def blastplot(
ax,
blastfile,
qsizes,
ssizes,
qbed,
sbed,
style="dot",
sampleN=None,
baseticks=False,
insetLabels=False,
stripNames=False,
highlights=None,
):
assert style in DotStyles
fp = open(blastfile)
qorder = qbed.order if qbed else None
sorder = sbed.order if sbed else None
data = []
for row in fp:
b = BlastLine(row)
query, subject = b.query, b.subject
if stripNames:
query = query.rsplit(".", 1)[0]
subject = subject.rsplit(".", 1)[0]
if qorder:
if query not in qorder:
continue
qi, q = qorder[query]
query = q.seqid
qstart, qend = q.start, q.end
else:
qstart, qend = b.qstart, b.qstop
if sorder:
if subject not in sorder:
continue
si, s = sorder[subject]
subject = s.seqid
sstart, send = s.start, s.end
else:
sstart, send = b.sstart, b.sstop
qi = qsizes.get_position(query, qstart)
qj = qsizes.get_position(query, qend)
si = ssizes.get_position(subject, sstart)
sj = ssizes.get_position(subject, send)
if None in (qi, si):
continue
data.append(((qi, qj), (si, sj)))
if sampleN:
if len(data) > sampleN:
data = sample(data, sampleN)
if not data:
return logging.error("no blast data imported")
xsize, ysize = qsizes.totalsize, ssizes.totalsize
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
if style == "line":
for a, b in data:
ax.plot(a, b, "ro-", mfc="w", mec="r", ms=3)
else:
data = [(x[0], y[0]) for x, y in data]
x, y = zip(*data)
if style == "circle":
ax.plot(x, y, "mo", mfc="w", mec="m", ms=3)
elif style == "dot":
ax.scatter(x, y, s=3, lw=0)
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
xchr_labels, ychr_labels = [], []
ignore = True # tag to mark whether to plot chr name (skip small ones)
ignore_size_x = ignore_size_y = 0
# plot the chromosome breaks
logging.debug("xbreaks={0} ybreaks={1}".format(len(qsizes), len(ssizes)))
for (seqid, beg, end) in qsizes.get_breaks():
ignore = abs(end - beg) < ignore_size_x
if ignore:
continue
seqid = rename_seqid(seqid)
xchr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot([end, end], ylim, "-", lw=1, color="grey")
for (seqid, beg, end) in ssizes.get_breaks():
ignore = abs(end - beg) < ignore_size_y
if ignore:
continue
seqid = rename_seqid(seqid)
ychr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot(xlim, [end, end], "-", lw=1, color="grey")
# plot the chromosome labels
for label, pos, ignore in xchr_labels:
if not ignore:
if insetLabels:
ax.text(pos,
0,
label,
size=8,
ha="center",
va="top",
color="grey")
else:
pos = 0.1 + pos * 0.8 / xsize
root.text(
pos,
0.91,
label,
size=10,
ha="center",
va="bottom",
rotation=45,
color="grey",
)
# remember y labels are inverted
for label, pos, ignore in ychr_labels:
if not ignore:
if insetLabels:
continue
pos = 0.9 - pos * 0.8 / ysize
root.text(0.91, pos, label, size=10, va="center", color="grey")
# Highlight regions based on a list of BedLine
qhighlights = shighlights = None
if highlights:
if isinstance(highlights[0], BedLine):
shighlights = highlights
elif len(highlights) == 2:
qhighlights, shighlights = highlights
if qhighlights:
for hl in qhighlights:
hls = qsizes.get_position(hl.seqid, hl.start)
ax.add_patch(
Rectangle((hls, 0), hl.span, ysize, fc="r", alpha=0.2, lw=0))
if shighlights:
for hl in shighlights:
hls = ssizes.get_position(hl.seqid, hl.start)
ax.add_patch(
Rectangle((0, hls), xsize, hl.span, fc="r", alpha=0.2, lw=0))
if baseticks:
def increaseDensity(a, ratio=4):
assert len(a) > 1
stepsize = a[1] - a[0]
newstepsize = int(stepsize / ratio)
return np.arange(0, a[-1], newstepsize)
# Increase the density of the ticks
xticks = ax.get_xticks()
yticks = ax.get_yticks()
xticks = increaseDensity(xticks, ratio=2)
yticks = increaseDensity(yticks, ratio=2)
ax.set_xticks(xticks)
# Plot outward ticklines
for pos in xticks[1:]:
if pos > xsize:
continue
pos = 0.1 + pos * 0.8 / xsize
root.plot((pos, pos), (0.08, 0.1), "-", color="grey", lw=2)
for pos in yticks[1:]:
if pos > ysize:
continue
pos = 0.9 - pos * 0.8 / ysize
root.plot((0.09, 0.1), (pos, pos), "-", color="grey", lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_base_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color="gray",
size=10)
plt.setp(ax.get_yticklabels(), rotation=90)
def coverage(args):
"""
%prog coverage fastafile ctg bedfile1 bedfile2 ..
Plot coverage from a set of BED files that contain the read mappings. The
paired read span will be converted to a new bedfile that contain the happy
mates. ctg is the chr/scf/ctg that you want to plot the histogram on.
If the bedfiles already contain the clone spans, turn on --spans.
"""
from jcvi.formats.bed import mates, bedpe
p = OptionParser(coverage.__doc__)
p.add_option("--ymax",
default=None,
type="int",
help="Limit ymax [default: %default]")
p.add_option(
"--spans",
default=False,
action="store_true",
help="BED files already contain clone spans [default: %default]")
opts, args, iopts = p.set_image_options(args, figsize="8x5")
if len(args) < 3:
sys.exit(not p.print_help())
fastafile, ctg = args[0:2]
bedfiles = args[2:]
sizes = Sizes(fastafile)
size = sizes.mapping[ctg]
plt.figure(1, (iopts.w, iopts.h))
ax = plt.gca()
bins = 100 # smooth the curve
lines = []
legends = []
not_covered = []
yy = .9
for bedfile, c in zip(bedfiles, "rgbcky"):
if not opts.spans:
pf = bedfile.rsplit(".", 1)[0]
matesfile = pf + ".mates"
if need_update(bedfile, matesfile):
matesfile, matesbedfile = mates([bedfile, "--lib"])
bedspanfile = pf + ".spans.bed"
if need_update(matesfile, bedspanfile):
bedpefile, bedspanfile = bedpe(
[bedfile, "--span", "--mates={0}".format(matesfile)])
bedfile = bedspanfile
bedsum = Bed(bedfile).sum(seqid=ctg)
notcoveredbases = size - bedsum
legend = bedfile.split(".")[0]
msg = "{0}: {1} bp not covered".format(legend,
thousands(notcoveredbases))
not_covered.append(msg)
print >> sys.stderr, msg
ax.text(.1, yy, msg, color=c, size=9, transform=ax.transAxes)
yy -= .08
cov = Coverage(bedfile, sizes.filename)
x, y = cov.get_plot_data(ctg, bins=bins)
line, = ax.plot(x, y, '-', color=c, lw=2, alpha=.5)
lines.append(line)
legends.append(legend)
leg = ax.legend(lines, legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(.5)
ylabel = "Average depth per {0}Kb".format(size / bins / 1000)
ax.set_xlim(0, size)
ax.set_ylim(0, opts.ymax)
ax.set_xlabel(ctg)
ax.set_ylabel(ylabel)
set_human_base_axis(ax)
figname = "{0}.{1}.pdf".format(fastafile, ctg)
savefig(figname, dpi=iopts.dpi, iopts=iopts)
def qc(args):
"""
%prog qc prefix
Expects data files including:
1. `prefix.bedpe` draws Bezier curve between paired reads
2. `prefix.sizes` draws length of the contig/scaffold
3. `prefix.gaps.bed` mark the position of the gaps in sequence
4. `prefix.bed.coverage` plots the base coverage
5. `prefix.pairs.bed.coverage` plots the clone coverage
See assembly.coverage.posmap() for the generation of these files.
"""
from jcvi.graphics.glyph import Bezier
p = OptionParser(qc.__doc__)
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(p.print_help())
prefix, = args
scf = prefix
# All these files *must* be present in the current folder
bedpefile = prefix + ".bedpe"
fastafile = prefix + ".fasta"
sizesfile = prefix + ".sizes"
gapsbedfile = prefix + ".gaps.bed"
bedfile = prefix + ".bed"
bedpefile = prefix + ".bedpe"
pairsbedfile = prefix + ".pairs.bed"
sizes = Sizes(fastafile).mapping
size = sizes[scf]
fig = plt.figure(1, (8, 5))
root = fig.add_axes([0, 0, 1, 1])
# the scaffold
root.add_patch(Rectangle((.1, .15), .8, .03, fc='k'))
# basecoverage and matecoverage
ax = fig.add_axes([.1, .45, .8, .45])
bins = 200 # Smooth the curve
basecoverage = Coverage(bedfile, sizesfile)
matecoverage = Coverage(pairsbedfile, sizesfile)
x, y = basecoverage.get_plot_data(scf, bins=bins)
baseline, = ax.plot(x, y, 'g-')
x, y = matecoverage.get_plot_data(scf, bins=bins)
mateline, = ax.plot(x, y, 'r-')
legends = ("Base coverage", "Mate coverage")
leg = ax.legend((baseline, mateline), legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(.5)
ax.set_xlim(0, size)
# draw the read pairs
fp = open(bedpefile)
pairs = []
for row in fp:
scf, astart, aend, scf, bstart, bend, clonename = row.split()
astart, bstart = int(astart), int(bstart)
aend, bend = int(aend), int(bend)
start = min(astart, bstart) + 1
end = max(aend, bend)
pairs.append((start, end))
bpratio = .8 / size
cutoff = 1000 # inserts smaller than this are not plotted
# this convert from base => x-coordinate
pos = lambda x: (.1 + x * bpratio)
ypos = .15 + .03
for start, end in pairs:
dist = end - start
if dist < cutoff:
continue
dist = min(dist, 10000)
# 10Kb == .25 canvas height
height = .25 * dist / 10000
xstart = pos(start)
xend = pos(end)
p0 = (xstart, ypos)
p1 = (xstart, ypos + height)
p2 = (xend, ypos + height)
p3 = (xend, ypos)
Bezier(root, p0, p1, p2, p3)
# gaps on the scaffold
fp = open(gapsbedfile)
for row in fp:
b = BedLine(row)
start, end = b.start, b.end
xstart = pos(start)
xend = pos(end)
root.add_patch(Rectangle((xstart, .15), xend - xstart, .03, fc='w'))
root.text(.5, .1, scf, color='b', ha="center")
warn_msg = "Only the inserts > {0}bp are shown".format(cutoff)
root.text(.5, .1, scf, color='b', ha="center")
root.text(.5, .05, warn_msg, color='gray', ha="center")
# clean up and output
set_human_base_axis(ax)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
figname = prefix + ".pdf"
savefig(figname, dpi=300)
def coverage(args):
"""
%prog coverage fastafile ctg bedfile1 bedfile2 ..
Plot coverage from a set of BED files that contain the read mappings. The
paired read span will be converted to a new bedfile that contain the happy
mates. ctg is the chr/scf/ctg that you want to plot the histogram on.
If the bedfiles already contain the clone spans, turn on --spans.
"""
from jcvi.formats.bed import mates, bedpe
p = OptionParser(coverage.__doc__)
p.add_option("--ymax", default=None, type="int",
help="Limit ymax [default: %default]")
p.add_option("--spans", default=False, action="store_true",
help="BED files already contain clone spans [default: %default]")
opts, args, iopts = p.set_image_options(args, figsize="8x5")
if len(args) < 3:
sys.exit(not p.print_help())
fastafile, ctg = args[0:2]
bedfiles = args[2:]
sizes = Sizes(fastafile)
size = sizes.mapping[ctg]
plt.figure(1, (iopts.w, iopts.h))
ax = plt.gca()
bins = 100 # smooth the curve
lines = []
legends = []
not_covered = []
yy = .9
for bedfile, c in zip(bedfiles, "rgbcky"):
if not opts.spans:
pf = bedfile.rsplit(".", 1)[0]
matesfile = pf + ".mates"
if need_update(bedfile, matesfile):
matesfile, matesbedfile = mates([bedfile, "--lib"])
bedspanfile = pf + ".spans.bed"
if need_update(matesfile, bedspanfile):
bedpefile, bedspanfile = bedpe([bedfile, "--span",
"--mates={0}".format(matesfile)])
bedfile = bedspanfile
bedsum = Bed(bedfile).sum(seqid=ctg)
notcoveredbases = size - bedsum
legend = bedfile.split(".")[0]
msg = "{0}: {1} bp not covered".format(legend, thousands(notcoveredbases))
not_covered.append(msg)
print >> sys.stderr, msg
ax.text(.1, yy, msg, color=c, size=9, transform=ax.transAxes)
yy -= .08
cov = Coverage(bedfile, sizes.filename)
x, y = cov.get_plot_data(ctg, bins=bins)
line, = ax.plot(x, y, '-', color=c, lw=2, alpha=.5)
lines.append(line)
legends.append(legend)
leg = ax.legend(lines, legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(.5)
ylabel = "Average depth per {0}Kb".format(size / bins / 1000)
ax.set_xlim(0, size)
ax.set_ylim(0, opts.ymax)
ax.set_xlabel(ctg)
ax.set_ylabel(ylabel)
set_human_base_axis(ax)
figname ="{0}.{1}.pdf".format(fastafile, ctg)
savefig(figname, dpi=iopts.dpi, iopts=iopts)
def qc(args):
"""
%prog qc prefix
Expects data files including:
1. `prefix.bedpe` draws Bezier curve between paired reads
2. `prefix.sizes` draws length of the contig/scaffold
3. `prefix.gaps.bed` mark the position of the gaps in sequence
4. `prefix.bed.coverage` plots the base coverage
5. `prefix.pairs.bed.coverage` plots the clone coverage
See assembly.coverage.posmap() for the generation of these files.
"""
from jcvi.graphics.glyph import Bezier
p = OptionParser(qc.__doc__)
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(p.print_help())
prefix, = args
scf = prefix
# All these files *must* be present in the current folder
bedpefile = prefix + ".bedpe"
fastafile = prefix + ".fasta"
sizesfile = prefix + ".sizes"
gapsbedfile = prefix + ".gaps.bed"
bedfile = prefix + ".bed"
bedpefile = prefix + ".bedpe"
pairsbedfile = prefix + ".pairs.bed"
sizes = Sizes(fastafile).mapping
size = sizes[scf]
fig = plt.figure(1, (8, 5))
root = fig.add_axes([0, 0, 1, 1])
# the scaffold
root.add_patch(Rectangle((.1, .15), .8, .03, fc='k'))
# basecoverage and matecoverage
ax = fig.add_axes([.1, .45, .8, .45])
bins = 200 # Smooth the curve
basecoverage = Coverage(bedfile, sizesfile)
matecoverage = Coverage(pairsbedfile, sizesfile)
x, y = basecoverage.get_plot_data(scf, bins=bins)
baseline, = ax.plot(x, y, 'g-')
x, y = matecoverage.get_plot_data(scf, bins=bins)
mateline, = ax.plot(x, y, 'r-')
legends = ("Base coverage", "Mate coverage")
leg = ax.legend((baseline, mateline), legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(.5)
ax.set_xlim(0, size)
# draw the read pairs
fp = open(bedpefile)
pairs = []
for row in fp:
scf, astart, aend, scf, bstart, bend, clonename = row.split()
astart, bstart = int(astart), int(bstart)
aend, bend = int(aend), int(bend)
start = min(astart, bstart) + 1
end = max(aend, bend)
pairs.append((start, end))
bpratio = .8 / size
cutoff = 1000 # inserts smaller than this are not plotted
# this convert from base => x-coordinate
pos = lambda x: (.1 + x * bpratio)
ypos = .15 + .03
for start, end in pairs:
dist = end - start
if dist < cutoff:
continue
dist = min(dist, 10000)
# 10Kb == .25 canvas height
height = .25 * dist / 10000
xstart = pos(start)
xend = pos(end)
p0 = (xstart, ypos)
p1 = (xstart, ypos + height)
p2 = (xend, ypos + height)
p3 = (xend, ypos)
Bezier(root, p0, p1, p2, p3)
# gaps on the scaffold
fp = open(gapsbedfile)
for row in fp:
b = BedLine(row)
start, end = b.start, b.end
xstart = pos(start)
xend = pos(end)
root.add_patch(Rectangle((xstart, .15), xend - xstart, .03, fc='w'))
root.text(.5, .1, scf, color='b', ha="center")
warn_msg = "Only the inserts > {0}bp are shown".format(cutoff)
root.text(.5, .1, scf, color='b', ha="center")
root.text(.5, .05, warn_msg, color='gray', ha="center")
# clean up and output
set_human_base_axis(ax)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
figname = prefix + ".pdf"
savefig(figname, dpi=300)
def blastplot(ax, blastfile, qsizes, ssizes, qbed, sbed,
style="dot", proportional=False, sampleN=None,
baseticks=False, insetLabels=False, stripNames=False,
highlights=None):
assert style in DotStyles
fp = open(blastfile)
qorder = qbed.order if qbed else None
sorder = sbed.order if sbed else None
data = []
for row in fp:
b = BlastLine(row)
query, subject = b.query, b.subject
if stripNames:
query = query.rsplit(".", 1)[0]
subject = subject.rsplit(".", 1)[0]
if qorder:
if query not in qorder:
continue
qi, q = qorder[query]
query = q.seqid
qstart, qend = q.start, q.end
else:
qstart, qend = b.qstart, b.qstop
if sorder:
if subject not in sorder:
continue
si, s = sorder[subject]
subject = s.seqid
sstart, send = s.start, s.end
else:
sstart, send = b.sstart, b.sstop
qi = qsizes.get_position(query, qstart)
qj = qsizes.get_position(query, qend)
si = ssizes.get_position(subject, sstart)
sj = ssizes.get_position(subject, send)
if None in (qi, si):
continue
data.append(((qi, qj), (si, sj)))
if sampleN:
if len(data) > sampleN:
data = sample(data, sampleN)
if not data:
return logging.error("no blast data imported")
xsize, ysize = qsizes.totalsize, ssizes.totalsize
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
if style == "line":
for a, b in data:
ax.plot(a, b, 'ro-', mfc="w", mec="r", ms=3)
else:
data = [(x[0], y[0]) for x, y in data]
x, y = zip(*data)
if style == "circle":
ax.plot(x, y, 'mo', mfc="w", mec="m", ms=3)
elif style == "dot":
ax.scatter(x, y, s=3, lw=0)
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
xchr_labels, ychr_labels = [], []
ignore = True # tag to mark whether to plot chr name (skip small ones)
#ignore_size_x = xsize * .02
#ignore_size_y = ysize * .02
ignore_size_x = ignore_size_y = 0
# plot the chromosome breaks
logging.debug("xbreaks={0} ybreaks={1}".format(len(qsizes), len(ssizes)))
for (seqid, beg, end) in qsizes.get_breaks():
ignore = abs(end - beg) < ignore_size_x
if ignore:
continue
seqid = rename_seqid(seqid)
xchr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot([end, end], ylim, "-", lw=1, color="grey")
for (seqid, beg, end) in ssizes.get_breaks():
ignore = abs(end - beg) < ignore_size_y
if ignore:
continue
seqid = rename_seqid(seqid)
ychr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot(xlim, [end, end], "-", lw=1, color="grey")
# plot the chromosome labels
for label, pos, ignore in xchr_labels:
if not ignore:
if insetLabels:
ax.text(pos, 0, label, size=8, \
ha="center", va="top", color="grey")
else:
pos = .1 + pos * .8 / xsize
root.text(pos, .91, label, size=10,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, ignore in ychr_labels:
if not ignore:
if insetLabels:
continue
pos = .9 - pos * .8 / ysize
root.text(.91, pos, label, size=10,
va="center", color="grey")
# Highlight regions based on a list of BedLine
qhighlights = shighlights = None
if highlights:
if isinstance(highlights[0], BedLine):
shighlights = highlights
elif len(highlights) == 2:
qhighlights, shighlights = highlights
if qhighlights:
for hl in qhighlights:
hls = qsizes.get_position(hl.seqid, hl.start)
ax.add_patch(Rectangle((hls, 0), hl.span, ysize,\
fc="r", alpha=.2, lw=0))
if shighlights:
for hl in shighlights:
hls = ssizes.get_position(hl.seqid, hl.start)
ax.add_patch(Rectangle((0, hls), xsize, hl.span, \
fc="r", alpha=.2, lw=0))
if baseticks:
def increaseDensity(a, ratio=4):
assert len(a) > 1
stepsize = a[1] - a[0]
newstepsize = int(stepsize / ratio)
return np.arange(0, a[-1], newstepsize)
# Increase the density of the ticks
xticks = ax.get_xticks()
yticks = ax.get_yticks()
xticks = increaseDensity(xticks, ratio=2)
yticks = increaseDensity(yticks, ratio=2)
ax.set_xticks(xticks)
#ax.set_yticks(yticks)
# Plot outward ticklines
for pos in xticks[1:]:
if pos > xsize:
continue
pos = .1 + pos * .8 / xsize
root.plot((pos, pos), (.08, .1), '-', color="grey", lw=2)
for pos in yticks[1:]:
if pos > ysize:
continue
pos = .9 - pos * .8 / ysize
root.plot((.09, .1), (pos, pos), '-', color="grey", lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_base_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
plt.setp(ax.get_yticklabels(), rotation=90)