def pairs(args):
"""
%prog pairs folder reference.fasta
Estimate insert size distribution. Compatible with a variety of aligners,
including CLC, BOWTIE and BWA.
"""
p = OptionParser(pairs.__doc__)
p.set_firstN()
p.set_mates()
p.set_aligner()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
cwd = os.getcwd()
aligner = opts.aligner
work = "-".join(("pairs", aligner))
mkdir(work)
if aligner == "clc":
from jcvi.apps.clc import align
from jcvi.formats.cas import pairs as ps
else:
from jcvi.formats.sam import pairs as ps
if aligner == "bowtie":
from jcvi.apps.bowtie import align
elif aligner == "bwa":
from jcvi.apps.bwa import align
folder, ref = args
ref = get_abs_path(ref)
messages = []
for p, prefix in iter_project(folder, 2):
samplefq = op.join(work, prefix + ".first.fastq")
first([str(opts.firstN)] + p + ["-o", samplefq])
os.chdir(work)
align_args = [ref, op.basename(samplefq)]
outfile, logfile = align(align_args)
bedfile, stats = ps([outfile, "--rclip={0}".format(opts.rclip)])
os.chdir(cwd)
median = stats.median
tag = "MP" if median > 1000 else "PE"
median = str(median)
pf, sf = median[:2], median[2:]
if sf and int(sf) != 0:
pf = str(int(pf) + 1) # Get the first two effective digits
lib = "{0}-{1}".format(tag, pf + "0" * len(sf))
for i, xp in enumerate(p):
suffix = "fastq.gz" if xp.endswith(".gz") else "fastq"
link = "{0}-{1}.{2}.{3}".format(lib, prefix.replace("-", ""), i + 1, suffix)
m = "\t".join(str(x) for x in (xp, link))
messages.append(m)
messages = "\n".join(messages)
write_file("f.meta", messages, tee=True)
def pairs(args):
"""
%prog pairs folder reference.fasta
Estimate insert size distribution. Compatible with a variety of aligners,
including BOWTIE and BWA.
"""
p = OptionParser(pairs.__doc__)
p.set_firstN()
p.set_mates()
p.set_aligner()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
cwd = os.getcwd()
aligner = opts.aligner
work = "-".join(("pairs", aligner))
mkdir(work)
from jcvi.formats.sam import pairs as ps
if aligner == "bowtie":
from jcvi.apps.bowtie import align
elif aligner == "bwa":
from jcvi.apps.bwa import align
folder, ref = args
ref = get_abs_path(ref)
messages = []
for p, prefix in iter_project(folder):
samplefq = []
for i in range(2):
samplefq.append(
op.join(work, prefix + "_{0}.first.fastq".format(i + 1)))
first([str(opts.firstN)] + [p[i]] + ["-o", samplefq[i]])
os.chdir(work)
align_args = [ref] + [op.basename(fq) for fq in samplefq]
outfile, logfile = align(align_args)
bedfile, stats = ps([outfile, "--rclip={0}".format(opts.rclip)])
os.chdir(cwd)
median = stats.median
tag = "MP" if median > 1000 else "PE"
median = str(median)
pf, sf = median[:2], median[2:]
if sf and int(sf) != 0:
pf = str(int(pf) + 1) # Get the first two effective digits
lib = "{0}-{1}".format(tag, pf + "0" * len(sf))
for i, xp in enumerate(p):
suffix = "fastq.gz" if xp.endswith(".gz") else "fastq"
link = "{0}-{1}.{2}.{3}".format(lib, prefix.replace("-", ""),
i + 1, suffix)
m = "\t".join(str(x) for x in (xp, link))
messages.append(m)
messages = "\n".join(messages)
write_file("f.meta", messages, tee=True)
def scaffold(args):
"""
%prog scaffold contigs.fasta MP*.fastq
Run SSPACE scaffolding.
"""
p = OptionParser(scaffold.__doc__)
p.set_aligner(aligner="bwa")
p.set_home("sspace")
p.set_cpus()
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
contigs = args[0]
libtxt = write_libraries(args[1:], aligner=opts.aligner)
# Requires getopts.pl which may be missing
download("http://mflib.org/xampp/perl/lib/getopts.pl")
cmd = "perl " + op.join(opts.sspace_home, "SSPACE_Standard_v3.0.pl")
cmd += " -l {0} -s {1} -T {2}".format(libtxt, contigs, opts.cpus)
runsh = "run.sh"
write_file(runsh, cmd)
def scaffold(args):
"""
%prog scaffold contigs.fasta MP*.fastq
Run SSPACE scaffolding.
"""
p = OptionParser(scaffold.__doc__)
p.set_aligner(aligner="bwa")
p.set_home("sspace")
p.set_cpus()
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
contigs = args[0]
libtxt = write_libraries(args[1:], aligner=opts.aligner)
# Requires getopts.pl which may be missing
download("http://web.vims.edu/bridge/bridge2/aw/lib/getopts.pl")
cmd = "perl " + op.join(opts.sspace_home, "SSPACE_Standard_v3.0.pl")
cmd += " -l {0} -s {1} -T {2}".format(libtxt, contigs, opts.cpus)
runsh = "run.sh"
write_file(runsh, cmd)
def prepare(args):
"""
%prog prepare barcode_key.csv reference.fasta
Prepare TASSEL pipeline.
"""
valid_enzymes = "ApeKI|ApoI|BamHI|EcoT22I|HinP1I|HpaII|MseI|MspI|" \
"NdeI|PasI|PstI|Sau3AI|SbfI|AsiSI-MspI|BssHII-MspI|" \
"FseI-MspI|PaeR7I-HhaI|PstI-ApeKI|PstI-EcoT22I|PstI-MspI" \
"PstI-TaqI|SalI-MspI|SbfI-MspI".split("|")
p = OptionParser(prepare.__doc__)
p.add_option("--enzyme",
default="ApeKI",
choices=valid_enzymes,
help="Restriction enzyme used [default: %default]")
p.set_home("tassel")
p.set_aligner(aligner="bwa")
p.set_cpus()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
barcode, reference = args
thome = opts.tassel_home
reference = get_abs_path(reference)
folders = ("fastq", "tagCounts", "mergedTagCounts", "topm", "tbt",
"mergedTBT", "hapmap", "hapmap/raw", "hapmap/mergedSNPs",
"hapmap/filt", "hapmap/bpec")
for f in folders:
mkdir(f)
# Build the pipeline
runsh = []
o = "-i fastq -k {0} -e {1} -o tagCounts".format(barcode, opts.enzyme)
cmd = run_pipeline(thome, "FastqToTagCountPlugin", o)
runsh.append(cmd)
o = "-i tagCounts -o mergedTagCounts/myMasterTags.cnt"
o += " -c 5 -t mergedTagCounts/myMasterTags.cnt.fq"
cmd = run_pipeline(thome, "MergeMultipleTagCountPlugin", o)
runsh.append(cmd)
runsh.append("cd mergedTagCounts")
cmd = "python -m jcvi.apps.{0} align --cpus {1}".\
format(opts.aligner, opts.cpus)
cmd += " {0} myMasterTags.cnt.fq".format(reference)
runsh.append(cmd)
runsh.append("cd ..")
o = "-i mergedTagCounts/*.sam -o topm/myMasterTags.topm"
cmd = run_pipeline(thome, "SAMConverterPlugin", o)
runsh.append(cmd)
o = "-i mergedTBT/myStudy.tbt.byte -y -m topm/myMasterTags.topm"
o += " -mUpd topm/myMasterTagsWithVariants.topm"
o += " -o hapmap/raw/myGBSGenos_chr+.hmp.txt"
o += " -mnF 0.8 -p myPedigreeFile.ped -mnMAF 0.02 -mnMAC 100000"
o += " -ref {0} -sC 1 -eC 10".format(reference)
cmd = run_pipeline(thome, "TagsToSNPByAlignmentPlugin", o)
runsh.append(cmd)
o = "-hmp hapmap/raw/myGBSGenos_chr+.hmp.txt"
o += " -o hapmap/mergedSNPs/myGBSGenos_mergedSNPs_chr+.hmp.txt"
o += " -misMat 0.1 -p myPedigreeFile.ped -callHets -sC 1 -eC 10"
cmd = run_pipeline(thome, "MergeDuplicateSNPsPlugin", o)
runsh.append(cmd)
o = "-hmp hapmap/mergedSNPs/myGBSGenos_mergedSNPs_chr+.hmp.txt"
o += " -o hapmap/filt/myGBSGenos_mergedSNPsFilt_chr+.hmp.txt"
o += " -mnTCov 0.01 -mnSCov 0.2 -mnMAF 0.01 -sC 1 -eC 10"
#o += "-hLD -mnR2 0.2 -mnBonP 0.005"
cmd = run_pipeline(thome, "GBSHapMapFiltersPlugin", o)
runsh.append(cmd)
runfile = "run.sh"
write_file(runfile, "\n".join(runsh), meta="run script")
def prepare(args):
"""
%prog prepare barcode_key.csv reference.fasta
Prepare TASSEL pipeline.
"""
valid_enzymes = "ApeKI|ApoI|BamHI|EcoT22I|HinP1I|HpaII|MseI|MspI|" \
"NdeI|PasI|PstI|Sau3AI|SbfI|AsiSI-MspI|BssHII-MspI|" \
"FseI-MspI|PaeR7I-HhaI|PstI-ApeKI|PstI-EcoT22I|PstI-MspI" \
"PstI-TaqI|SalI-MspI|SbfI-MspI".split("|")
p = OptionParser(prepare.__doc__)
p.add_option("--enzyme", default="ApeKI", choices=valid_enzymes,
help="Restriction enzyme used [default: %default]")
p.set_home("tassel")
p.set_aligner(aligner="bwa")
p.set_cpus()
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
barcode, reference = args
thome = opts.tassel_home
reference = get_abs_path(reference)
folders = ("fastq", "tagCounts", "mergedTagCounts", "topm",
"tbt", "mergedTBT", "hapmap", "hapmap/raw",
"hapmap/mergedSNPs", "hapmap/filt", "hapmap/bpec")
for f in folders:
mkdir(f)
# Build the pipeline
runsh = []
o = "-i fastq -k {0} -e {1} -o tagCounts".format(barcode, opts.enzyme)
cmd = run_pipeline(thome, "FastqToTagCountPlugin", o)
runsh.append(cmd)
o = "-i tagCounts -o mergedTagCounts/myMasterTags.cnt"
o += " -c 5 -t mergedTagCounts/myMasterTags.cnt.fq"
cmd = run_pipeline(thome, "MergeMultipleTagCountPlugin", o)
runsh.append(cmd)
runsh.append("cd mergedTagCounts")
cmd = "python -m jcvi.apps.{0} align --cpus {1}".\
format(opts.aligner, opts.cpus)
cmd += " {0} myMasterTags.cnt.fq".format(reference)
runsh.append(cmd)
runsh.append("cd ..")
o = "-i mergedTagCounts/*.sam -o topm/myMasterTags.topm"
cmd = run_pipeline(thome, "SAMConverterPlugin", o)
runsh.append(cmd)
o = "-i mergedTBT/myStudy.tbt.byte -y -m topm/myMasterTags.topm"
o += " -mUpd topm/myMasterTagsWithVariants.topm"
o += " -o hapmap/raw/myGBSGenos_chr+.hmp.txt"
o += " -mnF 0.8 -p myPedigreeFile.ped -mnMAF 0.02 -mnMAC 100000"
o += " -ref {0} -sC 1 -eC 10".format(reference)
cmd = run_pipeline(thome, "TagsToSNPByAlignmentPlugin", o)
runsh.append(cmd)
o = "-hmp hapmap/raw/myGBSGenos_chr+.hmp.txt"
o += " -o hapmap/mergedSNPs/myGBSGenos_mergedSNPs_chr+.hmp.txt"
o += " -misMat 0.1 -p myPedigreeFile.ped -callHets -sC 1 -eC 10"
cmd = run_pipeline(thome, "MergeDuplicateSNPsPlugin", o)
runsh.append(cmd)
o = "-hmp hapmap/mergedSNPs/myGBSGenos_mergedSNPs_chr+.hmp.txt"
o += " -o hapmap/filt/myGBSGenos_mergedSNPsFilt_chr+.hmp.txt"
o += " -mnTCov 0.01 -mnSCov 0.2 -mnMAF 0.01 -sC 1 -eC 10"
#o += "-hLD -mnR2 0.2 -mnBonP 0.005"
cmd = run_pipeline(thome, "GBSHapMapFiltersPlugin", o)
runsh.append(cmd)
runfile = "run.sh"
write_file(runfile, "\n".join(runsh))
