def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive [default: %default]")
p.add_option("--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive [default: %default]")
p.add_option("--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option("--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
peaks = not opts.nopeaks
N = int(N)
ks = KmerSpectrum(histfile)
ks.analyze(K=N)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1. / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".\
format(Genome_size / 1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
x, y = ks.get_xy(opts.vmin, opts.vmax)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
if peaks:
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, 'ko', lw=2, mec='k', mfc='w')
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
tc = "gray"
axt = ax.transAxes
ax.text(.95, .95, Total_Kmers_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .9, Kmer_coverage_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .85, Genome_size_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .8, Repetitive_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .75, SNPrate_msg, color=tc, transform=axt, ha="right")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title), color='r')
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel, color='r')
ax.set_ylabel(ylabel, color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def plot_breaks_and_labels(fig, root, ax, gx, gy, xsize, ysize,
qbreaks, sbreaks, sep=True, chrlw=.1,
sepcolor="g", minfont=5, stdpf=True):
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbreaks:
xsize_ratio = abs(end - beg) * .8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
if sep:
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbreaks:
ysize_ratio = abs(end - beg) * .8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize))
if sep:
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
for label, pos, fontsize in xchr_labels:
pos = .1 + pos * .8 / xsize
if fontsize >= minfont:
root.text(pos, .91, latex(label), size=fontsize,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, fontsize in ychr_labels:
pos = .9 - pos * .8 / ysize
if fontsize >= minfont:
root.text(.91, pos, latex(label), size=fontsize,
va="center", color="grey")
# Plot the frame
ax.plot(xlim, [0, 0], "-", lw=chrlw, color=sepcolor)
ax.plot(xlim, [ysize, ysize], "-", lw=chrlw, color=sepcolor)
ax.plot([0, 0], ylim, "-", lw=chrlw, color=sepcolor)
ax.plot([xsize, xsize], ylim, "-", lw=chrlw, color=sepcolor)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
return xlim, ylim
def dotplot(anchorfile, qbed, sbed, fig, root, ax, vmin=0, vmax=1,
is_self=False, synteny=False, cmap_text=None, genomenames=None,
sample_number=10000, ignore=.005, palette=None, chrlw=.01, title=None):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Normalize values to [%.1f, %.1f]" % (vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
value = vmin
if value > vmax:
value = vmax
if query not in qorder:
#logging.warning("ignore %s" % query)
continue
if subject not in sorder:
#logging.warning("ignore %s" % subject)
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = vmax - value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
# only show random subset, default to sample_number = 5000
if len(data) > sample_number:
logging.debug("Showing a random subset of %s data points (total %s) " \
"for clarity." % (sample_number, len(data)))
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
if not palette:
data.sort(key=lambda x: -x[2])
default_cm = cm.copper
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0, cmap=default_cm,
vmin=vmin, vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=default_cm, reverse=True)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
xchr_labels, ychr_labels = [], []
# Tag to mark whether to plot chr name (skip small ones)
ignore_size_x = ignore_size_y = 0
if ignore:
ignore_size_x = xsize * ignore
ignore_size_y = ysize * ignore
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
ignore = abs(end - beg) < ignore_size_x
seqid = seqid.split("_")[-1]
try:
seqid = int(seqid)
seqid = "c%d" % seqid
except:
pass
xchr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot([beg, beg], ylim, "g-", lw=chrlw)
for (seqid, beg, end) in sbed.get_breaks():
ignore = abs(end - beg) < ignore_size_y
seqid = seqid.split("_")[-1]
try:
seqid = int(seqid)
seqid = "c%d" % seqid
except:
pass
ychr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot(xlim, [beg, beg], "g-", lw=chrlw)
# plot the chromosome labels
for label, pos, ignore in xchr_labels:
pos = .1 + pos * .8 / xsize
if not ignore:
root.text(pos, .91, label,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, ignore in ychr_labels:
pos = .9 - pos * .8 / ysize
if not ignore:
root.text(.91, pos, label,
va="center", color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if title:
fig.suptitle(title, x=.05, y=.98, color="k")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def dotplot(anchorfile,
qbed,
sbed,
fig,
root,
ax,
vmin=0,
vmax=1,
is_self=False,
synteny=False,
cmap_text=None,
genomenames=None,
sample_number=10000,
minfont=5,
palette=None,
chrlw=.01,
title=None,
sepcolor="gainsboro"):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Normalize values to [%.1f, %.1f]" % (vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
value = vmin
if value > vmax:
value = vmax
if query not in qorder:
continue
if subject not in sorder:
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = vmax - value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
npairs = len(data)
# Only show random subset
if npairs > sample_number:
logging.debug("Showing a random subset of {0} data points (total {1}) " \
"for clarity.".format(sample_number, npairs))
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
if not palette:
data.sort(key=lambda x: -x[2])
default_cm = cm.copper
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x,
y,
c=c,
edgecolors="none",
s=2,
lw=0,
cmap=default_cm,
vmin=vmin,
vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=default_cm, reverse=True)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
xsize_ratio = abs(end - beg) * .8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbed.get_breaks():
ysize_ratio = abs(end - beg) * .8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
for label, pos, fontsize in xchr_labels:
pos = .1 + pos * .8 / xsize
if fontsize >= minfont:
root.text(pos,
.91,
latex(label),
size=fontsize,
ha="center",
va="bottom",
rotation=45,
color="grey")
# remember y labels are inverted
for label, pos, fontsize in ychr_labels:
pos = .9 - pos * .8 / ysize
if fontsize >= minfont:
root.text(.91,
pos,
latex(label),
size=fontsize,
va="center",
color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray',
size=10)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if not title:
title = "Inter-genomic comparison: {0} vs {1}".format(gx, gy)
if is_self:
title = "Intra-genomic comparison within {0}".format(gx)
npairs /= 2
title += " ({0} gene pairs)".format(thousands(npairs))
root.set_title(title, x=.5, y=.96, color="k")
logging.debug(title)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def multihistogram(args):
"""
%prog multihistogram *.histogram species
Plot the histogram based on a set of K-mer hisotograms. The method is based
on Star et al.'s method (Atlantic Cod genome paper).
"""
p = OptionParser(multihistogram.__doc__)
p.add_option("--kmin", default=15, type="int", help="Minimum K-mer size, inclusive")
p.add_option("--kmax", default=30, type="int", help="Maximum K-mer size, inclusive")
p.add_option("--vmin", default=2, type="int", help="Minimum value, inclusive")
p.add_option("--vmax", default=100, type="int", help="Maximum value, inclusive")
opts, args, iopts = p.set_image_options(args, figsize="10x5", dpi=300)
histfiles = args[:-1]
species = args[-1]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
A = fig.add_axes([0.08, 0.12, 0.38, 0.76])
B = fig.add_axes([0.58, 0.12, 0.38, 0.76])
lines = []
legends = []
genomesizes = []
for histfile in histfiles:
ks = KmerSpectrum(histfile)
x, y = ks.get_xy(opts.vmin, opts.vmax)
K = get_number(op.basename(histfile).split(".")[0].split("-")[-1])
if not opts.kmin <= K <= opts.kmax:
continue
line, = A.plot(x, y, "-", lw=1)
lines.append(line)
legends.append("K = {0}".format(K))
ks.analyze(K=K)
genomesizes.append((K, ks.genomesize / 1e6))
leg = A.legend(lines, legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(0.5)
title = "{0} genome K-mer histogram".format(species)
A.set_title(markup(title))
xlabel, ylabel = "Coverage (X)", "Counts"
A.set_xlabel(xlabel)
A.set_ylabel(ylabel)
set_human_axis(A)
title = "{0} genome size estimate".format(species)
B.set_title(markup(title))
x, y = zip(*genomesizes)
B.plot(x, y, "ko", mfc="w")
t = np.linspace(opts.kmin - 0.5, opts.kmax + 0.5, 100)
p = np.poly1d(np.polyfit(x, y, 2))
B.plot(t, p(t), "r:")
xlabel, ylabel = "K-mer size", "Estimated genome size (Mb)"
B.set_xlabel(xlabel)
B.set_ylabel(ylabel)
set_ticklabels_helvetica(B)
labels = ((0.04, 0.96, "A"), (0.54, 0.96, "B"))
panel_labels(root, labels)
normalize_axes(root)
imagename = species + ".multiK.pdf"
savefig(imagename, dpi=iopts.dpi, iopts=iopts)
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin", dest="vmin", default=1, type="int", help="minimum value, inclusive [default: %default]")
p.add_option("--vmax", dest="vmax", default=100, type="int", help="maximum value, inclusive [default: %default]")
p.add_option(
"--pdf", default=False, action="store_true", help="Print PDF instead of ASCII plot [default: %default]"
)
p.add_option("--coverage", default=0, type="int", help="Kmer coverage [default: auto]")
p.add_option("--nopeaks", default=False, action="store_true", help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
peaks = not opts.nopeaks
N = int(N)
if histfile.rsplit(".", 1)[-1] in ("mcdat", "mcidx"):
logging.debug("CA kmer index found")
histfile = meryl([histfile])
ks = KmerSpectrum(histfile)
ks.analyze(K=N)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1.0 / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size / 1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
x, y = ks.get_xy(opts.vmin, opts.vmax)
title = "{0} {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, "g-", lw=2, alpha=0.5)
ax = plt.gca()
if peaks:
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
if tcounts:
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, "ko", lw=2, mec="k", mfc="w")
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
messages = [Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg, Repetitive_msg, SNPrate_msg]
write_messages(ax, messages)
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title))
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin", dest="vmin", default=1, type="int",
help="minimum value, inclusive [default: %default]")
p.add_option("--vmax", dest="vmax", default=100, type="int",
help="maximum value, inclusive [default: %default]")
p.add_option("--pdf", default=False, action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
p.add_option("--coverage", default=0, type="int",
help="Kmer coverage [default: auto]")
p.add_option("--nopeaks", default=False, action="store_true",
help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
N = int(N)
KMERYL, KSOAP, KALLPATHS = range(3)
kformats = ("Meryl", "Soap", "AllPaths")
kformat = KMERYL
ascii = not opts.pdf
peaks = not opts.nopeaks
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
for row in fp:
if row.startswith("# 1:"):
kformat = KALLPATHS
break
if len(row.split()) == 1:
kformat = KSOAP
break
fp.seek(0)
logging.debug("Guessed format: {0}".format(kformats[kformat]))
data = []
for rowno, row in enumerate(fp):
if row[0] == '#':
continue
if kformat == KSOAP:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = Kcounts
data.append((K, counts))
covmax = 1000000
ks = KmerSpectrum(data)
ks.analyze(K=N, covmax=covmax)
Total_Kmers = int(totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1. / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".\
format(Genome_size / 1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() \
if opts.vmin <= a <= opts.vmax)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in counts if x in t]
x, y = zip(*tcounts)
plt.plot(x, y, 'ko', lw=2, mec='k', mfc='w')
tcounts = dict(tcounts)
if peaks:
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
tc = "gray"
axt = ax.transAxes
ax.text(.95, .95, Total_Kmers_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .9, Kmer_coverage_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .85, Genome_size_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .8, Repetitive_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .75, SNPrate_msg, color=tc, transform=axt, ha="right")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title), color='r')
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel, color='r')
ax.set_ylabel(ylabel, color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def plot_breaks_and_labels(
fig,
root,
ax,
gx,
gy,
xsize,
ysize,
qbreaks,
sbreaks,
sep=True,
chrlw=0.1,
sepcolor="g",
minfont=5,
stdpf=True,
chpf=True,
):
xlim = (0, 47724.0) # hard-coding xlim maximum
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbreaks:
xsize_ratio = abs(end - beg) * 0.8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
if chpf:
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
if sep:
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbreaks:
ysize_ratio = abs(end - beg) * 0.8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
if chpf:
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize*0.85))
if sep:
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
xchr_labels = [('chr\ 1', 1997.5, 12), ('chr\ 2', 5944.5, 12), ('chr\ 3', 9014.0, 12), ('chr\ 4', 11351.5, 12), ('chr\ 5', 13639.0, 12), ('chr\ 6', 17657.5, 12), ('chr\ 7', 22329.0, 12), ('chr\ 8', 25466.0, 12), ('chr\ 9', 28092.0, 12), ('chr\ 10', 31361.5, 12), ('chr\ 11', 34457.0, 12), ('chr\ 12', 37234.0, 12), ('chr\ 13', 41112.5, 12), ('chr\ 14', 43851.0, 12), ('chr\ 15', 45258.5, 12), ('scf\ 16', 46740.5, 12), ('scf\ 458', 47724.0, 12)]
for label, pos, fontsize in xchr_labels:
#print(xchr_labels)
pos = 0.1 + pos * 0.8 / xsize
if fontsize >= minfont:
root.text(
pos,
0.91,
latex(label),
size=fontsize*0.85,
ha="center",
va="bottom",
rotation=45,
color="black",
)
# remember y labels are inverted
ychr_labels = [('chr\ 1', 2672.0, 10.2), ('chr\ 2', 7532.0, 10.2), ('chr\ 3', 12035.0, 10.2), ('chr\ 4', 16228.0, 10.2), ('chr\ 5', 19784.5, 10.2), ('chr\ 6', 23211.0, 10.2), ('chr\ 7', 26612.5, 10.2), ('chr\ 8', 29773.0, 10.2), ('chr\ 9', 32518.0, 10.2), ('chr\ 10', 35004.5, 10.2), ('chr\ 11', 37760.0, 10.2), ('chr\ 12', 40635.5, 10.2), ('ChrSy', 42048.0, 0), ('ChrUn', 42140.5, 0)]
for label, pos, fontsize in ychr_labels:
#print(ychr_labels)
pos = 0.9 - pos * 0.8 / ysize
if fontsize >= minfont:
root.text(0.91, pos, latex(label), size=fontsize*0.85, va="center", color="black")
# Plot the frame
ax.plot(xlim, [0, 0], "-", lw=chrlw, color=sepcolor)
ax.plot(xlim, [ysize, ysize], "-", lw=chrlw, color=sepcolor)
ax.plot([0, 0], ylim, "-", lw=chrlw, color=sepcolor)
ax.plot([xsize, xsize], ylim, "-", lw=chrlw, color=sepcolor)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# The axis labels have been hardcoded (vs. gx gy as in original) so taht we can get the species names spelled out in italics, rather than the BED file name.
ax.set_xlabel('$\it{Zizania\ palustris}$', size=16)
ax.set_ylabel('$\it{Oryza\ sativa}$', size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(), color="black", size=10)
return xlim, ylim
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive [default: %default]")
p.add_option("--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive [default: %default]")
p.add_option("--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option("--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
N = int(N)
KMERYL, KSOAP, KALLPATHS = range(3)
kformats = ("Meryl", "Soap", "AllPaths")
kformat = KMERYL
ascii = not opts.pdf
peaks = not opts.nopeaks
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
for row in fp:
if row.startswith("# 1:"):
kformat = KALLPATHS
break
if len(row.split()) == 1:
kformat = KSOAP
break
fp.seek(0)
logging.debug("Guessed format: {0}".format(kformats[kformat]))
data = []
for rowno, row in enumerate(fp):
if row[0] == '#':
continue
if kformat == KSOAP:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = Kcounts
data.append((K, counts))
covmax = 1000000
ks = KmerSpectrum(data)
ks.analyze(K=N, covmax=covmax)
Total_Kmers = int(totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = Total_Kmers * 1. / Kmer_coverage / 1e6
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() \
if opts.vmin <= a <= opts.vmax)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
return asciiplot(x, y, title=title)
plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in counts if x in t]
x, y = zip(*tcounts)
plt.plot(x, y, 'ko', lw=2, mec='k', mfc='w')
tcounts = dict(tcounts)
if peaks:
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
tc = "gray"
axt = ax.transAxes
ax.text(.95, .95, Total_Kmers_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .9, Kmer_coverage_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .85, Genome_size_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .8, Repetitive_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .75, SNPrate_msg, color=tc, transform=axt, ha="right")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title), color='r')
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel, color='r')
ax.set_ylabel(ylabel, color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic.
"""
p = OptionParser(histogram.__doc__)
p.add_option(
"--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive",
)
p.add_option(
"--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive",
)
p.add_option(
"--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot",
)
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option(
"--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks",
)
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
peaks = not opts.nopeaks
N = int(N)
if histfile.rsplit(".", 1)[-1] in ("mcdat", "mcidx"):
logging.debug("CA kmer index found")
histfile = merylhistogram(histfile)
ks = KmerSpectrum(histfile)
ks.analyze(K=N)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1.0 / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size /
1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print(msg, file=sys.stderr)
x, y = ks.get_xy(opts.vmin, opts.vmax)
title = "{0} {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, "g-", lw=2, alpha=0.5)
ax = plt.gca()
if peaks:
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
if tcounts:
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, "ko", lw=2, mec="k", mfc="w")
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
messages = [
Total_Kmers_msg,
Kmer_coverage_msg,
Genome_size_msg,
Repetitive_msg,
SNPrate_msg,
]
write_messages(ax, messages)
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title))
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--pdf", default=False, action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
soap = False
for row in fp:
if len(row.split()) == 1:
soap = True
break
fp.seek(0)
for rowno, row in enumerate(fp):
if soap:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = counts
history = ["drop"]
for a, b in pairwise(sorted(hist.items())):
Ka, ca = a
Kb, cb = b
if ca <= cb:
status = "rise"
else:
status = "drop"
if history[-1] != status:
history.append(status)
if history == ["drop", "rise", "drop"]:
break
Total_Kmers = int(totalKmers)
Kmer_coverage = Ka
Genome_size = Total_Kmers * 1. / Ka / 1e6
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size)
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() if a <= 100)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
return asciiplot(x, y, title=title)
fig = plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
ax.text(.5, .9, _(Total_Kmers_msg),
ha="center", color='b', transform=ax.transAxes)
ax.text(.5, .8, _(Kmer_coverage_msg),
ha="center", color='b', transform=ax.transAxes)
ax.text(.5, .7, _(Genome_size_msg),
ha="center", color='b', transform=ax.transAxes)
ax.set_title(_(title), color='r')
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(_(xlabel), color='r')
ax.set_ylabel(_(ylabel), color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
plt.savefig(imagename, dpi=100)
print >> sys.stderr, "Image saved to `{0}`.".format(imagename)
def draw_depth(
root,
ax,
bed,
chrinfo={},
defaultcolor="k",
sepcolor="w",
ylim=100,
title=None,
subtitle=None,
):
""" Draw depth plot on the given axes, using data from bed
Args:
root (matplotlib.Axes): Canvas axes
ax (matplotlib.Axes): Axes to plot data on
bed (Bed): Bed data from mosdepth
chrinfo (ChrInfoFile): seqid => color, new name
defaultcolor (str): matplotlib-compatible color for data points
sepcolor (str): matplotlib-compatible color for chromosome breaks
ylim (int): Upper limit of the y-axis (depth)
title (str): Title of the figure, to the right of the axis
subtitle (str): Subtitle of the figure, just below title
"""
if chrinfo is None:
chrinfo = {}
sizes = bed.max_bp_in_chr
seqids = chrinfo.keys() if chrinfo else sizes.keys()
starts = {}
ends = {}
label_positions = []
start = 0
for seqid in seqids:
starts[seqid] = start
end = start + sizes[seqid]
ends[seqid] = end
label_positions.append((seqid, (start + end) / 2))
start = end
xsize = end
# Extract plotting data
data = []
data_by_seqid = defaultdict(list)
for b in bed:
seqid = b.seqid
if seqid not in starts:
continue
# chr01A 2000000 3000000 113.00
x = starts[seqid] + (b.start + b.end) / 2
y = float(b.accn)
c = chrinfo[seqid].color if seqid in chrinfo else "k"
data.append((x, y, c))
data_by_seqid[seqid].append(y)
x, y, c = zip(*data)
ax.scatter(
x,
y,
c=c,
edgecolors="none",
s=8,
lw=0,
)
logging.debug("Obtained {} data points with depth data".format(len(data)))
# Per seqid median
medians = {}
for seqid, values in data_by_seqid.items():
c = chrinfo[seqid].color if seqid in chrinfo else defaultcolor
seqid_start = starts[seqid]
seqid_end = ends[seqid]
seqid_median = np.median(values)
medians[seqid] = seqid_median
ax.plot(
(seqid_start, seqid_end),
(seqid_median, seqid_median),
"-",
lw=4,
color=c,
alpha=0.5,
)
# vertical lines for all the breaks
for pos in starts.values():
ax.plot((pos, pos), (0, ylim), "-", lw=1, color=sepcolor)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
median_depth_y = 0.88
chr_label_y = 0.08
for seqid, position in label_positions:
xpos = 0.1 + position * 0.8 / xsize
c = chrinfo[seqid].color if seqid in chrinfo else defaultcolor
newseqid = chrinfo[seqid].new_name if seqid in chrinfo else seqid
root.text(xpos,
chr_label_y,
newseqid,
color=c,
ha="center",
va="center",
rotation=20)
seqid_median = medians[seqid]
root.text(
xpos,
median_depth_y,
str(int(seqid_median)),
color=c,
ha="center",
va="center",
)
if title:
root.text(
0.95,
0.5,
markup(title),
color="darkslategray",
ha="center",
va="center",
size=15,
)
if subtitle:
root.text(
0.95,
0.375,
markup(subtitle),
color="darkslategray",
ha="center",
va="center",
size=15,
)
ax.set_xticks([])
ax.set_xlim(0, xsize)
ax.set_ylim(0, ylim)
ax.set_ylabel("Depth")
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color="gray",
size=10)
normalize_axes(root)
def dotplot(anchorfile, qbed, sbed, image_name, vmin, vmax, iopts,
is_self=False, synteny=False, cmap_text=None):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Normalize values to [%.1f, %.1f]" % (vmin, vmax))
for row in fp:
atoms = row.split()
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
value = vmin
if value > vmax:
value = vmax
if query not in qorder:
#logging.warning("ignore %s" % query)
continue
if subject not in sorder:
#logging.warning("ignore %s" % subject)
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = vmax - value
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1]) # the whole canvas
ax = fig.add_axes([.1, .1, .8, .8]) # the dot plot
sample_number = 5000 # only show random subset
if len(data) > sample_number:
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
data.sort(key=lambda x: -x[2])
default_cm = cm.copper
x, y, c = zip(*data)
ax.scatter(x, y, c=c, s=2, lw=0, cmap=default_cm,
vmin=vmin, vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=default_cm, reverse=True)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
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 * .005
ignore_size_y = ysize * .005
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
ignore = abs(end - beg) < ignore_size_x
seqid = seqid.split("_")[-1]
try:
seqid = int(seqid)
seqid = "c%d" % seqid
except:
pass
xchr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot([beg, beg], ylim, "g-", lw=1)
for (seqid, beg, end) in sbed.get_breaks():
ignore = abs(end - beg) < ignore_size_y
seqid = seqid.split("_")[-1]
try:
seqid = int(seqid)
seqid = "c%d" % seqid
except:
pass
ychr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot(xlim, [beg, beg], "g-", lw=1)
# plot the chromosome labels
for label, pos, ignore in xchr_labels:
pos = .1 + pos * .8 / xsize
if not ignore:
root.text(pos, .91, label,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, ignore in ychr_labels:
pos = .9 - pos * .8 / ysize
if not ignore:
root.text(.91, pos, label,
va="center", color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
to_ax_label = lambda fname: _(op.basename(fname).split(".")[0])
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
def multihistogram(args):
"""
%prog multihistogram *.histogram species
Plot the histogram based on a set of K-mer hisotograms. The method is based
on Star et al.'s method (Atlantic Cod genome paper).
"""
p = OptionParser(multihistogram.__doc__)
p.add_option("--kmin",
default=15,
type="int",
help="Minimum K-mer size, inclusive")
p.add_option("--kmax",
default=30,
type="int",
help="Maximum K-mer size, inclusive")
p.add_option("--vmin",
default=2,
type="int",
help="Minimum value, inclusive")
p.add_option("--vmax",
default=100,
type="int",
help="Maximum value, inclusive")
opts, args, iopts = p.set_image_options(args, figsize="10x5", dpi=300)
if len(args) < 1:
sys.exit(not p.print_help())
histfiles = args[:-1]
species = args[-1]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
A = fig.add_axes([0.08, 0.12, 0.38, 0.76])
B = fig.add_axes([0.58, 0.12, 0.38, 0.76])
lines = []
legends = []
genomesizes = []
for histfile in histfiles:
ks = KmerSpectrum(histfile)
x, y = ks.get_xy(opts.vmin, opts.vmax)
K = get_number(op.basename(histfile).split(".")[0].split("-")[-1])
if not opts.kmin <= K <= opts.kmax:
continue
(line, ) = A.plot(x, y, "-", lw=1)
lines.append(line)
legends.append("K = {0}".format(K))
ks.analyze(K=K, method="allpaths")
genomesizes.append((K, ks.genomesize / 1e6))
leg = A.legend(lines, legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(0.5)
title = "{0} genome K-mer histogram".format(species)
A.set_title(markup(title))
xlabel, ylabel = "Coverage (X)", "Counts"
A.set_xlabel(xlabel)
A.set_ylabel(ylabel)
set_human_axis(A)
title = "{0} genome size estimate".format(species)
B.set_title(markup(title))
x, y = zip(*genomesizes)
B.plot(x, y, "ko", mfc="w")
t = np.linspace(opts.kmin - 0.5, opts.kmax + 0.5, 100)
p = np.poly1d(np.polyfit(x, y, 2))
B.plot(t, p(t), "r:")
xlabel, ylabel = "K-mer size", "Estimated genome size (Mb)"
B.set_xlabel(xlabel)
B.set_ylabel(ylabel)
set_ticklabels_helvetica(B)
labels = ((0.04, 0.96, "A"), (0.54, 0.96, "B"))
panel_labels(root, labels)
normalize_axes(root)
imagename = species + ".multiK.pdf"
savefig(imagename, dpi=iopts.dpi, iopts=iopts)
def dotplot(anchorfile, qbed, sbed, fig, root, ax, vmin=0, vmax=1,
is_self=False, synteny=False, cmap_text=None, cmap="copper",
genomenames=None, sample_number=10000, minfont=5, palette=None,
chrlw=.01, title=None, sepcolor="gainsboro"):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Capping values within [{0:.1f}, {1:.1f}]"\
.format(vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
if cmap_text:
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
continue
if value > vmax:
continue
else:
value = 0
if query not in qorder:
continue
if subject not in sorder:
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
npairs = len(data)
# Only show random subset
if npairs > sample_number:
logging.debug("Showing a random subset of {0} data points (total {1}) " \
"for clarity.".format(sample_number, npairs))
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
#if not palette:
# data.sort(key=lambda x: -x[2])
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0, cmap=cmap,
vmin=vmin, vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=cmap)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
xsize_ratio = abs(end - beg) * .8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbed.get_breaks():
ysize_ratio = abs(end - beg) * .8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
for label, pos, fontsize in xchr_labels:
pos = .1 + pos * .8 / xsize
if fontsize >= minfont:
root.text(pos, .91, latex(label), size=fontsize,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, fontsize in ychr_labels:
pos = .9 - pos * .8 / ysize
if fontsize >= minfont:
root.text(.91, pos, latex(label), size=fontsize,
va="center", color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(markup(gx), size=16)
ax.set_ylabel(markup(gy), size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if not title:
title = "Inter-genomic comparison: {0} vs {1}".format(gx, gy)
if is_self:
title = "Intra-genomic comparison within {0}".format(gx)
npairs /= 2
title += " ({0} gene pairs)".format(thousands(npairs))
root.set_title(markup(title), x=.5, y=.96, color="k")
logging.debug(title)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic.
"""
p = OptionParser(histogram.__doc__)
p.add_option(
"--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive",
)
p.add_option(
"--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive",
)
p.add_option(
"--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot",
)
p.add_option(
"--method",
choices=("nbinom", "allpaths"),
default="nbinom",
help=
"'nbinom' - slow but more accurate for het or polyploid genome; 'allpaths' - fast and works for homozygous enomes",
)
p.add_option(
"--maxiter",
default=100,
type="int",
help="Max iterations for optimization. Only used with --method nbinom",
)
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option(
"--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks",
)
opts, args, iopts = p.set_image_options(args, figsize="7x7")
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
method = opts.method
vmin, vmax = opts.vmin, opts.vmax
ascii = not opts.pdf
peaks = not opts.nopeaks and method == "allpaths"
N = int(N)
if histfile.rsplit(".", 1)[-1] in ("mcdat", "mcidx"):
logging.debug("CA kmer index found")
histfile = merylhistogram(histfile)
ks = KmerSpectrum(histfile)
method_info = ks.analyze(K=N, maxiter=opts.maxiter, method=method)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.lambda_ if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1.0 / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1:.1f}x".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f} Mb".format(Genome_size /
1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print(msg, file=sys.stderr)
x, y = ks.get_xy(vmin, vmax)
title = "{0} {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (iopts.w, iopts.h))
plt.bar(x, y, fc="#b2df8a", lw=0)
# Plot the negative binomial fit
if method == "nbinom":
generative_model = method_info["generative_model"]
GG = method_info["Gbins"]
ll = method_info["lambda"]
rr = method_info["rho"]
kf_range = method_info["kf_range"]
stacked = generative_model(GG, ll, rr)
plt.plot(
kf_range,
stacked,
":",
color="#6a3d9a",
lw=2,
)
ax = plt.gca()
if peaks: # Only works for method 'allpaths'
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
if tcounts:
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, "ko", lw=3, mec="k", mfc="w")
ax.text(ks.max1, tcounts[ks.max1], "SNP peak")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
if method == "nbinom":
# Plot multiple CN locations, CN1, CN2, ... up to ploidy
cn_color = "#a6cee3"
for i in range(1, ks.ploidy + 1):
x = i * ks.lambda_
plt.plot((x, x), (0, ymax), "-.", color=cn_color)
plt.text(
x,
ymax * 0.95,
"CN{}".format(i),
ha="right",
va="center",
color=cn_color,
rotation=90,
)
messages = [
Total_Kmers_msg,
Kmer_coverage_msg,
Genome_size_msg,
Repetitive_msg,
SNPrate_msg,
]
if method == "nbinom":
messages += [ks.ploidy_message] + ks.copy_messages
write_messages(ax, messages)
ax.set_title(markup(title))
ax.set_xlim((0, vmax))
ax.set_ylim((0, ymax))
adjust_spines(ax, ["left", "bottom"], outward=True)
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
set_human_axis(ax)
imagename = histfile.split(".")[0] + "." + iopts.format
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
soap = False
for row in fp:
if len(row.split()) == 1:
soap = True
break
fp.seek(0)
for rowno, row in enumerate(fp):
if soap:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = counts
history = ["drop"]
for a, b in pairwise(sorted(hist.items())):
Ka, ca = a
Kb, cb = b
if ca <= cb:
status = "rise"
else:
status = "drop"
if history[-1] != status:
history.append(status)
if history == ["drop", "rise", "drop"]:
break
Total_Kmers = int(totalKmers)
Kmer_coverage = Ka
Genome_size = Total_Kmers * 1. / Ka / 1e6
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size)
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() if a <= 100)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
return asciiplot(x, y, title=title)
fig = plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
ax.text(.5,
.9,
_(Total_Kmers_msg),
ha="center",
color='b',
transform=ax.transAxes)
ax.text(.5,
.8,
_(Kmer_coverage_msg),
ha="center",
color='b',
transform=ax.transAxes)
ax.text(.5,
.7,
_(Genome_size_msg),
ha="center",
color='b',
transform=ax.transAxes)
ax.set_title(_(title), color='r')
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(_(xlabel), color='r')
ax.set_ylabel(_(ylabel), color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
plt.savefig(imagename, dpi=100)
print >> sys.stderr, "Image saved to `{0}`.".format(imagename)
