def draw(self, title="*Ks* distribution", filename="Ks_plot.pdf"):
ax = self.ax
ks_max = self.ks_max
lines = self.lines
labels = [markup(x) for x in self.labels]
legendp = self.legendp
if len(lines) > 1:
leg = ax.legend(
lines,
labels,
loc=legendp,
shadow=True,
fancybox=True,
prop={"size": 10},
)
leg.get_frame().set_alpha(0.5)
ax.set_xlim((0, ks_max - self.interval))
ylim = ax.get_ylim()[-1]
ax.set_ylim(0, ylim)
ax.set_title(markup(title), fontweight="bold")
ax.set_xlabel(markup("Synonymous substitutions per site (*Ks*)"))
ax.set_ylabel("Percentage of gene pairs (bin={})".format(
self.interval))
ax.set_xticklabels(ax.get_xticks(), family="Helvetica")
ax.set_yticklabels(ax.get_yticks(), family="Helvetica")
adjust_spines(ax, ["left", "bottom"], outward=True)
if filename:
savefig(filename, dpi=300)
def __init__(self, fig, root, canvas, chr, xlim, datadir,
order=None, hlsuffix=None, palette=None, cap=50,
gauge="bottom", plot_label=True, plot_chr_label=True,
gauge_step=5000000, vlines=None):
x, y, w, h = canvas
p = .01
root.add_patch(Rectangle((x - p, y - p), w + 2 * p, h + 2 * p, lw=1,
fill=False, ec="darkslategray", zorder=10))
datafiles = glob(op.join(datadir, chr + "*"))
ntracks = len(datafiles)
yinterval = h / ntracks
yy = y + h
if palette is None:
# Get the palette
import brewer2mpl
set2 = brewer2mpl.get_map('Set2', 'qualitative', ntracks).mpl_colors
else:
set2 = [palette] * ntracks
if order:
datafiles.sort(key=lambda x: order.index(x.split(".")[1]))
if gauge == "top":
gauge_ax = fig.add_axes([x, yy + p, w, .0001])
adjust_spines(gauge_ax, ["top"])
tpos = yy + .07
elif gauge == "bottom":
gauge_ax = fig.add_axes([x, y - p, w, .0001])
adjust_spines(gauge_ax, ["bottom"])
tpos = y - .07
start, end = xlim
fs = gauge_step < 1000000
setup_gauge_ax(gauge_ax, start, end, gauge_step, float_formatter=fs)
if plot_chr_label:
root.text(x + w / 2, tpos, chr, ha="center", va="center",
color="darkslategray", size=16)
for label, datafile, c in zip(order, datafiles, set2):
yy -= yinterval
ax = fig.add_axes([x, yy, w, yinterval * .9])
xy = XYtrack(ax, datafile, color=c)
xy.interpolate(end)
xy.cap(ymax=cap)
if vlines:
xy.vlines(vlines)
if hlsuffix:
hlfile = op.join(datadir, ".".join((label, hlsuffix)))
xy.import_hlfile(hlfile, chr)
if plot_label:
root.text(x - .035, yy + yinterval / 2, label,
ha="center", va="center", color=c)
xy.draw()
ax.set_xlim(*xlim)
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 fig3(args):
"""
%prog fig3 chrA02,A02,C2,chrC02 chr.sizes all.bed data
Napus Figure 3 displays alignments between quartet chromosomes, inset
with read histograms.
"""
from jcvi.formats.bed import Bed
p = OptionParser(fig3.__doc__)
p.add_option("--gauge_step",
default=10000000,
type="int",
help="Step size for the base scale")
opts, args, iopts = p.set_image_options(args, figsize="12x9")
if len(args) != 4:
sys.exit(not p.print_help())
chrs, sizes, bedfile, datadir = args
gauge_step = opts.gauge_step
diverge = iopts.diverge
rr, gg = diverge
chrs = [[x] for x in chrs.split(",")]
sizes = Sizes(sizes).mapping
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
chr_sizes, chr_sum_sizes, ratio = calc_ratio(chrs, sizes)
# Synteny panel
seqidsfile = make_seqids(chrs)
klayout = make_layout(chrs, chr_sum_sizes, ratio, template_f3a, shift=.05)
height = .07
r = height / 4
K = Karyotype(fig,
root,
seqidsfile,
klayout,
gap=gap,
height=height,
lw=2,
generank=False,
sizes=sizes,
heightpad=r,
roundrect=True,
plot_label=False)
# Chromosome labels
for kl in K.layout:
if kl.empty:
continue
lx, ly = kl.xstart, kl.y
if lx < .11:
lx += .1
ly += .06
label = kl.label
root.text(lx - .015, ly, label, fontsize=15, ha="right", va="center")
# Inset with datafiles
datafiles = ("chrA02.bzh.forxmgr", "parent.A02.per10kb.forxmgr",
"parent.C2.per10kb.forxmgr", "chrC02.bzh.forxmgr")
datafiles = [op.join(datadir, x) for x in datafiles]
tracks = K.tracks
hlfile = op.join(datadir, "bzh.regions.forhaibao")
xy_axes = []
for t, datafile in zip(tracks, datafiles):
ax = make_affix_axis(fig, t, -r, height=2 * r)
xy_axes.append(ax)
chr = t.seqids[0]
xy = XYtrack(ax, datafile, color="lightslategray")
start, end = 0, t.total
xy.interpolate(end)
xy.cap(ymax=40)
xy.import_hlfile(hlfile, chr, diverge=diverge)
xy.draw()
ax.set_xlim(start, end)
gauge_ax = make_affix_axis(fig, t, -r)
adjust_spines(gauge_ax, ["bottom"])
setup_gauge_ax(gauge_ax, start, end, gauge_step)
# Converted gene tracks
ax_Ar = make_affix_axis(fig, tracks[1], r, height=r / 2)
ax_Co = make_affix_axis(fig, tracks[2], r, height=r / 2)
order = Bed(bedfile).order
for asterisk in (False, True):
conversion_track(order,
"data/Genes.Converted.seuil.0.6.AtoC.txt",
0,
"A02",
ax_Ar,
rr,
asterisk=asterisk)
conversion_track(order,
"data/Genes.Converted.seuil.0.6.AtoC.txt",
1,
"C2",
ax_Co,
gg,
asterisk=asterisk)
conversion_track(order,
"data/Genes.Converted.seuil.0.6.CtoA.txt",
0,
"A02",
ax_Ar,
gg,
ypos=1,
asterisk=asterisk)
conversion_track(order,
"data/Genes.Converted.seuil.0.6.CtoA.txt",
1,
"C2",
ax_Co,
rr,
ypos=1,
asterisk=asterisk)
Ar, Co = xy_axes[1:3]
annotations = ((Ar, "Bra028920 Bra028897", "center",
"1DAn2+"), (Ar, "Bra020081 Bra020171", "right", "2DAn2+"),
(Ar, "Bra020218 Bra020286", "left",
"3DAn2+"), (Ar, "Bra008143 Bra008167", "left", "4DAn2-"),
(Ar, "Bra029317 Bra029251", "right",
"5DAn2+ (GSL)"), (Co, "Bo2g001000 Bo2g001300", "left",
"1DCn2-"), (Co, "Bo2g018560 Bo2g023700",
"right", "2DCn2-"),
(Co, "Bo2g024450 Bo2g025390", "left",
"3DCn2-"), (Co, "Bo2g081060 Bo2g082340", "left", "4DCn2+"),
(Co, "Bo2g161510 Bo2g164260", "right", "5DCn2-"))
for ax, genes, ha, label in annotations:
g1, g2 = genes.split()
x1, x2 = order[g1][1].start, order[g2][1].start
if ha == "center":
x = (x1 + x2) / 2 * .8
elif ha == "left":
x = x2
else:
x = x1
label = r"\textit{{{0}}}".format(label)
color = rr if "+" in label else gg
ax.text(x, 30, label, color=color, fontsize=9, ha=ha, va="center")
ax_Ar.set_xlim(0, tracks[1].total)
ax_Ar.set_ylim(-1, 1)
ax_Co.set_xlim(0, tracks[2].total)
ax_Co.set_ylim(-1, 1)
# Plot coverage in resequencing lines
gstep = 5000000
order = "swede,kale,h165,yudal,aviso,abu,bristol".split(",")
labels_dict = {"h165": "Resynthesized (H165)", "abu": "Aburamasari"}
hlsuffix = "regions.forhaibao"
chr1, chr2 = "chrA02", "chrC02"
t1, t2 = tracks[0], tracks[-1]
s1, s2 = sizes[chr1], sizes[chr2]
canvas1 = (t1.xstart, .75, t1.xend - t1.xstart, .2)
c = Coverage(fig,
root,
canvas1,
chr1, (0, s1),
datadir,
order=order,
gauge=None,
plot_chr_label=False,
gauge_step=gstep,
palette="gray",
cap=40,
hlsuffix=hlsuffix,
labels_dict=labels_dict,
diverge=diverge)
yys = c.yys
x1, x2 = .37, .72
tip = .02
annotations = ((x1, yys[2] + .3 * tip, tip, tip / 2,
"FLC"), (x1, yys[3] + .6 * tip, tip, tip / 2, "FLC"),
(x1, yys[5] + .6 * tip, tip, tip / 2,
"FLC"), (x2, yys[0] + .9 * tip, -1.2 * tip, 0, "GSL"),
(x2, yys[4] + .9 * tip, -1.2 * tip, 0,
"GSL"), (x2, yys[6] + .9 * tip, -1.2 * tip, 0, "GSL"))
arrowprops = dict(facecolor='black',
shrink=.05,
frac=.5,
width=1,
headwidth=4)
for x, y, dx, dy, label in annotations:
label = r"\textit{{{0}}}".format(label)
root.annotate(label,
xy=(x, y),
xytext=(x + dx, y + dy),
arrowprops=arrowprops,
color=rr,
fontsize=9,
ha="center",
va="center")
canvas2 = (t2.xstart, .05, t2.xend - t2.xstart, .2)
Coverage(fig,
root,
canvas2,
chr2, (0, s2),
datadir,
order=order,
gauge=None,
plot_chr_label=False,
gauge_step=gstep,
palette="gray",
cap=40,
hlsuffix=hlsuffix,
labels_dict=labels_dict,
diverge=diverge)
pad = .03
labels = ((.1, .67, "A"), (t1.xstart - 3 * pad, .95 + pad, "B"),
(t2.xstart - 3 * pad, .25 + pad, "C"))
panel_labels(root, labels)
normalize_axes(root)
image_name = "napus-fig3." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def f3a(args):
"""
%prog f3a chrA02,A02,C2,chrC02 chr.sizes all.bed data
Napus Figure 3A displays alignments between quartet chromosomes, inset
with read histograms.
"""
from jcvi.formats.bed import Bed
p = OptionParser(f3a.__doc__)
p.add_option("--gauge_step", default=10000000, type="int",
help="Step size for the base scale")
opts, args, iopts = p.set_image_options(args, figsize="10x6")
if len(args) != 4:
sys.exit(not p.print_help())
chrs, sizes, bedfile, datadir = args
gauge_step = opts.gauge_step
chrs = [[x] for x in chrs.split(",")]
sizes = Sizes(sizes).mapping
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
chr_sizes, chr_sum_sizes, ratio = calc_ratio(chrs, sizes)
# Synteny panel
seqidsfile = make_seqids(chrs)
klayout = make_layout(chrs, chr_sum_sizes, ratio, template_f3a)
height = .11
r = height / 4
K = Karyotype(fig, root, seqidsfile, klayout, gap=gap,
height=height, lw=2, generank=False, sizes=sizes,
heightpad=r, roundrect=True)
# Inset with datafiles
datafiles = ("chrA02.bzh.forxmgr", "parent.A02.per10kb.forxmgr",
"parent.C2.per10kb.forxmgr", "chrC02.bzh.forxmgr")
datafiles = [op.join(datadir, x) for x in datafiles]
tracks = K.tracks
hlfile = op.join(datadir, "bzh.regions.forhaibao")
for t, datafile in zip(tracks, datafiles):
ax = make_affix_axis(fig, t, -r, height=2 * r)
chr = t.seqids[0]
xy = XYtrack(ax, datafile, color="lightslategray")
start, end = 0, t.total
xy.interpolate(end)
xy.cap(ymax=40)
xy.import_hlfile(hlfile, chr)
xy.draw()
ax.set_xlim(start, end)
gauge_ax = make_affix_axis(fig, t, -r)
adjust_spines(gauge_ax, ["bottom"])
setup_gauge_ax(gauge_ax, start, end, gauge_step)
# Converted gene tracks
ax_Ar = make_affix_axis(fig, tracks[1], r, height=r/2)
ax_Co = make_affix_axis(fig, tracks[2], r, height=r/2)
order = Bed(bedfile).order
for asterisk in (False, True):
conversion_track(order, "data/Genes.Converted.seuil.0.6.AtoC.txt",
0, "A02", ax_Ar, "r", asterisk=asterisk)
conversion_track(order, "data/Genes.Converted.seuil.0.6.AtoC.txt",
1, "C2", ax_Co, "g", asterisk=asterisk)
conversion_track(order, "data/Genes.Converted.seuil.0.6.CtoA.txt",
0, "A02", ax_Ar, "g", ypos=1, asterisk=asterisk)
conversion_track(order, "data/Genes.Converted.seuil.0.6.CtoA.txt",
1, "C2", ax_Co, "r", ypos=1, asterisk=asterisk)
ax_Ar.set_xlim(0, tracks[1].total)
ax_Ar.set_ylim(-.5, 1.5)
ax_Co.set_xlim(0, tracks[2].total)
ax_Co.set_ylim(-.5, 1.5)
# Conversion legend
if False:
root.text(.81, .8, r"Converted A$\mathsf{_n}$ to C$\mathsf{_n}$",
va="center")
root.text(.81, .77, r"Converted C$\mathsf{_n}$ to A$\mathsf{_n}$",
va="center")
root.scatter([.8], [.8], s=20, color="g")
root.scatter([.8], [.77], s=20, color="r")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = "napusf3a." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def fig3(args):
"""
%prog fig3 chrA02,A02,C2,chrC02 chr.sizes all.bed data
Napus Figure 3 displays alignments between quartet chromosomes, inset
with read histograms.
"""
from jcvi.formats.bed import Bed
p = OptionParser(fig3.__doc__)
p.add_option("--gauge_step", default=10000000, type="int",
help="Step size for the base scale")
opts, args, iopts = p.set_image_options(args, figsize="12x9")
if len(args) != 4:
sys.exit(not p.print_help())
chrs, sizes, bedfile, datadir = args
gauge_step = opts.gauge_step
diverge = iopts.diverge
rr, gg = diverge
chrs = [[x] for x in chrs.split(",")]
sizes = Sizes(sizes).mapping
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
chr_sizes, chr_sum_sizes, ratio = calc_ratio(chrs, sizes)
# Synteny panel
seqidsfile = make_seqids(chrs)
klayout = make_layout(chrs, chr_sum_sizes, ratio, template_f3a, shift=.05)
height = .07
r = height / 4
K = Karyotype(fig, root, seqidsfile, klayout, gap=gap,
height=height, lw=2, generank=False, sizes=sizes,
heightpad=r, roundrect=True, plot_label=False)
# Chromosome labels
for kl in K.layout:
if kl.empty:
continue
lx, ly = kl.xstart, kl.y
if lx < .11:
lx += .1
ly += .06
label = kl.label
root.text(lx - .015, ly, label, fontsize=15,
ha="right", va="center")
# Inset with datafiles
datafiles = ("chrA02.bzh.forxmgr", "parent.A02.per10kb.forxmgr",
"parent.C2.per10kb.forxmgr", "chrC02.bzh.forxmgr")
datafiles = [op.join(datadir, x) for x in datafiles]
tracks = K.tracks
hlfile = op.join(datadir, "bzh.regions.forhaibao")
xy_axes = []
for t, datafile in zip(tracks, datafiles):
ax = make_affix_axis(fig, t, -r, height=2 * r)
xy_axes.append(ax)
chr = t.seqids[0]
xy = XYtrack(ax, datafile, color="lightslategray")
start, end = 0, t.total
xy.interpolate(end)
xy.cap(ymax=40)
xy.import_hlfile(hlfile, chr, diverge=diverge)
xy.draw()
ax.set_xlim(start, end)
gauge_ax = make_affix_axis(fig, t, -r)
adjust_spines(gauge_ax, ["bottom"])
setup_gauge_ax(gauge_ax, start, end, gauge_step)
# Converted gene tracks
ax_Ar = make_affix_axis(fig, tracks[1], r, height=r/2)
ax_Co = make_affix_axis(fig, tracks[2], r, height=r/2)
order = Bed(bedfile).order
for asterisk in (False, True):
conversion_track(order, "data/Genes.Converted.seuil.0.6.AtoC.txt",
0, "A02", ax_Ar, rr, asterisk=asterisk)
conversion_track(order, "data/Genes.Converted.seuil.0.6.AtoC.txt",
1, "C2", ax_Co, gg, asterisk=asterisk)
conversion_track(order, "data/Genes.Converted.seuil.0.6.CtoA.txt",
0, "A02", ax_Ar, gg, ypos=1, asterisk=asterisk)
conversion_track(order, "data/Genes.Converted.seuil.0.6.CtoA.txt",
1, "C2", ax_Co, rr, ypos=1, asterisk=asterisk)
Ar, Co = xy_axes[1:3]
annotations = ((Ar, "Bra028920 Bra028897", "center", "1DAn2+"),
(Ar, "Bra020081 Bra020171", "right", "2DAn2+"),
(Ar, "Bra020218 Bra020286", "left", "3DAn2+"),
(Ar, "Bra008143 Bra008167", "left", "4DAn2-"),
(Ar, "Bra029317 Bra029251", "right", "5DAn2+ (GSL)"),
(Co, "Bo2g001000 Bo2g001300", "left", "1DCn2-"),
(Co, "Bo2g018560 Bo2g023700", "right", "2DCn2-"),
(Co, "Bo2g024450 Bo2g025390", "left", "3DCn2-"),
(Co, "Bo2g081060 Bo2g082340", "left", "4DCn2+"),
(Co, "Bo2g161510 Bo2g164260", "right", "5DCn2-"))
for ax, genes, ha, label in annotations:
g1, g2 = genes.split()
x1, x2 = order[g1][1].start, order[g2][1].start
if ha == "center":
x = (x1 + x2) / 2 * .8
elif ha == "left":
x = x2
else:
x = x1
label = r"\textit{{{0}}}".format(label)
color = rr if "+" in label else gg
ax.text(x, 30, label, color=color, fontsize=9, ha=ha, va="center")
ax_Ar.set_xlim(0, tracks[1].total)
ax_Ar.set_ylim(-1, 1)
ax_Co.set_xlim(0, tracks[2].total)
ax_Co.set_ylim(-1, 1)
# Plot coverage in resequencing lines
gstep = 5000000
order = "swede,kale,h165,yudal,aviso,abu,bristol".split(",")
labels_dict = {"h165": "Resynthesized (H165)", "abu": "Aburamasari"}
hlsuffix = "regions.forhaibao"
chr1, chr2 = "chrA02", "chrC02"
t1, t2 = tracks[0], tracks[-1]
s1, s2 = sizes[chr1], sizes[chr2]
canvas1 = (t1.xstart, .75, t1.xend - t1.xstart, .2)
c = Coverage(fig, root, canvas1, chr1, (0, s1), datadir,
order=order, gauge=None, plot_chr_label=False,
gauge_step=gstep, palette="gray",
cap=40, hlsuffix=hlsuffix, labels_dict=labels_dict,
diverge=diverge)
yys = c.yys
x1, x2 = .37, .72
tip = .02
annotations = ((x1, yys[2] + .3 * tip, tip, tip / 2, "FLC"),
(x1, yys[3] + .6 * tip, tip, tip / 2, "FLC"),
(x1, yys[5] + .6 * tip, tip, tip / 2, "FLC"),
(x2, yys[0] + .9 * tip, -1.2 * tip, 0, "GSL"),
(x2, yys[4] + .9 * tip, -1.2 * tip, 0, "GSL"),
(x2, yys[6] + .9 * tip, -1.2 * tip, 0, "GSL"))
arrowprops=dict(facecolor='black', shrink=.05, frac=.5,
width=1, headwidth=4)
for x, y, dx, dy, label in annotations:
label = r"\textit{{{0}}}".format(label)
root.annotate(label, xy=(x, y), xytext=(x + dx, y + dy),
arrowprops=arrowprops, color=rr, fontsize=9,
ha="center", va="center")
canvas2 = (t2.xstart, .05, t2.xend - t2.xstart, .2)
Coverage(fig, root, canvas2, chr2, (0, s2), datadir,
order=order, gauge=None, plot_chr_label=False,
gauge_step=gstep, palette="gray",
cap=40, hlsuffix=hlsuffix, labels_dict=labels_dict,
diverge=diverge)
pad = .03
labels = ((.1, .67, "A"), (t1.xstart - 3 * pad, .95 + pad, "B"),
(t2.xstart - 3 * pad, .25 + pad, "C"))
panel_labels(root, labels)
normalize_axes(root)
image_name = "napus-fig3." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def simulate(args):
"""
%prog simulate
Run simulation on female restitution.
"""
import seaborn as sns
sns.set_style("darkgrid")
p = OptionParser(simulate.__doc__)
p.add_option(
"--verbose",
default=False,
action="store_true",
help="Verbose logging during simulation",
)
opts, args, iopts = p.set_image_options(args, figsize="7x10")
if len(args) != 0:
sys.exit(not p.print_help())
# Construct a composite figure with 6 tracks
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
rows = 7
ypad = 0.05
yinterval = (1 - 2 * ypad) / (rows + 1)
yy = 1 - ypad
xpad = 0.18
xwidth = 0.6
# Axes are vertically stacked, and share x-axis
axes = []
yy_positions = [] # Save yy positions so we can show details to the right laterr
for idx in range(rows):
yy_positions.append(yy)
yy -= yinterval
ax = fig.add_axes([xpad, yy, xwidth, yinterval * 0.85])
if idx != rows - 1:
plt.setp(ax.get_xticklabels(), visible=False)
axes.append(ax)
ax1, ax2, ax3, ax4, ax5, ax6, ax7 = axes
# Prepare the simulated data
# Simulate two parents
SS = Genome("SS", "SS", 10, 8)
SO = Genome("SO", "SO", 8, 10)
verbose = opts.verbose
all_F1s = [simulate_F1(SO, SS, verbose=verbose) for _ in range(1000)]
all_F2s = [simulate_F2(SO, SS, verbose=verbose) for _ in range(1000)]
all_F1intercrosses = [simulate_F1intercross(SO, SS, verbose) for _ in range(1000)]
all_BC1s = [simulate_BCn(1, SO, SS, verbose=verbose) for _ in range(1000)]
all_BC2s = [simulate_BCn(2, SO, SS, verbose=verbose) for _ in range(1000)]
all_BC3s = [simulate_BCn(3, SO, SS, verbose=verbose) for _ in range(1000)]
all_BC4s = [simulate_BCn(4, SO, SS, verbose=verbose) for _ in range(1000)]
# Plotting
f1s = plot_summary(ax1, all_F1s)
f2s = plot_summary(ax2, all_F2s)
f1is = plot_summary(ax3, all_F1intercrosses)
bc1s = plot_summary(ax4, all_BC1s)
bc2s = plot_summary(ax5, all_BC2s)
bc3s = plot_summary(ax6, all_BC3s)
bc4s = plot_summary(ax7, all_BC4s)
# Show title to the left
xx = xpad / 2
for (title, subtitle), yy in zip(
(
("F1", None),
("F2", "via selfing"),
("F2", "via intercross"),
("BC1", None),
("BC2", None),
("BC3", None),
("BC4", None),
),
yy_positions,
):
if subtitle:
yy -= 0.06
else:
yy -= 0.07
root.text(xx, yy, title, color="darkslategray", ha="center", va="center")
if subtitle:
yy -= 0.02
root.text(
xx, yy, subtitle, color="lightslategray", ha="center", va="center"
)
# Show summary stats to the right
xx = 1 - (1 - xpad - xwidth) / 2
for summary, yy in zip((f1s, f2s, f1is, bc1s, bc2s, bc3s, bc4s), yy_positions):
yy -= 0.04
root.text(
xx, yy, summary.SO_summary, color=SoColor, ha="center", va="center",
)
yy -= 0.02
root.text(
xx, yy, summary.SS_summary, color=SsColor, ha="center", va="center",
)
yy -= 0.02
root.text(
xx, yy, summary.percent_SO_summary, color=SoColor, ha="center", va="center",
)
ax7.set_xlabel("Number of unique chromosomes")
adjust_spines(ax7, ["bottom"], outward=True)
normalize_axes(root)
savefig("plotter.pdf", dpi=120)
outdir = "simulations"
mkdir(outdir)
# Write chromosomes to disk
for genomes, filename in (
(all_F1s, "all_F1s"),
(all_F2s, "all_F2s"),
(all_F1intercrosses, "all_F1intercrosses"),
(all_BC1s, "all_BC1s"),
(all_BC2s, "all_BC2s"),
(all_BC3s, "all_BC3s"),
(all_BC4s, "all_BC4s"),
):
write_chromosomes(genomes, op.join(outdir, filename))
def __init__(self,
fig,
root,
canvas,
chr,
xlim,
datadir,
order=None,
hlsuffix=None,
palette=None,
cap=50,
gauge="bottom",
plot_label=True,
plot_chr_label=True,
gauge_step=5000000,
vlines=None,
labels_dict={},
diverge=('r', 'g')):
x, y, w, h = canvas
p = .01
root.add_patch(
Rectangle((x - p, y - p),
w + 2 * p,
h + 2 * p,
lw=1,
fill=False,
ec="darkslategray",
zorder=10))
datafiles = glob(op.join(datadir, chr + "*"))
if order:
datafiles = [z for z in datafiles if z.split(".")[1] in order]
datafiles.sort(key=lambda x: order.index(x.split(".")[1]))
ntracks = len(datafiles)
yinterval = h / ntracks
yy = y + h
if palette is None:
# Get the palette
set2 = get_map('Set2', 'qualitative', ntracks).mpl_colors
else:
set2 = [palette] * ntracks
if gauge == "top":
gauge_ax = fig.add_axes([x, yy + p, w, .0001])
adjust_spines(gauge_ax, ["top"])
tpos = yy + .07
elif gauge == "bottom":
gauge_ax = fig.add_axes([x, y - p, w, .0001])
adjust_spines(gauge_ax, ["bottom"])
tpos = y - .07
start, end = xlim
if gauge:
fs = gauge_step < 1000000
setup_gauge_ax(gauge_ax,
start,
end,
gauge_step,
float_formatter=fs)
if plot_chr_label:
root.text(x + w / 2,
tpos,
chr,
ha="center",
va="center",
color="darkslategray",
size=16)
yys = []
for label, datafile, c in zip(order, datafiles, set2):
yy -= yinterval
yys.append(yy)
ax = fig.add_axes([x, yy, w, yinterval * .9])
xy = XYtrack(ax, datafile, color=c)
xy.interpolate(end)
xy.cap(ymax=cap)
if vlines:
xy.vlines(vlines)
if hlsuffix:
hlfile = op.join(datadir, ".".join((label, hlsuffix)))
xy.import_hlfile(hlfile, chr, diverge=diverge)
if plot_label:
label = labels_dict.get(label, label.capitalize())
label = r"\textit{{{0}}}".format(label)
root.text(x - .015,
yy + yinterval / 2,
label,
ha="right",
va="center")
xy.draw()
ax.set_xlim(*xlim)
self.yys = yys
def mosdepth(args):
"""
%prog mosdepth mosdepth.global.dist.txt groups
Plot depth vs. coverage per chromosome. Inspired by mosdepth plot. See also:
https://github.com/brentp/mosdepth
"""
import seaborn as sns
sns.set_style("darkgrid")
p = OptionParser(mosdepth.__doc__)
p.add_option("--maxdepth",
default=100,
type="int",
help="Maximum depth to plot")
p.add_option("--logscale",
default=False,
action="store_true",
help="Use log-scale on depth")
opts, args, iopts = p.set_image_options(args, style="dark", figsize="6x8")
if len(args) != 2:
sys.exit(p.print_help())
# Read in datasets
distfile, groupsfile = args
dists = parse_distfile(distfile)
groups = parse_groupsfile(groupsfile)
logscale = opts.logscale
# Construct a composite figure with N tracks indicated in the groups
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
rows = len(groups)
ypad = 0.05
yinterval = (1 - 2 * ypad) / (rows + 1)
yy = 1 - ypad
for group_idx, (chrs, colors) in enumerate(groups):
yy -= yinterval
ax = fig.add_axes([0.15, yy, 0.7, yinterval * 0.85])
for c, color in zip(chrs, colors):
cdata = dists[c].items()
logging.debug("Importing {} records for {}".format(len(cdata), c))
cx, cy = zip(*sorted(cdata))
ax.plot(cx, cy, "-", color=color)
if logscale:
ax.set_xscale("log", basex=2)
ax.set_xlim(1 if logscale else 0, opts.maxdepth)
ax.get_yaxis().set_visible(False)
if group_idx != rows - 1:
ax.get_xaxis().set_visible(False)
# Add legend to the right of the canvas
label_pad = 0.02
label_yy = yy + yinterval
for c, color in zip(chrs, colors):
label_yy -= label_pad
root.text(0.92, label_yy, c, color=color, ha="center", va="center")
root.text(
0.1,
0.5,
"Proportion of bases at coverage",
rotation=90,
color="darkslategray",
ha="center",
va="center",
)
root.text(0.5,
0.05,
"Coverage",
color="darkslategray",
ha="center",
va="center")
normalize_axes(root)
adjust_spines(ax, ["bottom"], outward=True)
pf = "mosdepth"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)