def subplot(ax,
data,
xlabel,
ylabel,
xlim=None,
ylim=1.1,
xcast=float,
ycast=float,
legend=None):
columned_data = zip(*data)
x, yy = columned_data[0], columned_data[1:]
lines = []
for y, m in zip(yy, "o^x"):
line, = ax.plot(x, y, "k:", marker=m, mec="k", mfc="w", ms=4)
lines.append(line)
if legend:
assert len(lines) == len(legend)
ax.legend(lines, legend, loc='best')
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
if xlim:
ax.set_xlim(0, xlim)
if ylim:
ax.set_ylim(0, ylim)
set_ticklabels_helvetica(ax, xcast=xcast, ycast=ycast)
def subplot(ax, data, xlabel, ylabel, xlim=None, ylim=1.1,
xcast=float, ycast=float, legend=None):
columned_data = zip(*data)
x, yy = columned_data[0], columned_data[1:]
lines = []
for y, m in zip(yy, "o^x"):
line, = ax.plot(x, y, "k:", marker=m, mec="k", mfc="w", ms=4)
lines.append(line)
if legend:
assert len(lines) == len(legend)
ax.legend(lines, legend, loc='best')
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
if xlim:
ax.set_xlim(0, xlim)
if ylim:
ax.set_ylim(0, ylim)
set_ticklabels_helvetica(ax, xcast=xcast, ycast=ycast)
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 histogram(args):
"""
%prog histogram [reads.fasta|reads.fastq]
Plot read length distribution for reads. The plot would be similar to the
one generated by SMRT-portal, for example:
http://blog.pacificbiosciences.com/2013/10/data-release-long-read-shotgun.html
Plot has two axes - corresponding to pdf and cdf, respectively. Also adding
number of reads, average/median, N50, and total length.
"""
from jcvi.utils.cbook import human_size, thousands, SUFFIXES
from jcvi.formats.fastq import fasta
from jcvi.graphics.histogram import stem_leaf_plot
from jcvi.graphics.base import plt, markup, human_formatter, \
human_base_formatter, savefig, set2, set_ticklabels_helvetica
p = OptionParser(histogram.__doc__)
p.set_histogram(vmax=50000, bins=100, xlabel="Read length",
title="Read length distribution")
p.add_option("--ylabel1", default="Counts",
help="Label of y-axis on the left")
p.add_option("--color", default='0', choices=[str(x) for x in range(8)],
help="Color of bars, which is an index 0-7 in brewer set2")
opts, args, iopts = p.set_image_options(args, figsize="6x6", style="dark")
if len(args) != 1:
sys.exit(not p.print_help())
fastafile, = args
fastafile, qualfile = fasta([fastafile, "--seqtk"])
sizes = Sizes(fastafile)
all_sizes = sorted(sizes.sizes)
xmin, xmax, bins = opts.vmin, opts.vmax, opts.bins
left, height = stem_leaf_plot(all_sizes, xmin, xmax, bins)
plt.figure(1, (iopts.w, iopts.h))
ax1 = plt.gca()
width = (xmax - xmin) * .5 / bins
color = set2[int(opts.color)]
ax1.bar(left, height, width=width, linewidth=0, fc=color, align="center")
ax1.set_xlabel(markup(opts.xlabel))
ax1.set_ylabel(opts.ylabel1)
ax2 = ax1.twinx()
cur_size = 0
total_size, l50, n50 = sizes.summary
cdf = {}
hsize = human_size(total_size)
tag = hsize[-2:]
unit = 1000 ** SUFFIXES[1000].index(tag)
for x in all_sizes:
if x not in cdf:
cdf[x] = (total_size - cur_size) * 1. / unit
cur_size += x
x, y = zip(*sorted(cdf.items()))
ax2.plot(x, y, '-', color="darkslategray")
ylabel2 = "{0} above read length".format(tag)
ax2.set_ylabel(ylabel2)
for ax in (ax1, ax2):
set_ticklabels_helvetica(ax)
ax.set_xlim((xmin - width / 2, xmax + width / 2))
tc = "gray"
axt = ax1.transAxes
xx, yy = .95, .95
ma = "Total bases: {0}".format(hsize)
mb = "Total reads: {0}".format(thousands(len(sizes)))
mc = "Average read length: {0}bp".format(thousands(np.mean(all_sizes)))
md = "Median read length: {0}bp".format(thousands(np.median(all_sizes)))
me = "N50 read length: {0}bp".format(thousands(l50))
for t in (ma, mb, mc, md, me):
print >> sys.stderr, t
ax1.text(xx, yy, t, color=tc, transform=axt, ha="right")
yy -= .05
ax1.set_title(markup(opts.title))
# Seaborn removes ticks for all styles except 'ticks'. Now add them back:
ax1.tick_params(axis="x", direction="out", length=3,
left=False, right=False, top=False, bottom=True)
ax1.xaxis.set_major_formatter(human_base_formatter)
ax1.yaxis.set_major_formatter(human_formatter)
figname = sizes.filename + ".pdf"
savefig(figname)
def histogram(args):
"""
%prog histogram [reads.fasta|reads.fastq]
Plot read length distribution for reads. The plot would be similar to the
one generated by SMRT-portal, for example:
http://blog.pacificbiosciences.com/2013/10/data-release-long-read-shotgun.html
Plot has two axes - corresponding to pdf and cdf, respectively. Also adding
number of reads, average/median, N50, and total length.
"""
from jcvi.utils.cbook import human_size, thousands, SUFFIXES
from jcvi.formats.fastq import fasta
from jcvi.graphics.histogram import stem_leaf_plot
from jcvi.graphics.base import (
plt,
markup,
human_formatter,
human_base_formatter,
savefig,
set2,
set_ticklabels_helvetica,
)
p = OptionParser(histogram.__doc__)
p.set_histogram(vmax=50000,
bins=100,
xlabel="Read length",
title="Read length distribution")
p.add_option("--ylabel1",
default="Counts",
help="Label of y-axis on the left")
p.add_option(
"--color",
default="0",
choices=[str(x) for x in range(8)],
help="Color of bars, which is an index 0-7 in brewer set2",
)
opts, args, iopts = p.set_image_options(args, figsize="6x6", style="dark")
if len(args) != 1:
sys.exit(not p.print_help())
(fastafile, ) = args
fastafile, qualfile = fasta([fastafile, "--seqtk"])
sizes = Sizes(fastafile)
all_sizes = sorted(sizes.sizes)
xmin, xmax, bins = opts.vmin, opts.vmax, opts.bins
left, height = stem_leaf_plot(all_sizes, xmin, xmax, bins)
plt.figure(1, (iopts.w, iopts.h))
ax1 = plt.gca()
width = (xmax - xmin) * 0.5 / bins
color = set2[int(opts.color)]
ax1.bar(left, height, width=width, linewidth=0, fc=color, align="center")
ax1.set_xlabel(markup(opts.xlabel))
ax1.set_ylabel(opts.ylabel1)
ax2 = ax1.twinx()
cur_size = 0
total_size, l50, n50 = sizes.summary
cdf = {}
hsize = human_size(total_size)
tag = hsize[-2:]
unit = 1000**SUFFIXES[1000].index(tag)
for x in all_sizes:
if x not in cdf:
cdf[x] = (total_size - cur_size) * 1.0 / unit
cur_size += x
x, y = zip(*sorted(cdf.items()))
ax2.plot(x, y, "-", color="darkslategray")
ylabel2 = "{0} above read length".format(tag)
ax2.set_ylabel(ylabel2)
for ax in (ax1, ax2):
set_ticklabels_helvetica(ax)
ax.set_xlim((xmin - width / 2, xmax + width / 2))
tc = "gray"
axt = ax1.transAxes
xx, yy = 0.95, 0.95
ma = "Total bases: {0}".format(hsize)
mb = "Total reads: {0}".format(thousands(len(sizes)))
mc = "Average read length: {0}bp".format(thousands(np.mean(all_sizes)))
md = "Median read length: {0}bp".format(thousands(np.median(all_sizes)))
me = "N50 read length: {0}bp".format(thousands(l50))
for t in (ma, mb, mc, md, me):
print(t, file=sys.stderr)
ax1.text(xx, yy, t, color=tc, transform=axt, ha="right")
yy -= 0.05
ax1.set_title(markup(opts.title))
# Seaborn removes ticks for all styles except 'ticks'. Now add them back:
ax1.tick_params(
axis="x",
direction="out",
length=3,
left=False,
right=False,
top=False,
bottom=True,
)
ax1.xaxis.set_major_formatter(human_base_formatter)
ax1.yaxis.set_major_formatter(human_formatter)
figname = sizes.filename + ".pdf"
savefig(figname)
def variation(args):
"""
%prog variation P1.bed P2.bed F1.bed
Associate IES in parents and progeny.
"""
p = OptionParser(variation.__doc__)
p.add_option("--diversity",
choices=("breakpoint", "variant"),
default="variant",
help="Plot diversity")
opts, args, iopts = p.set_image_options(args, figsize="6x6")
if len(args) != 3:
sys.exit(not p.print_help())
pfs = [op.basename(x).split('-')[0] for x in args]
P1, P2, F1 = pfs
newbedfile = "-".join(pfs) + ".bed"
if need_update(args, newbedfile):
newbed = Bed()
for pf, filename in zip(pfs, args):
bed = Bed(filename)
for b in bed:
b.accn = "-".join((pf, b.accn))
b.score = None
newbed.append(b)
newbed.print_to_file(newbedfile, sorted=True)
neworder = Bed(newbedfile).order
mergedbedfile = mergeBed(newbedfile, nms=True)
bed = Bed(mergedbedfile)
valid = 0
total_counts = Counter()
F1_counts = []
bp_diff = []
novelbedfile = "novel.bed"
fw = open(novelbedfile, "w")
for b in bed:
accns = b.accn.split(',')
pfs_accns = [x.split("-")[0] for x in accns]
pfs_counts = Counter(pfs_accns)
if len(pfs_counts) != 3:
print(b, file=fw)
continue
valid += 1
total_counts += pfs_counts
F1_counts.append(pfs_counts[F1])
# Collect breakpoint positions between P1 and F1
P1_accns = [x for x in accns if x.split("-")[0] == P1]
F1_accns = [x for x in accns if x.split("-")[0] == F1]
if len(P1_accns) != 1:
continue
ri, ref = neworder[P1_accns[0]]
P1_accns = [neworder[x][-1] for x in F1_accns]
bp_diff.extend(x.start - ref.start for x in P1_accns)
bp_diff.extend(x.end - ref.end for x in P1_accns)
print("A total of {0} sites show consistent deletions across samples.".\
format(percentage(valid, len(bed))), file=sys.stderr)
for pf, count in total_counts.items():
print("{0:>9}: {1:.2f} deletions/site".\
format(pf, count * 1. / valid), file=sys.stderr)
F1_counts = Counter(F1_counts)
# Plot the IES variant number diversity
from jcvi.graphics.base import plt, savefig, set_ticklabels_helvetica
fig = plt.figure(1, (iopts.w, iopts.h))
if opts.diversity == "variant":
left, height = zip(*sorted(F1_counts.items()))
for l, h in zip(left, height):
print("{0:>9} variants: {1}".format(l, h), file=sys.stderr)
plt.text(l,
h + 5,
str(h),
color="darkslategray",
size=8,
ha="center",
va="bottom",
rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Identified number of IES per site")
plt.ylabel("Counts")
plt.title("IES variation in progeny pool")
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".counts.pdf")
# Plot the IES breakpoint position diversity
else:
bp_diff = Counter(bp_diff)
bp_diff_abs = Counter()
for k, v in bp_diff.items():
bp_diff_abs[abs(k)] += v
plt.figure(1, (iopts.w, iopts.h))
left, height = zip(*sorted(bp_diff_abs.items()))
for l, h in zip(left, height)[:21]:
plt.text(l,
h + 50,
str(h),
color="darkslategray",
size=8,
ha="center",
va="bottom",
rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Progeny breakpoint relative to SB210")
plt.ylabel("Counts")
plt.xlim(-.5, 20.5)
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".breaks.pdf")
# Serialize the data to a file
fw = open("Breakpoint-offset-histogram.csv", "w")
for k, v in sorted(bp_diff.items()):
print("{0},{1}".format(k, v), file=fw)
fw.close()
total = sum(height)
zeros = bp_diff[0]
within_20 = sum([v for i, v in bp_diff.items() if -20 <= i <= 20])
print("No deviation: {0}".format(percentage(zeros, total)),
file=sys.stderr)
print(" Within 20bp: {0}".format(percentage(within_20, total)),
file=sys.stderr)
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 variation(args):
"""
%prog variation P1.bed P2.bed F1.bed
Associate IES in parents and progeny.
"""
p = OptionParser(variation.__doc__)
p.add_option("--diversity", choices=("breakpoint", "variant"),
default="variant", help="Plot diversity")
opts, args, iopts = p.set_image_options(args, figsize="6x6")
if len(args) != 3:
sys.exit(not p.print_help())
pfs = [op.basename(x).split('-')[0] for x in args]
P1, P2, F1 = pfs
newbedfile = "-".join(pfs) + ".bed"
if need_update(args, newbedfile):
newbed = Bed()
for pf, filename in zip(pfs, args):
bed = Bed(filename)
for b in bed:
b.accn = "-".join((pf, b.accn))
b.score = None
newbed.append(b)
newbed.print_to_file(newbedfile, sorted=True)
neworder = Bed(newbedfile).order
mergedbedfile = mergeBed(newbedfile, nms=True)
bed = Bed(mergedbedfile)
valid = 0
total_counts = Counter()
F1_counts = []
bp_diff = []
novelbedfile = "novel.bed"
fw = open(novelbedfile, "w")
for b in bed:
accns = b.accn.split(',')
pfs_accns = [x.split("-")[0] for x in accns]
pfs_counts = Counter(pfs_accns)
if len(pfs_counts) != 3:
print >> fw, b
continue
valid += 1
total_counts += pfs_counts
F1_counts.append(pfs_counts[F1])
# Collect breakpoint positions between P1 and F1
P1_accns = [x for x in accns if x.split("-")[0] == P1]
F1_accns = [x for x in accns if x.split("-")[0] == F1]
if len(P1_accns) != 1:
continue
ri, ref = neworder[P1_accns[0]]
P1_accns = [neworder[x][-1] for x in F1_accns]
bp_diff.extend(x.start - ref.start for x in P1_accns)
bp_diff.extend(x.end - ref.end for x in P1_accns)
print >> sys.stderr, \
"A total of {0} sites show consistent deletions across samples.".\
format(percentage(valid, len(bed)))
for pf, count in total_counts.items():
print >> sys.stderr, "{0:>9}: {1:.2f} deletions/site".\
format(pf, count * 1. / valid)
F1_counts = Counter(F1_counts)
# Plot the IES variant number diversity
from jcvi.graphics.base import plt, savefig, set_ticklabels_helvetica
fig = plt.figure(1, (iopts.w, iopts.h))
if opts.diversity == "variant":
left, height = zip(*sorted(F1_counts.items()))
for l, h in zip(left, height):
print >> sys.stderr, "{0:>9} variants: {1}".format(l, h)
plt.text(l, h + 5, str(h), color="darkslategray", size=8,
ha="center", va="bottom", rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Identified number of IES per site")
plt.ylabel("Counts")
plt.title("IES variation in progeny pool")
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".counts.pdf")
# Plot the IES breakpoint position diversity
else:
bp_diff = Counter(bp_diff)
bp_diff_abs = Counter()
for k, v in bp_diff.items():
bp_diff_abs[abs(k)] += v
plt.figure(1, (iopts.w, iopts.h))
left, height = zip(*sorted(bp_diff_abs.items()))
for l, h in zip(left, height)[:21]:
plt.text(l, h + 50, str(h), color="darkslategray", size=8,
ha="center", va="bottom", rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Progeny breakpoint relative to SB210")
plt.ylabel("Counts")
plt.xlim(-.5, 20.5)
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".breaks.pdf")
# Serialize the data to a file
fw = open("Breakpoint-offset-histogram.csv", "w")
for k, v in sorted(bp_diff.items()):
print >> fw, "{0},{1}".format(k, v)
fw.close()
total = sum(height)
zeros = bp_diff[0]
within_20 = sum([v for i, v in bp_diff.items() if -20 <= i <= 20])
print >> sys.stderr, "No deviation: {0}".format(percentage(zeros, total))
print >> sys.stderr, " Within 20bp: {0}".format(percentage(within_20, total))
