def run_bwa(target, ref_idx, tmp_fasta, out_dir, num_threads):
tmp_sort = tmpFileGet()
out_path = tmpFileGet(tmpDir=out_dir)
cmd = [['bwa', 'mem', '-t', num_threads, ref_idx, tmp_fasta],
['samtools', 'view', '-b', '-'],
['samtools', 'sort', '-O', 'bam', '-T', tmp_sort, '-']]
runProc(cmd, stdout=out_path)
def run_bwa(target, ref_idx, tmp_fasta, out_dir, num_threads):
tmp_sort = tmpFileGet()
out_path = tmpFileGet(tmpDir=out_dir)
cmd = [['bwa', 'mem', '-t', num_threads, ref_idx, tmp_fasta],
['samtools', 'view', '-b', '-'],
['samtools', 'sort', '-O', 'bam', '-T', tmp_sort, '-']]
runProc(cmd, stdout=out_path)
def extract_reads(bam, offset=50000):
tmp_reads = tmpFileGet(suffix='reads.fq')
tmp_shuf = tmpFileGet()
region_strs = ['{}:{}-{}'.format(chrom, start - offset, stop + offset) for chrom, start, stop, para in regions]
view_cmd = ['samtools', 'view', '-b', bam]
view_cmd.extend(region_strs)
cmd = [view_cmd,
['samtools', 'bamshuf', '-Ou', '-', tmp_shuf],
['samtools', 'bam2fq', '-']]
with open(tmp_reads, 'w') as tmp_paired_h:
runProc(cmd, stdout=tmp_reads)
return tmp_reads
def extract_fastq(target, genome, institute, tissue, reference, out_dir, experiment, bam_path, num_threads, ref_genome):
if is_paired_sequencing(bam_path):
fwd_fastq_path = tmpFileGet(prefix=experiment, suffix='fwd.fastq')
rev_fastq_path = tmpFileGet(prefix=experiment, suffix='rev.fastq')
cmd = ['samtools', 'fastq', '-1', fwd_fastq_path, '-2', rev_fastq_path, bam_path]
runProc(cmd)
run_paired_star(target, genome, institute, tissue, reference, out_dir, experiment, fwd_fastq_path,
rev_fastq_path, num_threads, ref_genome)
else:
fastq_path = tmpFileGet(prefix=experiment)
cmd = ['samtools', 'fastq', '-0', fastq_path, bam_path]
runProc(cmd)
run_single_star(target, genome, institute, tissue, reference, out_dir, experiment, fastq_path,
num_threads, ref_genome)
def extract_reads(bam, offset=50000):
tmp_reads = tmpFileGet(suffix='reads.fq')
tmp_shuf = tmpFileGet()
region_strs = [
'{}:{}-{}'.format(chrom, start - offset, stop + offset)
for chrom, start, stop, para in regions
]
view_cmd = ['samtools', 'view', '-b', bam]
view_cmd.extend(region_strs)
cmd = [
view_cmd, ['samtools', 'bamshuf', '-Ou', '-', tmp_shuf],
['samtools', 'bam2fq', '-']
]
with open(tmp_reads, 'w') as tmp_paired_h:
runProc(cmd, stdout=tmp_reads)
return tmp_reads
def __init__(self, dataFormat, liftFile, unmappedOutFile=None):
"""dataFormat should be 'genePred' or 'bedPlus=N'"""
self.dataFormat = dataFormat
self.liftFile = liftFile
self.unmappedOutFile = unmappedOutFile
self.unmappedOutFileTmp = None
if self.unmappedOutFile is None:
self.unmappedOutFileTmp = self.unmappedOutFile = fileOps.tmpFileGet("gencode.dropped")
def remap_reads(tmp_reads, index, out_bam):
sort_tmp = tmpFileGet()
cmd = [['bwa', 'mem', '-p', index, tmp_reads],
['samtools', 'view', '-b', '-'],
['samtools', 'sort', '-T', sort_tmp, '-O', 'bam', '-']]
with open(out_bam, 'w') as f_h:
runProc(cmd, stdout=f_h)
cmd = ['samtools', 'index', out_bam]
runProc(cmd)
def remap_reads(tmp_reads, index, out_bam):
sort_tmp = tmpFileGet()
cmd = [['bwa', 'mem', '-p', index, tmp_reads],
['samtools', 'view', '-b', '-'],
['samtools', 'sort', '-T', sort_tmp, '-O', 'bam', '-']]
with open(out_bam, 'w') as f_h:
runProc(cmd, stdout=f_h)
cmd = ['samtools', 'index', out_bam]
runProc(cmd)
def cat(target, args):
fofn = tmpFileGet()
files = [os.path.join(target.getGlobalTempDir(), x) for x in os.listdir(target.getGlobalTempDir())]
files = [x for x in files if os.path.isfile(x)]
assert len(files) > 0
with open(fofn, 'w') as outf:
for x in files:
outf.write(x + "\n")
cmd = ['samtools', 'merge', '-b', fofn, args.outBam]
runProc(cmd)
def main():
args = parse_args()
if args.outBam is None:
out_bam = tmpFileGet(suffix='merged.sorted.bam')
else:
out_bam = args.outBam
build_remapped_bam(args.inBam, args.consensusRef, out_bam)
wgs_results = pileup(out_bam, args.consensusVcf)
aln_size = get_aln_size(args.consensusRef)
plot_results(wgs_results, args.outPdf, aln_size)
if args.outBam is None:
os.remove(out_bam)
def main():
args = parse_args()
if args.outBam is None:
out_bam = tmpFileGet(suffix='merged.sorted.bam')
else:
out_bam = args.outBam
build_remapped_bam(args.inBam, args.consensusRef, out_bam)
wgs_results = pileup(out_bam, args.consensusVcf)
aln_size = get_aln_size(args.consensusRef)
plot_results(wgs_results, args.outPdf, aln_size)
if args.outBam is None:
os.remove(out_bam)
def cat(target, args):
fofn = tmpFileGet()
files = [
os.path.join(target.getGlobalTempDir(), x)
for x in os.listdir(target.getGlobalTempDir())
]
files = [x for x in files if os.path.isfile(x)]
assert len(files) > 0
with open(fofn, 'w') as outf:
for x in files:
outf.write(x + "\n")
cmd = ['samtools', 'merge', '-b', fofn, args.outBam]
runProc(cmd)