def test_sanitize_all_hyphen(self):
all_hyphens = "---"
new_string = strings.sanitize(all_hyphens)
self.assertEqual(new_string, "")
# Load sequence data into a data structure for internal use
seqdict = {}
files.build_seqdict(args.infile,seqdict)
rna_string = str(args.RNA)
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()
# We directly compare aligned sequences, but class implementation uses
# unaligned sequences (i.e. no gap characters '-')
san_rna_seq = strings.sanitize(rna_seq)
san_gen_seq = strings.sanitize(gen_seq)
seq_pair = classes.SeqPair(san_rna_seq,san_gen_seq,name)
# 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_nuc_seqs(gen_seq[i], rna_seq[i]):
# If we find residues in either sequence, we need to increment
# certain class values accordingly
if gen_seq[i] != '-':
seq_pair.incr_all()
if rna_seq[i] != '-':
def test_sanitize(self):
really_dirty_string = "This-strings-is-really-dirty"
new_string = strings.sanitize(really_dirty_string)
self.assertEqual(new_string, "Thisstringsisreallydirty")
# Load sequence data into a data structure for internal use
seqdict = {}
files.build_seqdict(args.infile,seqdict)
rna_string = str(args.RNA)
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()
# We directly compare aligned sequences, but class implementation uses
# unaligned sequences (i.e. no gap characters '-')
san_rna_seq = strings.sanitize(rna_seq)
san_gen_seq = strings.sanitize(gen_seq)
seq_pair = classes.SeqPair(san_rna_seq,san_gen_seq,name)
# 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):
# If we find residues in either sequence, we need to increment
# certain class values accordingly
if gen_seq[i] != '-':
seq_pair.incr_all()
def test_sanitize_all_hyphen(self):
all_hyphens = "---"
new_string = strings.sanitize(all_hyphens)
self.assertEqual(new_string, "")
def test_sanitize(self):
really_dirty_string = "This-strings-is-really-dirty"
new_string = strings.sanitize(really_dirty_string)
self.assertEqual(new_string, "Thisstringsisreallydirty")
gen_string = str(args.genomic)
# Sequences must be in upper case
for k in seqdict.keys():
if re.search(rna_string,k):
# Since we are writing these data back out again
# we want to keep track of sequence headers
rna_header = k
rna_seq = seqdict.get(k).upper()
elif re.search(gen_string,k):
gen_header = k
gen_seq = seqdict.get(k).upper()
else:
ref_header = k
ref_seq = seqdict.get(k).upper()
san_gen_seq = strings.sanitize(gen_seq)
san_ref_seq = strings.sanitize(ref_seq)
# Steal the RefPair class, but we do not care about the name for
# writing to output, use "name" as a placeholder
ref_pair = classes.RefPair(san_ref_seq,san_gen_seq,"name")
gen_start = 'NA' # Can't use False, as zero index also evaluates
ref_start = 'NA'
gen_list = []
ref_list = []
for i, (rg,rf) in enumerate(zip(gen_seq,ref_seq)):
# A gap in both genomic and reference sequences is unlikely,
# but we should account for it just in case
if rf == '-' and rg == '-':
#print "gap in both. Passing"
pass
gen_string = str(args.genomic)
# Sequences must be in upper case
for k in seqdict.keys():
if re.search(rna_string,k):
# Since we are writing these data back out again
# we want to keep track of sequence headers
rna_header = k
rna_seq = seqdict.get(k).upper()
elif re.search(gen_string,k):
gen_header = k
gen_seq = seqdict.get(k).upper()
else:
ref_header = k
ref_seq = seqdict.get(k).upper()
san_gen_seq = strings.sanitize(gen_seq)
san_ref_seq = strings.sanitize(ref_seq)
# Steal the RefPair class, but we do not care about the name for
# writing to output, use "name" as a placeholder
ref_pair = classes.RefPair(san_ref_seq,san_gen_seq,"name")
gen_start = 'NA' # Can't use False, as zero index also evaluates
ref_start = 'NA'
gen_list = []
ref_list = []
for i, (rg,rf) in enumerate(zip(gen_seq,ref_seq)):
#print "position: %d" % (i+1)
#print "reference nucleotide: %s" % (rf)
#print "reference codon position: %d" % (ref_pair.index_rposition())
#print "genomic nucleotide is: %s" % (rg)
#print "genomic codon position: %d" % (ref_pair.index_gposition())