def trf(args):
"""
%prog trf outdir
Run TRF on FASTA files.
"""
from jcvi.apps.base import iglob
p = OptionParser(trf.__doc__)
p.add_option("--mismatch",
default=31,
type="int",
help="Mismatch and gap penalty")
p.add_option("--minscore",
default=MINSCORE,
type="int",
help="Minimum score to report")
p.add_option("--period",
default=6,
type="int",
help="Maximum period to report")
p.add_option("--telomeres",
default=False,
action="store_true",
help="Run telomere search: minscore=140 period=7")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
outdir, = args
mm = MakeManager()
if opts.telomeres:
opts.minscore, opts.period = 140, 7
params = "2 {0} {0} 80 10 {1} {2}".\
format(opts.mismatch, opts.minscore, opts.period).split()
bedfiles = []
for fastafile in natsorted(iglob(outdir, "*.fa,*.fasta")):
pf = op.basename(fastafile).split(".")[0]
cmd1 = "trf {0} {1} -d -h".format(fastafile, " ".join(params))
datfile = op.basename(fastafile) + "." + ".".join(params) + ".dat"
bedfile = "{0}.trf.bed".format(pf)
cmd2 = "cat {} | awk '($8 <= {} && $9 >= 0)'".format(datfile, READLEN)
cmd2 += " | sed 's/ /\\t/g'"
cmd2 += " | awk '{{print \"{0}\\t\" $0}}' > {1}".format(pf, bedfile)
mm.add(fastafile, datfile, cmd1)
mm.add(datfile, bedfile, cmd2)
bedfiles.append(bedfile)
bedfile = "trf.bed"
cmd = "cat {0} > {1}".format(" ".join(natsorted(bedfiles)), bedfile)
mm.add(bedfiles, bedfile, cmd)
mm.write()
def trf(args):
"""
%prog trf outdir
Run TRF on FASTA files.
"""
from jcvi.apps.base import iglob
p = OptionParser(trf.__doc__)
p.add_option("--mismatch", default=31, type="int",
help="Mismatch and gap penalty")
p.add_option("--minscore", default=MINSCORE, type="int",
help="Minimum score to report")
p.add_option("--period", default=6, type="int",
help="Maximum period to report")
p.add_option("--minlength", default=MINSCORE / 2, type="int",
help="Minimum length of repeat tract")
p.add_option("--telomeres", default=False, action="store_true",
help="Run telomere search: minscore=140 period=7")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
outdir, = args
minlength = opts.minlength
mm = MakeManager()
if opts.telomeres:
opts.minscore, opts.period = 140, 7
params = "2 {0} {0} 80 10 {1} {2}".\
format(opts.mismatch, opts.minscore, opts.period).split()
bedfiles = []
for fastafile in natsorted(iglob(outdir, "*.fa,*.fasta")):
pf = op.basename(fastafile).split(".")[0]
cmd1 = "trf {0} {1} -d -h".format(fastafile, " ".join(params))
datfile = op.basename(fastafile) + "." + ".".join(params) + ".dat"
bedfile = "{0}.trf.bed".format(pf)
cmd2 = "cat {} | awk '($8 >= {} && $8 <= {})'".\
format(datfile, minlength, READLEN - minlength)
cmd2 += " | sed 's/ /\\t/g'"
cmd2 += " | awk '{{print \"{0}\\t\" $0}}' > {1}".format(pf, bedfile)
mm.add(fastafile, datfile, cmd1)
mm.add(datfile, bedfile, cmd2)
bedfiles.append(bedfile)
bedfile = "trf.bed"
cmd = "cat {0} > {1}".format(" ".join(natsorted(bedfiles)), bedfile)
mm.add(bedfiles, bedfile, cmd)
mm.write()
def liftover(args):
"""
%prog liftover lobstr_v3.0.2_hg38_ref.bed hg38.upper.fa
LiftOver CODIS/Y-STR markers.
"""
p = OptionParser(liftover.__doc__)
p.add_option("--checkvalid",
default=False,
action="store_true",
help="Check minscore, period and length")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
refbed, fastafile = args
genome = pyfasta.Fasta(fastafile)
edits = []
fp = open(refbed)
for i, row in enumerate(fp):
s = STRLine(row)
seq = genome[s.seqid][s.start - 1:s.end].upper()
s.motif = get_motif(seq, len(s.motif))
s.fix_counts(seq)
if opts.checkvalid and not s.is_valid():
continue
edits.append(s)
if i % 10000 == 0:
print(i, "lines read", file=sys.stderr)
edits = natsorted(edits, key=lambda x: (x.seqid, x.start))
for e in edits:
print(str(e))
def liftover(args):
"""
%prog liftover lobstr_v3.0.2_hg38_ref.bed hg38.upper.fa
LiftOver CODIS/Y-STR markers.
"""
p = OptionParser(liftover.__doc__)
p.add_option("--checkvalid", default=False, action="store_true",
help="Check minscore, period and length")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
refbed, fastafile = args
genome = pyfasta.Fasta(fastafile)
edits = []
fp = open(refbed)
for i, row in enumerate(fp):
s = STRLine(row)
seq = genome[s.seqid][s.start - 1: s.end].upper()
s.motif = get_motif(seq, len(s.motif))
s.fix_counts(seq)
if opts.checkvalid and not s.is_valid():
continue
edits.append(s)
if i % 10000 == 0:
print >> sys.stderr, i, "lines read"
edits = natsorted(edits, key=lambda x: (x.seqid, x.start))
for e in edits:
print str(e)
def trf(args):
"""
%prog trf outdir
Run TRF on FASTA files.
"""
from jcvi.apps.base import iglob
cparams = "1 1 2 80 5 200 2000"
p = OptionParser(trf.__doc__)
p.add_option("--mismatch",
default=31,
type="int",
help="Mismatch and gap penalty")
p.add_option("--minscore",
default=MINSCORE,
type="int",
help="Minimum score to report")
p.add_option("--period",
default=6,
type="int",
help="Maximum period to report")
p.add_option("--lobstr",
default=False,
action="store_true",
help="Generate output for lobSTR")
p.add_option("--telomeres",
default=False,
action="store_true",
help="Run telomere search: minscore=140 period=7")
p.add_option("--centromeres",
default=False,
action="store_true",
help="Run centromere search: {}".format(cparams))
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
outdir, = args
minlength = opts.minscore / 2
mm = MakeManager()
if opts.telomeres:
opts.minscore, opts.period = 140, 7
params = "2 {0} {0} 80 10 {1} {2}".\
format(opts.mismatch, opts.minscore, opts.period).split()
if opts.centromeres:
params = cparams.split()
bedfiles = []
for fastafile in natsorted(iglob(outdir, "*.fa,*.fasta")):
pf = op.basename(fastafile).rsplit(".", 1)[0]
# Commands starting with trf ignores errors
cmd1 = "-trf {0} {1} -d -h".format(fastafile, " ".join(params))
datfile = op.basename(fastafile) + "." + ".".join(params) + ".dat"
bedfile = "{0}.trf.bed".format(pf)
cmd2 = "cat {} | grep -v ^Parameters".format(datfile)
if opts.lobstr:
cmd2 += " | awk '($8 >= {} && $8 <= {})'".\
format(minlength, READLEN - minlength)
else:
cmd2 += " | awk '($8 >= 0)'"
cmd2 += " | sed 's/ /\\t/g'"
cmd2 += " | awk '{{print \"{0}\\t\" $0}}' > {1}".format(pf, bedfile)
mm.add(fastafile, datfile, cmd1)
mm.add(datfile, bedfile, cmd2)
bedfiles.append(bedfile)
bedfile = "trf.bed"
cmd = "cat {0} > {1}".format(" ".join(natsorted(bedfiles)), bedfile)
mm.add(bedfiles, bedfile, cmd)
mm.write()
