def run_smalt_paired(consensus_file, read1_fastq, read2_fastq, **kwarg):
index1 = '%s.sma' % consensus_file
command = 'rm -rf %s' % index1
if os.path.exists(index1):
return_code = command_runner.run_command(command)
index2 = '%s.smi' % consensus_file
command = 'rm -rf %s' % index2
if os.path.exists(index2):
return_code = command_runner.run_command(command)
index3 = '%s.fai' % consensus_file
command = 'rm -rf %s' % index3
if os.path.exists(index3):
return_code = command_runner.run_command(command)
command = "smalt index %s %s" % (consensus_file, consensus_file)
return_code = command_runner.run_command(command)
name = longest_common_substr_from_start(read1_fastq,
read2_fastq).rstrip('_')
read2_fastq_rev_comp = reverse_complement(read2_fastq)
sam_file = name + '.sam'
command = "smalt map -f samsoft -o %s %s %s %s" % (
sam_file, consensus_file, read1_fastq, read2_fastq_rev_comp)
return_code = command_runner.run_command(command)
return sam_file
def run_smalt_paired(consensus_file, read1_fastq, read2_fastq, **kwarg):
index1 = '%s.sma' % consensus_file
command = 'rm -rf %s' % index1
if os.path.exists(index1):
return_code = command_runner.run_command(command)
index2 = '%s.smi' % consensus_file
command = 'rm -rf %s' % index2
if os.path.exists(index2):
return_code = command_runner.run_command(command)
index3 = '%s.fai' % consensus_file
command = 'rm -rf %s' % index3
if os.path.exists(index3):
return_code = command_runner.run_command(command)
command = "smalt index %s %s" % (consensus_file, consensus_file)
return_code = command_runner.run_command(command)
name = longest_common_substr_from_start(read1_fastq, read2_fastq).rstrip('_')
read2_fastq_rev_comp = reverse_complement(read2_fastq)
sam_file = name + '.sam'
command = "smalt map -f samsoft -o %s %s %s %s" % (sam_file, consensus_file, read1_fastq, read2_fastq_rev_comp)
return_code = command_runner.run_command(command)
return sam_file
run_fine = False
fastq_file1=fastq_file1_unzip
files_and_dir.append(fastq_file1)
if fastq_file2 and fastq_file2.endswith('.gz'):
fastq_file2_unzip,ext = os.path.splitext(fastq_file2)
command = 'gunzip -c %s > %s'%(fastq_file2,fastq_file2_unzip)
return_code = command_runner.run_command(command)
if return_code is not 0:
run_fine = False
fastq_file2=fastq_file2_unzip
files_and_dir.append(fastq_file2)
#Get the sample name
if not sample_name:
if fastq_file2:
fastq_common = longest_common_substr_from_start(fastq_file1,fastq_file2)
#remove trailing underscore _ and get the base name
sample_name = os.path.basename(fastq_common.rstrip('_'))
else:
tmp,ext=os.path.splitext(os.path.basename(fastq_file1))
tmp=tmp.rstrip('1')
sample_name = os.path.basename(tmp.rstrip('_'))
BWA_bin=os.path.join(BWA_dir,'bwa')
# Check bwa version do not allow read group before version 0.9
if compare_version_number(get_bwa_version(BWA_bin), "0.5.9") <0:
logging.warning("Your version of bwa does not support the read group. Get version 0.5.9 or later to use this function.")
read_group_command=''
else:
if read_group:
read_group_command='-r "%s"'%(read_group)
run_fine = False
fastq_file1 = fastq_file1_unzip
files_and_dir.append(fastq_file1)
if fastq_file2 and fastq_file2.endswith('.gz'):
fastq_file2_unzip, ext = os.path.splitext(fastq_file2)
command = 'gunzip -c %s > %s' % (fastq_file2, fastq_file2_unzip)
return_code = command_runner.run_command(command)
if return_code is not 0:
run_fine = False
fastq_file2 = fastq_file2_unzip
files_and_dir.append(fastq_file2)
#Get the sample name
if not sample_name:
if fastq_file2:
fastq_common = longest_common_substr_from_start(
fastq_file1, fastq_file2)
#remove trailing underscore _ and get the base name
sample_name = os.path.basename(fastq_common.rstrip('_'))
else:
tmp, ext = os.path.splitext(os.path.basename(fastq_file1))
tmp = tmp.rstrip('1')
sample_name = os.path.basename(tmp.rstrip('_'))
BWA_bin = os.path.join(BWA_dir, 'bwa')
# Check bwa version do not allow read group before version 0.9
if compare_version_number(get_bwa_version(BWA_bin), "0.5.9") < 0:
logging.warning(
"Your version of bwa does not support the read group. Get version 0.5.9 or later to use this function."
)
read_group_command = ''
else:
open_corrected_sam.close()
return corrected_sam_file
def run_alignment(consensus_file, read1_fastq, read2_fastq, single_fastq, all_read_groups, snp_call=False):
try:
pipeline_param = utils_param.get_pipeline_parameters()
picard_dir = pipeline_param.get_picard_dir()
# GATK_dir=pipeline_param.get_gatk_dir()
samtools_dir = pipeline_param.get_samtools_dir()
except Config_file_error, e:
logging.exception('Config_file_error:')
sys.exit(1)
# Cleanup previous run if it exist
name = longest_common_substr_from_start(read1_fastq, read2_fastq).rstrip('_')
clean_up_prev_run(name)
file_to_remove = []
sam_file = run_smalt_paired(consensus_file, read1_fastq, read2_fastq)
file_to_remove.append(sam_file)
if os.path.exists(single_fastq):
sam_file_single = run_smalt_single(consensus_file, single_fastq)
file_to_remove.append(sam_file_single)
corrected_sam_file = correct_smalt_sam_file(sam_file, all_read_groups, sam_file_single)
else:
corrected_sam_file = correct_smalt_sam_file(sam_file, all_read_groups)
file_to_remove.append(corrected_sam_file)
name, ext = os.path.splitext(corrected_sam_file)
read1_fastq,
read2_fastq,
single_fastq,
all_read_groups,
snp_call=False):
try:
pipeline_param = utils_param.get_pipeline_parameters()
picard_dir = pipeline_param.get_picard_dir()
# GATK_dir=pipeline_param.get_gatk_dir()
samtools_dir = pipeline_param.get_samtools_dir()
except Config_file_error, e:
logging.exception('Config_file_error:')
sys.exit(1)
# Cleanup previous run if it exist
name = longest_common_substr_from_start(read1_fastq,
read2_fastq).rstrip('_')
clean_up_prev_run(name)
file_to_remove = []
sam_file = run_smalt_paired(consensus_file, read1_fastq, read2_fastq)
file_to_remove.append(sam_file)
if os.path.exists(single_fastq):
sam_file_single = run_smalt_single(consensus_file, single_fastq)
file_to_remove.append(sam_file_single)
corrected_sam_file = correct_smalt_sam_file(sam_file, all_read_groups,
sam_file_single)
else:
corrected_sam_file = correct_smalt_sam_file(sam_file, all_read_groups)
file_to_remove.append(corrected_sam_file)
name, ext = os.path.splitext(corrected_sam_file)
