
j = 0
# Need to keep track of gen index
gen_index = 0
try:
# Compare genomic and RNA sequences to find local regions of good
# similarity, this is taken as the start and end of aligned region
while not sequence.compare_seqs((strings.gulp(rna_seq, i, size)),
(strings.gulp(gen_seq, i, size)), num_equal):
if gen_seq[i] != '-':
# If there is actually an amino acid in the genomic sequence
# we need to move the index ahead
gen_index += 1
i += 1
while not sequence.compare_seqs((strings.gulp(rna_seq[::-1], j, size)),
(strings.gulp(gen_seq[::-1], j, size)), num_equal):
j += 1
# If we get an index error then we cannot find start and end of both sequences
except(IndexError):
print "Could not discern aligned part of sequences"
# Exit cleanly
sys.exit(0)
# Once we know the start and end, simply chop off everything else
def test_compare_seqs_opening_gap2(self):
seq1 = '-bcdefghi'
seq2 = '-bcdefghi'
self.assertFalse(sequence.compare_seqs(seq1, seq2, 7))
def test_compare_seqs_internal_gap2(self):
seq1 = 'a-cdefghi'
seq2 = 'abc-efghi'
self.assertTrue(sequence.compare_seqs(seq1, seq2, 7))
def test_compare_seqs_below_threshold(self):
seq1 = 'abcdefghi'
seq2 = 'abcdefxyz'
# only six characters are the same above
# therefore the test should fail
self.assertFalse(sequence.compare_seqs(seq1, seq2, 7))
def test_compare_seqs_opening_gap1(self):
seq1 = '-bcdefghi'
seq2 = 'abcdefghi'
# first character is a gap, therefore should evaluate False
self.assertFalse(sequence.compare_seqs(seq1, seq2, 7))
gen_string = str(args.genomic)
# Sequences must be in upper-case
for k in seqdict.keys():
if re.search(rna_string, k):
rna_seq = seqdict.get(k).upper()
elif re.search(gen_string, k):
gen_seq = seqdict.get(k).upper()
# Need to find beginning and end of aligned region
i = 0
j = 0
try:
# Compare genomic and RNA sequences to find local regions of good
# similarity, this is taken as the start and end of aligned region
while not sequence.compare_seqs(
(strings.gulp(rna_seq, i, size)),
(strings.gulp(gen_seq, i, size)), num_equal):
#while not sequence.compare_seqs(gen_seq[i], rna_seq[i]):
i += 1
while not sequence.compare_seqs(
(strings.gulp(rna_seq[::-1], j, size)),
(strings.gulp(gen_seq[::-1], j, size)), num_equal):
#while not sequence.compare_seqs(gen_seq[-j], rna_seq[-j]):
j += 1
# If we get an index error then we cannot find start and end of both sequences
except (IndexError):
print "Could not discern aligned part of sequences"
# Exit cleanly
sys.exit(0)
# Once we know the start and end, simply chop off everything else
def test_compare_seqs_allequal(self):
seq1 = 'abcdefghi'
seq2 = 'abcdefghi'
self.assertTrue(sequence.compare_seqs(seq1, seq2, 7))
def test_compare_seqs_nonequal(self):
seq1 = 'abcdefghi'
seq2 = 'jklmnopqr'
# 7 of 9 resiues used as standard setting in main program
self.assertFalse(sequence.compare_seqs(seq1,seq2,7))
if re.search(rna_string, k):
aa_rna_seq = aa_seqdict.get(k).upper()
elif re.search(gen_string, k):
aa_gen_seq = aa_seqdict.get(k).upper()
else:
aa_ref_seq = aa_seqdict.get(k).upper()
# Find the beginning and end of aligned region
i = 0
j = 0
try:
# Compare genomic and RNA sequences to find local regions of good
# similarity, this is taken as the start and end of aligned region
#while not sequence.compare_seqs((strings.gulp(aa_rna_seq, i, 10)),
# (strings.gulp(aa_gen_seq, i, 10)), 5):
while not sequence.compare_seqs(aa_gen_seq[i], aa_rna_seq[i]):
if i > len(aa_rna_seq):
raise IndexError
i += 1
#while not sequence.compare_seqs((strings.gulp(aa_rna_seq[::-1], j, 10)),
# (strings.gulp(aa_gen_seq[::-1], j, 10)), 5):
while not sequence.compare_seqs(aa_gen_seq[-j], aa_rna_seq[-j]):
if j > len(aa_gen_seq):
raise IndexError
j += 1
# If we get an index error then we cannot find start and end of both sequences
except (IndexError):
print "Could not discern aligned part of sequences"
# Exit cleanly
sys.exit(0)
def test_compare_seqs_internal_gap2(self):
seq1 = 'a-cdefghi'
seq2 = 'abc-efghi'
self.assertTrue(sequence.compare_seqs(seq1,seq2,7))
def test_compare_seqs_opening_gap2(self):
seq1 = '-bcdefghi'
seq2 = '-bcdefghi'
self.assertFalse(sequence.compare_seqs(seq1,seq2,7))
def test_compare_seqs_opening_gap1(self):
seq1 = '-bcdefghi'
seq2 = 'abcdefghi'
# first character is a gap, therefore should evaluate False
self.assertFalse(sequence.compare_seqs(seq1,seq2,7))
def test_compare_seqs_below_threshold(self):
seq1 = 'abcdefghi'
seq2 = 'abcdefxyz'
# only six characters are the same above
# therefore the test should fail
self.assertFalse(sequence.compare_seqs(seq1,seq2,7))
def test_compare_seqs_allequal(self):
seq1 = 'abcdefghi'
seq2 = 'abcdefghi'
self.assertTrue(sequence.compare_seqs(seq1,seq2,7))