def anchor(args):
"""
%prog anchor map.bed markers.blast > anchored.bed
Anchor scaffolds based on map.
"""
from jcvi.formats.blast import bed
p = OptionParser(anchor.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
mapbed, blastfile = args
bedfile = bed([blastfile])
markersbed = Bed(bedfile)
markers = markersbed.order
mapbed = Bed(mapbed, sorted=False)
for b in mapbed:
m = b.accn
if m not in markers:
continue
i, mb = markers[m]
new_accn = "{0}:{1}-{2}".format(mb.seqid, mb.start, mb.end)
b.accn = new_accn
print b
def rename(args):
"""
%prog rename map markers.blast > renamed.map
Rename markers according to the new mapping locations.
"""
from jcvi.formats.blast import bed
p = OptionParser(rename.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
mstmap, blastfile = args
bedfile = bed([blastfile])
markersbed = Bed(bedfile)
markers = markersbed.order
data = MSTMap(mstmap)
header = data.header
header = [header[0]] + ["seqid", "start"] + header[1:]
print "\t".join(header)
for b in data:
m, geno = b.id, b.genotype
if m not in markers:
continue
i, mb = markers[m]
print "\t".join(str(x) for x in \
(m, mb.seqid, mb.start, "\t".join(list(geno))))
def breakpoint(args):
"""
%prog breakpoint blastfile bedfile
Identify breakpoints where collinearity ends. `blastfile` contains mapping
from markers (query) to scaffolds (subject). `bedfile` contains marker
locations in the related species.
"""
from jcvi.formats.blast import bed
from jcvi.utils.range import range_interleave
p = OptionParser(breakpoint.__doc__)
p.add_option("--xdist",
type="int",
default=20,
help="xdist (in related genome) cutoff [default: %default]")
p.add_option("--ydist",
type="int",
default=200000,
help="ydist (in current genome) cutoff [default: %default]")
p.add_option("-n",
type="int",
default=5,
help="number of markers in a block [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
blastfile, bedfile = args
order = Bed(bedfile).order
blastbedfile = bed([blastfile])
bbed = Bed(blastbedfile)
key = lambda x: x[1]
for scaffold, bs in bbed.sub_beds():
blocks = get_blocks(scaffold,
bs,
order,
xdist=opts.xdist,
ydist=opts.ydist,
N=opts.n)
sblocks = []
for block in blocks:
xx, yy = zip(*block)
sblocks.append((scaffold, min(yy), max(yy)))
iblocks = range_interleave(sblocks)
for ib in iblocks:
ch, start, end = ib
print "{0}\t{1}\t{2}".format(ch, start - 1, end)
def breakpoint(args):
"""
%prog breakpoint blastfile bedfile
Identify breakpoints where collinearity ends. `blastfile` contains mapping
from markers (query) to scaffolds (subject). `bedfile` contains marker
locations in the related species.
"""
from jcvi.formats.blast import bed
from jcvi.utils.range import range_interleave
p = OptionParser(breakpoint.__doc__)
p.add_option("--xdist", type="int", default=20,
help="xdist (in related genome) cutoff [default: %default]")
p.add_option("--ydist", type="int", default=200000,
help="ydist (in current genome) cutoff [default: %default]")
p.add_option("-n", type="int", default=5,
help="number of markers in a block [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
blastfile, bedfile = args
order = Bed(bedfile).order
blastbedfile = bed([blastfile])
bbed = Bed(blastbedfile)
key = lambda x: x[1]
for scaffold, bs in bbed.sub_beds():
blocks = get_blocks(scaffold, bs, order,
xdist=opts.xdist, ydist=opts.ydist, N=opts.n)
sblocks = []
for block in blocks:
xx, yy = zip(*block)
sblocks.append((scaffold, min(yy), max(yy)))
iblocks = range_interleave(sblocks)
for ib in iblocks:
ch, start, end = ib
print "{0}\t{1}\t{2}".format(ch, start - 1, end)