def blat(args):
"""
%prog blat map1.txt ref.fasta
Make ALLMAPS input csv based on sequences. The tab-delimited txt file
include: name, LG, position, sequence.
"""
from jcvi.formats.base import is_number
from jcvi.formats.blast import best as blast_best, bed as blast_bed
from jcvi.apps.align import blat as blat_align
p = OptionParser(blat.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
maptxt, ref = args
pf = maptxt.rsplit(".", 1)[0]
register = {}
fastafile = pf + ".fasta"
fp = open(maptxt)
fw = open(fastafile, "w")
for row in fp:
name, lg, pos, seq = row.split()
if not is_number(pos):
continue
register[name] = (pf + '-' + lg, pos)
print(">{0}\n{1}\n".format(name, seq), file=fw)
fw.close()
blatfile = blat_align([ref, fastafile])
bestfile = blast_best([blatfile])
bedfile = blast_bed([bestfile])
b = Bed(bedfile).order
pf = ".".join(
(op.basename(maptxt).split(".")[0], op.basename(ref).split(".")[0]))
csvfile = pf + ".csv"
fp = open(maptxt)
fw = open(csvfile, "w")
for row in fp:
name, lg, pos, seq = row.split()
if name not in b:
continue
bbi, bb = b[name]
scaffold, scaffold_pos = bb.seqid, bb.start
print(",".join(str(x) for x in \
(scaffold, scaffold_pos, lg, pos)), file=fw)
fw.close()
def blat(args):
"""
%prog blat map1.txt ref.fasta
Make ALLMAPS input csv based on sequences. The tab-delimited txt file
include: name, LG, position, sequence.
"""
from jcvi.formats.base import is_number
from jcvi.formats.blast import best as blast_best, bed as blast_bed
from jcvi.apps.align import blat as blat_align
p = OptionParser(blat.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
maptxt, ref = args
pf = maptxt.rsplit(".", 1)[0]
register = {}
fastafile = pf + ".fasta"
fp = open(maptxt)
fw = open(fastafile, "w")
for row in fp:
name, lg, pos, seq = row.split()
if not is_number(pos):
continue
register[name] = (pf + '-' + lg, pos)
print(">{0}\n{1}\n".format(name, seq), file=fw)
fw.close()
blatfile = blat_align([ref, fastafile])
bestfile = blast_best([blatfile])
bedfile = blast_bed([bestfile])
b = Bed(bedfile).order
pf = ".".join((op.basename(maptxt).split(".")[0],
op.basename(ref).split(".")[0]))
csvfile = pf + ".csv"
fp = open(maptxt)
fw = open(csvfile, "w")
for row in fp:
name, lg, pos, seq = row.split()
if name not in b:
continue
bbi, bb = b[name]
scaffold, scaffold_pos = bb.seqid, bb.start
print(",".join(str(x) for x in \
(scaffold, scaffold_pos, lg, pos)), file=fw)
fw.close()
def synteny(args):
"""
%prog synteny mstmap.out novo.final.fasta reference.fasta
Plot MSTmap against reference genome.
"""
from jcvi.assembly.geneticmap import bed as geneticmap_bed
from jcvi.apps.align import blat
from jcvi.formats.blast import bed as blast_bed, best
p = OptionParser(synteny.__doc__)
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
mstmapout, novo, ref = args
pf = mstmapout.split(".")[0]
rf = ref.split(".")[0]
mstmapbed = geneticmap_bed([mstmapout])
cmd = "cut -d. -f1 {0}".format(mstmapbed)
tmpbed = mstmapbed + ".tmp"
sh(cmd, outfile=tmpbed)
os.rename(tmpbed, pf + ".bed")
cmd = "cut -f4 {0} | cut -d. -f1 | sort -u".format(mstmapbed)
idsfile = pf + ".ids"
sh(cmd, outfile=idsfile)
fastafile = pf + ".fasta"
cmd = "faSomeRecords {0} {1} {2}".format(novo, idsfile, fastafile)
sh(cmd)
blastfile = blat([ref, fastafile])
bestblastfile = best([blastfile])
blastbed = blast_bed([bestblastfile])
os.rename(blastbed, rf + ".bed")
anchorsfile = "{0}.{1}.anchors".format(pf, rf)
cmd = "paste {0} {0}".format(idsfile)
sh(cmd, outfile=anchorsfile)
def synteny(args):
"""
%prog synteny mstmap.out novo.final.fasta reference.fasta
Plot MSTmap against reference genome.
"""
from jcvi.assembly.geneticmap import bed as geneticmap_bed
from jcvi.apps.align import blat
from jcvi.formats.blast import bed as blast_bed, best
p = OptionParser(synteny.__doc__)
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
mstmapout, novo, ref = args
pf = mstmapout.split(".")[0]
rf = ref.split(".")[0]
mstmapbed = geneticmap_bed([mstmapout])
cmd = "cut -d. -f1 {0}".format(mstmapbed)
tmpbed = mstmapbed + ".tmp"
sh(cmd, outfile=tmpbed)
os.rename(tmpbed, pf + ".bed")
cmd = "cut -f4 {0} | cut -d. -f1 | sort -u".format(mstmapbed)
idsfile = pf + ".ids"
sh(cmd, outfile=idsfile)
fastafile = pf + ".fasta"
cmd = "faSomeRecords {0} {1} {2}".format(novo, idsfile, fastafile)
sh(cmd)
blastfile = blat([ref, fastafile])
bestblastfile = best([blastfile])
blastbed = blast_bed([bestblastfile])
os.rename(blastbed, rf + ".bed")
anchorsfile = "{0}.{1}.anchors".format(pf, rf)
cmd = "paste {0} {0}".format(idsfile)
sh(cmd, outfile=anchorsfile)
