def dotplot(anchorfile, qbed, sbed, fig, root, ax, vmin=0, vmax=1,
is_self=False, synteny=False, cmap_text=None, cmap="copper",
genomenames=None, sample_number=10000, minfont=5, palette=None,
chrlw=.1, title=None, sep=True, sepcolor="g", stdpf=True):
fp = open(anchorfile)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
gx, gy = markup(gx), markup(gy)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Capping values within [{0:.1f}, {1:.1f}]"\
.format(vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
if cmap_text:
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
continue
if value > vmax:
continue
else:
value = 0
if query not in qorder:
continue
if subject not in sorder:
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
npairs = downsample(data, sample_number=sample_number)
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0, cmap=cmap,
vmin=vmin, vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=cmap)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
qbreaks = qbed.get_breaks()
sbreaks = sbed.get_breaks()
xlim, ylim = plot_breaks_and_labels(fig, root, ax, gx, gy, xsize, ysize,
qbreaks, sbreaks, sep=sep, chrlw=chrlw,
sepcolor=sepcolor, minfont=minfont, stdpf=stdpf)
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if title is None:
title = "Inter-genomic comparison: {0} vs {1}".format(gx, gy)
if is_self:
title = "Intra-genomic comparison within {0}".format(gx)
npairs /= 2
title += " ({0} gene pairs)".format(thousands(npairs))
root.set_title(title, x=.5, y=.96, color="k")
if title:
logging.debug("Dot plot title: {}".format(title))
normalize_axes(root)
def dotplot(anchorfile,
qbed,
sbed,
fig,
root,
ax,
vmin=0,
vmax=1,
is_self=False,
synteny=False,
cmap_text=None,
genomenames=None,
sample_number=10000,
minfont=5,
palette=None,
chrlw=.01,
title=None,
sepcolor="gainsboro"):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Normalize values to [%.1f, %.1f]" % (vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
value = vmin
if value > vmax:
value = vmax
if query not in qorder:
continue
if subject not in sorder:
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = vmax - value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
npairs = len(data)
# Only show random subset
if npairs > sample_number:
logging.debug("Showing a random subset of {0} data points (total {1}) " \
"for clarity.".format(sample_number, npairs))
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
if not palette:
data.sort(key=lambda x: -x[2])
default_cm = cm.copper
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x,
y,
c=c,
edgecolors="none",
s=2,
lw=0,
cmap=default_cm,
vmin=vmin,
vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=default_cm, reverse=True)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
xsize_ratio = abs(end - beg) * .8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbed.get_breaks():
ysize_ratio = abs(end - beg) * .8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
for label, pos, fontsize in xchr_labels:
pos = .1 + pos * .8 / xsize
if fontsize >= minfont:
root.text(pos,
.91,
latex(label),
size=fontsize,
ha="center",
va="bottom",
rotation=45,
color="grey")
# remember y labels are inverted
for label, pos, fontsize in ychr_labels:
pos = .9 - pos * .8 / ysize
if fontsize >= minfont:
root.text(.91,
pos,
latex(label),
size=fontsize,
va="center",
color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray',
size=10)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if not title:
title = "Inter-genomic comparison: {0} vs {1}".format(gx, gy)
if is_self:
title = "Intra-genomic comparison within {0}".format(gx)
npairs /= 2
title += " ({0} gene pairs)".format(thousands(npairs))
root.set_title(title, x=.5, y=.96, color="k")
logging.debug(title)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def dotplot(anchorfile, qbed, sbed, fig, root, ax, vmin=0, vmax=1,
is_self=False, synteny=False, cmap_text=None, genomenames=None,
sample_number=10000, ignore=.005, palette=None, chrlw=.01, title=None):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Normalize values to [%.1f, %.1f]" % (vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
value = vmin
if value > vmax:
value = vmax
if query not in qorder:
#logging.warning("ignore %s" % query)
continue
if subject not in sorder:
#logging.warning("ignore %s" % subject)
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = vmax - value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
# only show random subset, default to sample_number = 5000
if len(data) > sample_number:
logging.debug("Showing a random subset of %s data points (total %s) " \
"for clarity." % (sample_number, len(data)))
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
if not palette:
data.sort(key=lambda x: -x[2])
default_cm = cm.copper
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0, cmap=default_cm,
vmin=vmin, vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=default_cm, reverse=True)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
xchr_labels, ychr_labels = [], []
# Tag to mark whether to plot chr name (skip small ones)
ignore_size_x = ignore_size_y = 0
if ignore:
ignore_size_x = xsize * ignore
ignore_size_y = ysize * ignore
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
ignore = abs(end - beg) < ignore_size_x
seqid = seqid.split("_")[-1]
try:
seqid = int(seqid)
seqid = "c%d" % seqid
except:
pass
xchr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot([beg, beg], ylim, "g-", lw=chrlw)
for (seqid, beg, end) in sbed.get_breaks():
ignore = abs(end - beg) < ignore_size_y
seqid = seqid.split("_")[-1]
try:
seqid = int(seqid)
seqid = "c%d" % seqid
except:
pass
ychr_labels.append((seqid, (beg + end) / 2, ignore))
ax.plot(xlim, [beg, beg], "g-", lw=chrlw)
# plot the chromosome labels
for label, pos, ignore in xchr_labels:
pos = .1 + pos * .8 / xsize
if not ignore:
root.text(pos, .91, label,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, ignore in ychr_labels:
pos = .9 - pos * .8 / ysize
if not ignore:
root.text(.91, pos, label,
va="center", color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if title:
fig.suptitle(title, x=.05, y=.98, color="k")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def ld(args):
"""
%prog ld map
Calculate pairwise linkage disequilibrium given MSTmap.
"""
import numpy as np
from random import sample
from jcvi.algorithms.matrix import symmetrize
p = OptionParser(ld.__doc__)
p.add_option("--subsample", default=500, type="int",
help="Subsample markers to speed up [default: %default]")
opts, args, iopts = p.set_image_options(args, figsize="8x8")
if len(args) != 1:
sys.exit(not p.print_help())
mstmap, = args
subsample = opts.subsample
data = MSTMap(mstmap)
# Take random subsample while keeping marker order
if subsample < data.nmarkers:
data = [data[x] for x in \
sorted(sample(xrange(len(data)), subsample))]
markerbedfile = mstmap + ".subsample.bed"
ldmatrix = mstmap + ".subsample.matrix"
if need_update(mstmap, (markerbedfile, ldmatrix)):
nmarkers = len(data)
fw = open(markerbedfile, "w")
print >> fw, "\n".join(x.bedline for x in data)
logging.debug("Write marker set of size {0} to file `{1}`."\
.format(nmarkers, markerbedfile))
M = np.zeros((nmarkers, nmarkers), dtype=float)
for i, j in combinations(range(nmarkers), 2):
a = data[i]
b = data[j]
M[i, j] = calc_ldscore(a.genotype, b.genotype)
M = symmetrize(M)
logging.debug("Write LD matrix to file `{0}`.".format(ldmatrix))
M.tofile(ldmatrix)
else:
nmarkers = len(Bed(markerbedfile))
M = np.fromfile(ldmatrix, dtype="float").reshape(nmarkers, nmarkers)
logging.debug("LD matrix `{0}` exists ({1}x{1})."\
.format(ldmatrix, nmarkers))
from jcvi.graphics.base import plt, savefig, Rectangle, draw_cmap
plt.rcParams["axes.linewidth"] = 0
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
ax = fig.add_axes([.1, .1, .8, .8]) # the heatmap
ax.matshow(M, cmap=iopts.cmap)
# Plot chromosomes breaks
bed = Bed(markerbedfile)
xsize = len(bed)
extent = (0, nmarkers)
chr_labels = []
ignore_size = 20
for (seqid, beg, end) in bed.get_breaks():
ignore = abs(end - beg) < ignore_size
pos = (beg + end) / 2
chr_labels.append((seqid, pos, ignore))
if ignore:
continue
ax.plot((end, end), extent, "w-", lw=1)
ax.plot(extent, (end, end), "w-", lw=1)
# Plot chromosome labels
for label, pos, ignore in chr_labels:
pos = .1 + pos * .8 / xsize
if not ignore:
root.text(pos, .91, label,
ha="center", va="bottom", rotation=45, color="grey")
root.text(.09, pos, label,
ha="right", va="center", color="grey")
ax.set_xlim(extent)
ax.set_ylim(extent)
ax.set_axis_off()
draw_cmap(root, "Pairwise LD (r2)", 0, 1, cmap=default_cm)
root.add_patch(Rectangle((.1, .1), .8, .8, fill=False, ec="k", lw=2))
m = mstmap.split(".")[0]
root.text(.5, .06, "Linkage Disequilibrium between {0} markers".format(m), ha="center")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = m + ".subsample" + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def dotplot(anchorfile, qbed, sbed, fig, root, ax, vmin=0, vmax=1,
is_self=False, synteny=False, cmap_text=None, cmap="copper",
genomenames=None, sample_number=10000, minfont=5, palette=None,
chrlw=.01, title=None, sepcolor="gainsboro"):
fp = open(anchorfile)
qorder = qbed.order
sorder = sbed.order
data = []
if cmap_text:
logging.debug("Capping values within [{0:.1f}, {1:.1f}]"\
.format(vmin, vmax))
block_id = 0
for row in fp:
atoms = row.split()
block_color = None
if row[0] == "#":
block_id += 1
if palette:
block_color = palette.get(block_id, "k")
continue
# first two columns are query and subject, and an optional third column
if len(atoms) < 2:
continue
query, subject = atoms[:2]
value = atoms[-1]
if cmap_text:
try:
value = float(value)
except ValueError:
value = vmax
if value < vmin:
continue
if value > vmax:
continue
else:
value = 0
if query not in qorder:
continue
if subject not in sorder:
continue
qi, q = qorder[query]
si, s = sorder[subject]
nv = value if block_color is None else block_color
data.append((qi, si, nv))
if is_self: # Mirror image
data.append((si, qi, nv))
npairs = len(data)
# Only show random subset
if npairs > sample_number:
logging.debug("Showing a random subset of {0} data points (total {1}) " \
"for clarity.".format(sample_number, npairs))
data = sample(data, sample_number)
# the data are plotted in this order, the least value are plotted
# last for aesthetics
#if not palette:
# data.sort(key=lambda x: -x[2])
x, y, c = zip(*data)
if palette:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0)
else:
ax.scatter(x, y, c=c, edgecolors="none", s=2, lw=0, cmap=cmap,
vmin=vmin, vmax=vmax)
if synteny:
clusters = batch_scan(data, qbed, sbed)
draw_box(clusters, ax)
if cmap_text:
draw_cmap(root, cmap_text, vmin, vmax, cmap=cmap)
xsize, ysize = len(qbed), len(sbed)
logging.debug("xsize=%d ysize=%d" % (xsize, ysize))
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbed.get_breaks():
xsize_ratio = abs(end - beg) * .8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbed.get_breaks():
ysize_ratio = abs(end - beg) * .8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
seqid = "".join(seqid_parse(seqid)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize))
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
for label, pos, fontsize in xchr_labels:
pos = .1 + pos * .8 / xsize
if fontsize >= minfont:
root.text(pos, .91, latex(label), size=fontsize,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, fontsize in ychr_labels:
pos = .9 - pos * .8 / ysize
if fontsize >= minfont:
root.text(.91, pos, latex(label), size=fontsize,
va="center", color="grey")
# create a diagonal to separate mirror image for self comparison
if is_self:
ax.plot(xlim, (0, ysize), 'm-', alpha=.5, lw=2)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# add genome names
if genomenames:
gx, gy = genomenames.split("_")
else:
to_ax_label = lambda fname: op.basename(fname).split(".")[0]
gx, gy = [to_ax_label(x.filename) for x in (qbed, sbed)]
ax.set_xlabel(markup(gx), size=16)
ax.set_ylabel(markup(gy), size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
if palette: # bottom-left has the palette, if available
colors = palette.colors
xstart, ystart = .1, .05
for category, c in sorted(colors.items()):
root.add_patch(Rectangle((xstart, ystart), .03, .02, lw=0, fc=c))
root.text(xstart + .04, ystart, category, color=c)
xstart += .1
if not title:
title = "Inter-genomic comparison: {0} vs {1}".format(gx, gy)
if is_self:
title = "Intra-genomic comparison within {0}".format(gx)
npairs /= 2
title += " ({0} gene pairs)".format(thousands(npairs))
root.set_title(markup(title), x=.5, y=.96, color="k")
logging.debug(title)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()