def test_remove_gaps(self):
s1 = ''.join(stats.sample_wr(translate.AAs(), 100))
others = [''.join([mut(x, 0.2,0.1) for x in s1]) for i in range(9)]
seqs = [s1]+others
als = muscle.alignSequences(seqs)
res = len(als) == len(seqs)
for i in range(len(als)):
self.assertTrue(als[i].replace("-",'') == seqs[i].replace("-",''))
def test002():
s1 = ''.join(stats.sample_wr(translate.AAs(), 100))
others = [''.join([mut(x, 0.2,0.1) for x in s1]) for i in range(9)]
seqs = [s1]+others
res = False
try:
als = muscle.alignSequences(seqs, exepath=os.path.expanduser("~/develop/muscle3.8.13/muscle"))
except muscle.MuscleError, me:
res = True
def test001():
s1 = ''.join(stats.sample_wr(translate.AAs(), 100))
others = [''.join([mut(x, 0.2,0.1) for x in s1]) for i in range(9)]
seqs = [s1]+others
als = muscle.alignSequences(seqs)
res = len(als) == len(seqs)
for i in range(len(als)):
res = res and (als[i].replace("-",'') == seqs[i].replace("-",''))
return True
def test001():
s1 = ''.join(stats.sample_wr(translate.AAs(), 100))
others = [''.join([mut(x, 0.2, 0.1) for x in s1]) for i in range(9)]
seqs = [s1] + others
als = muscle.alignSequences(seqs)
res = len(als) == len(seqs)
for i in range(len(als)):
res = res and (als[i].replace("-", '') == seqs[i].replace("-", ''))
return True
def test_remove_gaps(self):
s1 = ''.join(stats.sample_wr(translate.AAs(), 100))
others = [''.join([mut(x, 0.2, 0.1) for x in s1]) for i in range(9)]
seqs = [s1] + others
als = muscle.alignSequences(seqs)
res = len(als) == len(seqs)
for i in range(len(als)):
self.assertTrue(
als[i].replace("-", '') == seqs[i].replace("-", ''))
def test002():
s1 = ''.join(stats.sample_wr(translate.AAs(), 100))
others = [''.join([mut(x, 0.2, 0.1) for x in s1]) for i in range(9)]
seqs = [s1] + others
res = False
try:
als = muscle.alignSequences(
seqs, exepath=os.path.expanduser("~/develop/muscle3.8.13/muscle"))
except muscle.MuscleError, me:
res = True
def test_gapped_index(self):
s1 = ''.join(stats.sample_wr(translate.AAs(), 50))
# No gaps: pgap = 0.0
others = [''.join([mut(x, 0.2,0.0) for x in s1]) for i in range(9)]
seqs = [s1]+others
res = False
try:
als = muscle.alignSequences(seqs)
#print als
self.assertTrue(len(als) == len(seqs))
for (i, s) in enumerate(seqs):
self.assertTrue(s == als[i].replace("-",''))
except muscle.MuscleError as me:
self.assertTrue(False)
def test_gapped_index(self):
s1 = ''.join(stats.sample_wr(translate.AAs(), 50))
# No gaps: pgap = 0.0
others = [''.join([mut(x, 0.2, 0.0) for x in s1]) for i in range(9)]
seqs = [s1] + others
res = False
try:
als = muscle.alignSequences(seqs)
#print als
self.assertTrue(len(als) == len(seqs))
for (i, s) in enumerate(seqs):
self.assertTrue(s == als[i].replace("-", ''))
except muscle.MuscleError as me:
self.assertTrue(False)
def makeAlignments(ortho_dict, cdna_dicts, filter_fxn=default_filter_fxn, filter_data=None, alignment_print_fxn=default_alignment_print_fxn):
alignment_dict = {}
num_aligns = 0
#print cdna_dicts.keys()
for orf in ortho_dict.keys():
ortho_orfs = ortho_dict[orf]
#print orf, ortho_orfs
seqs = {}
for (spec, sorf) in ortho_orfs:
try:
genome = cdna_dicts[spec]
seq = genome[sorf]
# Translate and so on
prot = translate.translate(seq)
if prot:
seqs[spec] = (sorf, prot)
else:
print("# protein", sorf, "did not translate")
#print seq
#print translate.translateRaw(seq)
except KeyError as ke:
print("#", ke, spec, sorf, orf)
pass
species = seqs.keys()
if filter_fxn(orf, seqs, filter_data): #len(species) == len(genome_dicts.keys()): # Found as many orthologs as genomes
prots = [seqs[key][1] for key in species]
try:
protal = muscle.alignSequences(prots, 16)
hdrs = [(spec, seqs[spec][0]) for spec in species]
alignment_dict[orf] = (len(protal), hdrs, protal)
num_aligns += 1
alignment_print_fxn(num_aligns, prots, protal, hdrs, orf)
except muscle.MuscleError as me:
print("#", me)
return alignment_dict
def secondField(h):
f = None
try:
f = biofile.secondField(h)
except:
f = biofile.firstField(h)
return f
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fname, 'r')) #, key_fxn=biofile.secondField)
if options.translate_sequences:
seqs = [translate.translate(s) for s in seqs]
if not options.dont_align_sequences:
aligned_seqs = muscle.alignSequences(seqs)
seqs = aligned_seqs
zhs = [(h,s) for (h,s) in zip(headers,seqs) if not s is None]
all_keys = [biofile.firstField(h) for (h,s) in zhs]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h,s) in zhs])
gene_orf_dict = dict([(secondField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(v,k) for (k,v) in gene_orf_dict.items()])
# Write output
n_written = 0
data_outs.write("header\n")
for orf in query_keys:
n_written += 1
# Write out stopping time
if '_' in seq:
store_seq = False
if store_seq:
new_header = '{sname} {hdr}'.format(sname=species_name, hdr=hdr)
#named_headers[species_name] = new_header
#named_seqs[species_name] = seq
new_headers.append(new_header)
new_seqs.append(seq)
#(headers, seqs) = zip(*[(named_headers[x],named_seqs[x]) for x in sorted(named_seqs.keys())])
headers = new_headers
seqs = new_seqs
if options.align:
#print os.path.expanduser('/cygdrive/f/develop/muscle3.8.31/muscle')
aligned_seqs = muscle.alignSequences(seqs) #, exepath='~\\develop\\muscle3.8.31\\muscle')
seqs = aligned_seqs
# Write output
n_written = 0
for (hdr, seq) in zip(headers,seqs):
line = ">{hdr}\n{seq}\n".format(hdr=hdr, seq=seq)
data_outs.write(line)
n_written += 1
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
f = None
try:
f = biofile.secondField(h)
except:
f = biofile.firstField(h)
return f
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fname, "r")) # , key_fxn=biofile.secondField)
if options.translate_sequences:
seqs = [translate.translate(s) for s in seqs]
if not options.dont_align_sequences:
aligned_seqs = muscle.alignSequences(seqs)
seqs = aligned_seqs
zhs = [(h, s) for (h, s) in zip(headers, seqs) if not s is None]
all_keys = [biofile.firstField(h) for (h, s) in zhs]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h, s) in zhs])
gene_orf_dict = dict([(secondField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(v, k) for (k, v) in gene_orf_dict.items()])
# Write output
n_written = 0
data_outs.write("header\n")
for orf in query_keys:
n_written += 1
# Write out stopping time
