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 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 estimategaps(args):
"""
%prog estimategaps JM-4 chr1 JMMale-1
Illustrate ALLMAPS gap estimation algorithm.
"""
p = OptionParser(estimategaps.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="6x6", dpi=300)
if len(args) != 3:
sys.exit(not p.print_help())
pf, seqid, mlg = args
bedfile = pf + ".lifted.bed"
agpfile = pf + ".agp"
function = lambda x: x.cm
cc = Map(bedfile, scaffold_info=True, function=function)
agp = AGP(agpfile)
g = GapEstimator(cc, agp, seqid, mlg, function=function)
pp, chrsize, mlgsize = g.pp, g.chrsize, g.mlgsize
spl, spld = g.spl, g.spld
g.compute_all_gaps(verbose=False)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
# Panel A
xstart, ystart = 0.15, 0.65
w, h = 0.7, 0.3
t = np.linspace(0, chrsize, 1000)
ax = fig.add_axes([xstart, ystart, w, h])
mx, my = zip(*g.scatter_data)
rho = spearmanr(mx, my)
dsg = "g"
ax.vlines(pp, 0, mlgsize, colors="beige")
ax.plot(mx, my, ".", color=set2[3])
ax.plot(t, spl(t), "-", color=dsg)
ax.text(0.05, 0.95, mlg, va="top", transform=ax.transAxes)
normalize_lms_axis(ax, xlim=chrsize, ylim=mlgsize, ylabel="Genetic distance (cM)")
if rho < 0:
ax.invert_yaxis()
# Panel B
ystart -= 0.28
h = 0.25
ax = fig.add_axes([xstart, ystart, w, h])
ax.vlines(pp, 0, mlgsize, colors="beige")
ax.plot(t, spld(t), "-", lw=2, color=dsg)
ax.plot(pp, spld(pp), "o", mfc="w", mec=dsg, ms=5)
normalize_lms_axis(
ax,
xlim=chrsize,
ylim=25 * 1e-6,
xfactor=1e-6,
xlabel="Physical position (Mb)",
yfactor=1000000,
ylabel="Recomb. rate\n(cM / Mb)",
)
ax.xaxis.grid(False)
# Panel C (specific to JMMale-1)
a, b = "scaffold_1076", "scaffold_861"
sizes = dict(
(x.component_id, (x.object_beg, x.object_end, x.component_span, x.orientation))
for x in g.agp
if not x.is_gap
)
a_beg, a_end, asize, ao = sizes[a]
b_beg, b_end, bsize, bo = sizes[b]
gapsize = g.get_gapsize(a)
total_size = asize + gapsize + bsize
ratio = 0.6 / total_size
y = 0.16
pad = 0.03
pb_ratio = w / chrsize
# Zoom
lsg = "lightslategray"
root.plot((0.15 + pb_ratio * a_beg, 0.2), (ystart, ystart - 0.14), ":", color=lsg)
root.plot((0.15 + pb_ratio * b_end, 0.3), (ystart, ystart - 0.08), ":", color=lsg)
ends = []
for tag, size, marker, beg in zip(
(a, b), (asize, bsize), (49213, 81277), (0.2, 0.2 + (asize + gapsize) * ratio)
):
end = beg + size * ratio
marker = beg + marker * ratio
ends.append((beg, end, marker))
root.plot((marker,), (y,), "o", color=lsg)
root.text((beg + end) / 2, y + pad, latex(tag), ha="center", va="center")
HorizontalChromosome(root, beg, end, y, height=0.025, fc="gainsboro")
begs, ends, markers = zip(*ends)
fontprop = dict(color=lsg, ha="center", va="center")
ypos = y + pad * 2
root.plot(markers, (ypos, ypos), "-", lw=2, color=lsg)
root.text(
sum(markers) / 2,
ypos + pad,
"Distance: 1.29cM $\Leftrightarrow$ 211,824bp (6.1 cM/Mb)",
**fontprop
)
ypos = y - pad
xx = markers[0], ends[0]
root.plot(xx, (ypos, ypos), "-", lw=2, color=lsg)
root.text(sum(xx) / 2, ypos - pad, "34,115bp", **fontprop)
xx = markers[1], begs[1]
root.plot(xx, (ypos, ypos), "-", lw=2, color=lsg)
root.text(sum(xx) / 2, ypos - pad, "81,276bp", **fontprop)
root.plot((ends[0], begs[1]), (y, y), ":", lw=2, color=lsg)
root.text(
sum(markers) / 2,
ypos - 3 * pad,
r"$\textit{Estimated gap size: 96,433bp}$",
color="r",
ha="center",
va="center",
)
labels = ((0.05, 0.95, "A"), (0.05, 0.6, "B"), (0.05, 0.27, "C"))
panel_labels(root, labels)
normalize_axes(root)
pf = "estimategaps"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def plot_breaks_and_labels(fig, root, ax, gx, gy, xsize, ysize,
qbreaks, sbreaks, sep=True, chrlw=.1,
sepcolor="g", minfont=5, stdpf=True):
xlim = (0, xsize)
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbreaks:
xsize_ratio = abs(end - beg) * .8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
if sep:
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbreaks:
ysize_ratio = abs(end - beg) * .8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize))
if sep:
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
for label, pos, fontsize in xchr_labels:
pos = .1 + pos * .8 / xsize
if fontsize >= minfont:
root.text(pos, .91, latex(label), size=fontsize,
ha="center", va="bottom", rotation=45, color="grey")
# remember y labels are inverted
for label, pos, fontsize in ychr_labels:
pos = .9 - pos * .8 / ysize
if fontsize >= minfont:
root.text(.91, pos, latex(label), size=fontsize,
va="center", color="grey")
# Plot the frame
ax.plot(xlim, [0, 0], "-", lw=chrlw, color=sepcolor)
ax.plot(xlim, [ysize, ysize], "-", lw=chrlw, color=sepcolor)
ax.plot([0, 0], ylim, "-", lw=chrlw, color=sepcolor)
ax.plot([xsize, xsize], ylim, "-", lw=chrlw, color=sepcolor)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
ax.set_xlabel(gx, size=16)
ax.set_ylabel(gy, size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(),
color='gray', size=10)
return xlim, ylim
def gcdepth(args):
"""
%prog gcdepth sample_name tag
Plot GC content vs depth vs genomnic bins. Inputs are mosdepth output:
- NA12878_S1.mosdepth.global.dist.txt
- NA12878_S1.mosdepth.region.dist.txt
- NA12878_S1.regions.bed.gz
- NA12878_S1.regions.bed.gz.csi
- NA12878_S1.regions.gc.bed.gz
A sample mosdepth.sh script might look like:
```
#!/bin/bash
LD_LIBRARY_PATH=mosdepth/htslib/ mosdepth/mosdepth $1 \\
bams/$1.bam -t 4 -c chr1 -n --by 1000
bedtools nuc -fi GRCh38/WholeGenomeFasta/genome.fa \\
-bed $1.regions.bed.gz \\
| pigz -c > $1.regions.gc.bed.gz
```
"""
import hashlib
from jcvi.algorithms.formula import MAD_interval as confidence_interval
from jcvi.graphics.base import latex, plt, savefig, set2
p = OptionParser(gcdepth.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
sample_name, tag = args
# The tag is used to add to title, also provide a random (hashed) color
coloridx = int(hashlib.sha256(tag).hexdigest(), 16) % len(set2)
color = set2[coloridx]
# mosdepth outputs a table that we can use to plot relationship
gcbedgz = sample_name + ".regions.gc.bed.gz"
df = pd.read_csv(gcbedgz, delimiter="\t")
mf = df.loc[:, ("4_usercol", "6_pct_gc")]
mf.columns = ["depth", "gc"]
# We discard any bins that are gaps
mf = mf[(mf["depth"] > 0.001) | (mf["gc"] > 0.001)]
# Create GC bins
gcbins = defaultdict(list)
for i, row in mf.iterrows():
gcp = int(round(row["gc"] * 100))
gcbins[gcp].append(row["depth"])
gcd = sorted(
(k * 0.01, confidence_interval(v)) for (k, v) in gcbins.items())
gcd_x, gcd_y = zip(*gcd)
m, lo, hi = zip(*gcd_y)
# Plot
plt.plot(
mf["gc"],
mf["depth"],
".",
color="lightslategray",
ms=2,
mec="lightslategray",
alpha=0.1,
)
patch = plt.fill_between(
gcd_x,
lo,
hi,
facecolor=color,
alpha=0.25,
zorder=10,
linewidth=0.0,
label="Median +/- MAD band",
)
plt.plot(gcd_x, m, "-", color=color, lw=2, zorder=20)
ax = plt.gca()
ax.legend(handles=[patch], loc="best")
ax.set_xlim(0, 1)
ax.set_ylim(0, 100)
ax.set_title("{} ({})".format(latex(sample_name), tag))
ax.set_xlabel("GC content")
ax.set_ylabel("Depth")
savefig(sample_name + ".gcdepth.png")
def gcdepth(args):
"""
%prog gcdepth sample_name tag
Plot GC content vs depth vs genomnic bins. Inputs are mosdepth output:
- NA12878_S1.mosdepth.global.dist.txt
- NA12878_S1.mosdepth.region.dist.txt
- NA12878_S1.regions.bed.gz
- NA12878_S1.regions.bed.gz.csi
- NA12878_S1.regions.gc.bed.gz
A sample mosdepth.sh script might look like:
```
#!/bin/bash
LD_LIBRARY_PATH=mosdepth/htslib/ mosdepth/mosdepth $1 \\
bams/$1.bam -t 4 -c chr1 -n --by 1000
bedtools nuc -fi GRCh38/WholeGenomeFasta/genome.fa \\
-bed $1.regions.bed.gz \\
| pigz -c > $1.regions.gc.bed.gz
```
"""
import hashlib
from jcvi.algorithms.formula import MAD_interval as confidence_interval
from jcvi.graphics.base import latex, plt, savefig, set2
p = OptionParser(gcdepth.__doc__)
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
sample_name, tag = args
# The tag is used to add to title, also provide a random (hashed) color
coloridx = int(hashlib.sha1(tag).hexdigest(), 16) % len(set2)
color = set2[coloridx]
# mosdepth outputs a table that we can use to plot relationship
gcbedgz = sample_name + ".regions.gc.bed.gz"
df = pd.read_csv(gcbedgz, delimiter="\t")
mf = df.loc[:, ("4_usercol", "6_pct_gc")]
mf.columns = ["depth", "gc"]
# We discard any bins that are gaps
mf = mf[(mf["depth"] > .001) | (mf["gc"] > .001)]
# Create GC bins
gcbins = defaultdict(list)
for i, row in mf.iterrows():
gcp = int(round(row["gc"] * 100))
gcbins[gcp].append(row["depth"])
gcd = sorted((k * .01, confidence_interval(v))
for (k, v) in gcbins.items())
gcd_x, gcd_y = zip(*gcd)
m, lo, hi = zip(*gcd_y)
# Plot
plt.plot(mf["gc"], mf["depth"], ".", color="lightslategray", ms=2,
mec="lightslategray", alpha=.1)
patch = plt.fill_between(gcd_x, lo, hi,
facecolor=color, alpha=.25, zorder=10,
linewidth=0.0, label="Median +/- MAD band")
plt.plot(gcd_x, m, "-", color=color, lw=2, zorder=20)
ax = plt.gca()
ax.legend(handles=[patch], loc="best")
ax.set_xlim(0, 1)
ax.set_ylim(0, 100)
ax.set_title("{} ({})".format(latex(sample_name), tag))
ax.set_xlabel("GC content")
ax.set_ylabel("Depth")
savefig(sample_name + ".gcdepth.png")
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 seeds(args):
"""
%prog seeds [pngfile|jpgfile]
Extract seed metrics from [pngfile|jpgfile]. Use --rows and --cols to crop image.
"""
p = OptionParser(seeds.__doc__)
p.set_outfile()
opts, args, iopts = add_seeds_options(p, args)
if len(args) != 1:
sys.exit(not p.print_help())
pngfile, = args
pf = opts.prefix or op.basename(pngfile).rsplit(".", 1)[0]
sigma, kernel = opts.sigma, opts.kernel
rows, cols = opts.rows, opts.cols
labelrows, labelcols = opts.labelrows, opts.labelcols
ff = opts.filter
calib = opts.calibrate
outdir = opts.outdir
if outdir != '.':
mkdir(outdir)
if calib:
calib = json.load(must_open(calib))
pixel_cm_ratio, tr = calib["PixelCMratio"], calib["RGBtransform"]
tr = np.array(tr)
resizefile, mainfile, labelfile, exif = \
convert_image(pngfile, pf, outdir=outdir,
rotate=opts.rotate,
rows=rows, cols=cols,
labelrows=labelrows, labelcols=labelcols)
oimg = load_image(resizefile)
img = load_image(mainfile)
fig, (ax1, ax2, ax3, ax4) = plt.subplots(ncols=4, nrows=1,
figsize=(iopts.w, iopts.h))
# Edge detection
img_gray = rgb2gray(img)
logging.debug("Running {0} edge detection ...".format(ff))
if ff == "canny":
edges = canny(img_gray, sigma=opts.sigma)
elif ff == "roberts":
edges = roberts(img_gray)
elif ff == "sobel":
edges = sobel(img_gray)
edges = clear_border(edges, buffer_size=opts.border)
selem = disk(kernel)
closed = closing(edges, selem) if kernel else edges
filled = binary_fill_holes(closed)
# Watershed algorithm
if opts.watershed:
distance = distance_transform_edt(filled)
local_maxi = peak_local_max(distance, threshold_rel=.05, indices=False)
coordinates = peak_local_max(distance, threshold_rel=.05)
markers, nmarkers = label(local_maxi, return_num=True)
logging.debug("Identified {0} watershed markers".format(nmarkers))
labels = watershed(closed, markers, mask=filled)
else:
labels = label(filled)
# Object size filtering
w, h = img_gray.shape
canvas_size = w * h
min_size = int(round(canvas_size * opts.minsize / 100))
max_size = int(round(canvas_size * opts.maxsize / 100))
logging.debug("Find objects with pixels between {0} ({1}%) and {2} ({3}%)"\
.format(min_size, opts.minsize, max_size, opts.maxsize))
# Plotting
ax1.set_title('Original picture')
ax1.imshow(oimg)
params = "{0}, $\sigma$={1}, $k$={2}".format(ff, sigma, kernel)
if opts.watershed:
params += ", watershed"
ax2.set_title('Edge detection\n({0})'.format(params))
closed = gray2rgb(closed)
ax2_img = labels
if opts.edges:
ax2_img = closed
elif opts.watershed:
ax2.plot(coordinates[:, 1], coordinates[:, 0], 'g.')
ax2.imshow(ax2_img, cmap=iopts.cmap)
ax3.set_title('Object detection')
ax3.imshow(img)
filename = op.basename(pngfile)
if labelfile:
accession = extract_label(labelfile)
else:
accession = pf
# Calculate region properties
rp = regionprops(labels)
rp = [x for x in rp if min_size <= x.area <= max_size]
nb_labels = len(rp)
logging.debug("A total of {0} objects identified.".format(nb_labels))
objects = []
for i, props in enumerate(rp):
i += 1
if i > opts.count:
break
y0, x0 = props.centroid
orientation = props.orientation
major, minor = props.major_axis_length, props.minor_axis_length
major_dx = cos(orientation) * major / 2
major_dy = sin(orientation) * major / 2
minor_dx = sin(orientation) * minor / 2
minor_dy = cos(orientation) * minor / 2
ax2.plot((x0 - major_dx, x0 + major_dx),
(y0 + major_dy, y0 - major_dy), 'r-')
ax2.plot((x0 - minor_dx, x0 + minor_dx),
(y0 - minor_dy, y0 + minor_dy), 'r-')
npixels = int(props.area)
# Sample the center of the blob for color
d = min(int(round(minor / 2 * .35)) + 1, 50)
x0d, y0d = int(round(x0)), int(round(y0))
square = img[(y0d - d):(y0d + d), (x0d - d):(x0d + d)]
pixels = []
for row in square:
pixels.extend(row)
logging.debug("Seed #{0}: {1} pixels ({2} sampled) - {3:.2f}%".\
format(i, npixels, len(pixels), 100. * npixels / canvas_size))
rgb = pixel_stats(pixels)
objects.append(Seed(filename, accession, i, rgb, props, exif))
minr, minc, maxr, maxc = props.bbox
rect = Rectangle((minc, minr), maxc - minc, maxr - minr,
fill=False, ec='w', lw=1)
ax3.add_patch(rect)
mc, mr = (minc + maxc) / 2, (minr + maxr) / 2
ax3.text(mc, mr, "{0}".format(i), color='w',
ha="center", va="center", size=6)
for ax in (ax2, ax3):
ax.set_xlim(0, h)
ax.set_ylim(w, 0)
# Output identified seed stats
ax4.text(.1, .92, "File: {0}".format(latex(filename)), color='g')
ax4.text(.1, .86, "Label: {0}".format(latex(accession)), color='m')
yy = .8
fw = must_open(opts.outfile, "w")
if not opts.noheader:
print(Seed.header(calibrate=calib), file=fw)
for o in objects:
if calib:
o.calibrate(pixel_cm_ratio, tr)
print(o, file=fw)
i = o.seedno
if i > 7:
continue
ax4.text(.01, yy, str(i), va="center", bbox=dict(fc='none', ec='k'))
ax4.text(.1, yy, o.pixeltag, va="center")
yy -= .04
ax4.add_patch(Rectangle((.1, yy - .025), .12, .05, lw=0,
fc=rgb_to_hex(o.rgb)))
ax4.text(.27, yy, o.hashtag, va="center")
yy -= .06
ax4.text(.1 , yy, "(A total of {0} objects displayed)".format(nb_labels),
color="darkslategrey")
normalize_axes(ax4)
for ax in (ax1, ax2, ax3):
xticklabels = [int(x) for x in ax.get_xticks()]
yticklabels = [int(x) for x in ax.get_yticks()]
ax.set_xticklabels(xticklabels, family='Helvetica', size=8)
ax.set_yticklabels(yticklabels, family='Helvetica', size=8)
image_name = op.join(outdir, pf + "." + iopts.format)
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
return objects
def seeds(args):
"""
%prog seeds [pngfile|jpgfile]
Extract seed metrics from [pngfile|jpgfile]. Use --rows and --cols to crop image.
"""
p = OptionParser(seeds.__doc__)
p.set_outfile()
opts, args, iopts = add_seeds_options(p, args)
if len(args) != 1:
sys.exit(not p.print_help())
(pngfile, ) = args
pf = opts.prefix or op.basename(pngfile).rsplit(".", 1)[0]
sigma, kernel = opts.sigma, opts.kernel
rows, cols = opts.rows, opts.cols
labelrows, labelcols = opts.labelrows, opts.labelcols
ff = opts.filter
calib = opts.calibrate
outdir = opts.outdir
if outdir != ".":
mkdir(outdir)
if calib:
calib = json.load(must_open(calib))
pixel_cm_ratio, tr = calib["PixelCMratio"], calib["RGBtransform"]
tr = np.array(tr)
nbcolor = opts.changeBackground
pngfile = convert_background(pngfile, nbcolor)
resizefile, mainfile, labelfile, exif = convert_image(
pngfile,
pf,
outdir=outdir,
rotate=opts.rotate,
rows=rows,
cols=cols,
labelrows=labelrows,
labelcols=labelcols,
)
oimg = load_image(resizefile)
img = load_image(mainfile)
fig, (ax1, ax2, ax3, ax4) = plt.subplots(ncols=4,
nrows=1,
figsize=(iopts.w, iopts.h))
# Edge detection
img_gray = rgb2gray(img)
logging.debug("Running {0} edge detection ...".format(ff))
if ff == "canny":
edges = canny(img_gray, sigma=opts.sigma)
elif ff == "roberts":
edges = roberts(img_gray)
elif ff == "sobel":
edges = sobel(img_gray)
edges = clear_border(edges, buffer_size=opts.border)
selem = disk(kernel)
closed = closing(edges, selem) if kernel else edges
filled = binary_fill_holes(closed)
# Watershed algorithm
if opts.watershed:
distance = distance_transform_edt(filled)
local_maxi = peak_local_max(distance,
threshold_rel=0.05,
indices=False)
coordinates = peak_local_max(distance, threshold_rel=0.05)
markers, nmarkers = label(local_maxi, return_num=True)
logging.debug("Identified {0} watershed markers".format(nmarkers))
labels = watershed(closed, markers, mask=filled)
else:
labels = label(filled)
# Object size filtering
w, h = img_gray.shape
canvas_size = w * h
min_size = int(round(canvas_size * opts.minsize / 100))
max_size = int(round(canvas_size * opts.maxsize / 100))
logging.debug(
"Find objects with pixels between {0} ({1}%) and {2} ({3}%)".format(
min_size, opts.minsize, max_size, opts.maxsize))
# Plotting
ax1.set_title("Original picture")
ax1.imshow(oimg)
params = "{0}, $\sigma$={1}, $k$={2}".format(ff, sigma, kernel)
if opts.watershed:
params += ", watershed"
ax2.set_title("Edge detection\n({0})".format(params))
closed = gray2rgb(closed)
ax2_img = labels
if opts.edges:
ax2_img = closed
elif opts.watershed:
ax2.plot(coordinates[:, 1], coordinates[:, 0], "g.")
ax2.imshow(ax2_img, cmap=iopts.cmap)
ax3.set_title("Object detection")
ax3.imshow(img)
filename = op.basename(pngfile)
if labelfile:
accession = extract_label(labelfile)
else:
accession = pf
# Calculate region properties
rp = regionprops(labels)
rp = [x for x in rp if min_size <= x.area <= max_size]
nb_labels = len(rp)
logging.debug("A total of {0} objects identified.".format(nb_labels))
objects = []
for i, props in enumerate(rp):
i += 1
if i > opts.count:
break
y0, x0 = props.centroid
orientation = props.orientation
major, minor = props.major_axis_length, props.minor_axis_length
major_dx = cos(orientation) * major / 2
major_dy = sin(orientation) * major / 2
minor_dx = sin(orientation) * minor / 2
minor_dy = cos(orientation) * minor / 2
ax2.plot((x0 - major_dx, x0 + major_dx),
(y0 + major_dy, y0 - major_dy), "r-")
ax2.plot((x0 - minor_dx, x0 + minor_dx),
(y0 - minor_dy, y0 + minor_dy), "r-")
npixels = int(props.area)
# Sample the center of the blob for color
d = min(int(round(minor / 2 * 0.35)) + 1, 50)
x0d, y0d = int(round(x0)), int(round(y0))
square = img[(y0d - d):(y0d + d), (x0d - d):(x0d + d)]
pixels = []
for row in square:
pixels.extend(row)
logging.debug("Seed #{0}: {1} pixels ({2} sampled) - {3:.2f}%".format(
i, npixels, len(pixels), 100.0 * npixels / canvas_size))
rgb = pixel_stats(pixels)
objects.append(Seed(filename, accession, i, rgb, props, exif))
minr, minc, maxr, maxc = props.bbox
rect = Rectangle((minc, minr),
maxc - minc,
maxr - minr,
fill=False,
ec="w",
lw=1)
ax3.add_patch(rect)
mc, mr = (minc + maxc) / 2, (minr + maxr) / 2
ax3.text(mc,
mr,
"{0}".format(i),
color="w",
ha="center",
va="center",
size=6)
for ax in (ax2, ax3):
ax.set_xlim(0, h)
ax.set_ylim(w, 0)
# Output identified seed stats
ax4.text(0.1, 0.92, "File: {0}".format(latex(filename)), color="g")
ax4.text(0.1, 0.86, "Label: {0}".format(latex(accession)), color="m")
yy = 0.8
fw = must_open(opts.outfile, "w")
if not opts.noheader:
print(Seed.header(calibrate=calib), file=fw)
for o in objects:
if calib:
o.calibrate(pixel_cm_ratio, tr)
print(o, file=fw)
i = o.seedno
if i > 7:
continue
ax4.text(0.01, yy, str(i), va="center", bbox=dict(fc="none", ec="k"))
ax4.text(0.1, yy, o.pixeltag, va="center")
yy -= 0.04
ax4.add_patch(
Rectangle((0.1, yy - 0.025),
0.12,
0.05,
lw=0,
fc=rgb_to_hex(o.rgb)))
ax4.text(0.27, yy, o.hashtag, va="center")
yy -= 0.06
ax4.text(
0.1,
yy,
"(A total of {0} objects displayed)".format(nb_labels),
color="darkslategray",
)
normalize_axes(ax4)
for ax in (ax1, ax2, ax3):
xticklabels = [int(x) for x in ax.get_xticks()]
yticklabels = [int(x) for x in ax.get_yticks()]
ax.set_xticklabels(xticklabels, family="Helvetica", size=8)
ax.set_yticklabels(yticklabels, family="Helvetica", size=8)
image_name = op.join(outdir, pf + "." + iopts.format)
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
return objects
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")
p.add_option("--ymax", type="int", help="Set Y-axis max")
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, merge = 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, merge=merge)
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(latex(chr), color="darkslategray")
for i, ax in enumerate(axarr):
lineplot(ax, [linebins[i]], nbins, chr, window, shift, \
color="{0}{1}".format(colors[i], 'r'))
if opts.ymax:
ax.set_ylim(0, opts.ymax)
plt.subplots_adjust(hspace=0.5)
image_name = chr + "." + 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()
def estimategaps(args):
"""
%prog estimategaps JM-4 chr1 JMMale-1
Illustrate ALLMAPS gap estimation algorithm.
"""
p = OptionParser(estimategaps.__doc__)
opts, args, iopts = p.set_image_options(args, figsize="6x6", dpi=300)
if len(args) != 3:
sys.exit(not p.print_help())
pf, seqid, mlg = args
bedfile = pf + ".lifted.bed"
agpfile = pf + ".agp"
function = lambda x: x.cm
cc = Map(bedfile, scaffold_info=True, function=function)
agp = AGP(agpfile)
g = GapEstimator(cc, agp, seqid, mlg, function=function)
pp, chrsize, mlgsize = g.pp, g.chrsize, g.mlgsize
spl, spld = g.spl, g.spld
g.compute_all_gaps(verbose=False)
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
# Panel A
xstart, ystart = .15, .65
w, h = .7, .3
t = np.linspace(0, chrsize, 1000)
ax = fig.add_axes([xstart, ystart, w, h])
mx, my = zip(*g.scatter_data)
rho = spearmanr(mx, my)
dsg = "g"
ax.vlines(pp, 0, mlgsize, colors="beige")
ax.plot(mx, my, ".", color=set2[3])
ax.plot(t, spl(t), "-", color=dsg)
ax.text(.05, .95, mlg, va="top", transform=ax.transAxes)
normalize_lms_axis(ax, xlim=chrsize, ylim=mlgsize,
ylabel="Genetic distance (cM)")
if rho < 0:
ax.invert_yaxis()
# Panel B
ystart -= .28
h = .25
ax = fig.add_axes([xstart, ystart, w, h])
ax.vlines(pp, 0, mlgsize, colors="beige")
ax.plot(t, spld(t), "-", lw=2, color=dsg)
ax.plot(pp, spld(pp), "o", mfc="w", mec=dsg, ms=5)
normalize_lms_axis(ax, xlim=chrsize, ylim=25 * 1e-6,
xfactor=1e-6, xlabel="Physical position (Mb)",
yfactor=1000000, ylabel="Recomb. rate\n(cM / Mb)")
# Panel C (specific to JMMale-1)
a, b = "scaffold_1076", "scaffold_861"
sizes = dict((x.component_id, (x.object_beg, x.object_end,
x.component_span, x.orientation)) \
for x in g.agp if not x.is_gap)
a_beg, a_end, asize, ao = sizes[a]
b_beg, b_end, bsize, bo = sizes[b]
gapsize = g.get_gapsize(a)
total_size = asize + gapsize + bsize
ratio = .6 / total_size
y = .16
pad = .03
pb_ratio = w / chrsize
# Zoom
lsg = "lightslategray"
root.plot((.15 + pb_ratio * a_beg, .2),
(ystart, ystart - .14), ":", color=lsg)
root.plot((.15 + pb_ratio * b_end, .3),
(ystart, ystart - .08), ":", color=lsg)
ends = []
for tag, size, marker, beg in zip((a, b), (asize, bsize), (49213, 81277),
(.2, .2 + (asize + gapsize) * ratio)):
end = beg + size * ratio
marker = beg + marker * ratio
ends.append((beg, end, marker))
root.plot((marker,), (y,), "o", color=lsg)
root.text((beg + end) / 2, y + pad, latex(tag),
ha="center", va="center")
HorizontalChromosome(root, beg, end, y, height=.025, fc='gainsboro')
begs, ends, markers = zip(*ends)
fontprop = dict(color=lsg, ha="center", va="center")
ypos = y + pad * 2
root.plot(markers, (ypos, ypos), "-", lw=2, color=lsg)
root.text(sum(markers) / 2, ypos + pad,
"Distance: 1.29cM $\Leftrightarrow$ 211,824bp (6.1 cM/Mb)", **fontprop)
ypos = y - pad
xx = markers[0], ends[0]
root.plot(xx, (ypos, ypos), "-", lw=2, color=lsg)
root.text(sum(xx) / 2, ypos - pad, "34,115bp", **fontprop)
xx = markers[1], begs[1]
root.plot(xx, (ypos, ypos), "-", lw=2, color=lsg)
root.text(sum(xx) / 2, ypos - pad, "81,276bp", **fontprop)
root.plot((ends[0], begs[1]), (y, y), ":", lw=2, color=lsg)
root.text(sum(markers) / 2, ypos - 3 * pad, r"$\textit{Estimated gap size: 96,433bp}$",
color="r", ha="center", va="center")
labels = ((.05, .95, 'A'), (.05, .6, 'B'), (.05, .27, 'C'))
panel_labels(root, labels)
normalize_axes(root)
pf = "estimategaps"
image_name = pf + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def draw_chromosomes(
root,
bedfile,
sizes,
iopts,
mergedist,
winsize,
imagemap,
mappingfile=None,
gauge=False,
legend=True,
empty=False,
title=None,
):
bed = Bed(bedfile)
prefix = bedfile.rsplit(".", 1)[0]
if imagemap:
imgmapfile = prefix + ".map"
mapfh = open(imgmapfile, "w")
print('<map id="' + prefix + '">', file=mapfh)
if mappingfile:
mappings = DictFile(mappingfile, delimiter="\t")
classes = sorted(set(mappings.values()))
preset_colors = (DictFile(
mappingfile, keypos=1, valuepos=2, delimiter="\t")
if DictFile.num_columns(mappingfile) >= 3 else {})
else:
classes = sorted(set(x.accn for x in bed))
mappings = dict((x, x) for x in classes)
preset_colors = {}
logging.debug("A total of {} classes found: {}".format(
len(classes), ",".join(classes)))
# Assign colors to classes
ncolors = max(3, min(len(classes), 12))
palette = set1_n if ncolors <= 8 else set3_n
colorset = palette(number=ncolors)
colorset = sample_N(colorset, len(classes))
class_colors = dict(zip(classes, colorset))
class_colors.update(preset_colors)
logging.debug("Assigned colors: {}".format(class_colors))
chr_lens = {}
centromeres = {}
if sizes:
chr_lens = Sizes(sizes).sizes_mapping
else:
for b, blines in groupby(bed, key=(lambda x: x.seqid)):
blines = list(blines)
maxlen = max(x.end for x in blines)
chr_lens[b] = maxlen
for b in bed:
accn = b.accn
if accn == "centromere":
centromeres[b.seqid] = b.start
if accn in mappings:
b.accn = mappings[accn]
else:
b.accn = "-"
chr_number = len(chr_lens)
if centromeres:
assert chr_number == len(
centromeres), "chr_number = {}, centromeres = {}".format(
chr_number, centromeres)
r = 0.7 # width and height of the whole chromosome set
xstart, ystart = 0.15, 0.85
xinterval = r / chr_number
xwidth = xinterval * 0.5 # chromosome width
max_chr_len = max(chr_lens.values())
ratio = r / max_chr_len # canvas / base
# first the chromosomes
for a, (chr, clen) in enumerate(sorted(chr_lens.items())):
xx = xstart + a * xinterval + 0.5 * xwidth
root.text(xx, ystart + 0.01, str(get_number(chr)), ha="center")
if centromeres:
yy = ystart - centromeres[chr] * ratio
ChromosomeWithCentromere(root,
xx,
ystart,
yy,
ystart - clen * ratio,
width=xwidth)
else:
Chromosome(root, xx, ystart, ystart - clen * ratio, width=xwidth)
chr_idxs = dict((a, i) for i, a in enumerate(sorted(chr_lens.keys())))
alpha = 1
# color the regions
for chr in sorted(chr_lens.keys()):
segment_size, excess = 0, 0
bac_list = []
prev_end, prev_klass = 0, None
for b in bed.sub_bed(chr):
clen = chr_lens[chr]
idx = chr_idxs[chr]
klass = b.accn
if klass == "centromere":
continue
start = b.start
end = b.end
if start < prev_end + mergedist and klass == prev_klass:
start = prev_end
xx = xstart + idx * xinterval
yystart = ystart - end * ratio
yyend = ystart - start * ratio
root.add_patch(
Rectangle(
(xx, yystart),
xwidth,
yyend - yystart,
fc=class_colors.get(klass, "lightslategray"),
lw=0,
alpha=alpha,
))
prev_end, prev_klass = b.end, klass
if imagemap:
"""
`segment` : size of current BAC being investigated + `excess`
`excess` : left-over bases from the previous BAC, as a result of
iterating over `winsize` regions of `segment`
"""
if excess == 0:
segment_start = start
segment = (end - start + 1) + excess
while True:
if segment < winsize:
bac_list.append(b.accn)
excess = segment
break
segment_end = segment_start + winsize - 1
tlx, tly, brx, bry = (
xx,
(1 - ystart) + segment_start * ratio,
xx + xwidth,
(1 - ystart) + segment_end * ratio,
)
print(
"\t" + write_ImageMapLine(
tlx,
tly,
brx,
bry,
iopts.w,
iopts.h,
iopts.dpi,
chr + ":" + ",".join(bac_list),
segment_start,
segment_end,
),
file=mapfh,
)
segment_start += winsize
segment -= winsize
bac_list = []
if imagemap and excess > 0:
bac_list.append(b.accn)
segment_end = end
tlx, tly, brx, bry = (
xx,
(1 - ystart) + segment_start * ratio,
xx + xwidth,
(1 - ystart) + segment_end * ratio,
)
print(
"\t" + write_ImageMapLine(
tlx,
tly,
brx,
bry,
iopts.w,
iopts.h,
iopts.dpi,
chr + ":" + ",".join(bac_list),
segment_start,
segment_end,
),
file=mapfh,
)
if imagemap:
print("</map>", file=mapfh)
mapfh.close()
logging.debug("Image map written to `{0}`".format(mapfh.name))
if gauge:
xstart, ystart = 0.9, 0.85
Gauge(root, xstart, ystart - r, ystart, max_chr_len)
if "centromere" in class_colors:
del class_colors["centromere"]
# class legends, four in a row
if legend:
xstart = 0.1
xinterval = 0.8 / len(class_colors)
xwidth = 0.04
yy = 0.08
for klass, cc in sorted(class_colors.items()):
if klass == "-":
continue
root.add_patch(
Rectangle((xstart, yy),
xwidth,
xwidth,
fc=cc,
lw=0,
alpha=alpha))
root.text(xstart + xwidth + 0.01, yy, latex(klass), fontsize=10)
xstart += xinterval
if empty:
root.add_patch(
Rectangle((xstart, yy), xwidth, xwidth, fill=False, lw=1))
root.text(xstart + xwidth + 0.01, yy, empty, fontsize=10)
if title:
root.text(0.5, 0.95, markup(title), ha="center", va="center")
def test_latex(s, expected):
from jcvi.graphics.base import latex
assert latex(s) == expected, "Expect {}".format(expected)
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")
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",
)
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",
)
p.add_option("--ymax", type="int", help="Set Y-axis max")
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, merge = 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,
merge=merge)
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(latex(chr), color="darkslategray")
for i, ax in enumerate(axarr):
lineplot(
ax,
[linebins[i]],
nbins,
chr,
window,
shift,
color="{0}{1}".format(colors[i], "r"),
)
if opts.ymax:
ax.set_ylim(0, opts.ymax)
plt.subplots_adjust(hspace=0.5)
image_name = chr + "." + iopts.format
savefig(image_name, dpi=iopts.dpi, iopts=iopts)
def plot_breaks_and_labels(
fig,
root,
ax,
gx,
gy,
xsize,
ysize,
qbreaks,
sbreaks,
sep=True,
chrlw=0.1,
sepcolor="g",
minfont=5,
stdpf=True,
chpf=True,
):
xlim = (0, 47724.0) # hard-coding xlim maximum
ylim = (ysize, 0) # invert the y-axis
# Tag to mark whether to plot chr name (skip small ones)
xchr_labels, ychr_labels = [], []
th = TextHandler(fig)
# plot the chromosome breaks
for (seqid, beg, end) in qbreaks:
xsize_ratio = abs(end - beg) * 0.8 / xsize
fontsize = th.select_fontsize(xsize_ratio)
if chpf:
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
xchr_labels.append((seqid, (beg + end) / 2, fontsize))
if sep:
ax.plot([beg, beg], ylim, "-", lw=chrlw, color=sepcolor)
for (seqid, beg, end) in sbreaks:
ysize_ratio = abs(end - beg) * 0.8 / ysize
fontsize = th.select_fontsize(ysize_ratio)
if chpf:
seqid = "".join(seqid_parse(seqid, stdpf=stdpf)[:2])
ychr_labels.append((seqid, (beg + end) / 2, fontsize*0.85))
if sep:
ax.plot(xlim, [beg, beg], "-", lw=chrlw, color=sepcolor)
# plot the chromosome labels
xchr_labels = [('chr\ 1', 1997.5, 12), ('chr\ 2', 5944.5, 12), ('chr\ 3', 9014.0, 12), ('chr\ 4', 11351.5, 12), ('chr\ 5', 13639.0, 12), ('chr\ 6', 17657.5, 12), ('chr\ 7', 22329.0, 12), ('chr\ 8', 25466.0, 12), ('chr\ 9', 28092.0, 12), ('chr\ 10', 31361.5, 12), ('chr\ 11', 34457.0, 12), ('chr\ 12', 37234.0, 12), ('chr\ 13', 41112.5, 12), ('chr\ 14', 43851.0, 12), ('chr\ 15', 45258.5, 12), ('scf\ 16', 46740.5, 12), ('scf\ 458', 47724.0, 12)]
for label, pos, fontsize in xchr_labels:
#print(xchr_labels)
pos = 0.1 + pos * 0.8 / xsize
if fontsize >= minfont:
root.text(
pos,
0.91,
latex(label),
size=fontsize*0.85,
ha="center",
va="bottom",
rotation=45,
color="black",
)
# remember y labels are inverted
ychr_labels = [('chr\ 1', 2672.0, 10.2), ('chr\ 2', 7532.0, 10.2), ('chr\ 3', 12035.0, 10.2), ('chr\ 4', 16228.0, 10.2), ('chr\ 5', 19784.5, 10.2), ('chr\ 6', 23211.0, 10.2), ('chr\ 7', 26612.5, 10.2), ('chr\ 8', 29773.0, 10.2), ('chr\ 9', 32518.0, 10.2), ('chr\ 10', 35004.5, 10.2), ('chr\ 11', 37760.0, 10.2), ('chr\ 12', 40635.5, 10.2), ('ChrSy', 42048.0, 0), ('ChrUn', 42140.5, 0)]
for label, pos, fontsize in ychr_labels:
#print(ychr_labels)
pos = 0.9 - pos * 0.8 / ysize
if fontsize >= minfont:
root.text(0.91, pos, latex(label), size=fontsize*0.85, va="center", color="black")
# Plot the frame
ax.plot(xlim, [0, 0], "-", lw=chrlw, color=sepcolor)
ax.plot(xlim, [ysize, ysize], "-", lw=chrlw, color=sepcolor)
ax.plot([0, 0], ylim, "-", lw=chrlw, color=sepcolor)
ax.plot([xsize, xsize], ylim, "-", lw=chrlw, color=sepcolor)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# The axis labels have been hardcoded (vs. gx gy as in original) so taht we can get the species names spelled out in italics, rather than the BED file name.
ax.set_xlabel('$\it{Zizania\ palustris}$', size=16)
ax.set_ylabel('$\it{Oryza\ sativa}$', size=16)
# beautify the numeric axis
for tick in ax.get_xticklines() + ax.get_yticklines():
tick.set_visible(False)
set_human_axis(ax)
plt.setp(ax.get_xticklabels() + ax.get_yticklabels(), color="black", size=10)
return xlim, ylim
