def get_data( self, chrom, start, end, **kwargs ):
start, end = int(start), int(end)
chrom = str(chrom)
source = open( self.original_dataset.file_name )
index = Indexes( self.converted_dataset.file_name )
results = []
for start, end, offset in index.find(chrom, start, end):
source.seek(offset)
feature = source.readline().split()
payload = { 'uid': offset, 'start': start, 'end': end, 'name': feature[3] }
try:
payload['strand'] = feature[5]
except IndexError:
pass
if 'include_blocks' in kwargs:
try:
block_sizes = [ int(n) for n in feature[10].split(',') if n != '']
block_starts = [ int(n) for n in feature[11].split(',') if n != '' ]
blocks = zip(block_sizes, block_starts)
payload['blocks'] = [ (start + block[1], start + block[1] + block[0]) for block in blocks]
except IndexError:
pass
try:
payload['thick_start'] = int(feature[6])
payload['thick_end'] = int(feature[7])
except IndexError:
pass
results.append(payload)
return results
def main():
# Read options, args.
parser = optparse.OptionParser()
(options, args) = parser.parse_args()
in_file, out_file = args
# Do conversion.
index = Indexes()
reader = galaxy_utils.sequence.vcf.Reader( open( in_file ) )
offset = reader.metadata_len
for vcf_line in reader:
# VCF format provides a chrom and 1-based position for each variant.
# IntervalIndex expects 0-based coordinates.
index.add( vcf_line.chrom, vcf_line.pos - 1, vcf_line.pos, offset )
offset += len( vcf_line.raw_line )
index.write( open( out_file, "w" ) )
def get_data(self, chrom, start, end, **kwargs):
start, end = int(start), int(end)
chrom = str(chrom)
source = open(self.original_dataset.file_name)
index = Indexes(self.converted_dataset.file_name)
results = []
for start, end, offset in index.find(chrom, start, end):
source.seek(offset)
feature = source.readline().split()
payload = {
'uid': offset,
'start': start,
'end': end,
'name': feature[3]
}
try:
payload['strand'] = feature[5]
except IndexError:
pass
if 'include_blocks' in kwargs:
try:
block_sizes = [
int(n) for n in feature[10].split(',') if n != ''
]
block_starts = [
int(n) for n in feature[11].split(',') if n != ''
]
blocks = zip(block_sizes, block_starts)
payload['blocks'] = [(start + block[1],
start + block[1] + block[0])
for block in blocks]
except IndexError:
pass
try:
payload['thick_start'] = int(feature[6])
payload['thick_end'] = int(feature[7])
except IndexError:
pass
results.append(payload)
return results
def main():
# Read options, args.
parser = optparse.OptionParser()
(options, args) = parser.parse_args()
input_fname, output_fname = args
# Do conversion.
index = Indexes()
offset = 0
for line in open( input_fname, "r" ):
chrom, start = line.split()[ 0:2 ]
# Pileup format is 1-based.
start = int( start ) - 1
index.add( chrom, start, start + 1, offset )
offset += len( line )
index.write( open(output_fname, "w") )
def main():
# Arguments
input_fname, out_fname = sys.argv[1:]
# Do conversion.
index = Indexes()
offset = 0
reader_wrapper = GFFReaderWrapper( fileinput.FileInput( input_fname ), fix_strand=True )
for feature in list( reader_wrapper ):
# Add feature; index expects BED coordinates.
if isinstance( feature, GenomicInterval ):
convert_gff_coords_to_bed( feature )
index.add( feature.chrom, feature.start, feature.end, offset )
# Always increment offset, even if feature is not an interval and hence
# not included in the index.
offset += feature.raw_size
index.write( open(out_fname, "w") )
def main():
input_fname = sys.argv[1]
out_fname = sys.argv[2]
index = Indexes()
offset = 0
for line in open(input_fname, "r"):
feature = line.strip().split()
if not feature or feature[0].startswith("track") or feature[0].startswith("#"):
offset += len(line)
continue
chrom = feature[0]
chrom_start = int(feature[1])
chrom_end = int(feature[2])
index.add( chrom, chrom_start, chrom_end, offset )
offset += len(line)
index.write( open(out_fname, "w") )
def main():
# Read options, args.
parser = optparse.OptionParser()
parser.add_option('-c', '--chr-col', type='int', dest='chrom_col', default=1)
parser.add_option('-s', '--start-col', type='int', dest='start_col', default=2)
parser.add_option('-e', '--end-col', type='int', dest='end_col', default=3)
(options, args) = parser.parse_args()
input_fname, output_fname = args
# Make column indices 0-based.
options.chrom_col -= 1
options.start_col -= 1
options.end_col -= 1
# Do conversion.
index = Indexes()
offset = 0
for line in open(input_fname, "r"):
feature = line.strip().split()
if not feature or feature[0].startswith("track") or feature[0].startswith("#"):
offset += len(line)
continue
chrom = feature[options.chrom_col]
chrom_start = int(feature[options.start_col])
chrom_end = int(feature[options.end_col])
index.add(chrom, chrom_start, chrom_end, offset)
offset += len(line)
index.write(open(output_fname, "w"))
def main():
# Read options, args.
parser = optparse.OptionParser()
(options, args) = parser.parse_args()
in_file, out_file = args
# Do conversion.
index = Indexes()
reader = galaxy_utils.sequence.vcf.Reader(open(in_file))
offset = reader.metadata_len
for vcf_line in reader:
# VCF format provides a chrom and 1-based position for each variant.
# IntervalIndex expects 0-based coordinates.
index.add(vcf_line.chrom, vcf_line.pos - 1, vcf_line.pos, offset)
offset += len(vcf_line.raw_line)
index.write(open(out_file, "w"))
def main():
# Read options, args.
parser = optparse.OptionParser()
(options, args) = parser.parse_args()
input_fname, output_fname = args
# Do conversion.
index = Indexes()
offset = 0
for line in open(input_fname, "r"):
chrom, start = line.split()[0:2]
# Pileup format is 1-based.
start = int(start) - 1
index.add(chrom, start, start + 1, offset)
offset += len(line)
index.write(open(output_fname, "w"))
def main():
# Arguments
input_fname, out_fname = sys.argv[1:]
# Do conversion.
index = Indexes()
offset = 0
reader_wrapper = GFFReaderWrapper(fileinput.FileInput(input_fname),
fix_strand=True)
for feature in list(reader_wrapper):
# Add feature; index expects BED coordinates.
if isinstance(feature, GenomicInterval):
convert_gff_coords_to_bed(feature)
index.add(feature.chrom, feature.start, feature.end, offset)
# Always increment offset, even if feature is not an interval and hence
# not included in the index.
offset += feature.raw_size
index.write(open(out_fname, "wb"))
def main():
input_fname = sys.argv[1]
out_fname = sys.argv[2]
index = Indexes()
offset = 0
for line in open(input_fname, "r"):
feature = line.strip().split()
if not feature or feature[0].startswith(
"track") or feature[0].startswith("#"):
offset += len(line)
continue
chrom = feature[0]
chrom_start = int(feature[1])
chrom_end = int(feature[2])
index.add(chrom, chrom_start, chrom_end, offset)
offset += len(line)
index.write(open(out_fname, "w"))
