def main():
p = OptionParser(__doc__)
p.add_option("--order",
help="The order to plot the tracks, comma-separated")
opts, args, iopts = p.set_image_options()
if len(args) != 3:
sys.exit(not p.print_help())
chr, sizes, datadir = args
order = opts.order
hlsuffix = opts.hlsuffix
if order:
order = order.split(",")
sizes = Sizes(sizes)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
canvas = (.12, .35, .8, .35)
chr_size = sizes.get_size(chr)
Coverage(fig,
root,
canvas,
chr, (0, chr_size),
datadir,
order=order,
hlsuffix=hlsuffix)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = chr + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def likelihood2(args):
"""
%prog likelihood2 100_20.json
Plot the likelihood surface and marginal distributions.
"""
from matplotlib import gridspec
p = OptionParser(likelihood2.__doc__)
opts, args, iopts = p.set_image_options(args,
figsize="10x5",
style="white",
cmap="coolwarm")
if len(args) != 1:
sys.exit(not p.print_help())
jsonfile, = args
fig = plt.figure(figsize=(iopts.w, iopts.h))
gs = gridspec.GridSpec(2, 2)
ax1 = fig.add_subplot(gs[:, 0])
ax2 = fig.add_subplot(gs[0, 1])
ax3 = fig.add_subplot(gs[1, 1])
plt.tight_layout(pad=3)
pf = plot_panel(jsonfile, ax1, ax2, ax3, opts.cmap)
root = fig.add_axes([0, 0, 1, 1])
normalize_axes(root)
image_name = "likelihood2.{}.".format(pf) + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
p.add_option("--order",
help="The order to plot the tracks, comma-separated")
opts, args, iopts = p.set_image_options()
if len(args) != 3:
sys.exit(not p.print_help())
chr, sizes, datadir = args
order = opts.order
hlsuffix = opts.hlsuffix
if order:
order = order.split(",")
sizes = Sizes(sizes)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
canvas = (.12, .35, .8, .35)
chr_size = sizes.get_size(chr)
c = Coverage(fig, root, canvas, chr, (0, chr_size), datadir,
order=order, hlsuffix=hlsuffix)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = chr + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def resample(args):
"""
%prog resample yellow-catfish-resample.txt medicago-resample.txt
Plot ALLMAPS performance across resampled real data.
"""
p = OptionParser(resample.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x4", dpi=300)
if len(args) != 2:
sys.exit(not p.print_help())
dataA, dataB = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
A = fig.add_axes([0.1, 0.18, 0.32, 0.64])
B = fig.add_axes([0.6, 0.18, 0.32, 0.64])
dataA = import_data(dataA)
dataB = import_data(dataB)
xlabel = "Fraction of markers"
ylabels = ("Anchor rate", "Runtime (m)")
legend = ("anchor rate", "runtime")
subplot_twinx(A, dataA, xlabel, ylabels, title="Yellow catfish", legend=legend)
subplot_twinx(B, dataB, xlabel, ylabels, title="Medicago", legend=legend)
labels = ((0.04, 0.92, "A"), (0.54, 0.92, "B"))
panel_labels(root, labels)
normalize_axes(root)
image_name = "resample." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
p.add_option(
"--customfont",
default="Airswing.ttf",
choices=available_fonts,
help="Custom font name",
)
p.add_option("--color", default="limegreen", help="Font color")
p.add_option("--size", default=36, type="int", help="Font size")
opts, args, iopts = p.set_image_options(figsize="2x1", dpi=60, format="png")
if len(args) != 1:
sys.exit(not p.print_help())
(text,) = args
plt.rcdefaults()
fig = plt.figure(1, (iopts.w, iopts.h))
ax = fig.add_axes([0, 0, 1, 1])
ax.text(0.5, 0.5, text, color=opts.color, ha="center", va="center")
fontprop(ax, opts.customfont, size=opts.size)
ax.set_xlim(0, 1)
ax.set_ylim(0, 1)
ax.set_axis_off()
image_name = text + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
p.add_option("--nocircles",
default=False,
action="store_true",
help="Do not plot chromosome circles")
opts, args, iopts = p.set_image_options(figsize="8x7")
if len(args) != 2:
sys.exit(not p.print_help())
seqidsfile, layoutfile = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig,
root,
seqidsfile,
layoutfile,
plot_circles=(not opts.nocircles))
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
p.add_option("--switch",
help="Rename the seqid with two-column file [default: %default]")
p.add_option("--tree",
help="Display trees on the bottom of the figure [default: %default]")
p.add_option("--extra", help="Extra features in BED format")
opts, args, iopts = p.set_image_options(figsize="8x7")
if len(args) != 3:
sys.exit(not p.print_help())
datafile, bedfile, layoutfile = args
switch = opts.switch
tree = opts.tree
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(fig, root, datafile, bedfile, layoutfile,
switch=switch, tree=tree, extra_features=opts.extra)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def ploidy(args):
"""
%prog ploidy b1.blocks all.bed b1.layout
Build a figure that illustrates the WGD history of the vanilla genome.
"""
p = OptionParser(ploidy.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="12x6")
if len(args) != 3:
sys.exit(not p.print_help())
blocksfile, bedfile, blockslayout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
draw_ploidy(fig, root, blocksfile, bedfile, blockslayout)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "vanilla-karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def regression(args):
"""
%prog regression postgenomic-s.tsv
Plot chronological vs. predicted age.
"""
p = OptionParser(regression.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x8")
if len(args) != 1:
sys.exit(not p.print_help())
(tsvfile, ) = args
df = pd.read_csv(tsvfile, sep="\t")
chrono = "Chronological age (yr)"
pred = "Predicted age (yr)"
resdf = pd.DataFrame({
chrono: df["hli_calc_age_sample_taken"],
pred: df["Predicted Age"]
})
g = sns.jointplot(chrono,
pred,
resdf,
joint_kws={"s": 6},
xlim=(0, 100),
ylim=(0, 80))
g.fig.set_figwidth(iopts.w)
g.fig.set_figheight(iopts.h)
outfile = tsvfile.rsplit(".", 1)[0] + ".regression.pdf"
savefig(outfile)
def pomegranate(args):
"""
%prog cotton seqids karyotype.layout mcscan.out all.bed synteny.layout
Build a figure that calls graphics.karyotype to illustrate the high ploidy
of WGD history of pineapple genome. The script calls both graphics.karyotype
and graphic.synteny.
"""
p = OptionParser(pomegranate.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="9x7")
if len(args) != 5:
sys.exit(not p.print_help())
seqidsfile, klayout, datafile, bedfile, slayout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
Synteny(fig, root, datafile, bedfile, slayout)
# legend showing the orientation of the genes
draw_gene_legend(root, 0.42, 0.52, 0.48)
labels = ((0.04, 0.96, "A"), (0.04, 0.52, "B"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "pomegranate-karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def resample(args):
"""
%prog resample yellow-catfish-resample.txt medicago-resample.txt
Plot ALLMAPS performance across resampled real data.
"""
p = OptionParser(resample.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x4", dpi=300)
if len(args) != 2:
sys.exit(not p.print_help())
dataA, dataB = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
A = fig.add_axes([.1, .18, .32, .64])
B = fig.add_axes([.6, .18, .32, .64])
dataA = import_data(dataA)
dataB = import_data(dataB)
xlabel = "Fraction of markers"
ylabels = ("Anchor rate", "Runtime (m)")
legend = ("anchor rate", "runtime")
subplot_twinx(A, dataA, xlabel, ylabels,
title="Yellow catfish", legend=legend)
subplot_twinx(B, dataB, xlabel, ylabels,
title="Medicago", legend=legend)
labels = ((.04, .92, "A"), (.54, .92, "B"))
panel_labels(root, labels)
normalize_axes(root)
image_name = "resample." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def pomegranate(args):
"""
%prog cotton seqids karyotype.layout mcscan.out all.bed synteny.layout
Build a figure that calls graphics.karyotype to illustrate the high ploidy
of WGD history of pineapple genome. The script calls both graphics.karyotype
and graphic.synteny.
"""
p = OptionParser(pomegranate.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="9x7")
if len(args) != 5:
sys.exit(not p.print_help())
seqidsfile, klayout, datafile, bedfile, slayout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
Synteny(fig, root, datafile, bedfile, slayout)
# legend showing the orientation of the genes
draw_gene_legend(root, .42, .52, .48)
labels = ((.04, .96, 'A'), (.04, .52, 'B'))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "pomegranate-karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
p.add_option("--switch",
help="Rename the seqid with two-column file [default: %default]")
p.add_option("--tree",
help="Display trees on the bottom of the figure [default: %default]")
p.add_option("--extra", help="Extra features in BED format")
p.add_option("--scalebar", default=False, action="store_true",
help="Add scale bar to the plot")
opts, args, iopts = p.set_image_options(figsize="8x7")
if len(args) != 3:
sys.exit(not p.print_help())
datafile, bedfile, layoutfile = args
switch = opts.switch
tree = opts.tree
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(fig, root, datafile, bedfile, layoutfile,
switch=switch, tree=tree, extra_features=opts.extra,
scalebar=opts.scalebar)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def allelefreq(args):
"""
%prog allelefreq HD,DM1,SCA1,SCA17
Plot the allele frequencies of some STRs.
"""
p = OptionParser(allelefreq.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="10x10")
if len(args) != 1:
sys.exit(not p.print_help())
loci, = args
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(ncols=2,
nrows=2,
figsize=(iopts.w, iopts.h))
plt.tight_layout(pad=4)
treds, df = read_treds()
df = df.set_index(["abbreviation"])
for ax, locus in zip((ax1, ax2, ax3, ax4), loci.split(",")):
plot_allelefreq(ax, df, locus)
root = fig.add_axes([0, 0, 1, 1])
pad = .03
panel_labels(root, ((pad / 2, 1 - pad, "A"), (1 / 2., 1 - pad, "B"),
(pad / 2, 1 / 2., "C"), (1 / 2., 1 / 2., "D")))
normalize_axes(root)
image_name = "allelefreq." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def coverage(args):
"""
%prog coverage *.coverage
Plot coverage along chromosome. The coverage file can be generated with:
$ samtools depth a.bam > a.coverage
The plot is a simple line plot using matplotlib.
"""
from jcvi.graphics.base import savefig
p = OptionParser(coverage.__doc__)
opts, args, iopts = p.set_image_options(args, format="png")
if len(args) != 1:
sys.exit(not p.print_help())
covfile, = args
df = pd.read_csv(covfile, sep='\t', names=["Ref", "Position", "Depth"])
xlabel, ylabel = "Position", "Depth"
df.plot(xlabel, ylabel, color='g')
image_name = covfile + "." + iopts.format
savefig(image_name)
def main(args):
"""
%prog table.csv
Render a table on canvas. Input is a CSV file.
"""
p = OptionParser(main.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="7x7")
if len(args) != 1:
sys.exit(not p.print_help())
(csvfile, ) = args
pf = csvfile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
csv_table = CsvTable(csvfile)
draw_table(root, csv_table)
normalize_axes(root)
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def coverage(args):
"""
%prog coverage *.coverage
Plot coverage along chromosome. The coverage file can be generated with:
$ samtools depth a.bam > a.coverage
The plot is a simple line plot using matplotlib.
"""
from jcvi.graphics.base import savefig
p = OptionParser(coverage.__doc__)
opts, args, iopts = p.set_image_options(args, format="png")
if len(args) != 1:
sys.exit(not p.print_help())
(covfile, ) = args
df = pd.read_csv(covfile, sep="\t", names=["Ref", "Position", "Depth"])
xlabel, ylabel = "Position", "Depth"
df.plot(xlabel, ylabel, color="g")
image_name = covfile + "." + iopts.format
savefig(image_name)
def wgd(args):
"""
%prog wgd vplanifoliaA_blocks.bed vplanifoliaA.sizes
Create a wgd figure.
"""
from jcvi.graphics.chromosome import draw_chromosomes
p = OptionParser(synteny.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x5")
(bedfile, sizesfile) = args
fig = plt.figure(1, (iopts.w, iopts.h))
ax1 = fig.add_axes([0, 0, 1, 1])
title = r"Genome duplication $\alpha^{O}$ event in $\textit{Vanilla}$"
draw_chromosomes(
ax1,
bedfile,
sizes=sizesfile,
iopts=iopts,
mergedist=200000,
winsize=50000,
imagemap=False,
gauge=True,
legend=False,
title=title,
)
normalize_axes([ax1])
image_name = "wgd.pdf"
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def birch(args):
"""
%prog birch seqids layout
Plot birch macro-synteny, with an embedded phylogenetic tree to the right.
"""
p = OptionParser(birch.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x6")
if len(args) != 2:
sys.exit(not p.print_help())
seqids, layout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
K = Karyotype(fig, root, seqids, layout)
L = K.layout
xs = .79
dt = dict(rectangle=False, circle=False)
# Embed a phylogenetic tree to the right
coords = {}
coords["Amborella"] = (xs, L[0].y)
coords["Vitis"] = (xs, L[1].y)
coords["Prunus"] = (xs, L[2].y)
coords["Betula"] = (xs, L[3].y)
coords["Populus"] = (xs, L[4].y)
coords["Arabidopsis"] = (xs, L[5].y)
coords["fabids"] = join_nodes(root, coords, "Prunus", "Betula", xs, **dt)
coords["malvids"] = join_nodes(root, coords, \
"Populus", "Arabidopsis", xs, **dt)
coords["rosids"] = join_nodes(root, coords, "fabids", "malvids", xs, **dt)
coords["eudicots"] = join_nodes(root, coords, "rosids", "Vitis", xs, **dt)
coords["angiosperm"] = join_nodes(root, coords, \
"eudicots", "Amborella", xs, **dt)
# Show branch length
branch_length(root, coords["Amborella"], coords["angiosperm"], ">160.0")
branch_length(root, coords["eudicots"], coords["angiosperm"],
">78.2", va="top")
branch_length(root, coords["Vitis"], coords["eudicots"], "138.5")
branch_length(root, coords["rosids"], coords["eudicots"],
"19.8", va="top")
branch_length(root, coords["Prunus"], coords["fabids"],
"104.2", ha="right", va="top")
branch_length(root, coords["Arabidopsis"], coords["malvids"],
"110.2", va="top")
branch_length(root, coords["fabids"], coords["rosids"],
"19.8", ha="right", va="top")
branch_length(root, coords["malvids"], coords["rosids"],
"8.5", va="top")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "birch"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def report(args):
'''
%prog report ksfile
generate a report given a Ks result file (as produced by synonymous_calc.py).
describe the median Ks, Ka values, as well as the distribution in stem-leaf plot
'''
from jcvi.utils.cbook import SummaryStats
from jcvi.graphics.histogram import stem_leaf_plot
p = OptionParser(report.__doc__)
p.add_option("--pdf", default=False, action="store_true",
help="Generate graphic output for the histogram [default: %default]")
p.add_option("--components", default=1, type="int",
help="Number of components to decompose peaks [default: %default]")
add_plot_options(p)
opts, args, iopts = p.set_image_options(args, figsize="5x5")
if len(args) != 1:
sys.exit(not p.print_help())
ks_file, = args
data = read_ks_file(ks_file)
ks_min = opts.vmin
ks_max = opts.vmax
bins = opts.bins
for f in fields.split(",")[1:]:
columndata = [getattr(x, f) for x in data]
ks = ("ks" in f)
if not ks:
continue
columndata = [x for x in columndata if ks_min <= x <= ks_max]
st = SummaryStats(columndata)
title = "{0} ({1}): ".format(descriptions[f], ks_file)
title += "Median:{0:.3f} (1Q:{1:.3f}|3Q:{2:.3f}||".\
format(st.median, st.firstq, st.thirdq)
title += "Mean:{0:.3f}|Std:{1:.3f}||N:{2})".\
format(st.mean, st.sd, st.size)
tbins = (0, ks_max, bins) if ks else (0, .6, 10)
digit = 2 if (ks_max * 1. / bins) < .1 else 1
stem_leaf_plot(columndata, *tbins, digit=digit, title=title)
if not opts.pdf:
return
components = opts.components
data = [x.ng_ks for x in data]
data = [x for x in data if ks_min <= x <= ks_max]
fig = plt.figure(1, (iopts.w, iopts.h))
ax = fig.add_axes([.12, .1, .8, .8])
kp = KsPlot(ax, ks_max, opts.bins, legendp=opts.legendp)
kp.add_data(data, components, fill=opts.fill)
kp.draw(title=opts.title)
def oropetium(args):
"""
%prog oropetium mcscan.out all.bed layout switch.ids
Build a composite figure that calls graphis.synteny.
"""
p = OptionParser(oropetium.__doc__)
p.add_option("--extra", help="Extra features in BED format")
opts, args, iopts = p.set_image_options(args, figsize="9x6")
if len(args) != 4:
sys.exit(not p.print_help())
datafile, bedfile, slayout, switch = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(
fig, root, datafile, bedfile, slayout, switch=switch, extra_features=opts.extra
)
# legend showing the orientation of the genes
draw_gene_legend(root, 0.4, 0.57, 0.74, text=True, repeat=True)
# On the left panel, make a species tree
fc = "lightslategrey"
coords = {}
xs, xp = 0.16, 0.03
coords["oropetium"] = (xs, 0.7)
coords["setaria"] = (xs, 0.6)
coords["sorghum"] = (xs, 0.5)
coords["rice"] = (xs, 0.4)
coords["brachypodium"] = (xs, 0.3)
xs -= xp
coords["Panicoideae"] = join_nodes(root, coords, "setaria", "sorghum", xs)
xs -= xp
coords["BEP"] = join_nodes(root, coords, "rice", "brachypodium", xs)
coords["PACMAD"] = join_nodes(root, coords, "oropetium", "Panicoideae", xs)
xs -= xp
coords["Poaceae"] = join_nodes(root, coords, "BEP", "PACMAD", xs)
# Names of the internal nodes
for tag in ("BEP", "Poaceae"):
nx, ny = coords[tag]
nx, ny = nx - 0.005, ny - 0.02
root.text(nx, ny, tag, rotation=90, ha="right", va="top", color=fc)
for tag in ("PACMAD",):
nx, ny = coords[tag]
nx, ny = nx - 0.005, ny + 0.02
root.text(nx, ny, tag, rotation=90, ha="right", va="bottom", color=fc)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "oropetium"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def compare2(args):
"""
%prog compare2
Compare performances of various variant callers on simulated STR datasets.
"""
p = OptionParser(compare2.__doc__)
p.add_option('--maxinsert',
default=300,
type="int",
help="Maximum number of repeats")
add_simulate_options(p)
opts, args, iopts = p.set_image_options(args, figsize="10x5")
if len(args) != 0:
sys.exit(not p.print_help())
depth = opts.depth
readlen = opts.readlen
distance = opts.distance
max_insert = opts.maxinsert
fig, (ax1, ax2) = plt.subplots(ncols=2,
nrows=1,
figsize=(iopts.w, iopts.h))
plt.tight_layout(pad=2)
# ax1: lobSTR vs TREDPARSE with haploid model
lobstr_results = parse_results("lobstr_results_homo.txt")
tredparse_results = parse_results("tredparse_results_homo.txt")
title = SIMULATED_HAPLOID + \
r" ($D=%s\times, L=%dbp, V=%dbp$)" % (depth, readlen, distance)
plot_compare(ax1,
title,
tredparse_results,
lobstr_results,
max_insert=max_insert)
# ax2: lobSTR vs TREDPARSE with diploid model
lobstr_results = parse_results("lobstr_results_het.txt", exclude=20)
tredparse_results = parse_results("tredparse_results_het.txt", exclude=20)
title = SIMULATED_DIPLOID + \
r" ($D=%s\times, L=%dbp, V=%dbp$)" % (depth, readlen, distance)
plot_compare(ax2,
title,
tredparse_results,
lobstr_results,
max_insert=max_insert)
for ax in (ax1, ax2):
ax.set_xlim(0, max_insert)
ax.set_ylim(0, max_insert)
root = fig.add_axes([0, 0, 1, 1])
pad = .03
panel_labels(root, ((pad / 2, 1 - pad, "A"), (1 / 2., 1 - pad, "B")))
normalize_axes(root)
image_name = "tredparse." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def utricularia(args):
from jcvi.graphics.synteny import main as synteny_main
p = OptionParser(synteny_main.__doc__)
p.add_option("--switch", help="Rename the seqid with two-column file")
opts, args, iopts = p.set_image_options(args, figsize="8x7")
if len(args) != 3:
sys.exit(not p.print_help())
datafile, bedfile, layoutfile = args
switch = opts.switch
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
s = Synteny(fig,
root,
datafile,
bedfile,
layoutfile,
loc_label=False,
switch=switch)
light = "lightslategrey"
RoundRect(root, (0.02, 0.69), 0.96, 0.24, fill=False, lw=2, ec=light)
RoundRect(root, (0.02, 0.09), 0.96, 0.48, fill=False, lw=2, ec=light)
za, zb = s.layout[1].ratio, s.layout[-1].ratio # zoom level
if za != 1:
root.text(
0.96,
0.89,
"{}x zoom".format(za).replace(".0x", "x"),
color=light,
ha="right",
va="center",
size=14,
)
if zb != 1:
root.text(
0.96,
0.12,
"{}x zoom".format(zb).replace(".0x", "x"),
color=light,
ha="right",
va="center",
size=14,
)
# legend showing the orientation of the genes
draw_gene_legend(root, 0.22, 0.3, 0.64, text=True)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def oropetium(args):
"""
%prog oropetium mcscan.out all.bed layout switch.ids
Build a composite figure that calls graphis.synteny.
"""
p = OptionParser(oropetium.__doc__)
p.add_option("--extra", help="Extra features in BED format")
opts, args, iopts = p.set_image_options(args, figsize="9x6")
if len(args) != 4:
sys.exit(not p.print_help())
datafile, bedfile, slayout, switch = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(fig, root, datafile, bedfile, slayout,
switch=switch, extra_features=opts.extra)
# legend showing the orientation of the genes
draw_gene_legend(root, .4, .57, .74, text=True, repeat=True)
# On the left panel, make a species tree
fc = 'lightslategrey'
coords = {}
xs, xp = .16, .03
coords["oropetium"] = (xs, .7)
coords["setaria"] = (xs, .6)
coords["sorghum"] = (xs, .5)
coords["rice"] = (xs, .4)
coords["brachypodium"] = (xs, .3)
xs -= xp
coords["Panicoideae"] = join_nodes(root, coords, "setaria", "sorghum", xs)
xs -= xp
coords["BEP"] = join_nodes(root, coords, "rice", "brachypodium", xs)
coords["PACMAD"] = join_nodes(root, coords, "oropetium", "Panicoideae", xs)
xs -= xp
coords["Poaceae"] = join_nodes(root, coords, "BEP", "PACMAD", xs)
# Names of the internal nodes
for tag in ("BEP", "Poaceae"):
nx, ny = coords[tag]
nx, ny = nx - .005, ny - .02
root.text(nx, ny, tag, rotation=90, ha="right", va="top", color=fc)
for tag in ("PACMAD",):
nx, ny = coords[tag]
nx, ny = nx - .005, ny + .02
root.text(nx, ny, tag, rotation=90, ha="right", va="bottom", color=fc)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "oropetium"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def litchi(args):
"""
%prog litchi mcscan.out all.bed layout switch.ids
Build a composite figure that calls graphis.synteny.
"""
p = OptionParser(litchi.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="9x6")
if len(args) != 4:
sys.exit(not p.print_help())
datafile, bedfile, slayout, switch = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(fig, root, datafile, bedfile, slayout, switch=switch)
# legend showing the orientation of the genes
draw_gene_legend(root, .4, .7, .82)
# On the left panel, make a species tree
fc = 'lightslategrey'
coords = {}
xs, xp = .16, .03
coords["lychee"] = (xs, .37)
coords["clementine"] = (xs, .5)
coords["cacao"] = (xs, .6)
coords["strawberry"] = (xs, .7)
coords["grape"] = (xs, .8)
xs -= xp
coords["Sapindales"] = join_nodes(root, coords, "clementine", "lychee", xs)
xs -= xp
coords["Rosid-II"] = join_nodes(root, coords, "cacao", "Sapindales", xs)
xs -= xp
coords["Rosid"] = join_nodes(root, coords, "strawberry", "Rosid-II", xs)
xs -= xp
coords["crown"] = join_nodes(root,
coords,
"grape",
"Rosid",
xs,
circle=False)
# Names of the internal nodes
for tag in ("Rosid", "Rosid-II", "Sapindales"):
nx, ny = coords[tag]
nx, ny = nx - .01, ny - .02
root.text(nx, ny, tag, rotation=90, ha="right", va="top", color=fc)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "litchi"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def compare(args):
"""
%prog compare Evaluation.csv
Compare performances of various variant callers on simulated STR datasets.
"""
p = OptionParser(compare.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="10x10")
if len(args) != 1:
sys.exit(not p.print_help())
datafile, = args
pf = datafile.rsplit(".", 1)[0]
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(ncols=2,
nrows=2,
figsize=(iopts.w, iopts.h))
plt.tight_layout(pad=3)
bbox = {'facecolor': 'tomato', 'alpha': .2, 'ec': 'w'}
pad = 2
# Read benchmark data
df = pd.read_csv("Evaluation.csv")
truth = df["Truth"]
axes = (ax1, ax2, ax3, ax4)
progs = ("Manta", "Isaac", "GATK", "lobSTR")
markers = ("bx-", "yo-", "md-", "c+-")
for ax, prog, marker in zip(axes, progs, markers):
ax.plot(truth, df[prog], marker)
ax.plot(truth, truth, 'k--') # to show diagonal
ax.axhline(infected_thr, color='tomato')
ax.text(max(truth) - pad,
infected_thr + pad,
'Risk threshold',
bbox=bbox,
ha="right")
ax.axhline(ref_thr, color='tomato')
ax.text(max(truth) - pad,
ref_thr - pad,
'Reference repeat count',
bbox=bbox,
ha="right",
va="top")
ax.set_title(SIMULATED_HAPLOID)
ax.set_xlabel(r'Num of CAG repeats inserted ($\mathit{h}$)')
ax.set_ylabel('Num of CAG repeats called')
ax.legend([prog, 'Truth'], loc='best')
root = fig.add_axes([0, 0, 1, 1])
pad = .03
panel_labels(root, ((pad / 2, 1 - pad, "A"), (1 / 2., 1 - pad, "B"),
(pad / 2, 1 / 2., "C"), (1 / 2., 1 / 2., "D")))
normalize_axes(root)
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def report(args):
'''
%prog report ksfile
generate a report given a Ks result file (as produced by synonymous_calc.py).
describe the median Ks, Ka values, as well as the distribution in stem-leaf plot
'''
from jcvi.utils.cbook import SummaryStats
from jcvi.graphics.histogram import stem_leaf_plot
p = OptionParser(report.__doc__)
p.add_option("--pdf", default=False, action="store_true",
help="Generate graphic output for the histogram [default: %default]")
p.add_option("--components", default=1, type="int",
help="Number of components to decompose peaks [default: %default]")
add_plot_options(p)
opts, args, iopts = p.set_image_options(args, figsize="5x5")
if len(args) != 1:
sys.exit(not p.print_help())
ks_file, = args
data = KsFile(ks_file)
ks_min = opts.vmin
ks_max = opts.vmax
bins = opts.bins
for f in fields.split(",")[1:]:
columndata = [getattr(x, f) for x in data]
ks = ("ks" in f)
if not ks:
continue
columndata = [x for x in columndata if ks_min <= x <= ks_max]
st = SummaryStats(columndata)
title = "{0} ({1}): ".format(descriptions[f], ks_file)
title += "Median:{0:.3f} (1Q:{1:.3f}|3Q:{2:.3f}||".\
format(st.median, st.firstq, st.thirdq)
title += "Mean:{0:.3f}|Std:{1:.3f}||N:{2})".\
format(st.mean, st.sd, st.size)
tbins = (0, ks_max, bins) if ks else (0, .6, 10)
digit = 2 if (ks_max * 1. / bins) < .1 else 1
stem_leaf_plot(columndata, *tbins, digit=digit, title=title)
if not opts.pdf:
return
components = opts.components
data = [x.ng_ks for x in data]
data = [x for x in data if ks_min <= x <= ks_max]
fig = plt.figure(1, (iopts.w, iopts.h))
ax = fig.add_axes([.12, .1, .8, .8])
kp = KsPlot(ax, ks_max, opts.bins, legendp=opts.legendp)
kp.add_data(data, components, fill=opts.fill, fitted=opts.fit)
kp.draw(title=opts.title)
def snpplot(args):
"""
%prog counts.cdt
Illustrate the histogram per SNP site.
"""
p = OptionParser(snpplot.__doc__)
opts, args, iopts = p.set_image_options(args, format="png")
if len(args) != 1:
sys.exit(not p.print_help())
(datafile,) = args
# Read in CDT file
fp = open(datafile)
next(fp)
next(fp)
data = []
for row in fp:
atoms = row.split()[4:]
nval = len(atoms)
values = [float(x) for x in atoms]
# normalize
values = [x * 1.0 / sum(values) for x in values]
data.append(values)
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
xmin, xmax = 0.1, 0.9
ymin, ymax = 0.1, 0.9
yinterval = (ymax - ymin) / len(data)
colors = "rbg" if nval == 3 else ["lightgray"] + list("rbg")
ystart = ymax
for d in data:
xstart = xmin
for dd, c in zip(d, colors):
xend = xstart + (xmax - xmin) * dd
root.plot((xstart, xend), (ystart, ystart), "-", color=c)
xstart = xend
ystart -= yinterval
root.text(
0.05,
0.5,
"{0} LMD50 SNPs".format(len(data)),
ha="center",
va="center",
rotation=90,
color="lightslategray",
)
for x, t, c in zip((0.3, 0.5, 0.7), ("REF", "ALT", "HET"), "rbg"):
root.text(x, 0.95, t, color=c, ha="center", va="center")
normalize_axes(root)
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def mtdotplots(args):
"""
%prog mtdotplots Mt3.5 Mt4.0 medicago.medicago.lifted.1x1.anchors
Plot Mt3.5 and Mt4.0 side-by-side. This is essentially combined from two
graphics.dotplot() function calls as panel A and B.
"""
from jcvi.graphics.dotplot import check_beds, dotplot
p = OptionParser(mtdotplots.__doc__)
p.set_beds()
opts, args, iopts = p.set_image_options(args, figsize="16x8", dpi=90)
if len(args) != 3:
sys.exit(not p.print_help())
a, b, ac = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
r1 = fig.add_axes([0, 0, .5, 1])
r2 = fig.add_axes([.5, 0, .5, 1])
a1 = fig.add_axes([.05, .1, .4, .8])
a2 = fig.add_axes([.55, .1, .4, .8])
anchorfile = op.join(a, ac)
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
dotplot(anchorfile,
qbed,
sbed,
fig,
r1,
a1,
is_self=is_self,
genomenames="Mt3.5_Mt3.5")
opts.qbed = opts.sbed = None
anchorfile = op.join(b, ac)
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
dotplot(anchorfile,
qbed,
sbed,
fig,
r2,
a2,
is_self=is_self,
genomenames="Mt4.0_Mt4.0")
root.text(.03, .95, "A", ha="center", va="center", size=36)
root.text(.53, .95, "B", ha="center", va="center", size=36)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "mtdotplots"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def multilineplot(args):
"""
%prog multilineplot fastafile chr1
Combine multiple line plots in one vertical stack
Inputs must be BED-formatted.
--lines: traditional line plots, useful for plotting feature freq
"""
p = OptionParser(multilineplot.__doc__)
p.add_option("--lines",
help="Features to plot in lineplot [default: %default]")
p.add_option("--colors",
help="List of colors matching number of input bed files")
p.add_option("--mode", default="span", choices=("span", "count", "score"),
help="Accumulate feature based on [default: %default]")
p.add_option("--binned", default=False, action="store_true",
help="Specify whether the input is already binned; " +
"if True, input files are considered to be binfiles")
add_window_options(p)
opts, args, iopts = p.set_image_options(args, figsize="8x5")
if len(args) != 2:
sys.exit(not p.print_help())
fastafile, chr = args
window, shift, subtract = check_window_options(opts)
linebeds = []
colors = opts.colors
if opts.lines:
lines = opts.lines.split(",")
assert len(colors) == len(lines), "Number of chosen colors must match" + \
" number of input bed files"
linebeds = get_beds(lines, binned=opts.binned)
linebins = get_binfiles(linebeds, fastafile, shift, mode=opts.mode, binned=opts.binned)
clen = Sizes(fastafile).mapping[chr]
nbins = get_nbins(clen, shift)
plt.rcParams["xtick.major.size"] = 0
plt.rcParams["ytick.major.size"] = 0
plt.rcParams["figure.figsize"] = iopts.w, iopts.h
fig, axarr = plt.subplots(nrows=len(lines))
if len(linebeds) == 1:
axarr = (axarr, )
fig.suptitle(chr, color="darkslategray")
for i, ax in enumerate(axarr):
lineplot(ax, [linebins[i]], nbins, chr, window, shift, \
color="{0}{1}".format(colors[i], 'r'))
plt.subplots_adjust(hspace=0.5)
image_name = chr + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def birch(args):
"""
%prog birch seqids layout
Plot birch macro-synteny, with an embedded phylogenetic tree to the right.
"""
p = OptionParser(birch.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x6")
if len(args) != 2:
sys.exit(not p.print_help())
seqids, layout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
K = Karyotype(fig, root, seqids, layout)
L = K.layout
xs = 0.79
dt = dict(rectangle=False, circle=False)
# Embed a phylogenetic tree to the right
coords = {}
coords["Amborella"] = (xs, L[0].y)
coords["Vitis"] = (xs, L[1].y)
coords["Prunus"] = (xs, L[2].y)
coords["Betula"] = (xs, L[3].y)
coords["Populus"] = (xs, L[4].y)
coords["Arabidopsis"] = (xs, L[5].y)
coords["fabids"] = join_nodes(root, coords, "Prunus", "Betula", xs, **dt)
coords["malvids"] = join_nodes(root, coords, "Populus", "Arabidopsis", xs, **dt)
coords["rosids"] = join_nodes(root, coords, "fabids", "malvids", xs, **dt)
coords["eudicots"] = join_nodes(root, coords, "rosids", "Vitis", xs, **dt)
coords["angiosperm"] = join_nodes(root, coords, "eudicots", "Amborella", xs, **dt)
# Show branch length
branch_length(root, coords["Amborella"], coords["angiosperm"], ">160.0")
branch_length(root, coords["eudicots"], coords["angiosperm"], ">78.2", va="top")
branch_length(root, coords["Vitis"], coords["eudicots"], "138.5")
branch_length(root, coords["rosids"], coords["eudicots"], "19.8", va="top")
branch_length(
root, coords["Prunus"], coords["fabids"], "104.2", ha="right", va="top"
)
branch_length(root, coords["Arabidopsis"], coords["malvids"], "110.2", va="top")
branch_length(
root, coords["fabids"], coords["rosids"], "19.8", ha="right", va="top"
)
branch_length(root, coords["malvids"], coords["rosids"], "8.5", va="top")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "birch"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def scaffold(args):
"""
%prog scaffold scaffold.fasta synteny.blast synteny.sizes synteny.bed
physicalmap.blast physicalmap.sizes physicalmap.bed
As evaluation of scaffolding, visualize external line of evidences:
* Plot synteny to an external genome
* Plot alignments to physical map
* Plot alignments to genetic map (TODO)
Each trio defines one panel to be plotted. blastfile defines the matchings
between the evidences vs scaffolds. Then the evidence sizes, and evidence
bed to plot dot plots.
This script will plot a dot in the dot plot in the corresponding location
the plots are one contig/scaffold per plot.
"""
from jcvi.utils.iter import grouper
p = OptionParser(scaffold.__doc__)
p.add_option("--cutoff", type="int", default=1000000,
help="Plot scaffolds with size larger than [default: %default]")
p.add_option("--highlights",
help="A set of regions in BED format to highlight [default: %default]")
opts, args, iopts = p.set_image_options(args, figsize="14x8", dpi=150)
if len(args) < 4 or len(args) % 3 != 1:
sys.exit(not p.print_help())
highlights = opts.highlights
scafsizes = Sizes(args[0])
trios = list(grouper(args[1:], 3))
trios = [(a, Sizes(b), Bed(c)) for a, b, c in trios]
if highlights:
hlbed = Bed(highlights)
for scaffoldID, scafsize in scafsizes.iter_sizes():
if scafsize < opts.cutoff:
continue
logging.debug("Loading {0} (size={1})".format(scaffoldID,
thousands(scafsize)))
tmpname = scaffoldID + ".sizes"
tmp = open(tmpname, "w")
tmp.write("{0}\t{1}".format(scaffoldID, scafsize))
tmp.close()
tmpsizes = Sizes(tmpname)
tmpsizes.close(clean=True)
if highlights:
subhighlights = list(hlbed.sub_bed(scaffoldID))
imagename = ".".join((scaffoldID, opts.format))
plot_one_scaffold(scaffoldID, tmpsizes, None, trios, imagename, iopts,
highlights=subhighlights)
def main():
p = OptionParser(__doc__)
p.add_option(
"--basepair",
default=False,
action="store_true",
help="Use base pair position instead of gene rank",
)
p.add_option(
"--nocircles",
default=False,
action="store_true",
help="Do not plot chromosome circles",
)
p.add_option(
"--shadestyle",
default="curve",
choices=Shade.Styles,
help="Style of syntenic wedges",
)
p.add_option("-p",
"--prefix",
default="karyotype",
dest="outpfx",
type="string",
help="File prefix for output image",
metavar="FILE_PREFIX")
opts, args, iopts = p.set_image_options(figsize="8x7")
if len(args) != 2:
sys.exit(not p.print_help())
seqidsfile, layoutfile = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(
fig,
root,
seqidsfile,
layoutfile,
plot_circles=(not opts.nocircles),
shadestyle=opts.shadestyle,
generank=(not opts.basepair),
)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = opts.outpfx
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def venn(args):
"""
%prog venn *.benchmark
Display benchmark results as Venn diagram.
"""
from matplotlib_venn import venn2
p = OptionParser(venn.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="9x9")
if len(args) < 1:
sys.exit(not p.print_help())
bcs = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
pad = .02
ystart = 1
ywidth = 1. / len(bcs)
tags = ("Bowers", "YGOB", "Schnable")
for bc, tag in zip(bcs, tags):
fp = open(bc)
data = []
for row in fp:
prog, pcounts, tcounts, shared = row.split()
pcounts = int(pcounts)
tcounts = int(tcounts)
shared = int(shared)
data.append((prog, pcounts, tcounts, shared))
xstart = 0
xwidth = 1. / len(data)
for prog, pcounts, tcounts, shared in data:
a, b, c = pcounts - shared, tcounts - shared, shared
ax = fig.add_axes([xstart + pad, ystart - ywidth + pad,
xwidth - 2 * pad, ywidth - 2 * pad])
venn2(subsets=(a, b, c), set_labels=(prog, tag), ax=ax)
message = "Sn={0} Pu={1}".\
format(percentage(shared, tcounts, precision=0, mode=-1),
percentage(shared, pcounts, precision=0, mode=-1))
print(message, file=sys.stderr)
ax.text(.5, .92, latex(message), ha="center", va="center",
transform=ax.transAxes, color='b')
ax.set_axis_off()
xstart += xwidth
ystart -= ywidth
panel_labels(root, ((.04, .96, "A"), (.04, .96 - ywidth, "B"),
(.04, .96 - 2 * ywidth, "C")))
panel_labels(root, ((.5, .98, "A. thaliana duplicates"),
(.5, .98 - ywidth, "14 Yeast genomes"),
(.5, .98 - 2 * ywidth, "4 Grass genomes")))
normalize_axes(root)
savefig("venn.pdf", dpi=opts.dpi)
def venn(args):
"""
%prog venn *.benchmark
Display benchmark results as Venn diagram.
"""
from matplotlib_venn import venn2
p = OptionParser(venn.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="9x9")
if len(args) < 1:
sys.exit(not p.print_help())
bcs = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
pad = .02
ystart = 1
ywidth = 1. / len(bcs)
tags = ("Bowers", "YGOB", "Schnable")
for bc, tag in zip(bcs, tags):
fp = open(bc)
data = []
for row in fp:
prog, pcounts, tcounts, shared = row.split()
pcounts = int(pcounts)
tcounts = int(tcounts)
shared = int(shared)
data.append((prog, pcounts, tcounts, shared))
xstart = 0
xwidth = 1. / len(data)
for prog, pcounts, tcounts, shared in data:
a, b, c = pcounts - shared, tcounts - shared, shared
ax = fig.add_axes([xstart + pad, ystart - ywidth + pad,
xwidth - 2 * pad, ywidth - 2 * pad])
venn2(subsets=(a, b, c), set_labels=(prog, tag), ax=ax)
message = "Sn={0} Pu={1}".\
format(percentage(shared, tcounts, precision=0, mode=-1),
percentage(shared, pcounts, precision=0, mode=-1))
print >> sys.stderr, message
ax.text(.5, .92, latex(message), ha="center", va="center",
transform=ax.transAxes, color='b')
ax.set_axis_off()
xstart += xwidth
ystart -= ywidth
panel_labels(root, ((.04, .96, "A"), (.04, .96 - ywidth, "B"),
(.04, .96 - 2 * ywidth, "C")))
panel_labels(root, ((.5, .98, "A. thaliana duplicates"),
(.5, .98 - ywidth, "14 Yeast genomes"),
(.5, .98 - 2 * ywidth, "4 Grass genomes")))
normalize_axes(root)
savefig("venn.pdf", dpi=opts.dpi)
def litchi(args):
"""
%prog litchi mcscan.out all.bed layout switch.ids
Build a composite figure that calls graphis.synteny.
"""
p = OptionParser(litchi.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="9x6")
if len(args) != 4:
sys.exit(not p.print_help())
datafile, bedfile, slayout, switch = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(fig, root, datafile, bedfile, slayout, switch=switch)
# legend showing the orientation of the genes
draw_gene_legend(root, .4, .7, .82)
# On the left panel, make a species tree
fc = 'lightslategrey'
coords = {}
xs, xp = .16, .03
coords["lychee"] = (xs, .37)
coords["clementine"] = (xs, .5)
coords["cacao"] = (xs, .6)
coords["strawberry"] = (xs, .7)
coords["grape"] = (xs, .8)
xs -= xp
coords["Sapindales"] = join_nodes(root, coords, "clementine", "lychee", xs)
xs -= xp
coords["Rosid-II"] = join_nodes(root, coords, "cacao", "Sapindales", xs)
xs -= xp
coords["Rosid"] = join_nodes(root, coords, "strawberry", "Rosid-II", xs)
xs -= xp
coords["crown"] = join_nodes(root, coords, "grape", "Rosid", xs,
circle=False)
# Names of the internal nodes
for tag in ("Rosid", "Rosid-II", "Sapindales"):
nx, ny = coords[tag]
nx, ny = nx - .01, ny - .02
root.text(nx, ny, tag, rotation=90, ha="right", va="top", color=fc)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "litchi"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
p.add_option(
"--switch", help="Rename the seqid with two-column file [default: %default]"
)
p.add_option(
"--tree", help="Display trees on the bottom of the figure [default: %default]"
)
p.add_option("--extra", help="Extra features in BED format")
p.add_option(
"--scalebar",
default=False,
action="store_true",
help="Add scale bar to the plot",
)
p.add_option(
"--shadestyle",
default="curve",
choices=Shade.Styles,
help="Style of syntenic wedges",
)
opts, args, iopts = p.set_image_options(figsize="8x7")
if len(args) != 3:
sys.exit(not p.print_help())
datafile, bedfile, layoutfile = args
switch = opts.switch
tree = opts.tree
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Synteny(
fig,
root,
datafile,
bedfile,
layoutfile,
switch=switch,
tree=tree,
extra_features=opts.extra,
scalebar=opts.scalebar,
shadestyle=opts.shadestyle,
)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def multireport(args):
"""
%prog multireport layoutfile
Generate several Ks value distributions in the same figure. If the layout
file is missing then a template file listing all ks files will be written.
The layout file contains the Ks file, number of components, colors, and labels:
# Ks file, ncomponents, label, color, marker
LAP.sorghum.ks, 1, LAP-sorghum, r, o
SES.sorghum.ks, 1, SES-sorghum, g, +
MOL.sorghum.ks, 1, MOL-sorghum, m, ^
If color or marker is missing, then a random one will be assigned.
"""
p = OptionParser(multireport.__doc__)
p.set_outfile(outfile="Ks_plot.pdf")
add_plot_options(p)
opts, args, iopts = p.set_image_options(args, figsize="8x6")
if len(args) != 1:
sys.exit(not p.print_help())
(layoutfile, ) = args
ks_min = opts.vmin
ks_max = opts.vmax
bins = opts.bins
fill = opts.fill
layout = Layout(layoutfile)
print(layout, file=sys.stderr)
fig = plt.figure(1, (iopts.w, iopts.h))
ax = fig.add_axes([0.12, 0.13, 0.8, 0.8])
kp = KsPlot(ax, ks_max, bins, legendp=opts.legendp)
for lo in layout:
data = KsFile(lo.ksfile)
data = [x.ng_ks for x in data]
data = [x for x in data if ks_min <= x <= ks_max]
kp.add_data(
data,
lo.components,
label=lo.label,
color=lo.color,
marker=lo.marker,
fill=fill,
fitted=opts.fit,
kde=opts.kde,
)
kp.draw(title=opts.title, filename=opts.outfile)
def covlen(args):
"""
%prog covlen covfile fastafile
Plot coverage vs length. `covfile` is two-column listing contig id and
depth of coverage.
"""
import numpy as np
import pandas as pd
import seaborn as sns
from jcvi.formats.base import DictFile
p = OptionParser(covlen.__doc__)
p.add_option("--maxsize", default=1000000, type="int", help="Max contig size")
p.add_option("--maxcov", default=100, type="int", help="Max contig size")
p.add_option("--color", default='m', help="Color of the data points")
p.add_option("--kind", default="scatter",
choices=("scatter", "reg", "resid", "kde", "hex"),
help="Kind of plot to draw")
opts, args, iopts = p.set_image_options(args, figsize="8x8")
if len(args) != 2:
sys.exit(not p.print_help())
covfile, fastafile = args
cov = DictFile(covfile, cast=float)
s = Sizes(fastafile)
data = []
maxsize, maxcov = opts.maxsize, opts.maxcov
for ctg, size in s.iter_sizes():
c = cov.get(ctg, 0)
if size > maxsize:
continue
if c > maxcov:
continue
data.append((size, c))
x, y = zip(*data)
x = np.array(x)
y = np.array(y)
logging.debug("X size {0}, Y size {1}".format(x.size, y.size))
df = pd.DataFrame()
xlab, ylab = "Length", "Coverage of depth (X)"
df[xlab] = x
df[ylab] = y
sns.jointplot(xlab, ylab, kind=opts.kind, data=df,
xlim=(0, maxsize), ylim=(0, maxcov),
stat_func=None, edgecolor="w", color=opts.color)
figname = covfile + ".pdf"
savefig(figname, dpi=iopts.dpi, iopts=iopts)
def snpplot(args):
"""
%prog counts.cdt
Illustrate the histogram per SNP site.
"""
p = OptionParser(snpplot.__doc__)
opts, args, iopts = p.set_image_options(args, format="png")
if len(args) != 1:
sys.exit(not p.print_help())
datafile, = args
# Read in CDT file
fp = open(datafile)
next(fp)
next(fp)
data = []
for row in fp:
atoms = row.split()[4:]
nval = len(atoms)
values = [float(x) for x in atoms]
# normalize
values = [x * 1. / sum(values) for x in values]
data.append(values)
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
xmin, xmax = .1, .9
ymin, ymax = .1, .9
yinterval = (ymax - ymin) / len(data)
colors = "rbg" if nval == 3 else ["lightgray"] + list("rbg")
ystart = ymax
for d in data:
xstart = xmin
for dd, c in zip(d, colors):
xend = xstart + (xmax - xmin) * dd
root.plot((xstart, xend), (ystart, ystart), "-", color=c)
xstart = xend
ystart -= yinterval
root.text(.05, .5, "{0} LMD50 SNPs".format(len(data)),
ha="center", va="center", rotation=90, color="lightslategray")
for x, t, c in zip((.3, .5, .7), ("REF", "ALT", "HET"), "rbg"):
root.text(x, .95, t, color=c, ha="center", va="center")
normalize_axes(root)
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def amborella(args):
"""
%prog amborella seqids karyotype.layout mcscan.out all.bed synteny.layout
Build a composite figure that calls graphics.karyotype and graphics.synteny.
"""
p = OptionParser(amborella.__doc__)
p.add_option(
"--tree",
help="Display trees on the bottom of the figure [default: %default]")
p.add_option(
"--switch",
help="Rename the seqid with two-column file [default: %default]")
opts, args, iopts = p.set_image_options(args, figsize="8x7")
if len(args) != 5:
sys.exit(not p.print_help())
seqidsfile, klayout, datafile, bedfile, slayout = args
switch = opts.switch
tree = opts.tree
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
Synteny(fig, root, datafile, bedfile, slayout, switch=switch, tree=tree)
# legend showing the orientation of the genes
draw_gene_legend(root, .5, .68, .5)
# annotate the WGD events
fc = 'lightslategrey'
x = .05
radius = .012
TextCircle(root, x, .86, '$\gamma$', radius=radius)
TextCircle(root, x, .95, '$\epsilon$', radius=radius)
root.plot([x, x], [.83, .9], ":", color=fc, lw=2)
pts = plot_cap((x, .95), np.radians(range(-70, 250)), .02)
x, y = zip(*pts)
root.plot(x, y, ":", color=fc, lw=2)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "amborella"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def movieframe(args):
"""
%prog movieframe tour test.clm contigs.ref.anchors
Draw heatmap and synteny in the same plot.
"""
p = OptionParser(movieframe.__doc__)
p.add_option("--label", help="Figure title")
p.set_beds()
p.set_outfile(outfile=None)
opts, args, iopts = p.set_image_options(args,
figsize="16x8",
style="white",
cmap="coolwarm",
format="png",
dpi=120)
if len(args) != 3:
sys.exit(not p.print_help())
tour, clmfile, anchorsfile = args
tour = tour.split(",")
image_name = opts.outfile or ("movieframe." + iopts.format)
label = opts.label or op.basename(image_name).rsplit(".", 1)[0]
clm = CLMFile(clmfile)
totalbins, bins, breaks = make_bins(tour, clm.tig_to_size)
M = read_clm(clm, totalbins, bins)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1]) # whole canvas
ax1 = fig.add_axes([.05, .1, .4, .8]) # heatmap
ax2 = fig.add_axes([.55, .1, .4, .8]) # dot plot
ax2_root = fig.add_axes([.5, 0, .5, 1]) # dot plot canvas
# Left axis: heatmap
plot_heatmap(ax1, M, breaks, iopts)
# Right axis: synteny
qbed, sbed, qorder, sorder, is_self = check_beds(anchorsfile,
p,
opts,
sorted=False)
dotplot(anchorsfile, qbed, sbed, fig, ax2_root, ax2, sep=False, title="")
root.text(.5, .98, clm.name, color="g", ha="center", va="center")
root.text(.5, .95, label, color="darkslategray", ha="center", va="center")
normalize_axes(root)
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def ploidy(args):
"""
%prog ploidy seqids karyotype.layout mcscan.out all.bed synteny.layout
Build a figure that calls graphics.karyotype to illustrate the high ploidy
of WGD history of pineapple genome. The script calls both graphics.karyotype
and graphic.synteny.
"""
p = OptionParser(ploidy.__doc__)
p.add_option("--switch", help="Rename the seqid with two-column file")
opts, args, iopts = p.set_image_options(args, figsize="9x7")
if len(args) != 5:
sys.exit(not p.print_help())
seqidsfile, klayout, datafile, bedfile, slayout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
Synteny(fig, root, datafile, bedfile, slayout, switch=opts.switch)
# legend showing the orientation of the genes
draw_gene_legend(root, .27, .37, .52)
# annotate the WGD events
fc = 'lightslategrey'
x = .09
radius = .012
TextCircle(root, x, .825, r'$\tau$', radius=radius, fc=fc)
TextCircle(root, x, .8, r'$\sigma$', radius=radius, fc=fc)
TextCircle(root, x, .72, r'$\rho$', radius=radius, fc=fc)
for ypos in (.825, .8, .72):
root.text(.12, ypos, r"$\times2$", color=fc, ha="center", va="center")
root.plot([x, x], [.85, .775], ":", color=fc, lw=2)
root.plot([x, x], [.75, .675], ":", color=fc, lw=2)
labels = ((.04, .96, 'A'), (.04, .54, 'B'))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "pineapple-karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def ploidy(args):
"""
%prog cotton seqids karyotype.layout mcscan.out all.bed synteny.layout
Build a figure that calls graphics.karyotype to illustrate the high ploidy
of WGD history of pineapple genome. The script calls both graphics.karyotype
and graphic.synteny.
"""
p = OptionParser(ploidy.__doc__)
p.add_option("--switch", help="Rename the seqid with two-column file")
opts, args, iopts = p.set_image_options(args, figsize="9x7")
if len(args) != 5:
sys.exit(not p.print_help())
seqidsfile, klayout, datafile, bedfile, slayout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
Synteny(fig, root, datafile, bedfile, slayout, switch=opts.switch)
# legend showing the orientation of the genes
draw_gene_legend(root, .27, .37, .52)
# annotate the WGD events
fc = 'lightslategrey'
x = .09
radius = .012
TextCircle(root, x, .825, r'$\tau$', radius=radius, fc=fc)
TextCircle(root, x, .8, r'$\sigma$', radius=radius, fc=fc)
TextCircle(root, x, .72, r'$\rho$', radius=radius, fc=fc)
for ypos in (.825, .8, .72):
root.text(.12, ypos, r"$\times2$", color=fc, ha="center", va="center")
root.plot([x, x], [.85, .775], ":", color=fc, lw=2)
root.plot([x, x], [.75, .675], ":", color=fc, lw=2)
labels = ((.04, .96, 'A'), (.04, .54, 'B'))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "pineapple-karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def ploidy(args):
"""
%prog ploidy seqids layout
Build a figure that calls graphics.karyotype to illustrate the high ploidy
of B. napus genome.
"""
p = OptionParser(ploidy.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x7")
if len(args) != 2:
sys.exit(not p.print_help())
seqidsfile, klayout = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
fc = "darkslategrey"
radius = .012
ot = -.05 # use this to adjust vertical position of the left panel
TextCircle(root, .1, .9 + ot, r'$\gamma$', radius=radius, fc=fc)
root.text(.1, .88 + ot, r"$\times3$", ha="center", va="top", color=fc)
TextCircle(root, .08, .79 + ot, r'$\alpha$', radius=radius, fc=fc)
TextCircle(root, .12, .79 + ot, r'$\beta$', radius=radius, fc=fc)
root.text(.1, .77 + ot, r"$\times3\times2\times2$", ha="center", va="top", color=fc)
root.text(.1, .67 + ot, r"Brassica triplication", ha="center",
va="top", color=fc, size=11)
root.text(.1, .65 + ot, r"$\times3\times2\times2\times3$", ha="center", va="top", color=fc)
root.text(.1, .42 + ot, r"Allo-tetraploidy", ha="center",
va="top", color=fc, size=11)
root.text(.1, .4 + ot, r"$\times3\times2\times2\times3\times2$", ha="center", va="top", color=fc)
bb = dict(boxstyle="round,pad=.5", fc="w", ec="0.5", alpha=0.5)
root.text(.5, .2 + ot, r"\noindent\textit{Brassica napus}\\"
"(A$\mathsf{_n}$C$\mathsf{_n}$ genome)", ha="center",
size=16, color="k", bbox=bb)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "napus"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def amborella(args):
"""
%prog amborella seqids karyotype.layout mcscan.out all.bed synteny.layout
Build a composite figure that calls graphics.karyotype and graphics.synteny.
"""
p = OptionParser(amborella.__doc__)
p.add_option("--tree",
help="Display trees on the bottom of the figure [default: %default]")
p.add_option("--switch",
help="Rename the seqid with two-column file [default: %default]")
opts, args, iopts = p.set_image_options(args, figsize="8x7")
if len(args) != 5:
sys.exit(not p.print_help())
seqidsfile, klayout, datafile, bedfile, slayout = args
switch = opts.switch
tree = opts.tree
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, klayout)
Synteny(fig, root, datafile, bedfile, slayout, switch=switch, tree=tree)
# legend showing the orientation of the genes
draw_gene_legend(root, .5, .68, .5)
# annotate the WGD events
fc = 'lightslategrey'
x = .05
radius = .012
TextCircle(root, x, .86, '$\gamma$', radius=radius)
TextCircle(root, x, .95, '$\epsilon$', radius=radius)
root.plot([x, x], [.83, .9], ":", color=fc, lw=2)
pts = plot_cap((x, .95), np.radians(range(-70, 250)), .02)
x, y = zip(*pts)
root.plot(x, y, ":", color=fc, lw=2)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "amborella"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def ccn(args):
"""
%prog ccn combined.tsv
Plot several ccn plots including chr1,chrX,chrY,chrM
"""
p = OptionParser(ccn.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="12x8")
if len(args) != 1:
sys.exit(not p.print_help())
tsvfile, = args
df = pd.read_csv(tsvfile, sep="\t")
composite_ccn(df, size=(iopts.w, iopts.h))
outfile = tsvfile.rsplit(".", 1)[0] + ".ccn.pdf"
savefig(outfile)
def correlation(args):
"""
%prog correlation postgenomic-s.tsv
Plot correlation of age vs. postgenomic features.
"""
p = OptionParser(correlation.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="12x8")
if len(args) != 1:
sys.exit(not p.print_help())
tsvfile, = args
df = pd.read_csv(tsvfile, sep="\t")
composite_correlation(df, size=(iopts.w, iopts.h))
outfile = tsvfile.rsplit(".", 1)[0] + ".correlation.pdf"
savefig(outfile)
def mtdotplots(args):
"""
%prog mtdotplots Mt3.5 Mt4.0 medicago.medicago.lifted.1x1.anchors
Plot Mt3.5 and Mt4.0 side-by-side. This is essentially combined from two
graphics.dotplot() function calls as panel A and B.
"""
from jcvi.graphics.dotplot import check_beds, dotplot
p = OptionParser(mtdotplots.__doc__)
p.set_beds()
opts, args, iopts = p.set_image_options(args, figsize="16x8", dpi=90)
if len(args) != 3:
sys.exit(not p.print_help())
a, b, ac = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
r1 = fig.add_axes([0, 0, .5, 1])
r2 = fig.add_axes([.5, 0, .5, 1])
a1 = fig.add_axes([.05, .1, .4, .8])
a2 = fig.add_axes([.55, .1, .4, .8])
anchorfile = op.join(a, ac)
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
dotplot(anchorfile, qbed, sbed, fig, r1, a1, is_self=is_self,
genomenames="Mt3.5_Mt3.5")
opts.qbed = opts.sbed = None
anchorfile = op.join(b, ac)
qbed, sbed, qorder, sorder, is_self = check_beds(anchorfile, p, opts)
dotplot(anchorfile, qbed, sbed, fig, r2, a2, is_self=is_self,
genomenames="Mt4.0_Mt4.0")
root.text(.03, .95, "A", ha="center", va="center", size=36)
root.text(.53, .95, "B", ha="center", va="center", size=36)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "mtdotplots"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def qc(args):
"""
%prog qc postgenomic-s.tsv
Plot basic statistics of a given sample:
Age, Gender, Ethnicity, Cohort, Chemistry
"""
p = OptionParser(heritability.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="10x6")
if len(args) != 1:
sys.exit(not p.print_help())
tsvfile, = args
df = pd.read_csv(tsvfile, sep="\t")
composite_qc(df, size=(iopts.w, iopts.h))
outfile = tsvfile.rsplit(".", 1)[0] + ".qc.pdf"
savefig(outfile)
def multireport(args):
"""
%prog multireport layoutfile
Generate several Ks value distributions in the same figure. If the layout
file is missing then a template file listing all ks files will be written.
The layout file contains the Ks file, number of components, colors, and labels:
# Ks file, ncomponents, label, color, marker
LAP.sorghum.ks, 1, LAP-sorghum, r, o
SES.sorghum.ks, 1, SES-sorghum, g, +
MOL.sorghum.ks, 1, MOL-sorghum, m, ^
If color or marker is missing, then a random one will be assigned.
"""
p = OptionParser(multireport.__doc__)
p.set_outfile(outfile="Ks_plot.pdf")
add_plot_options(p)
opts, args, iopts = p.set_image_options(args, figsize="5x5")
if len(args) != 1:
sys.exit(not p.print_help())
layoutfile, = args
ks_min = opts.vmin
ks_max = opts.vmax
bins = opts.bins
fill = opts.fill
layout = Layout(layoutfile)
print >> sys.stderr, layout
fig = plt.figure(1, (iopts.w, iopts.h))
ax = fig.add_axes([.12, .1, .8, .8])
kp = KsPlot(ax, ks_max, bins, legendp=opts.legendp)
for lo in layout:
data = KsFile(lo.ksfile)
data = [x.ng_ks for x in data]
data = [x for x in data if ks_min <= x <= ks_max]
kp.add_data(data, lo.components, label=lo.label, \
color=lo.color, marker=lo.marker,
fill=fill, fitted=opts.fit)
kp.draw(title=opts.title, filename=opts.outfile)
def movieframe(args):
"""
%prog movieframe tour test.clm contigs.ref.anchors
Draw heatmap and synteny in the same plot.
"""
p = OptionParser(movieframe.__doc__)
p.add_option("--label", help="Figure title")
p.set_beds()
p.set_outfile(outfile=None)
opts, args, iopts = p.set_image_options(args, figsize="16x8",
style="white", cmap="coolwarm",
format="png", dpi=120)
if len(args) != 3:
sys.exit(not p.print_help())
tour, clmfile, anchorsfile = args
tour = tour.split(",")
image_name = opts.outfile or ("movieframe." + iopts.format)
label = opts.label or op.basename(image_name).rsplit(".", 1)[0]
clm = CLMFile(clmfile)
totalbins, bins, breaks = make_bins(tour, clm.tig_to_size)
M = read_clm(clm, totalbins, bins)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1]) # whole canvas
ax1 = fig.add_axes([.05, .1, .4, .8]) # heatmap
ax2 = fig.add_axes([.55, .1, .4, .8]) # dot plot
ax2_root = fig.add_axes([.5, 0, .5, 1]) # dot plot canvas
# Left axis: heatmap
plot_heatmap(ax1, M, breaks, iopts)
# Right axis: synteny
qbed, sbed, qorder, sorder, is_self = check_beds(anchorsfile, p, opts,
sorted=False)
dotplot(anchorsfile, qbed, sbed, fig, ax2_root, ax2, sep=False, title="")
root.text(.5, .98, clm.name, color="g", ha="center", va="center")
root.text(.5, .95, label, color="darkslategray", ha="center", va="center")
normalize_axes(root)
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def main():
p = OptionParser(__doc__)
opts, args, iopts = p.set_image_options(figsize="8x7")
if len(args) != 2:
sys.exit(not p.print_help())
seqidsfile, layoutfile = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
Karyotype(fig, root, seqidsfile, layoutfile)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
pf = "karyotype"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def plotall(xargs):
"""
%prog plotall input.bed
Plot the matchings between the reconstructed pseudomolecules and the maps.
This command will plot each reconstructed object (non-singleton).
"""
p = OptionParser(plotall.__doc__)
add_allmaps_plot_options(p)
opts, args, iopts = p.set_image_options(xargs, figsize="10x6")
if len(args) != 1:
sys.exit(not p.print_help())
inputbed, = args
pf = inputbed.rsplit(".", 1)[0]
agpfile = pf + ".agp"
agp = AGP(agpfile)
objects = [ob for ob, lines in agp.iter_object() if len(lines) > 1]
for seqid in sorted(objects):
plot(xargs + [seqid])
def covlen(args):
"""
%prog covlen covfile fastafile
Plot coverage vs lenght. `covfile` is two-column listing contig id and
depth of coverage.
"""
import numpy as np
import seaborn as sns
from jcvi.formats.base import DictFile
p = OptionParser(covlen.__doc__)
p.add_option("--maxsize", default=100000, type="int", help="Max contig size")
p.add_option("--maxcov", default=100, type="int", help="Max contig size")
opts, args, iopts = p.set_image_options(args, figsize="8x8")
if len(args) != 2:
sys.exit(not p.print_help())
covfile, fastafile = args
cov = DictFile(covfile, cast=float)
s = Sizes(fastafile)
data = []
maxsize, maxcov = opts.maxsize, opts.maxcov
for ctg, size in s.iter_sizes():
c = cov[ctg]
if size > maxsize:
continue
if c > maxcov:
continue
data.append((size, c))
x, y = zip(*data)
x = np.array(x)
y = np.array(y)
logging.debug("X size {0}, Y size {1}".format(x.size, y.size))
sns.jointplot(x, y, kind="kde")
figname = covfile + ".pdf"
savefig(figname, dpi=iopts.dpi, iopts=iopts)
def plot(args):
"""
%prog plot workdir sample chr1,chr2
Plot some chromosomes for visual proof. Separate multiple chromosomes with
comma. Must contain folder workdir/sample-cn/.
"""
from jcvi.graphics.base import savefig
p = OptionParser(plot.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x7", format="png")
if len(args) != 3:
sys.exit(not p.print_help())
workdir, sample_key, chrs = args
chrs = chrs.split(",")
hmm = CopyNumberHMM(workdir=workdir)
hmm.plot(sample_key, chrs=chrs)
image_name = sample_key + "_cn." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def utricularia(args):
from jcvi.graphics.synteny import main as synteny_main
p = OptionParser(synteny_main.__doc__)
p.add_option("--switch",
help="Rename the seqid with two-column file")
opts, args, iopts = p.set_image_options(args, figsize="8x7")
if len(args) != 3:
sys.exit(not p.print_help())
datafile, bedfile, layoutfile = args
switch = opts.switch
pf = datafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
s = Synteny(fig, root, datafile, bedfile, layoutfile, loc_label=False, switch=switch)
light = "lightslategrey"
RoundRect(root, (.02, .69), .96, .24, fill=False, lw=2, ec=light)
RoundRect(root, (.02, .09), .96, .48, fill=False, lw=2, ec=light)
za, zb = s.layout[1].ratio, s.layout[-1].ratio # zoom level
if za != 1:
root.text(.96, .89, "{}x zoom".format(za).replace(".0x", "x"),
color=light, ha="right", va="center", size=14)
if zb != 1:
root.text(.96, .12, "{}x zoom".format(zb).replace(".0x", "x"),
color=light, ha="right", va="center", size=14)
# legend showing the orientation of the genes
draw_gene_legend(root, .22, .3, .64, text=True)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def regression(args):
"""
%prog regression postgenomic-s.tsv
Plot chronological vs. predicted age.
"""
p = OptionParser(regression.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="8x8")
if len(args) != 1:
sys.exit(not p.print_help())
tsvfile, = args
df = pd.read_csv(tsvfile, sep="\t")
chrono = "Chronological age (yr)"
pred = "Predicted age (yr)"
resdf = pd.DataFrame({chrono: df["hli_calc_age_sample_taken"], pred: df["Predicted Age"]})
g = sns.jointplot(chrono, pred, resdf, joint_kws={"s": 6},
xlim=(0, 100), ylim=(0, 80))
g.fig.set_figwidth(iopts.w)
g.fig.set_figheight(iopts.h)
outfile = tsvfile.rsplit(".", 1)[0] + ".regression.pdf"
savefig(outfile)
def simulation(args):
"""
%prog simulation inversion.txt translocation.txt maps.txt multimaps.txt
Plot ALLMAPS accuracy across a range of simulated datasets.
"""
p = OptionParser(simulation.__doc__)
opts, args, iopts = p.set_image_options(args, dpi=300)
if len(args) != 4:
sys.exit(not p.print_help())
dataA, dataB, dataC, dataD = args
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
A = fig.add_axes([.12, .62, .35, .35])
B = fig.add_axes([.62, .62, .35, .35])
C = fig.add_axes([.12, .12, .35, .35])
D = fig.add_axes([.62, .12, .35, .35])
dataA = import_data(dataA)
dataB = import_data(dataB)
dataC = import_data(dataC)
dataD = import_data(dataD)
subplot(A, dataA, "Inversion error rate", "Accuracy", xlim=.5)
subplot(B, dataB, "Translocation error rate", "Accuracy", xlim=.5,
legend=("intra-chromosomal", "inter-chromosomal",
"75\% intra + 25\% inter"))
subplot(C, dataC, "Number of input maps", "Accuracy", xcast=int)
subplot(D, dataD, "Number of input maps", "Accuracy", xcast=int)
labels = ((.03, .97, "A"), (.53, .97, "B"),
(.03, .47, "C"), (.53, .47, "D"))
panel_labels(root, labels)
normalize_axes(root)
image_name = "simulation." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)