def bam(args):
"""
%prog snp input.gsnap ref.fasta
Convert GSNAP output to BAM.
"""
from jcvi.formats.sizes import Sizes
from jcvi.formats.sam import index
p = OptionParser(bam.__doc__)
p.set_home("eddyyeh")
p.set_cpus()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
gsnapfile, fastafile = args
EYHOME = opts.eddyyeh_home
pf = gsnapfile.rsplit(".", 1)[0]
uniqsam = pf + ".unique.sam"
if need_update((gsnapfile, fastafile), uniqsam):
cmd = op.join(EYHOME, "gsnap2gff3.pl")
sizesfile = Sizes(fastafile).filename
cmd += " --format sam -i {0} -o {1}".format(gsnapfile, uniqsam)
cmd += " -u -l {0} -p {1}".format(sizesfile, opts.cpus)
sh(cmd)
index([uniqsam])
def bam(args):
"""
%prog snp input.gsnap ref.fasta
Convert GSNAP output to BAM.
"""
from jcvi.formats.sizes import Sizes
from jcvi.formats.sam import index
p = OptionParser(bam.__doc__)
p.set_home("eddyyeh")
p.set_cpus()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
gsnapfile, fastafile = args
EYHOME = opts.eddyyeh_home
pf = gsnapfile.rsplit(".", 1)[0]
uniqsam = pf + ".unique.sam"
if need_update((gsnapfile, fastafile), uniqsam):
cmd = op.join(EYHOME, "gsnap2gff3.pl")
sizesfile = Sizes(fastafile).filename
cmd += " --format sam -i {0} -o {1}".format(gsnapfile, uniqsam)
cmd += " -u -l {0} -p {1}".format(sizesfile, opts.cpus)
sh(cmd)
index([uniqsam])
def simulate(args):
"""
%prog simulate run_dir 1 300
Simulate BAMs with varying inserts with dwgsim. The above command will
simulate between 1 to 300 CAGs in the HD region, in a directory called
`run_dir`.
"""
p = OptionParser(simulate.__doc__)
p.add_option("--ref",
default="/Users/htang/projects/ref/hg38.upper.fa",
help="Reference genome sequence")
add_simulate_options(p)
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
rundir, startunits, endunits = args
startunits, endunits = int(startunits), int(endunits)
basecwd = os.getcwd()
mkdir(rundir)
os.chdir(rundir)
cwd = os.getcwd()
# Huntington region
pad_left, pad_right = 1000, 10000
chr, start, end = 'chr4', 3074877, 3074933
fasta = Fasta(opts.ref)
seq_left = fasta[chr][start - pad_left:start - 1]
seq_right = fasta[chr][end:end + pad_right]
motif = 'CAG'
reffastafile = "ref.fasta"
seq = str(fasta[chr][start - pad_left:end + pad_right])
make_fasta(seq, reffastafile, id=chr.upper())
# Write fake sequence
for units in range(startunits, endunits + 1):
pf = str(units)
mkdir(pf)
os.chdir(pf)
seq = str(seq_left) + motif * units + str(seq_right)
fastafile = pf + ".fasta"
make_fasta(seq, fastafile, id=chr.upper())
# Simulate reads on it
wgsim([
fastafile, "--depth={}".format(opts.depth),
"--readlen={}".format(opts.readlen),
"--distance={}".format(opts.distance), "--outfile={}".format(pf)
])
read1 = pf + ".bwa.read1.fastq"
read2 = pf + ".bwa.read2.fastq"
samfile, _ = align(["../{}".format(reffastafile), read1, read2])
indexed_samfile = index([samfile])
sh("mv {} ../{}.bam".format(indexed_samfile, pf))
sh("mv {}.bai ../{}.bam.bai".format(indexed_samfile, pf))
os.chdir(cwd)
shutil.rmtree(pf)
os.chdir(basecwd)