def deploy_binary():
aws_pool.make_pool()
with misc.chdir("./bin"):
misc.call("python3 -m zipfile -c muta.zip muta")
aws_pool.pool.run(f"rm -rf {convention.remote_path}/muta")
aws_pool.pool.run("rm -rf /tmp/muta.zip")
for e in aws_pool.pool:
print(f"{e.host} upload muta.zip")
e.put("muta.zip", "/tmp/muta.zip")
aws_pool.pool.run(f"python3 -m zipfile -e /tmp/muta.zip {convention.remote_path}")
aws_pool.pool.run(f"cd {convention.remote_path}/muta && chmod +x muta-chain && chmod +x muta-keypair")
def GROSeqPL(args):
call("mkdir -p alignment conv_rpkm")
#if (os.path.isfile(args.file_1) and "L001" in args.file_1):
# read_concat(args)
fq_to_bam(args)
wig_convert(args)
homer(args)
convergent(args)
gmean_cal(args)
extract_rpkm(args)
call("rm -rf alignment/{output}.sam".format(**vars(args)))
def read_concat(args):
index_1 = args.file_1.find("L001")
cat_R1 = args.file_1.replace(args.file_1[index_1:], "L00*_R1*")
index_2 = args.file_2.find("L001")
cat_R2 = args.file_2.replace(args.file_2[index_2:], "L00*_R2*")
args.file_1 = args.file_1.replace("L001_", "")
args.file_2 = args.file_2.replace("L001_", "")
call("cat {0}> {1}".format(cat_R1, args.file_1))
call("cat {0}> {1}".format(cat_R2, args.file_2))
call("rm -f {0}".format(cat_R1[:-4]))
return
def homer(args):
if args.custom_genome:
call(
"/bin/homer/bin/makeTagDirectory conv_rpkm/{0} alignment/{0}.bam -genome {1}.fa"
.format(args.output, args.custom_genome))
else:
call(
"/bin/homer/bin/makeTagDirectory conv_rpkm/{0} alignment/{0}.bam -genome {1}.fa"
.format(args.output, args.genome))
# call("/bin/homer/bin/findPeaks conv_rpkm/{0} -style groseq -o auto -uniqmap /usr/local/homer/data/uniqmap/mm9-uniqmap".format(args.output))
call("/bin/homer/bin/findPeaks conv_rpkm/{0} -style groseq -o auto".format(
args.output))
return
def build_binary():
with misc.chdir(convention.muta_path):
misc.call("unset ROCKSDB_LIB_DIR && cargo build --release --example muta-chain")
with misc.chdir("./devtools/keypair"):
misc.call("cargo build --release")
misc.call("rm -rf ./bin/muta")
misc.call("mkdir -p ./bin/muta")
a = os.path.join(convention.muta_path, "target/release/examples/muta-chain")
misc.call(f"cp {a} ./bin/muta")
a = os.path.join(convention.muta_path, "target/release/muta-keypair")
misc.call(f"cp {a} ./bin/muta")
def parseFILE(args):
genomefile = args.genome
normdef = ''
if args.normalization == 'T':
normdef = ' -t 1000000000 '
if args.strandspecific == 'F':
prefix = args.bamfile.replace('.bam', '')
call('python2 /bin/bam2wig.py -i %s -o %s -s %s %s' %
(args.bamfile, prefix, genomefile, normdef))
call('rm -rf %s.wig' % prefix)
else:
prefix_pos = args.bamfile.replace('.bam', '.pos')
call('/bin/samtools view -@ %s -F 0x10 -hb -o %s.bam %s' %
(args.threads, prefix_pos, args.bamfile))
call('/bin/samtools sort -@ %s %s.bam -o %s.sort.bam' %
(args.threads, prefix_pos, prefix_pos))
call('mv %s.sort.bam %s.bam' % (prefix_pos, prefix_pos))
call('/bin/samtools index -@ %s %s.bam' % (args.threads, prefix_pos))
call('python2 /bin/bam2wig.py -i %s.bam -o %s -s %s %s' %
(prefix_pos, prefix_pos, genomefile, normdef))
# Need to add minus symbol in minus bw file
prefix_neg = args.bamfile.replace('.bam', '.neg')
call('/bin/samtools view -@ %s -f 0x10 -hb -o %s.bam %s' %
(args.threads, prefix_neg, args.bamfile))
call('/bin/samtools sort -@ %s %s.bam -o %s.sort.bam' %
(args.threads, prefix_neg, prefix_neg))
call('mv %s.sort.bam %s.bam' % (prefix_neg, prefix_neg))
call('/bin/samtools index -@ %s %s.bam' % (args.threads, prefix_neg))
call('python2 /bin/bam2wig.py -i %s.bam -o %s -s %s %s' %
(prefix_neg, prefix_neg, genomefile, normdef))
fout = open('%s.2.wig' % prefix_neg, 'w')
for line in open('%s.wig' % prefix_neg):
if line.startswith('variableStep'):
fout.write(line)
else:
fout.write('%s\t-%s\n' % (line.split()[0], line.split()[1]))
fout.close()
call('wigToBigWig -clip %s.2.wig %s %s.bw' %
(prefix_neg, genomefile, prefix_neg))
call('rm -rf %s.bam* %s.bam*' % (prefix_pos, prefix_neg))
call('rm -rf %s.wig %s.wig' % (prefix_pos, prefix_neg))
call('rm -rf %s.2.wig' % (prefix_neg))
def build_binary():
os.makedirs('./bin/telnet', exist_ok=True)
with misc.chdir('./telnet'):
misc.call('go build -o ../bin/telnet/ github.com/libraries/muta_aws_fabric/telnet/cmd/server')
misc.call('go build -o ../bin/telnet/ github.com/libraries/muta_aws_fabric/telnet/cmd/client')
def gmean_cal(args):
call(
"awk '{{OFS=\"\\t\"}}{{printf \"%s\\t%s\\t%s\\t%s_%s_%s\\t.\\t.\\n\", $1, $2, $3, $1, $2, $3}}' conv_rpkm/{output}.transcripts.convergent.bed > conv_rpkm/{output}.transcripts.convergent.6.bed"
.format(**vars(args)),
shell=True)
call(
"/bin/samtools view -@ {threads} alignment/{output}.pos.bam | gfold count -annf BED -ann conv_rpkm/{output}.transcripts.convergent.6.bed -tag stdin -o conv_rpkm/{output}.pos.cnt"
.format(**vars(args)),
shell=True)
call(
"/bin/samtools view -@ {threads} alignment/{output}.neg.bam | gfold count -annf BED -ann conv_rpkm/{output}.transcripts.convergent.6.bed -tag stdin -o conv_rpkm/{output}.neg.cnt"
.format(**vars(args)),
shell=True)
call(
"/bin/samtools view -@ {threads} alignment/{output}.pos.bam | gfold count -annf BED -s T -ann {annotation} -tag stdin -o conv_rpkm/{output}.pos3.cnt"
.format(**vars(args)),
shell=True)
call(
"/bin/samtools view -@ {threads} alignment/{output}.neg.bam | gfold count -annf BED -s T -ann {annotation} -tag stdin -o conv_rpkm/{output}.neg3.cnt"
.format(**vars(args)),
shell=True)
call(
"python2 /bin/COVT.gmean_cal.py conv_rpkm/{output} > conv_rpkm/{output}.gmean.cnt"
.format(**vars(args)),
shell=True)
call(
"sort -gr -k 4 conv_rpkm/{output}.gmean.cnt > conv_rpkm/{output}.gmean.cnt.sort"
.format(**vars(args)),
shell=True)
call(
"python2 /bin/Add.col.py conv_rpkm/{output}.gmean.cnt.sort > conv_rpkm/{output}.gmean.bed"
.format(**vars(args)),
shell=True)
return
def convergent(args):
call(
"grep -v \"#\" conv_rpkm/{0}/transcripts.txt | awk '{{OFS=\"\t\"}}{{print $2, $3, $4, $1, $6, $5}}' > conv_rpkm/{0}.transcript.bed"
.format(args.output),
shell=True)
call("/bin/bedtools/bedtools sort -i conv_rpkm/{0}.transcript.bed > see".
format(args.output),
shell=True)
call("mv see conv_rpkm/{0}.transcript.bed".format(args.output), shell=True)
call(
"grep -v \"+\" conv_rpkm/{0}.transcript.bed > conv_rpkm/{0}.transcripts.minus.bed"
.format(args.output),
shell=True)
call(
"grep \"+\" conv_rpkm/{0}.transcript.bed > conv_rpkm/{0}.transcripts.plus.bed"
.format(args.output),
shell=True)
call(
"/bin/bedtools/bedtools multiinter -i conv_rpkm/{0}.transcripts.plus.bed conv_rpkm/{0}.transcripts.minus.bed |grep \"1,2\" |awk \'{{OFS=\"\\t\"}}{{ if ($3-$2>100){{print $1, $2, $3}} }}\' > conv_rpkm/{0}.transcripts.convergent.bed"
.format(args.output),
shell=True)
return
def fq_to_bam(args):
if args.custom_genome:
# path, folder = os.path.split(args.custom_genome)
args.genome = args.custom_genome
if args.file_1:
call(
"/bin/bowtie2/bowtie2 -p {threads} -x {genome} -1 {file_1} -2 {file_2} --non-deterministic -S alignment/{output}.sam"
.format(**vars(args)))
else:
call(
"/bin/bowtie2/bowtie2 -p {threads} -x {genome} -U {file} --non-deterministic -S alignment/{output}.sam"
.format(**vars(args)))
call(
"/bin/samtools view -@ {threads} -bhS -F 4 alignment/{output}.sam -o alignment/{output}.bam"
.format(**vars(args)))
call(
"/bin/samtools sort -@ {threads} alignment/{output}.bam -o alignment/{output}.sort.bam"
.format(**vars(args)))
call("mv alignment/{output}.sort.bam alignment/{output}.bam".format(
**vars(args)))
call(
"/bin/samtools index -@ {threads} alignment/{output}.bam alignment/{output}.bam.bai"
.format(**vars(args)))
call(
"/bin/samtools stats -@ {threads} alignment/{output}.bam > alignment/{output}.stats.txt"
.format(**vars(args)),
shell=True)
return