def setUpClass(self):
self.mod_file = os.path.join(os.path.dirname(__file__),
"../test_data/CAST_to_BL6_chr19.mod")
self.logger = logger.build_logger()
self.transform = transform.build_transform(self.mod_file, self.logger)
self.positions, self.deltas = zip(*self.transform.get('chr19'))
self.position = 0
self.mod_file = os.path.join(os.path.dirname(__file__),
"../test_data/CAST_to_BL6_chr19.mod")
self.logger = logger.build_logger()
self.for_trans = transform.build_transform(self.mod_file, self.logger)
self.for_file = os.path.join(os.path.dirname(__file__),
"../test_data/CAST_to_BL6_chr19.dat")
self.for_data = pickle.load(open(self.for_file, 'r'))
def npf(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = 'chrom chromStart chromEnd name score strand a b c d'
curr_chrom = ""
with open(args.input, 'r') as input_:
for line in input_:
if not line.startswith('chrom'):
gene = line.rstrip()
data = {k:g for k,g in zip(keys.split(), gene.split('\t'))}
if data.get('chrom') != curr_chrom:
curr_chrom = data.get('chrom')
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
try:
start_delta = find_delta(positions,
deltas,
int(data.get('chromStart')))
end_delta = find_delta(positions,
deltas,
int(data.get('chromEnd')))
data['chromStart'] = int(data.get('chromStart')) + start_delta
data['chromEnd'] = int(data.get('chromEnd')) + end_delta
out.write('%s\n' % \
'\t'.join([str(data.get(k)) for k in keys.split()]))
except IndexError:
out.write('%s\n' % \
'\t'.join([str(data.get(k)) for k in keys.split()]))
def smrna_txt(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = 'name num_trna trna_begin trna_end isotype anticodon up_region down_region intron_begin intron_end cove hmm 2_str scanner'
curr_chrom = ""
with open(args.input, 'r') as input_:
for line in input_:
gene = line.rstrip()
data = {k:g for k,g in zip(keys.split(), gene.split())}
if data.get('name') != curr_chrom:
curr_chrom = data.get('name')
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
try:
start_delta = find_delta(positions,
deltas,
int(data.get('trna_begin')))
end_delta = find_delta(positions,
deltas,
int(data.get('trna_end')))
data['trna_begin'] = int(data.get('trna_begin')) + start_delta
data['trna_end'] = int(data.get('trna_end')) + end_delta
out.write('%s\n' % \
'\t'.join([str(data.get(k)) for k in keys.split()]))
except IndexError:
pass
def smrna_table_txt(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = 'name chrom start end strand mature hairpin'
curr_chrom = ""
with open(args.input, 'r') as input_:
for line in input_:
gene = line.rstrip()
data = {k:g for k,g in zip(keys.split(), gene.split())}
if data.get('chrom') != curr_chrom:
curr_chrom = data.get('chrom')
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
try:
start_delta = find_delta(positions,
deltas,
int(data.get('start')))
end_delta = find_delta(positions,
deltas,
int(data.get('end')))
data['start'] = int(data.get('start')) + start_delta
data['end'] = int(data.get('end')) + end_delta
out.write('%s\n' % \
'\t'.join([str(data.get(k)) for k in keys.split()]))
except IndexError:
pass
def gtf(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = "seqname source feature start end score strand frame attribute"
curr_chrom = ""
with open(args.input, 'r') as input_:
for line in input_:
gene = line.rstrip()
data = gene.split('\t')
if data[0] != curr_chrom:
curr_chrom = data[0]
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
try:
start_delta = find_delta(positions,
deltas,
int(data[3]))
end_delta = find_delta(positions,
deltas,
int(data[4]))
data[3] = int(data[3]) + start_delta
data[4] = int(data[4]) + end_delta
out.write('%s\n' % \
'\t'.join([str(d) for d in data]))
except IndexError:
pass
def setUpClass(self):
self.alignment_file = os.path.join(os.path.dirname(__file__),
"../test_data/cast_ATAC_chr19.bam")
self.input_ = pysam.AlignmentFile(self.alignment_file, 'rb')
self.lines = random.sample([i for i in self.input_], 100)
self.mod_file = os.path.join(
os.path.dirname(__file__), "../test_data/CAST_to_BL6_chr19.mod")
self.logger = build_logger()
self.curr_chrom = 'chr19'
self.chrom_mods = build_transform(self.mod_file, self.logger)
self.positions, self.deltas = get_positions_and_deltas(self.chrom_mods,
self.curr_chrom,
self.logger)
self.output = (self.positions, self.deltas)
def smrna_12_bed(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = 'chrom chromStart chromEnd name score strand thickStart thickEnd itemRgb blockCount blockSizes blockStart'
curr_chrom = ""
with open(args.input, 'r') as input_:
for line in input_:
if not line.startswith('chrom'):
gene = line.rstrip()
data = {k:g for k,g in zip(keys.split(), gene.split('\t'))}
if data.get('chrom') != curr_chrom:
curr_chrom = data.get('chrom')
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
try:
c_start_delta = find_delta(positions,
deltas,
int(data.get('chromStart')))
c_end_delta = find_delta(positions,
deltas,
int(data.get('chromEnd')))
t_start_delta = find_delta(positions,
deltas,
int(data.get('thickStart')))
t_end_delta = find_delta(positions,
deltas,
int(data.get('thickEnd')))
b_tmp_data = find_delta(positions,
deltas,
(int(data.get('chromStart')) + \
int(data.get('blockStart'))))
b_start_delta = b_tmp_data - int(data.get('chromStart'))
data['chromStart'] = int(data.get('chromStart')) + c_start_delta
data['chromEnd'] = int(data.get('chromEnd')) + c_end_delta
data['thickStart'] = int(data.get('thickStart')) + t_start_delta
data['thickEnd'] = int(data.get('thickEnd')) + t_end_delta
data['blockStart'] = int(data.get('blockStart')) + b_start_delta
out.write('%s\n' % \
'\t'.join([str(data.get(k)) for k in keys.split()]))
except IndexError:
pass
def bam(args, logger):
if not args.chrom_sizes:
exit("Chrom sizes required for bam conversion")
chrom_mods = build_transform(args.mod, logger)
input_ = AlignmentFile(args.input, 'rb')
header = update_header(input_.header.as_dict(), args.chrom_sizes)
output = AlignmentFile(args.output, 'wb', header=header)
curr_chrom = ""
for line in input_:
if input_.references[line.reference_id] != curr_chrom:
curr_chrom = input_.references[line.reference_id]
positions, deltas = get_positions_and_deltas(chrom_mods,
curr_chrom,
logger)
try:
start_delta = find_delta(positions,
deltas,
int(line.reference_start))
# end_delta = find_delta(positions,
# deltas,
# int(line.reference_end))
mod_index = build_modification_index(positions,
deltas,
line,
start_delta)
# new_cigar = update_cigar(mod_index, line.cigar)
# if len(line.cigar) < len(new_cigar):
# line.cigar = new_cigar[-1*len(line.cigar):]
# else:
# line.cigar = new_cigar
line.reference_start = int(line.reference_start) + start_delta
output.write(line)
except IndexError:
print "IndexError: ", line
pass
except TypeError:
print "TypeError:", line
pass
def wig(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = 'dataValue'
curr_chrom = ""
chrom_pattern = compile('chrom=(\S+)\s')
start_pattern = compile('start=(\d+)')
with open(args.input, 'r') as input_:
for line in input_:
if not 'chrom' in line:
out.write(line)
# location = line.rstrip()
# data = {k:g for k,g in zip(keys.split(), location.split())}
# try:
# start_delta = find_delta(positions,
# deltas,
# int(data.get('chromStart')))
# data['chromStart'] = int(data.get('chromStart')) + start_delta
# out.write('%s\n' % \
# '\t'.join([str(data.get(k)) for k in keys.split()]))
# except IndexError:
# out.write('%s\n' % \
# '\t'.join([str(data.get(k)) for k in keys.split()]))
else:
chrom_search = chrom_pattern.search(line)
if chrom_search.groups()[0] != curr_chrom:
curr_chrom = chrom_search.groups()[0]
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
start_location = int(start_pattern.search(line).groups()[0])
start_delta = find_delta(positions, deltas, start_location)
new_line = sub('start=%d' % start_location,
'start=%d' % (start_location + start_delta),
line)
out.write(new_line)
def smrna_lib_fa(args, logger):
out = open(args.output, 'w')
chrom_mods = build_transform(args.mod, logger)
keys = 'chrom start end strand'
curr_chrom = ""
with open(args.input, 'r') as input_:
for line in input_:
if line.startswith('>'):
gene = line.rstrip()
gene_list = match('>(.*):(\d+)-(\d+)\((.*)\)', gene)
data = {k:g for k,g in zip(keys.split(), gene_list.groups())}
if data.get('chrom') != curr_chrom:
curr_chrom = data.get('chrom')
try:
positions, deltas = zip(*chrom_mods.get(curr_chrom))
logger.info("CONTIG: '%s'" % curr_chrom)
except TypeError:
logger.warn(
"CONTIG: '%s' is not in MOD File." % \
curr_chrom)
positions, deltas = (), ()
try:
start_delta = find_delta(positions,
deltas,
int(data.get('start')))
end_delta = find_delta(positions,
deltas,
int(data.get('end')))
data['start'] = int(data.get('start')) + start_delta
data['end'] = int(data.get('end')) + end_delta
out.write('>%s:%s-%s(%s)\n' % \
tuple([str(data.get(k)) for k in keys.split()]))
except IndexError:
pass
else:
out.write('%s' % line)
def atac(args, logger):
"""
"""
if not args.chrom_sizes:
exit("Chrom sizes required for bam conversion")
chrom_mods = build_transform(args.mod, logger)
input_ = AlignmentFile(args.input, 'rb')
header = update_header(input_.header.as_dict(), args.chrom_sizes)
output = AlignmentFile(args.output, 'wb', header=header)
curr_chrom = ""
for line in input_:
if input_.references[line.reference_id] != curr_chrom:
curr_chrom = input_.references[line.reference_id]
positions, deltas = get_positions_and_deltas(
chrom_mods, curr_chrom, logger)
# if line.is_reverse and (line.reference_length != len(line.seq)):
# print line
# print line.reference_length
# print line.cigar
# print len(line.seq)
# print len(line.get_reference_positions())
# try:
if not line.is_reverse:
start_delta = find_delta(positions, deltas,
int(line.reference_start))
line.reference_start = int(line.reference_start) + start_delta
else:
end_delta = find_delta(positions, deltas, int(line.reference_end))
mapped_end = int(line.reference_end) + end_delta
line.reference_start = mapped_end - len(
line.seq) # line.reference_length
output.write(line)
