LOG.info("Parsing VCF file...")
# not all chromosomes/seqid will be processed if not in vcf file
processed_seqids = OrderedDict()
for seqid in tb.contigs:
processed_seqids[seqid] = False
left = VCFtoChainInfo()
right = VCFtoChainInfo()
chain_info = {}
if diploid:
left.output_file = g2g_fu.prepend_before_extension(output_file, 'left')
right.output_file = g2g_fu.prepend_before_extension(
output_file, 'right')
chain_info['left'] = left
chain_info['right'] = right
g2g_fu.delete_file(left.output_file)
g2g_fu.delete_file(right.output_file)
else:
left.output_file = output_file
chain_info['left'] = left
g2g_fu.delete_file(left.output_file)
try:
all_chrom = [c for c in fasta_file.references]
def prepare_fasta_patch(filename_fasta, filename_output, bgzip=False, diploid=False):
"""
Initialize fasta_patch variables
:param filename_fasta:
:param filename_vcf:
:param strain:
:param filename_output:
:param bgzip:
:param diploid:
:return:
"""
filename_output = g2g_fu.check_file(filename_output, 'w')
output_file_dir = os.path.abspath(os.path.dirname(filename_output))
new_filename_output = filename_output
# let's figure out what our output names will be
if filename_output.lower().endswith('.gz'):
# strip off .gz
new_filename_output = filename_output[:-3]
if not filename_output.lower().endswith('.fa'):
raise G2GValueError("Expecting output filename extension to be either '.fa.gz' or '.fa'")
if diploid:
filename_output_l = g2g_fu.prepend_before_extension(new_filename_output, 'l')
filename_output_r = g2g_fu.prepend_before_extension(new_filename_output, 'r')
g2g_fu.delete_index_files(filename_output_l)
g2g_fu.delete_index_files(filename_output_r)
else:
filename_output_l = new_filename_output
filename_output_r = None
g2g_fu.delete_index_files(filename_output_l)
# at this point we are hoping for a .fa extension
# let's figure out our input and process accordingly
if filename_fasta.lower().endswith('.fa.gz'):
# decompress the fasta file if it is compressed
LOG.info("Copying and decompressing fasta file")
# copy file and preserve gz extension for bgzip -d to work
tmp_file_name = os.path.basename(filename_fasta) # something.gz
LOG.debug("tmp_file_name={0}".format(tmp_file_name))
tmp_fasta = os.path.join(output_file_dir, tmp_file_name) # /path/something.fa.gz
LOG.debug("tmp_fasta={0}".format(tmp_fasta))
LOG.debug("COPYING {0} to {1}".format(filename_fasta, tmp_fasta))
shutil.copy(filename_fasta, tmp_fasta) # cp /original/something.fa.gz /output/something.fa.gz
LOG.debug("DECOMPRESSING {0}".format(tmp_fasta))
g2g_fu.bgzip_decompress(tmp_fasta)
tmp_fasta = tmp_fasta[:-3] # /path/something.fa
LOG.debug("tmp_fasta={0}".format(tmp_fasta))
LOG.debug("Moving '{0}' to '{1}'...".format(tmp_fasta, filename_output_l))
shutil.move(tmp_fasta, filename_output_l)
elif filename_fasta.lower().endswith('.fa'):
LOG.debug("File is not compressed")
LOG.debug("COPYING {0} to {1}".format(filename_fasta, filename_output_l))
shutil.copy(filename_fasta, filename_output_l)
else:
raise G2GValueError("Expecting input filename extension to be either '.fa.gz' or '.fa'")
if diploid:
LOG.debug("Copying '{0}' to '{1}'...".format(filename_output_l, filename_output_r))
shutil.copy(filename_output_l, filename_output_r)
# build a temporary fasta index
pysam.FastaFile(filename_output_l)
return filename_output_l, filename_output_r
def prepare_fasta_patch(filename_fasta, filename_output, bgzip=False, diploid=False):
"""
Initialize fasta_patch variables
:param filename_fasta:
:param filename_vcf:
:param strain:
:param filename_output:
:param bgzip:
:param diploid:
:return:
"""
filename_output = g2g_fu.check_file(filename_output, "w")
output_file_dir = os.path.abspath(os.path.dirname(filename_output))
new_filename_output = filename_output
# let's figure out what our output names will be
if filename_output.lower().endswith(".gz"):
# strip off .gz
new_filename_output = filename_output[:-3]
if not filename_output.lower().endswith(".fa"):
raise G2GValueError("Expecting output filename extension to be either '.fa.gz' or '.fa'")
if diploid:
filename_output_l = g2g_fu.prepend_before_extension(new_filename_output, "l")
filename_output_r = g2g_fu.prepend_before_extension(new_filename_output, "r")
g2g_fu.delete_index_files(filename_output_l)
g2g_fu.delete_index_files(filename_output_r)
else:
filename_output_l = new_filename_output
filename_output_r = None
g2g_fu.delete_index_files(filename_output_l)
# at this point we are hoping for a .fa extension
# let's figure out our input and process accordingly
if filename_fasta.lower().endswith(".fa.gz"):
# decompress the fasta file if it is compressed
LOG.info("Copying and decompressing fasta file")
# copy file and preserve gz extension for bgzip -d to work
tmp_file_name = os.path.basename(filename_fasta) # something.gz
LOG.debug("tmp_file_name={0}".format(tmp_file_name))
tmp_fasta = os.path.join(output_file_dir, tmp_file_name) # /path/something.fa.gz
LOG.debug("tmp_fasta={0}".format(tmp_fasta))
LOG.debug("COPYING {0} to {1}".format(filename_fasta, tmp_fasta))
shutil.copy(filename_fasta, tmp_fasta) # cp /original/something.fa.gz /output/something.fa.gz
LOG.debug("DECOMPRESSING {0}".format(tmp_fasta))
g2g_fu.bgzip_decompress(tmp_fasta)
tmp_fasta = tmp_fasta[:-3] # /path/something.fa
LOG.debug("tmp_fasta={0}".format(tmp_fasta))
LOG.debug("Moving '{0}' to '{1}'...".format(tmp_fasta, filename_output_l))
shutil.move(tmp_fasta, filename_output_l)
elif filename_fasta.lower().endswith(".fa"):
LOG.debug("File is not compressed")
LOG.debug("COPYING {0} to {1}".format(filename_fasta, filename_output_l))
shutil.copy(filename_fasta, filename_output_l)
else:
raise G2GValueError("Expecting input filename extension to be either '.fa.gz' or '.fa'")
if diploid:
LOG.debug("Copying '{0}' to '{1}'...".format(filename_output_l, filename_output_r))
shutil.copy(filename_output_l, filename_output_r)
# build a temporary fasta index
pysam.FastaFile(filename_output_l)
return filename_output_l, filename_output_r
LOG.info("Parsing VCF file...")
# not all chromosomes/seqid will be processed if not in vcf file
processed_seqids = OrderedDict()
for seqid in tb.contigs:
processed_seqids[seqid] = False
left = VCFtoChainInfo()
right = VCFtoChainInfo()
chain_info = {}
if diploid:
left.output_file = g2g_fu.prepend_before_extension(output_file, 'left')
right.output_file = g2g_fu.prepend_before_extension(output_file, 'right')
chain_info['left'] = left
chain_info['right'] = right
g2g_fu.delete_file(left.output_file)
g2g_fu.delete_file(right.output_file)
else:
left.output_file = output_file
chain_info['left'] = left
g2g_fu.delete_file(left.output_file)
try:
all_chrom = [c for c in fasta_file.references]
all_chrom_length = [n for n in fasta_file.lengths]