def realign_file(args, model, output_filename, alignment_filename):
# begin of HACK
if args.expand_model:
old_tracks = args.tracks
args.tracks.add('trf_cons')
m = model
if args.annotation_model:
m = args.annotation_model
annotations = compute_annotations(args, alignment_filename, m)
if args.expand_model:
consensuses = annotations['trf_cons']
args.tracks = old_tracks
if 'trf_cons' not in old_tracks:
del args.tracks['trf_cons']
# end of HACK
with Open(output_filename, 'w') as output_file_object:
for aln in Fasta.load(
alignment_filename,
args.alignment_regexp,
Alignment,
sequence_selectors=args.sequence_regexp):
if len(aln.sequences) < 2:
sys.stderr.write("ERROR: not enough sequences in file\n")
return 1
if len(args.draw) == 0:
drawer = brainwash(AlignmentCanvas)()
else:
drawer = AlignmentCanvas()
drawer.add_original_alignment(aln)
aln, unmask_repeats = args.mask_repeats(aln, annotations)
seq1, seq2 = tuple(map(Fasta.alnToSeq, aln.sequences[:2]))
perf.msg("Data loaded in {time} seconds.")
perf.replace()
if args.expand_model:
# Potrebujem zistit konsenzy
A = consensuses[aln.names[0]]
B = consensuses[aln.names[1]]
cons = list(A.union(B))
real_model = model.expandModel({'consensus': cons})
else:
real_model = model
realigner = args.algorithm()
realigner.setDrawer(drawer)
realigner.prepareData(seq1, aln.names[0], seq2, aln.names[1], aln,
real_model, annotations, args)
aln = realigner.realign(0, len(seq1), 0, len(seq2))
aln = unmask_repeats(aln)
perf.msg("Sequence was realigned in {time} seconds.")
perf.replace()
if len(args.draw) > 0:
drawer.add_sequence('X', seq1)
drawer.add_sequence('Y', seq2)
drawer.add_alignment_line(101, (255, 0, 255, 255), 2,
AlignmentPositionGenerator(
Alignment([aln[0], aln[2]])))
drawer.draw(args.draw, 2000, 2000)
perf.msg("Image was drawn in {time} seconds.")
# Save output_file
Fasta.saveAlignmentPiece(aln, output_file_object)
def main(files_filename, output_filename, suffix, base_dir):
X = ""
Y = ""
A = ""
with Open(output_filename, "w") as ff:
files = json.load(Open(files_filename))
total = len(files)
done = 0
for filename in files:
if done % 100 == 0:
print "{}/{} {:.2}%".format(done, total, 100.0 * done / total)
if filename == "":
Fasta.saveAlignmentPiece([(X_name, X), (Y_name, Y), (A_name, A)], ff)
X = ""
Y = ""
A = ""
continue
done += 1
old_filename = filename
keep = False
if filename.count("keep") == 0:
filename = filename[:-2] + suffix
if base_dir != None:
filename = base_dir + "/" + filename.split("/")[-1]
try:
with Open(filename, "r") as f:
l = len("".join(f).strip())
if l == 0:
filename = old_filename
keep = True
except IOError:
filename = old_filename
keep = True
if filename.count("keep") > 0:
keep = True
aln = list(Fasta.load(filename, ""))[0]
assert len(aln) == 3
assert len(aln[0][1]) == len(aln[1][1]) == len(aln[2][1])
X += aln[0][1]
if keep:
A += "." * len(aln[0][1])
else:
A += aln[1][1]
Y += aln[2][1]
X_name = aln[0][0]
A_name = aln[1][0]
Y_name = aln[2][0]
def main(files_filename, output_filename, suffix, base_dir):
X = ""
Y = ""
A = ""
with Open(output_filename, 'w') as ff:
files = json.load(Open(files_filename))
total = len(files)
done = 0
for filename in files:
if done %100 ==0:
print '{}/{} {:.2}%'.format(done, total, 100.0 * done / total)
if filename == "":
Fasta.saveAlignmentPiece([(X_name, X), (Y_name, Y), (A_name, A)], ff)
X = ""
Y = ""
A = ""
continue
done += 1
old_filename = filename
keep = False
if filename.count('keep') == 0:
filename = filename[:-2] + suffix
if base_dir != None:
filename = base_dir + '/' + filename.split('/')[-1]
try:
with Open(filename, 'r') as f:
l = len(''.join(f).strip())
if l == 0:
filename = old_filename
keep = True
except IOError:
filename = old_filename
keep = True
if filename.count('keep') > 0:
keep = True
aln = list(Fasta.load(filename, ''))[0]
assert(len(aln) == 3)
assert(len(aln[0][1]) == len(aln[1][1]) == len(aln[2][1]))
X += aln[0][1]
if keep:
A += '.' * len(aln[0][1])
else:
A += aln[1][1]
Y += aln[2][1]
X_name = aln[0][0]
A_name = aln[1][0]
Y_name = aln[2][0]
def main(input_file, output_file):
for trf_executable in trf_paths:
if os.path.exists(trf_executable):
trf = TRFDriver(trf_executable)
#break
if not trf:
raise "No trf found"
repeats = trf.run(input_file)
with open(output_file, 'w') as f:
for alignment in Fasta.load(input_file, '\.[0-9]*$', Alignment):
if len(alignment.sequences) != 2:
print 'error'
continue
#print alignment.names
annotation = list('.' * len(alignment.sequences[0]))
annotationX = list('.' * len(alignment.sequences[0]))
annotationY = list('.' * len(alignment.sequences[0]))
trf = None
for seq_name in alignment.names:
index = None
for i in range(len(alignment.names)):
if seq_name == alignment.names[i]:
index = i
translator = alignment.seq_to_aln[index]
revtranslator = alignment.aln_to_seq[index]
for repeat in repeats[seq_name]:
for i in range(translator[repeat.start], translator[repeat.end]):
annotation[i] = 'R'
j = i - translator[repeat.start]
if index == 0:
annotationX[i] = repeat.consensus[revtranslator[j] % len(repeat.consensus)]
else:
annotationY[i] = repeat.consensus[revtranslator[j] % len(repeat.consensus)]
d = defaultdict(int)
ll = 0
for v in annotation:
if v != 'R':
if ll > 0:
d[ll] += 1
ll = 0
else:
ll += 1
#for x, y in sorted(d.iteritems(), key=lambda x: x[1]):
# print '{}: {}'.format(x, y)
#if len(d.keys()) > 0:
# print('Number of repeats: {}, average length: {}, maximum length: {}, minimum length: {}'.format(
# sum(d.values()),
# sum([x * y for x, y in d.iteritems()])/ max(sum(d.values()), 1),
# max(d.keys()),
# min(d.keys())
# ))
seqX = alignment.sequences
nm = alignment.names[0]
aln = [(alignment.names[0], alignment.sequences[0].replace('.', '-')),
('consensusX' + nm, ''.join(annotationX)),
('annotation' + nm, ''.join(annotation)),
('consensusY' + nm, ''.join(annotationY)),
(alignment.names[1], alignment.sequences[1].replace('.','-'))]
Fasta.saveAlignmentPiece(aln, f, -1)
def main(input_file, output_file):
for trf_executable in trf_paths:
if os.path.exists(trf_executable):
trf = TRFDriver(trf_executable)
#break
if not trf:
raise "No trf found"
repeats = trf.run(input_file)
with open(output_file, 'w') as f:
for alignment in Fasta.load(input_file, '\.[0-9]*$', Alignment):
if len(alignment.sequences) != 2:
print 'error'
continue
#print alignment.names
annotation = list('.' * len(alignment.sequences[0]))
annotationX = list('.' * len(alignment.sequences[0]))
annotationY = list('.' * len(alignment.sequences[0]))
trf = None
for seq_name in alignment.names:
index = None
for i in range(len(alignment.names)):
if seq_name == alignment.names[i]:
index = i
translator = alignment.seq_to_aln[index]
revtranslator = alignment.aln_to_seq[index]
for repeat in repeats[seq_name]:
for i in range(translator[repeat.start],
translator[repeat.end]):
annotation[i] = 'R'
j = i - translator[repeat.start]
if index == 0:
annotationX[i] = repeat.consensus[
revtranslator[j] % len(repeat.consensus)]
else:
annotationY[i] = repeat.consensus[
revtranslator[j] % len(repeat.consensus)]
d = defaultdict(int)
ll = 0
for v in annotation:
if v != 'R':
if ll > 0:
d[ll] += 1
ll = 0
else:
ll += 1
#for x, y in sorted(d.iteritems(), key=lambda x: x[1]):
# print '{}: {}'.format(x, y)
#if len(d.keys()) > 0:
# print('Number of repeats: {}, average length: {}, maximum length: {}, minimum length: {}'.format(
# sum(d.values()),
# sum([x * y for x, y in d.iteritems()])/ max(sum(d.values()), 1),
# max(d.keys()),
# min(d.keys())
# ))
seqX = alignment.sequences
nm = alignment.names[0]
aln = [
(alignment.names[0], alignment.sequences[0].replace('.', '-')),
('consensusX' + nm, ''.join(annotationX)),
('annotation' + nm, ''.join(annotation)),
('consensusY' + nm, ''.join(annotationY)),
(alignment.names[1], alignment.sequences[1].replace('.', '-'))
]
Fasta.saveAlignmentPiece(aln, f, -1)
