def run_mutect_one_job(tempdir, vcf, reference, intervals, normal_bam,
tumour_bam):
commands = []
for i, interval in enumerate(intervals):
ival_temp_dir = os.path.join(tempdir, str(i))
helpers.makedirs(ival_temp_dir)
unfiltered_output = os.path.join(ival_temp_dir, 'mutect.vcf.gz')
cmd = mutect_run_command(reference, interval, normal_bam, tumour_bam,
unfiltered_output)
commands.append(cmd)
output = os.path.join(ival_temp_dir, 'mutect.vcf.gz')
cmd = mutect_filter_command(reference, unfiltered_output, output)
commands.append(cmd)
parallel_temp_dir = os.path.join(tempdir, 'gnu_parallel_temp')
helpers.run_in_gnu_parallel(commands, parallel_temp_dir)
vcf_files = [
os.path.join(tempdir, str(i), 'mutect.vcf.gz')
for i in range(len(intervals))
]
merge_tempdir = os.path.join(tempdir, 'mutect_merge')
helpers.makedirs(merge_tempdir)
merge_vcfs(vcf_files, vcf, merge_tempdir)
def run_samtools_germline_one_job(tempdir,
vcf,
reference,
intervals,
bam_file,
samtools_docker_image=None,
vcftools_docker_image=None):
commands = []
for i, interval in enumerate(intervals):
ival_temp_dir = os.path.join(tempdir, str(i))
helpers.makedirs(ival_temp_dir)
output = os.path.join(ival_temp_dir, 'germline.vcf.gz')
cmd = samtools_germline_command(output, reference, interval, bam_file)
commands.append(cmd)
parallel_temp_dir = os.path.join(tempdir, 'gnu_parallel_temp')
helpers.run_in_gnu_parallel(commands, parallel_temp_dir,
samtools_docker_image)
vcf_files = [
os.path.join(tempdir, str(i), 'germline.vcf.gz')
for i in range(len(intervals))
]
merge_tempdir = os.path.join(tempdir, 'germline_merge')
helpers.makedirs(merge_tempdir)
merge_vcfs(vcf_files,
vcf,
merge_tempdir,
docker_image=vcftools_docker_image)
def run_samtools_germline_one_job(tempdir, vcf, reference, intervals,
bam_file):
commands = []
for i, interval in enumerate(intervals):
ival_temp_dir = os.path.join(tempdir, str(i))
helpers.makedirs(ival_temp_dir)
output = os.path.join(ival_temp_dir, 'germline.vcf.gz')
cmd = samtools_germline_command(output, reference, interval, bam_file)
commands.append(cmd)
parallel_temp_dir = os.path.join(tempdir, 'gnu_parallel_temp')
helpers.run_in_gnu_parallel(commands, parallel_temp_dir)
vcf_files = [
os.path.join(tempdir, str(i), 'germline.vcf.gz')
for i in range(len(intervals))
]
merge_tempdir = os.path.join(tempdir, 'germline_merge')
helpers.makedirs(merge_tempdir)
temp_vcf = os.path.join(merge_tempdir, 'merged_rtg.vcf')
merge_vcfs(vcf_files, temp_vcf, merge_tempdir)
normal_id = bamutils.get_sample_id(bam_file)
vcfutils.update_germline_header_sample_ids(temp_vcf, vcf, normal_id)
def run_museq_one_job(tempdir,
museq_vcf,
reference,
intervals,
museq_params,
tumour_bam=None,
normal_bam=None,
titan_mode=False):
'''
Run museq script for all chromosomes and merge VCF files
:param tumour: path to tumour bam
:param normal: path to normal bam
:param out: path to the temporary output VCF file for the merged VCF files
:param log: path to the log file
:param config: path to the config YAML file
'''
commands = []
for i, interval in enumerate(intervals):
ival_temp_dir = os.path.join(tempdir, str(i))
helpers.makedirs(ival_temp_dir)
output = os.path.join(ival_temp_dir, 'museq.vcf')
log = os.path.join(ival_temp_dir, 'museq.log')
command = run_museq(output,
log,
reference,
interval,
museq_params,
ival_temp_dir,
tumour_bam=tumour_bam,
normal_bam=normal_bam,
return_cmd=True,
titan_mode=titan_mode)
commands.append(command)
parallel_temp_dir = os.path.join(tempdir, 'gnu_parallel_temp')
helpers.run_in_gnu_parallel(commands, parallel_temp_dir)
vcf_files = [
os.path.join(tempdir, str(i), 'museq.vcf')
for i in range(len(intervals))
]
merge_tempdir = os.path.join(tempdir, 'museq_merge')
helpers.makedirs(merge_tempdir)
temp_museq_vcf = os.path.join(merge_tempdir, 'temp_museq_merge.vcf')
merge_vcfs(vcf_files, temp_museq_vcf, merge_tempdir)
tumour_id = get_sample_id(tumour_bam)
normal_id = get_sample_id(normal_bam)
update_header_sample_ids(temp_museq_vcf, museq_vcf, tumour_id, normal_id)
def strelka_one_node(
normal_bam_file,
tumour_bam_file,
ref_genome_fasta_file,
indel_file,
snv_file,
tmp_dir,
regions,
known_sizes,
is_exome=False,
):
commands = []
chromosomes = [val.split('_')[0] for val in regions]
for chrom in chromosomes:
chrom_temp_dir = os.path.join(tmp_dir, 'chroms', str(chrom))
helpers.makedirs(chrom_temp_dir)
outfile = os.path.join(chrom_temp_dir, 'depth.txt')
cmd = [
'GetChromDepth',
'--align-file', normal_bam_file,
'--chrom', chrom,
'--output-file', outfile,
# '--ref', ref_genome,
]
commands.append(cmd)
parallel_temp_dir = os.path.join(tmp_dir, 'gnu_parallel_temp_depths')
helpers.run_in_gnu_parallel(commands, parallel_temp_dir)
depthfiles = [os.path.join(tmp_dir, 'chroms', str(chrom), 'depth.txt') for chrom in chromosomes]
depth_file = os.path.join(tmp_dir, 'chrom_depths.txt')
merge_chromosome_depths_plain(depthfiles, depth_file)
commands = []
for i, region in enumerate(regions):
ival_temp_dir = os.path.join(tmp_dir, 'intervals', str(i))
helpers.makedirs(ival_temp_dir)
indel_out = os.path.join(ival_temp_dir, 'strelka_indel.vcf')
snv_out = os.path.join(ival_temp_dir, 'strelka_snv.vcf')
stats_out = os.path.join(ival_temp_dir, 'stats.txt')
cmd = genome_segment_cmd(
depth_file,
normal_bam_file,
tumour_bam_file,
ref_genome_fasta_file,
indel_out,
snv_out,
stats_out,
region,
known_sizes,
is_exome=is_exome,
)
commands.append(cmd)
parallel_temp_dir = os.path.join(tmp_dir, 'gnu_parallel_temp')
helpers.run_in_gnu_parallel(commands, parallel_temp_dir)
indel_files = [os.path.join(tmp_dir, 'intervals', str(i), 'strelka_indel.vcf')
for i, region in enumerate(regions)]
merge_temp = os.path.join(tmp_dir, 'snv_merge')
snv_files = [os.path.join(tmp_dir, 'intervals', str(i), 'strelka_snv.vcf')
for i, region in enumerate(regions)]
temp_strelka_snv = os.path.join(tmp_dir, 'snv_merge', 'temp_strelka_merge_snv.vcf')
concatenate_vcf(snv_files, temp_strelka_snv, merge_temp)
temp_strelka_indel = os.path.join(tmp_dir, 'indel_merge' 'temp_strelka_merge_indel.vcf')
concatenate_vcf(indel_files, temp_strelka_indel, merge_temp)
tumour_id = get_sample_id(tumour_bam_file)
normal_id = get_sample_id(normal_bam_file)
update_header_sample_ids(temp_strelka_snv, snv_file, tumour_id, normal_id)
update_header_sample_ids(temp_strelka_indel, indel_file, tumour_id, normal_id)