def untar_index( # pylint: disable=too-many-locals,too-many-arguments
self, genome_file_name, genome_idx, bt2_1_file, bt2_2_file,
bt2_3_file, bt2_4_file, bt2_rev1_file, bt2_rev2_file):
"""
Extracts the Bowtie2 index files from the genome index tar file.
Parameters
----------
genome_file_name : str
Location string of the genome fasta file
genome_idx : str
Location of the Bowtie2 index file
bt2_1_file : str
Location of the <genome>.1.bt2 index file
bt2_2_file : str
Location of the <genome>.2.bt2 index file
bt2_3_file : str
Location of the <genome>.3.bt2 index file
bt2_4_file : str
Location of the <genome>.4.bt2 index file
bt2_rev1_file : str
Location of the <genome>.rev.1.bt2 index file
bt2_rev2_file : str
Location of the <genome>.rev.2.bt2 index file
Returns
-------
bool
Boolean indicating if the task was successful
"""
if "no-untar" in self.configuration and self.configuration[
"no-untar"] is True:
return True
gfl = genome_file_name.split("/")
au_handle = alignerUtils()
au_handle.bowtie2_untar_index(gfl[-1], genome_idx, bt2_1_file,
bt2_2_file, bt2_3_file, bt2_4_file,
bt2_rev1_file, bt2_rev2_file)
return True
def gem_indexer(self, genome_file, index_loc): # pylint: disable=unused-argument, no-self-use
"""
GEM Indexer
Parameters
----------
genome_file : str
Location of the genome assembly FASTA file
idx_loc : str
Location of the output index file
"""
try:
au_handle = alignerUtils()
au_handle.gem_index_genome(genome_file)
except (IOError, OSError) as msg:
logger.fatal("I/O error({0}): {1}".format(
msg.errno, msg.strerror))
return False
try:
command_line = ['pigz ', genome_file + ".gem"]
logger.info("args for pigz:" + " ".join(command_line))
process = subprocess.Popen(" ".join(command_line), shell=True)
process.wait()
except OSError:
logger.warn("OSERROR: pigz not installed, using gzip")
command_line = 'gzip ' + genome_file + ".gem"
args = shlex.split(command_line)
process = subprocess.Popen(args)
process.wait()
if genome_file + ".gem.gz" != index_loc:
with open(index_loc, "wb") as f_out:
with open(genome_file + ".gem.gz") as f_in:
f_out.write(f_in.read())
return True
def bwa_aligner_single( # pylint: disable=too-many-arguments, no-self-use
self, genome_file_loc, read_file_loc, bam_loc, genome_idx,
mem_params): # pylint: disable=unused-argument
"""
BWA MEM Aligner - Single Ended
Parameters
----------
genome_file_loc : str
Location of the genomic fasta
read_file_loc : str
Location of the FASTQ file
bam_loc : str
Location of the output aligned bam file
genome_idx : idx
Location of the BWA index file
aln_params : dict
Alignment parameters
Returns
-------
bam_loc : str
Location of the output file
"""
g_dir = genome_idx.split("/")
g_dir = "/".join(g_dir[:-1])
untar_idx = True
if "no-untar" in self.configuration and self.configuration[
"no-untar"] is True:
untar_idx = False
if untar_idx is True:
try:
tar = tarfile.open(genome_idx)
tar.extractall(path=g_dir)
tar.close()
except IOError:
return False
gfl = genome_file_loc.split("/")
genome_fa_ln = genome_idx.replace('.tar.gz', '/') + gfl[-1]
shutil.copy(genome_file_loc, genome_fa_ln)
if (os.path.isfile(genome_fa_ln) is False
or os.path.getsize(genome_fa_ln) == 0):
return False
if (os.path.isfile(read_file_loc) is False
or os.path.getsize(read_file_loc) == 0):
return False
out_bam = read_file_loc + '.out.bam'
au_handle = alignerUtils()
logger.info("BWA FINISHED: " + str(
au_handle.bwa_mem_align_reads(genome_fa_ln, out_bam, mem_params,
read_file_loc)))
try:
with open(bam_loc, "wb") as f_out:
with open(out_bam, "rb") as f_in:
f_out.write(f_in.read())
except IOError:
return False
os.remove(out_bam)
#shutil.rmtree(g_dir)
return True
def bowtie2_aligner_paired( # pylint: disable=too-many-arguments, no-self-use
self, genome_file_loc, read_file_loc1, read_file_loc2, bam_loc,
genome_idx, aln_params): # pylint: disable=unused-argument
"""
Bowtie2 Aligner - Paired End
Parameters
----------
genome_file_loc : str
Location of the genomic fasta
read_file_loc1 : str
Location of the FASTQ file
read_file_loc2 : str
Location of the FASTQ file
bam_loc : str
Location of the output aligned bam file
genome_idx : idx
Location of the Bowtie2 index file
aln_params : dict
Alignment parameters
Returns
-------
bam_loc : str
Location of the output file
"""
g_dir = genome_idx.split("/")
g_dir = "/".join(g_dir[:-1])
untar_idx = True
if "no-untar" in self.configuration and self.configuration[
"no-untar"] is True:
untar_idx = False
if untar_idx is True:
try:
tar = tarfile.open(genome_idx)
tar.extractall(path=g_dir)
tar.close()
except IOError:
return False
gfl = genome_file_loc.split("/")
genome_fa_ln = genome_idx.replace('.tar.gz', '/') + gfl[-1]
if os.path.isfile(genome_fa_ln) is False:
shutil.copy(genome_file_loc, genome_fa_ln)
out_bam = read_file_loc1 + '.out.bam'
au_handle = alignerUtils()
logger.info("BOWTIE2 FINISHED: " + str(
au_handle.bowtie2_align_reads(genome_fa_ln, out_bam, aln_params,
read_file_loc1, read_file_loc2)))
try:
with open(bam_loc, "wb") as f_out:
with open(out_bam, "rb") as f_in:
f_out.write(f_in.read())
except IOError:
return False
# shutil.rmtree(g_dir)
return True
def bowtie2_indexer(self, file_loc, index_loc): # pylint: disable=unused-argument, no-self-use
"""
Bowtie2 Indexer
Parameters
----------
file_loc : str
Location of the genome assembly FASTA file
idx_loc : str
Location of the output index file
"""
file_name = file_loc.split('/')
file_name[-1] = file_name[-1].replace('.fasta', '')
file_name[-1].replace('.fa', '')
file_name = "/".join(file_name)
au_handle = alignerUtils()
au_handle.bowtie_index_genome(file_loc, file_name)
try:
# tar.gz the index
logger.info("BOWTIE2 - index_loc", index_loc,
index_loc.replace('.tar.gz', ''))
idx_out_pregz = index_loc.replace('.tar.gz', '.tar')
index_dir = index_loc.replace('.tar.gz', '')
os.mkdir(index_dir)
idx_split = index_dir.split("/")
shutil.move(file_name + ".1.bt2", index_dir)
shutil.move(file_name + ".2.bt2", index_dir)
shutil.move(file_name + ".3.bt2", index_dir)
shutil.move(file_name + ".4.bt2", index_dir)
shutil.move(file_name + ".rev.1.bt2", index_dir)
shutil.move(file_name + ".rev.2.bt2", index_dir)
index_folder = idx_split[-1]
tar = tarfile.open(idx_out_pregz, "w")
tar.add(index_dir, arcname=index_folder)
tar.close()
except IOError as error:
logger.fatal("I/O error({0}): {1}".format(error.errno,
error.strerror))
return False
try:
command_line = 'pigz ' + idx_out_pregz
args = shlex.split(command_line)
process = subprocess.Popen(args)
process.wait()
except OSError:
logger.warn("OSERROR: pigz not installed, using gzip")
command_line = 'gzip ' + idx_out_pregz
args = shlex.split(command_line)
process = subprocess.Popen(args)
process.wait()
return True
def bwa_indexer(self, file_loc, idx_out): # pylint disable=no-self-use
"""
BWA Indexer
Parameters
----------
file_loc : str
Location of the genome assebly FASTA file
idx_out : str
Location of the output index file
Returns
-------
bool
"""
au_handler = alignerUtils()
amb_loc, ann_loc, bwt_loc, pac_loc, sa_loc = au_handler.bwa_index_genome(
file_loc)
try:
# tar.gz the index
logger.info("BWA - idx_out", idx_out,
idx_out.replace('.tar.gz', ''))
idx_out_pregz = idx_out.replace('.tar.gz', '.tar')
index_dir = idx_out.replace('.tar.gz', '')
os.mkdir(index_dir)
idx_split = index_dir.split("/")
shutil.move(amb_loc, index_dir)
shutil.move(ann_loc, index_dir)
shutil.move(bwt_loc, index_dir)
shutil.move(pac_loc, index_dir)
shutil.move(sa_loc, index_dir)
index_folder = idx_split[-1]
tar = tarfile.open(idx_out_pregz, "w")
tar.add(index_dir, arcname=index_folder)
tar.close()
except (IOError, OSError) as msg:
logger.fatal("I/O error({0}) - BWA INDEXER: {1}".format(
msg.errno, msg.strerror))
return False
try:
command_line = 'pigz ' + idx_out_pregz
args = shlex.split(command_line)
process = subprocess.Popen(args)
process.wait()
except OSError:
logger.warn("OSERROR: pigz not installed, using gzip")
command_line = 'gzip ' + idx_out_pregz
args = shlex.split(command_line)
process = subprocess.Popen(args)
process.wait()
shutil.rmtree(index_dir)
return True