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.graphics.base import set_image_options
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 = set_image_options(p, 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(3, args[1:]))
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(tx=None):
"""
%prog newicktree
Plot Newick formatted tree. The gene structure can be plotted along if
--gffdir is given. The gff file needs to be `genename.gff`. If --sizes is
on, also show the number of amino acids.
"""
p = OptionParser(main.__doc__)
p.add_option("--outgroup", help="Root the tree using the outgroup. " + \
"Use comma to separate multiple taxa.")
p.add_option("--rmargin",
default=.3,
type="float",
help="Set blank rmargin to the right [default: %default]")
p.add_option(
"--gffdir",
default=None,
help="The directory that contain GFF files [default: %default]")
p.add_option("--sizes",
default=None,
help="The FASTA file or the sizes file [default: %default]")
opts, args, iopts = set_image_options(p, figsize="8x6")
if len(args) != 1:
sys.exit(not p.print_help())
datafile, = args
outgroup = None
if opts.outgroup:
outgroup = opts.outgroup.split(",")
pf = datafile.rsplit(".", 1)[0]
if tx:
pf = "demo"
else:
tx = open(datafile).read()
logging.debug("Load tree file `{0}`.".format(datafile))
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
draw_tree(root,
tx,
rmargin=opts.rmargin,
outgroup=outgroup,
gffdir=opts.gffdir,
sizes=opts.sizes)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
def main(tx=None):
"""
%prog newicktree
Plot Newick formatted tree. The gene structure can be plotted along if
--gffdir is given. The gff file needs to be `genename.gff`. If --sizes is
on, also show the number of amino acids.
"""
p = OptionParser(main.__doc__)
p.add_option("--outgroup", help="Root the tree using the outgroup. " + \
"Use comma to separate multiple taxa.")
p.add_option("--rmargin", default=.3, type="float",
help="Set blank rmargin to the right [default: %default]")
p.add_option("--gffdir", default=None,
help="The directory that contain GFF files [default: %default]")
p.add_option("--sizes", default=None,
help="The FASTA file or the sizes file [default: %default]")
opts, args, iopts = set_image_options(p, figsize="8x6")
if len(args) != 1:
sys.exit(not p.print_help())
datafile, = args
outgroup = None
if opts.outgroup:
outgroup = opts.outgroup.split(",")
pf = datafile.rsplit(".", 1)[0]
if tx:
pf = "demo"
else:
tx = open(datafile).read()
logging.debug("Load tree file `{0}`.".format(datafile))
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
draw_tree(root, tx, rmargin=opts.rmargin,
outgroup=outgroup, gffdir=opts.gffdir, sizes=opts.sizes)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
def main():
"""
%prog bedfile id_mappings
Takes a bedfile that contains the coordinates of features to plot on the
chromosomes, and `id_mappings` file that map the ids to certain class. Each
class will get assigned a unique color. `id_mappings` file is optional (if
omitted, will not paint the chromosome features, except the centromere).
"""
p = OptionParser(main.__doc__)
p.add_option("--title", default="Medicago truncatula v3.5",
help="title of the image [default: `%default`]")
p.add_option("--gauge", default=False, action="store_true",
help="draw a gauge with size label [default: %default]")
p.add_option("--imagemap", default=False, action="store_true",
help="generate an HTML image map associated with the image [default: %default]")
p.add_option("--winsize", default=50000, type="int",
help="if drawing an imagemap, specify the window size (bases) of each map element "
"[default: %default bp]")
opts, args, iopts = set_image_options(p, figsize="6x6", dpi=300)
if len(args) not in (1, 2):
sys.exit(p.print_help())
bedfile = args[0]
mappingfile = None
if len(args) == 2:
mappingfile = args[1]
winsize = opts.winsize
imagemap = opts.imagemap
w, h = iopts.w, iopts.h
dpi = iopts.dpi
prefix = bedfile.rsplit(".", 1)[0]
figname = prefix + "." + opts.format
if imagemap:
imgmapfile = prefix + '.map'
mapfh = open(imgmapfile, "w")
print >> mapfh, '<map id="' + prefix + '">'
if mappingfile:
mappings = dict(x.split() for x in open(mappingfile))
classes = sorted(set(mappings.values()))
logging.debug("A total of {0} classes found: {1}".format(len(classes),
','.join(classes)))
else:
mappings = {}
classes = []
logging.debug("No classes registered (no id_mappings given).")
mycolors = "wrgbymc"
class_colors = dict(zip(classes, mycolors))
bed = Bed(bedfile)
chr_lens = {}
centromeres = {}
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)
assert chr_number == len(centromeres)
fig = plt.figure(1, (w, h))
root = fig.add_axes([0, 0, 1, 1])
r = .7 # width and height of the whole chromosome set
xstart, ystart = .15, .85
xinterval = r / chr_number
xwidth = xinterval * .5 # chromosome width
max_chr_len = max(chr_lens.values())
ratio = r / max_chr_len # canvas / base
# first the chromosomes
for a, (chr, cent_position) in enumerate(sorted(centromeres.items())):
clen = chr_lens[chr]
xx = xstart + a * xinterval + .5 * xwidth
yy = ystart - cent_position * ratio
root.text(xx, ystart + .01, _(chr), ha="center")
ChromosomeWithCentromere(root, xx, ystart, yy,
ystart - clen * ratio, width=xwidth)
chr_idxs = dict((a, i) for i, a in enumerate(sorted(chr_lens.keys())))
alpha = .75
# color the regions
for chr in sorted(chr_lens.keys()):
segment_size, excess = 0, 0
bac_list = []
for b in bed.sub_bed(chr):
clen = chr_lens[chr]
idx = chr_idxs[chr]
klass = b.accn
start = b.start
end = b.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, "w"), lw=0, alpha=alpha))
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 >> mapfh, '\t' + write_ImageMapLine(tlx, tly, brx, bry, \
w, h, dpi, chr+":"+",".join(bac_list), segment_start, segment_end)
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 >> mapfh, '\t' + write_ImageMapLine(tlx, tly, brx, bry, \
w, h, dpi, chr+":"+",".join(bac_list), segment_start, segment_end)
if imagemap:
print >> mapfh, '</map>'
mapfh.close()
logging.debug("Image map written to `{0}`".format(mapfh.name))
if opts.gauge:
tip = .008 # the ticks on the gauge bar
extra = .006 # the offset for the unit label
xstart, ystart = .9, .85
yy = ystart
gauge = int(ceil(max_chr_len / 1e6))
mb = ratio * 1e6
yinterval = 2 * mb
root.plot([xstart, xstart], [yy, yy - r], 'b-', lw=2)
for x in xrange(0, gauge, 2):
if x % 10:
root.plot([xstart, xstart + tip], [yy, yy], "b-")
else:
root.plot([xstart - tip, xstart + tip], [yy, yy], 'b-', lw=2)
root.text(xstart + tip + extra, yy, _(x),
color="gray", va="center")
yy -= yinterval
root.text(xstart, yy - .03, _("Mb"), color="gray", va="center")
# class legends, four in a row
xstart = .1
xinterval = .2
xwidth = .04
yy = .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 + .01, yy, _(klass), fontsize=9)
xstart += xinterval
root.text(.5, .95, opts.title, fontstyle="italic", ha="center", va="center")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
plt.savefig(figname, dpi=dpi)
logging.debug("Figure saved to `{0}` {1}".format(figname, iopts))
help="Style of the dots, one of {0} [default: %default]".\
format("|".join(DotStyles)))
p.add_option(
"--proportional",
default=False,
action="store_true",
help="Make image width:height equal to seq ratio [default: %default]")
p.add_option("--stripNames",
default=False,
action="store_true",
help="Remove trailing .? from gene names [default: %default]")
p.add_option("--sample",
default=None,
type="int",
help="Only plot maximum of N dots [default: %default]")
opts, args, iopts = set_image_options(p, figsize="8x8", dpi=150)
qsizes, ssizes = opts.qsizes, opts.ssizes
qbed, sbed = opts.qbed, opts.sbed
proportional = opts.proportional
if len(args) != 1:
sys.exit(not p.print_help())
if qbed:
qsizes = qsizes or sizes([qbed])
qbed = Bed(qbed)
if sbed:
ssizes = ssizes or sizes([sbed])
sbed = Bed(sbed)
def main():
"""
%prog bedfile id_mappings
Takes a bedfile that contains the coordinates of features to plot on the
chromosomes, and `id_mappings` file that map the ids to certain class. Each
class will get assigned a unique color. `id_mappings` file is optional (if
omitted, will not paint the chromosome features, except the centromere).
"""
p = OptionParser(main.__doc__)
p.add_option("--title",
default="Medicago truncatula v3.5",
help="title of the image [default: `%default`]")
p.add_option("--gauge",
default=False,
action="store_true",
help="draw a gauge with size label [default: %default]")
p.add_option(
"--imagemap",
default=False,
action="store_true",
help=
"generate an HTML image map associated with the image [default: %default]"
)
p.add_option(
"--winsize",
default=50000,
type="int",
help=
"if drawing an imagemap, specify the window size (bases) of each map element "
"[default: %default bp]")
opts, args, iopts = set_image_options(p, figsize="6x6", dpi=300)
if len(args) not in (1, 2):
sys.exit(p.print_help())
bedfile = args[0]
mappingfile = None
if len(args) == 2:
mappingfile = args[1]
winsize = opts.winsize
imagemap = opts.imagemap
w, h = iopts.w, iopts.h
dpi = iopts.dpi
prefix = bedfile.rsplit(".", 1)[0]
figname = prefix + "." + opts.format
if imagemap:
imgmapfile = prefix + '.map'
mapfh = open(imgmapfile, "w")
print >> mapfh, '<map id="' + prefix + '">'
if mappingfile:
mappings = dict(x.split() for x in open(mappingfile))
classes = sorted(set(mappings.values()))
logging.debug("A total of {0} classes found: {1}".format(
len(classes), ','.join(classes)))
else:
mappings = {}
classes = []
logging.debug("No classes registered (no id_mappings given).")
mycolors = "wrgbymc"
class_colors = dict(zip(classes, mycolors))
bed = Bed(bedfile)
chr_lens = {}
centromeres = {}
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)
assert chr_number == len(centromeres)
fig = plt.figure(1, (w, h))
root = fig.add_axes([0, 0, 1, 1])
r = .7 # width and height of the whole chromosome set
xstart, ystart = .15, .85
xinterval = r / chr_number
xwidth = xinterval * .5 # chromosome width
max_chr_len = max(chr_lens.values())
ratio = r / max_chr_len # canvas / base
# first the chromosomes
for a, (chr, cent_position) in enumerate(sorted(centromeres.items())):
clen = chr_lens[chr]
xx = xstart + a * xinterval + .5 * xwidth
yy = ystart - cent_position * ratio
root.text(xx, ystart + .01, _(chr), ha="center")
ChromosomeWithCentromere(root,
xx,
ystart,
yy,
ystart - clen * ratio,
width=xwidth)
chr_idxs = dict((a, i) for i, a in enumerate(sorted(chr_lens.keys())))
alpha = .75
# color the regions
for chr in sorted(chr_lens.keys()):
segment_size, excess = 0, 0
bac_list = []
for b in bed.sub_bed(chr):
clen = chr_lens[chr]
idx = chr_idxs[chr]
klass = b.accn
start = b.start
end = b.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, "w"),
lw=0,
alpha=alpha))
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 >> mapfh, '\t' + write_ImageMapLine(tlx, tly, brx, bry, \
w, h, dpi, chr+":"+",".join(bac_list), segment_start, segment_end)
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 >> mapfh, '\t' + write_ImageMapLine(tlx, tly, brx, bry, \
w, h, dpi, chr+":"+",".join(bac_list), segment_start, segment_end)
if imagemap:
print >> mapfh, '</map>'
mapfh.close()
logging.debug("Image map written to `{0}`".format(mapfh.name))
if opts.gauge:
tip = .008 # the ticks on the gauge bar
extra = .006 # the offset for the unit label
xstart, ystart = .9, .85
yy = ystart
gauge = int(ceil(max_chr_len / 1e6))
mb = ratio * 1e6
yinterval = 2 * mb
root.plot([xstart, xstart], [yy, yy - r], 'b-', lw=2)
for x in xrange(0, gauge, 2):
if x % 10:
root.plot([xstart, xstart + tip], [yy, yy], "b-")
else:
root.plot([xstart - tip, xstart + tip], [yy, yy], 'b-', lw=2)
root.text(xstart + tip + extra,
yy,
_(x),
color="gray",
va="center")
yy -= yinterval
root.text(xstart, yy - .03, _("Mb"), color="gray", va="center")
# class legends, four in a row
xstart = .1
xinterval = .2
xwidth = .04
yy = .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 + .01, yy, _(klass), fontsize=9)
xstart += xinterval
root.text(.5,
.95,
opts.title,
fontstyle="italic",
ha="center",
va="center")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
plt.savefig(figname, dpi=dpi)
logging.debug("Figure saved to `{0}` {1}".format(figname, iopts))
def coverage(args):
"""
%prog coverage fastafile ctg bedfile1 bedfile2 ..
Plot coverage from a set of BED files that contain the read mappings. The
paired read span will be converted to a new bedfile that contain the happy
mates. ctg is the chr/scf/ctg that you want to plot the histogram on.
If the bedfiles already contain the clone spans, turn on --spans.
"""
from jcvi.formats.bed import mates, bedpe
p = OptionParser(coverage.__doc__)
p.add_option("--ymax", default=None, type="int",
help="Limit ymax [default: %default]")
p.add_option("--spans", default=False, action="store_true",
help="BED files already contain clone spans [default: %default]")
opts, args, iopts = set_image_options(p, args, figsize="8x5")
if len(args) < 3:
sys.exit(not p.print_help())
fastafile, ctg = args[0:2]
bedfiles = args[2:]
sizes = Sizes(fastafile)
size = sizes.mapping[ctg]
fig = plt.figure(1, (iopts.w, iopts.h))
ax = plt.gca()
bins = 100 # smooth the curve
lines = []
legends = []
not_covered = []
yy = .9
for bedfile, c in zip(bedfiles, "rgbcky"):
if not opts.spans:
pf = bedfile.rsplit(".", 1)[0]
matesfile = pf + ".mates"
if need_update(bedfile, matesfile):
matesfile, matesbedfile = mates([bedfile, "--lib"])
bedspanfile = pf + ".spans.bed"
if need_update(matesfile, bedspanfile):
bedpefile, bedspanfile = bedpe([bedfile, "--span",
"--mates={0}".format(matesfile)])
bedfile = bedspanfile
bedsum = Bed(bedfile).sum(seqid=ctg)
notcoveredbases = size - bedsum
legend = _(bedfile.split(".")[0])
msg = "{0}: {1} bp not covered".format(legend, thousands(notcoveredbases))
not_covered.append(msg)
print >> sys.stderr, msg
ax.text(.1, yy, msg, color=c, size=9, transform=ax.transAxes)
yy -= .08
cov = Coverage(bedfile, sizes.filename)
x, y = cov.get_plot_data(ctg, bins=bins)
line, = ax.plot(x, y, '-', color=c, lw=2, alpha=.5)
lines.append(line)
legends.append(legend)
leg = ax.legend(lines, legends, shadow=True, fancybox=True)
leg.get_frame().set_alpha(.5)
ylabel = "Average depth per {0}Kb".format(size / bins / 1000)
ax.set_xlim(0, size)
ax.set_ylim(0, opts.ymax)
ax.set_xlabel(ctg)
ax.set_ylabel(ylabel)
set_human_base_axis(ax)
figname ="{0}.{1}.pdf".format(fastafile, ctg)
plt.savefig(figname, dpi=iopts.dpi)
logging.debug("Figure saved to `{0}` {1}.".format(figname, iopts))
def heatmap(args):
"""
%prog heatmap fastafile chr1
Combine stack plot with heatmap to show abundance of various tracks along
given chromosome. Need to give multiple beds to --stacks and --heatmaps
"""
p = OptionParser(heatmap.__doc__)
p.add_option("--stacks",
default="Exons,Introns,DNA_transposons,Retrotransposons",
help="Features to plot in stackplot [default: %default]")
p.add_option("--heatmaps",
default="Copia,Gypsy,hAT,Helitron,Introns,Exons",
help="Features to plot in heatmaps [default: %default]")
p.add_option("--meres", default=None,
help="Extra centromere / telomere features [default: %default]")
add_window_options(p)
opts, args, iopts = set_image_options(p, args, figsize="8x5")
if len(args) != 2:
sys.exit(not p.print_help())
fastafile, chr = args
window, shift = check_window_options(opts)
stacks = opts.stacks.split(",")
heatmaps = opts.heatmaps.split(",")
stackbeds = [x + ".bed" for x in stacks]
heatmapbeds = [x + ".bed" for x in heatmaps]
stackbins = get_binfiles(stackbeds, fastafile, shift)
heatmapbins = get_binfiles(heatmapbeds, fastafile, shift)
window, shift = check_window_options(opts)
margin = .06
inner = .015
clen = Sizes(fastafile).mapping[chr]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
# Gauge
ratio = draw_gauge(root, margin, clen, rightmargin=4 * margin)
yinterval = .3
xx = margin
yy = 1 - margin
yy -= yinterval
xlen = clen / ratio
if "_" in chr:
ca, cb = chr.split("_")
cc = ca[0].upper() + cb
root.add_patch(Rectangle((xx, yy), xlen, yinterval - inner, color=gray))
ax = fig.add_axes([xx, yy, xlen, yinterval - inner])
nbins = clen / shift
if clen % shift:
nbins += 1
owindow = clen / 100
if owindow > window:
window = owindow / shift * shift
stackplot(ax, stackbins, nbins, palette, chr, window, shift)
root.text(xx + inner, yy + yinterval - 2 * inner, cc, va="top")
# Legends
xx += xlen + .01
yspace = (yinterval - inner) / (len(stackbins) + 1)
yy = 1 - margin - yinterval
for s, p in zip(stacks, palette):
s = s.replace("_", " ")
s = Registration.get(s, s)
yy += yspace
root.add_patch(Rectangle((xx, yy), inner, inner, color=p, lw=0))
root.text(xx + 1.5 * inner, yy, s, size=10)
yh = .05 # Heatmap height
# Heatmaps
xx = margin
yy = 1 - margin - yinterval - inner
for s, p in zip(heatmaps, heatmapbins):
s = s.replace("_", " ")
s = Registration.get(s, s)
yy -= yh
m = stackarray(p, chr, window, shift)
Y = np.array([m, m])
root.imshow(Y, extent=(xx, xx + xlen, yy, yy + yh - inner),
interpolation="nearest", aspect="auto")
root.text(xx + xlen + .01, yy, s, size=10)
yy -= yh
meres = opts.meres
if meres:
bed = Bed(meres)
for b in bed:
if b.seqid != chr:
continue
pos = (b.start + b.end) / 2
cpos = pos / ratio
xx = margin + cpos
accn = b.accn.capitalize()
root.add_patch(CirclePolygon((xx, yy), radius=.01, fc="m", ec="m"))
root.text(xx + .014, yy, _(accn), va="center", color="m")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = chr + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
def stack(args):
"""
%prog stack fastafile
Create landscape plots that show the amounts of genic sequences, and repetitive
sequences along the chromosomes.
"""
p = OptionParser(stack.__doc__)
p.add_option("--top", default=10, type="int",
help="Draw the first N chromosomes [default: %default]")
p.add_option("--stacks",
default="Exons,Introns,DNA_transposons,Retrotransposons",
help="Features to plot in stackplot [default: %default]")
p.add_option("--switch",
help="Change chr names based on two-column file [default: %default]")
add_window_options(p)
opts, args, iopts = set_image_options(p, args, figsize="8x8")
if len(args) != 1:
sys.exit(not p.print_help())
fastafile, = args
top = opts.top
window, shift = check_window_options(opts)
switch = opts.switch
if switch:
switch = DictFile(opts.switch)
bedfiles = [x + ".bed" for x in opts.stacks.split(",")]
binfiles = get_binfiles(bedfiles, fastafile, shift)
sizes = Sizes(fastafile)
s = list(sizes.iter_sizes())[:top]
maxl = max(x[1] for x in s)
margin = .08
inner = .02 # y distance between tracks
pf = fastafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
max_len = s
# Gauge
ratio = draw_gauge(root, margin, maxl)
# Per chromosome
yinterval = (1 - 2 * margin) / (top + 1)
xx = margin
yy = 1 - margin
for chr, clen in s:
yy -= yinterval
xlen = clen / ratio
if "_" in chr:
ca, cb = chr.split("_")
cc = ca[0].upper() + cb
if switch and cc in switch:
cc = "\n".join((cc, "({0})".format(switch[cc])))
root.add_patch(Rectangle((xx, yy), xlen, yinterval - inner, color=gray))
ax = fig.add_axes([xx, yy, xlen, yinterval - inner])
nbins = clen / shift
if clen % shift:
nbins += 1
stackplot(ax, binfiles, nbins, palette, chr, window, shift)
root.text(xx - .04, yy + .5 * (yinterval - inner), cc, ha="center", va="center")
ax.set_xlim(0, nbins)
ax.set_ylim(0, 1)
ax.set_axis_off()
# Legends
yy -= yinterval
xx = margin
for b, p in zip(bedfiles, palette):
b = b.rsplit(".", 1)[0].replace("_", " ")
b = Registration.get(b, b)
root.add_patch(Rectangle((xx, yy), inner, inner, color=p, lw=0))
xx += 2 * inner
root.text(xx, yy, _(b), size=13)
xx += len(b) * .012 + inner
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
def main():
p = OptionParser(__doc__)
p.add_option("--groups", default=False, action="store_true",
help="The first row contains group info [default: %default]")
p.add_option("--rowgroups", help="Row groupings [default: %default]")
p.add_option("--horizontalbar", default=False, action="store_true",
help="Horizontal color bar [default: vertical]")
p.add_option("--cmap", default="jet",
help="Use this color map [default: %default]")
opts, args, iopts = set_image_options(p, figsize="8x8")
if len(args) != 1:
sys.exit(not p.print_help())
datafile, = args
pf = datafile.rsplit(".", 1)[0]
rowgroups = opts.rowgroups
groups, rows, cols, data = parse_csv(datafile, vmin=1, groups=opts.groups)
cols = [x.replace("ay ", "") for x in cols]
if rowgroups:
fp = open(rowgroups)
rgroups = []
for row in fp:
a, b = row.split()
irows = [rows.index(x) for x in b.split(",")]
rgroups.append((a, min(irows), max(irows)))
plt.rcParams["axes.linewidth"] = 0
xstart = .18
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
ax = fig.add_axes([xstart, .15, .7, .7])
default_cm = cm.get_cmap(opts.cmap)
im = ax.matshow(data, cmap=default_cm, norm=LogNorm(vmin=1, vmax=10000))
nrows, ncols = len(rows), len(cols)
xinterval = .7 / ncols
yinterval = .7 / max(nrows, ncols)
plt.xticks(range(ncols), cols, rotation=45, size=10, ha="center")
plt.yticks(range(nrows), rows, size=10)
for x in ax.get_xticklines() + ax.get_yticklines():
x.set_visible(False)
ax.set_xlim(-.5, ncols - .5)
t = [1, 10, 100, 1000, 10000]
pad = .06
if opts.horizontalbar:
ypos = .5 * (1 - nrows * yinterval) - pad
axcolor = fig.add_axes([.3, ypos, .4, .02])
orientation = "horizontal"
else:
axcolor = fig.add_axes([.9, .3, .02, .4])
orientation = "vertical"
fig.colorbar(im, cax=axcolor, ticks=t, format=_("%d"), orientation=orientation)
if groups:
groups = [(key, len(list(nn))) for key, nn in groupby(groups)]
yy = .5 + .5 * nrows / ncols * .7 + .06
e = .005
sep = -.5
for k, kl in groups:
# Separator in the array area
sep += kl
ax.plot([sep, sep], [-.5, nrows - .5], "w-", lw=2)
# Group labels on the top
kl *= xinterval
root.plot([xstart + e, xstart + kl - e], [yy, yy], "-", color="gray", lw=2)
root.text(xstart + .5 * kl, yy + e, k, ha="center", color="gray")
xstart += kl
if rowgroups:
from jcvi.graphics.glyph import TextCircle
xpos = .04
tip = .015
assert rgroups
ystart = 1 - .5 * (1 - nrows * yinterval)
for gname, start, end in rgroups:
start = ystart - start * yinterval
end = ystart - (end + 1) * yinterval
start -= tip / 3
end += tip / 3
# Bracket the groups
root.plot((xpos, xpos + tip), (start, start), "k-", lw=2)
root.plot((xpos, xpos), (start, end), "k-", lw=2)
root.plot((xpos, xpos + tip), (end, end), "k-", lw=2)
TextCircle(root, xpos, .5 * (start + end), gname)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + opts.cmap + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
p.add_option("--qbed", help="Path to qbed")
p.add_option("--sbed", help="Path to sbed")
p.add_option("--qselect", default=0, type="int",
help="Minimum size of query contigs to select [default: %default]")
p.add_option("--sselect", default=0, type="int",
help="Minimum size of subject contigs to select [default: %default]")
p.add_option("--style", default="dot", choices=DotStyles,
help="Style of the dots, one of {0} [default: %default]".\
format("|".join(DotStyles)))
p.add_option("--proportional", default=False, action="store_true",
help="Make image width:height equal to seq ratio [default: %default]")
p.add_option("--stripNames", default=False, action="store_true",
help="Remove trailing .? from gene names [default: %default]")
p.add_option("--sample", default=None, type="int",
help="Only plot maximum of N dots [default: %default]")
opts, args, iopts = set_image_options(p, figsize="8x8", dpi=150)
qsizes, ssizes = opts.qsizes, opts.ssizes
qbed, sbed = opts.qbed, opts.sbed
proportional = opts.proportional
if len(args) != 1:
sys.exit(not p.print_help())
if qbed:
qsizes = qsizes or sizes([qbed])
qbed = Bed(qbed)
if sbed:
ssizes = ssizes or sizes([sbed])
sbed = Bed(sbed)
if __name__ == "__main__":
p = OptionParser(__doc__)
add_beds(p)
p.add_option("--synteny", default=False, action="store_true",
help="Run a fast synteny scan and display blocks [default: %default]")
p.add_option("--cmap", default="Synonymous substitutions (Ks)",
help="Draw colormap box on the bottom-left corner "
"[default: `%default`]")
p.add_option("--vmin", dest="vmin", type="float", default=0,
help="Minimum value in the colormap [default: %default]")
p.add_option("--vmax", dest="vmax", type="float", default=1,
help="Maximum value in the colormap [default: %default]")
opts, args, iopts = set_image_options(p, sys.argv[1:], figsize="8x8", dpi=90)
if len(args) != 1:
sys.exit(not p.print_help())
qbed, sbed, qorder, sorder, is_self = check_beds(p, opts)
synteny = opts.synteny
vmin, vmax = opts.vmin, opts.vmax
cmap_text = opts.cmap
anchorfile = args[0]
image_name = op.splitext(anchorfile)[0] + "." + opts.format
dotplot(anchorfile, qbed, sbed, image_name, vmin, vmax, iopts,
is_self=is_self, synteny=synteny, cmap_text=cmap_text)
def stack(args):
"""
%prog stack fastafile
Create landscape plots that show the amounts of genic sequences, and repetitive
sequences along the chromosomes.
"""
p = OptionParser(stack.__doc__)
p.add_option("--top",
default=10,
type="int",
help="Draw the first N chromosomes [default: %default]")
p.add_option("--stacks",
default="Exons,Introns,DNA_transposons,Retrotransposons",
help="Features to plot in stackplot [default: %default]")
p.add_option(
"--switch",
help="Change chr names based on two-column file [default: %default]")
add_window_options(p)
opts, args, iopts = set_image_options(p, args, figsize="8x8")
if len(args) != 1:
sys.exit(not p.print_help())
fastafile, = args
top = opts.top
window, shift, subtract = check_window_options(opts)
switch = opts.switch
if switch:
switch = DictFile(opts.switch)
bedfiles = [x + ".bed" for x in opts.stacks.split(",")]
binfiles = get_binfiles(bedfiles, fastafile, shift, subtract)
sizes = Sizes(fastafile)
s = list(sizes.iter_sizes())[:top]
maxl = max(x[1] for x in s)
margin = .08
inner = .02 # y distance between tracks
pf = fastafile.rsplit(".", 1)[0]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
max_len = s
# Gauge
ratio = draw_gauge(root, margin, maxl)
# Per chromosome
yinterval = (1 - 2 * margin) / (top + 1)
xx = margin
yy = 1 - margin
for chr, clen in s:
yy -= yinterval
xlen = clen / ratio
if "_" in chr:
ca, cb = chr.split("_")
cc = ca[0].upper() + cb
if switch and cc in switch:
cc = "\n".join((cc, "({0})".format(switch[cc])))
root.add_patch(Rectangle((xx, yy), xlen, yinterval - inner,
color=gray))
ax = fig.add_axes([xx, yy, xlen, yinterval - inner])
nbins = clen / shift
if clen % shift:
nbins += 1
stackplot(ax, binfiles, nbins, palette, chr, window, shift)
root.text(xx - .04,
yy + .5 * (yinterval - inner),
cc,
ha="center",
va="center")
ax.set_xlim(0, nbins)
ax.set_ylim(0, 1)
ax.set_axis_off()
# Legends
yy -= yinterval
xx = margin
for b, p in zip(bedfiles, palette):
b = b.rsplit(".", 1)[0].replace("_", " ")
b = Registration.get(b, b)
root.add_patch(Rectangle((xx, yy), inner, inner, color=p, lw=0))
xx += 2 * inner
root.text(xx, yy, _(b), size=13)
xx += len(b) * .012 + inner
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = pf + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
def heatmap(args):
"""
%prog heatmap fastafile chr1
Combine stack plot with heatmap to show abundance of various tracks along
given chromosome. Need to give multiple beds to --stacks and --heatmaps
"""
p = OptionParser(heatmap.__doc__)
p.add_option("--stacks",
default="Exons,Introns,DNA_transposons,Retrotransposons",
help="Features to plot in stackplot [default: %default]")
p.add_option("--heatmaps",
default="Copia,Gypsy,hAT,Helitron,Introns,Exons",
help="Features to plot in heatmaps [default: %default]")
p.add_option(
"--meres",
default=None,
help="Extra centromere / telomere features [default: %default]")
add_window_options(p)
opts, args, iopts = set_image_options(p, args, figsize="8x5")
if len(args) != 2:
sys.exit(not p.print_help())
fastafile, chr = args
window, shift, subtract = check_window_options(opts)
stacks = opts.stacks.split(",")
heatmaps = opts.heatmaps.split(",")
stackbeds = [x + ".bed" for x in stacks]
heatmapbeds = [x + ".bed" for x in heatmaps]
stackbins = get_binfiles(stackbeds, fastafile, shift, subtract)
heatmapbins = get_binfiles(heatmapbeds, fastafile, shift, subtract)
margin = .06
inner = .015
clen = Sizes(fastafile).mapping[chr]
fig = plt.figure(1, (iopts.w, iopts.h))
root = fig.add_axes([0, 0, 1, 1])
# Gauge
ratio = draw_gauge(root, margin, clen, rightmargin=4 * margin)
yinterval = .3
xx = margin
yy = 1 - margin
yy -= yinterval
xlen = clen / ratio
if "_" in chr:
ca, cb = chr.split("_")
cc = ca[0].upper() + cb
root.add_patch(Rectangle((xx, yy), xlen, yinterval - inner, color=gray))
ax = fig.add_axes([xx, yy, xlen, yinterval - inner])
nbins = clen / shift
if clen % shift:
nbins += 1
owindow = clen / 100
if owindow > window:
window = owindow / shift * shift
stackplot(ax, stackbins, nbins, palette, chr, window, shift)
root.text(xx + inner, yy + yinterval - 2 * inner, cc, va="top")
# Legends
xx += xlen + .01
yspace = (yinterval - inner) / (len(stackbins) + 1)
yy = 1 - margin - yinterval
for s, p in zip(stacks, palette):
s = s.replace("_", " ")
s = Registration.get(s, s)
yy += yspace
root.add_patch(Rectangle((xx, yy), inner, inner, color=p, lw=0))
root.text(xx + 1.5 * inner, yy, s, size=10)
yh = .05 # Heatmap height
# Heatmaps
xx = margin
yy = 1 - margin - yinterval - inner
for s, p in zip(heatmaps, heatmapbins):
s = s.replace("_", " ")
s = Registration.get(s, s)
yy -= yh
m = stackarray(p, chr, window, shift)
Y = np.array([m, m])
root.imshow(Y,
extent=(xx, xx + xlen, yy, yy + yh - inner),
interpolation="nearest",
aspect="auto")
root.text(xx + xlen + .01, yy, s, size=10)
yy -= yh
meres = opts.meres
if meres:
bed = Bed(meres)
for b in bed:
if b.seqid != chr:
continue
pos = (b.start + b.end) / 2
cpos = pos / ratio
xx = margin + cpos
accn = b.accn.capitalize()
root.add_patch(CirclePolygon((xx, yy), radius=.01, fc="m", ec="m"))
root.text(xx + .014, yy, _(accn), va="center", color="m")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
image_name = chr + "." + iopts.format
logging.debug("Print image to `{0}` {1}".format(image_name, iopts))
plt.savefig(image_name, dpi=iopts.dpi)
plt.rcdefaults()
