def scenario(args):
"""
%prog scenario
Illustration of the two-step genome merger process for B. rapa companion paper.
"""
p = OptionParser(__doc__)
opts, args = p.parse_args()
fig = plt.figure(1, (5, 5))
root = fig.add_axes([0, 0, 1, 1])
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
# Layout format: (x, y, label, (chr lengths))
anc = (0.5, 0.9, "Ancestor", (1, ))
s1 = (0.2, 0.6, "Genome I", (1, ))
s2 = (0.5, 0.6, "Genome II", (1, ))
s3 = (0.8, 0.6, "Genome III", (1, ))
tetra = (0.35, 0.4, "Tetraploid I / II", (0.5, 0.9))
hexa = (0.5, 0.1, "Hexaploid I / II / III", (0.36, 0.46, 0.9))
labels = (anc, s1, s2, s3, tetra, hexa)
connections = (
(anc, s1),
(anc, s2),
(anc, s3),
(s1, tetra),
(s2, tetra),
(tetra, hexa),
(s3, hexa),
)
xinterval = 0.02
yratio = 0.05
for xx, yy, label, chrl in labels:
# RoundLabel(root, xx, yy, label)
root.text(xx, yy, label, ha="center", va="center")
offset = len(label) * 0.012
for i, c in enumerate(chrl):
ya = yy + yratio * c
yb = yy - yratio * c
Chromosome(root, xx - offset + i * xinterval, ya, yb, width=0.01)
# Comments
comments = ((0.15, 0.33, "II dominant"), (0.25, 0.03, "III dominant"))
for xx, yy, c in comments:
root.text(xx, yy, c, size=9, ha="center", va="center")
# Branches
tip = 0.04
for a, b in connections:
xa, ya, la, chra = a
xb, yb, lb, chrb = b
plt.plot((xa, xb), (ya - tip, yb + 2 * tip), "k-", lw=2, alpha=0.5)
figname = fname() + ".pdf"
savefig(figname, dpi=300)
def plot_data(x, y, tour, M):
from jcvi.graphics.base import plt, savefig
plt.plot(x, y, "ro")
for ia, ib in pairwise(tour):
plt.plot((x[ia], x[ib]), (y[ia], y[ib]), "r-")
score = evaluate(tour, M)
plt.title("Score={0:.2f}".format(score))
savefig("demo.pdf")
def plot_data(x, y, tour, M):
from jcvi.graphics.base import plt, savefig
plt.plot(x, y, "ro")
for ia, ib in pairwise(tour):
plt.plot((x[ia], x[ib]), (y[ia], y[ib]), "r-")
score = evaluate(tour, M)
plt.title("Score={0:.2f}".format(score))
savefig("demo.pdf")
def scenario(args):
"""
%prog scenario
Illustration of the two-step genome merger process for B. rapa companion paper.
"""
p = OptionParser(__doc__)
opts, args = p.parse_args()
fig = plt.figure(1, (5, 5))
root = fig.add_axes([0, 0, 1, 1])
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
# Layout format: (x, y, label, (chr lengths))
anc = (.5, .9, "Ancestor", (1,))
s1 = (.2, .6, "Genome I", (1,))
s2 = (.5, .6, "Genome II", (1,))
s3 = (.8, .6, "Genome III", (1,))
tetra = (.35, .4, "Tetraploid I / II", (.5, .9))
hexa = (.5, .1, "Hexaploid I / II / III", (.36, .46, .9))
labels = (anc, s1, s2, s3, tetra, hexa)
connections = ((anc, s1), (anc, s2), (anc, s3),\
(s1, tetra), (s2, tetra),
(tetra, hexa), (s3, hexa))
xinterval = .02
yratio = .05
for xx, yy, label, chrl in labels:
#RoundLabel(root, xx, yy, label)
root.text(xx, yy, label, ha="center", va="center")
offset = len(label) * .012
for i, c in enumerate(chrl):
ya = yy + yratio * c
yb = yy - yratio * c
Chromosome(root, xx - offset + i * xinterval, ya, yb, width=.01)
# Comments
comments = ((.15, .33, "II dominant"),
(.25, .03, "III dominant"))
for xx, yy, c in comments:
root.text(xx, yy, c, size=9, ha="center", va="center")
# Branches
tip = .04
for a, b in connections:
xa, ya, la, chra = a
xb, yb, lb, chrb = b
plt.plot((xa, xb), (ya - tip, yb + 2 * tip), 'k-', lw=2, alpha=.5)
figname = fname() + ".pdf"
savefig(figname, dpi=300)
def excision(args):
"""
%prog excision
Illustrate the mechanism of illegitimate recombination.
"""
p = OptionParser(__doc__)
opts, args = p.parse_args(args)
fig = plt.figure(1, (5, 5))
root = fig.add_axes([0, 0, 1, 1])
plt.plot((.2, .8), (.6, .6), 'r-', lw=3)
plt.plot((.4, .6), (.6, .6), 'b>-', mfc='g', mec='w', ms=12, lw=3)
plt.plot((.3, .7), (.5, .5), 'r-', lw=3)
plt.plot((.5, ), (.5, ), 'b>-', mfc='g', mec='w', ms=12, lw=3)
# Circle excision
plt.plot((.5, ), (.45, ), 'b>-', mfc='g', mec='w', ms=12, lw=3)
circle = CirclePolygon((.5, .4), .05, fill=False, lw=3, ec="b")
root.add_patch(circle)
arrow_dist = .07
ar_xpos, ar_ypos = .5, .52
root.annotate(" ", (ar_xpos, ar_ypos),
(ar_xpos, ar_ypos + arrow_dist),
arrowprops=arrowprops)
RoundLabel(root, .2, .64, "Gene")
RoundLabel(root, .3, .54, "Excision")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
figname = fname() + ".pdf"
savefig(figname, dpi=300)
def excision(args):
"""
%prog excision
Illustrate the mechanism of illegitimate recombination.
"""
p = OptionParser(__doc__)
opts, args = p.parse_args(args)
fig = plt.figure(1, (5, 5))
root = fig.add_axes([0, 0, 1, 1])
plt.plot((0.2, 0.8), (0.6, 0.6), "r-", lw=3)
plt.plot((0.4, 0.6), (0.6, 0.6), "b>-", mfc="g", mec="w", ms=12, lw=3)
plt.plot((0.3, 0.7), (0.5, 0.5), "r-", lw=3)
plt.plot((0.5, ), (0.5, ), "b>-", mfc="g", mec="w", ms=12, lw=3)
# Circle excision
plt.plot((0.5, ), (0.45, ), "b>-", mfc="g", mec="w", ms=12, lw=3)
circle = CirclePolygon((0.5, 0.4), 0.05, fill=False, lw=3, ec="b")
root.add_patch(circle)
arrow_dist = 0.07
ar_xpos, ar_ypos = 0.5, 0.52
root.annotate(" ", (ar_xpos, ar_ypos), (ar_xpos, ar_ypos + arrow_dist),
arrowprops=arrowprops)
RoundLabel(root, 0.2, 0.64, "Gene")
RoundLabel(root, 0.3, 0.54, "Excision")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
figname = fname() + ".pdf"
savefig(figname, dpi=300)
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic.
"""
p = OptionParser(histogram.__doc__)
p.add_option(
"--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive",
)
p.add_option(
"--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive",
)
p.add_option(
"--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot",
)
p.add_option(
"--method",
choices=("nbinom", "allpaths"),
default="nbinom",
help=
"'nbinom' - slow but more accurate for het or polyploid genome; 'allpaths' - fast and works for homozygous enomes",
)
p.add_option(
"--maxiter",
default=100,
type="int",
help="Max iterations for optimization. Only used with --method nbinom",
)
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option(
"--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks",
)
opts, args, iopts = p.set_image_options(args, figsize="7x7")
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
method = opts.method
vmin, vmax = opts.vmin, opts.vmax
ascii = not opts.pdf
peaks = not opts.nopeaks and method == "allpaths"
N = int(N)
if histfile.rsplit(".", 1)[-1] in ("mcdat", "mcidx"):
logging.debug("CA kmer index found")
histfile = merylhistogram(histfile)
ks = KmerSpectrum(histfile)
method_info = ks.analyze(K=N, maxiter=opts.maxiter, method=method)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.lambda_ if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1.0 / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1:.1f}x".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f} Mb".format(Genome_size /
1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print(msg, file=sys.stderr)
x, y = ks.get_xy(vmin, vmax)
title = "{0} {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (iopts.w, iopts.h))
plt.bar(x, y, fc="#b2df8a", lw=0)
# Plot the negative binomial fit
if method == "nbinom":
generative_model = method_info["generative_model"]
GG = method_info["Gbins"]
ll = method_info["lambda"]
rr = method_info["rho"]
kf_range = method_info["kf_range"]
stacked = generative_model(GG, ll, rr)
plt.plot(
kf_range,
stacked,
":",
color="#6a3d9a",
lw=2,
)
ax = plt.gca()
if peaks: # Only works for method 'allpaths'
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
if tcounts:
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, "ko", lw=3, mec="k", mfc="w")
ax.text(ks.max1, tcounts[ks.max1], "SNP peak")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
if method == "nbinom":
# Plot multiple CN locations, CN1, CN2, ... up to ploidy
cn_color = "#a6cee3"
for i in range(1, ks.ploidy + 1):
x = i * ks.lambda_
plt.plot((x, x), (0, ymax), "-.", color=cn_color)
plt.text(
x,
ymax * 0.95,
"CN{}".format(i),
ha="right",
va="center",
color=cn_color,
rotation=90,
)
messages = [
Total_Kmers_msg,
Kmer_coverage_msg,
Genome_size_msg,
Repetitive_msg,
SNPrate_msg,
]
if method == "nbinom":
messages += [ks.ploidy_message] + ks.copy_messages
write_messages(ax, messages)
ax.set_title(markup(title))
ax.set_xlim((0, vmax))
ax.set_ylim((0, ymax))
adjust_spines(ax, ["left", "bottom"], outward=True)
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
set_human_axis(ax)
imagename = histfile.split(".")[0] + "." + iopts.format
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive [default: %default]")
p.add_option("--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive [default: %default]")
p.add_option("--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option("--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
peaks = not opts.nopeaks
N = int(N)
ks = KmerSpectrum(histfile)
ks.analyze(K=N)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1. / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".\
format(Genome_size / 1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
x, y = ks.get_xy(opts.vmin, opts.vmax)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
if peaks:
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, 'ko', lw=2, mec='k', mfc='w')
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
tc = "gray"
axt = ax.transAxes
ax.text(.95, .95, Total_Kmers_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .9, Kmer_coverage_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .85, Genome_size_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .8, Repetitive_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .75, SNPrate_msg, color=tc, transform=axt, ha="right")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title), color='r')
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel, color='r')
ax.set_ylabel(ylabel, color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin", dest="vmin", default=1, type="int", help="minimum value, inclusive [default: %default]")
p.add_option("--vmax", dest="vmax", default=100, type="int", help="maximum value, inclusive [default: %default]")
p.add_option(
"--pdf", default=False, action="store_true", help="Print PDF instead of ASCII plot [default: %default]"
)
p.add_option("--coverage", default=0, type="int", help="Kmer coverage [default: auto]")
p.add_option("--nopeaks", default=False, action="store_true", help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
peaks = not opts.nopeaks
N = int(N)
if histfile.rsplit(".", 1)[-1] in ("mcdat", "mcidx"):
logging.debug("CA kmer index found")
histfile = meryl([histfile])
ks = KmerSpectrum(histfile)
ks.analyze(K=N)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1.0 / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size / 1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
x, y = ks.get_xy(opts.vmin, opts.vmax)
title = "{0} {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, "g-", lw=2, alpha=0.5)
ax = plt.gca()
if peaks:
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
if tcounts:
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, "ko", lw=2, mec="k", mfc="w")
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
messages = [Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg, Repetitive_msg, SNPrate_msg]
write_messages(ax, messages)
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title))
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin", dest="vmin", default=1, type="int",
help="minimum value, inclusive [default: %default]")
p.add_option("--vmax", dest="vmax", default=100, type="int",
help="maximum value, inclusive [default: %default]")
p.add_option("--pdf", default=False, action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
p.add_option("--coverage", default=0, type="int",
help="Kmer coverage [default: auto]")
p.add_option("--nopeaks", default=False, action="store_true",
help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
N = int(N)
KMERYL, KSOAP, KALLPATHS = range(3)
kformats = ("Meryl", "Soap", "AllPaths")
kformat = KMERYL
ascii = not opts.pdf
peaks = not opts.nopeaks
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
for row in fp:
if row.startswith("# 1:"):
kformat = KALLPATHS
break
if len(row.split()) == 1:
kformat = KSOAP
break
fp.seek(0)
logging.debug("Guessed format: {0}".format(kformats[kformat]))
data = []
for rowno, row in enumerate(fp):
if row[0] == '#':
continue
if kformat == KSOAP:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = Kcounts
data.append((K, counts))
covmax = 1000000
ks = KmerSpectrum(data)
ks.analyze(K=N, covmax=covmax)
Total_Kmers = int(totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1. / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".\
format(Genome_size / 1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() \
if opts.vmin <= a <= opts.vmax)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in counts if x in t]
x, y = zip(*tcounts)
plt.plot(x, y, 'ko', lw=2, mec='k', mfc='w')
tcounts = dict(tcounts)
if peaks:
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
tc = "gray"
axt = ax.transAxes
ax.text(.95, .95, Total_Kmers_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .9, Kmer_coverage_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .85, Genome_size_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .8, Repetitive_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .75, SNPrate_msg, color=tc, transform=axt, ha="right")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title), color='r')
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel, color='r')
ax.set_ylabel(ylabel, color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic.
"""
p = OptionParser(histogram.__doc__)
p.add_option(
"--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive",
)
p.add_option(
"--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive",
)
p.add_option(
"--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot",
)
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option(
"--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks",
)
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
peaks = not opts.nopeaks
N = int(N)
if histfile.rsplit(".", 1)[-1] in ("mcdat", "mcidx"):
logging.debug("CA kmer index found")
histfile = merylhistogram(histfile)
ks = KmerSpectrum(histfile)
ks.analyze(K=N)
Total_Kmers = int(ks.totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = int(round(Total_Kmers * 1.0 / Kmer_coverage))
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, thousands(Total_Kmers))
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size /
1e6)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print(msg, file=sys.stderr)
x, y = ks.get_xy(opts.vmin, opts.vmax)
title = "{0} {1}-mer histogram".format(species, N)
if ascii:
asciiplot(x, y, title=title)
return Genome_size
plt.figure(1, (6, 6))
plt.plot(x, y, "g-", lw=2, alpha=0.5)
ax = plt.gca()
if peaks:
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in ks.counts if x in t]
if tcounts:
x, y = zip(*tcounts)
tcounts = dict(tcounts)
plt.plot(x, y, "ko", lw=2, mec="k", mfc="w")
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
messages = [
Total_Kmers_msg,
Kmer_coverage_msg,
Genome_size_msg,
Repetitive_msg,
SNPrate_msg,
]
write_messages(ax, messages)
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title))
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
return Genome_size
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--vmin",
dest="vmin",
default=1,
type="int",
help="minimum value, inclusive [default: %default]")
p.add_option("--vmax",
dest="vmax",
default=100,
type="int",
help="maximum value, inclusive [default: %default]")
p.add_option("--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
p.add_option("--coverage",
default=0,
type="int",
help="Kmer coverage [default: auto]")
p.add_option("--nopeaks",
default=False,
action="store_true",
help="Do not annotate K-mer peaks")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
N = int(N)
KMERYL, KSOAP, KALLPATHS = range(3)
kformats = ("Meryl", "Soap", "AllPaths")
kformat = KMERYL
ascii = not opts.pdf
peaks = not opts.nopeaks
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
for row in fp:
if row.startswith("# 1:"):
kformat = KALLPATHS
break
if len(row.split()) == 1:
kformat = KSOAP
break
fp.seek(0)
logging.debug("Guessed format: {0}".format(kformats[kformat]))
data = []
for rowno, row in enumerate(fp):
if row[0] == '#':
continue
if kformat == KSOAP:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = Kcounts
data.append((K, counts))
covmax = 1000000
ks = KmerSpectrum(data)
ks.analyze(K=N, covmax=covmax)
Total_Kmers = int(totalKmers)
coverage = opts.coverage
Kmer_coverage = ks.max2 if not coverage else coverage
Genome_size = Total_Kmers * 1. / Kmer_coverage / 1e6
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size)
Repetitive_msg = ks.repetitive
SNPrate_msg = ks.snprate
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() \
if opts.vmin <= a <= opts.vmax)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
return asciiplot(x, y, title=title)
plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
t = (ks.min1, ks.max1, ks.min2, ks.max2, ks.min3)
tcounts = [(x, y) for x, y in counts if x in t]
x, y = zip(*tcounts)
plt.plot(x, y, 'ko', lw=2, mec='k', mfc='w')
tcounts = dict(tcounts)
if peaks:
ax.text(ks.max1, tcounts[ks.max1], "SNP peak", va="top")
ax.text(ks.max2, tcounts[ks.max2], "Main peak")
tc = "gray"
axt = ax.transAxes
ax.text(.95, .95, Total_Kmers_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .9, Kmer_coverage_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .85, Genome_size_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .8, Repetitive_msg, color=tc, transform=axt, ha="right")
ax.text(.95, .75, SNPrate_msg, color=tc, transform=axt, ha="right")
ymin, ymax = ax.get_ylim()
ymax = ymax * 7 / 6
ax.set_title(markup(title), color='r')
ax.set_ylim((ymin, ymax))
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(xlabel, color='r')
ax.set_ylabel(ylabel, color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
savefig(imagename, dpi=100)
def bites(args):
"""
%prog bites
Illustrate the pipeline for automated bite discovery.
"""
p = OptionParser(__doc__)
opts, args = p.parse_args()
fig = plt.figure(1, (6, 6))
root = fig.add_axes([0, 0, 1, 1])
# HSP pairs
hsps = (((50, 150), (60, 180)),
((190, 250), (160, 235)),
((300, 360), (270, 330)),
((430, 470), (450, 490)),
((570, 620), (493, 543)),
((540, 555), (370, 385)), # non-collinear hsps
)
titlepos = (.9, .65, .4)
titles = ("Compare orthologous region",
"Find collinear HSPs",
"Scan paired gaps")
ytip = .01
mrange = 650.
m = lambda x: x / mrange * .7 + .1
for i, (ya, title) in enumerate(zip(titlepos, titles)):
yb = ya - .1
plt.plot((.1, .8), (ya, ya), "-", color="gray", lw=2, zorder=1)
plt.plot((.1, .8), (yb, yb), "-", color="gray", lw=2, zorder=1)
RoundLabel(root, .5, ya + 4 * ytip, title)
root.text(.9, ya, "A. thaliana", ha="center", va="center")
root.text(.9, yb, "B. rapa", ha="center", va="center")
myhsps = hsps
if i >= 1:
myhsps = hsps[:-1]
for (a, b), (c, d) in myhsps:
a, b, c, d = [m(x) for x in (a, b, c, d)]
r1 = Rectangle((a, ya - ytip), b - a, 2 * ytip, fc='r', lw=0, zorder=2)
r2 = Rectangle((c, yb - ytip), d - c, 2 * ytip, fc='r', lw=0, zorder=2)
r3 = Rectangle((a, ya - ytip), b - a, 2 * ytip, fill=False, zorder=3)
r4 = Rectangle((c, yb - ytip), d - c, 2 * ytip, fill=False, zorder=3)
r5 = Polygon(((a, ya - ytip), (c, yb + ytip),
(d, yb + ytip), (b, ya - ytip)),
fc='r', alpha=.2)
rr = (r1, r2, r3, r4, r5)
if i == 2:
rr = rr[:-1]
for r in rr:
root.add_patch(r)
# Gap pairs
hspa, hspb = zip(*myhsps)
gapa, gapb = [], []
for (a, b), (c, d) in pairwise(hspa):
gapa.append((b + 1, c - 1))
for (a, b), (c, d) in pairwise(hspb):
gapb.append((b + 1, c - 1))
gaps = zip(gapa, gapb)
tpos = titlepos[-1]
yy = tpos - .05
for i, ((a, b), (c, d)) in enumerate(gaps):
i += 1
a, b, c, d = [m(x) for x in (a, b, c, d)]
xx = (a + b + c + d) / 4
TextCircle(root, xx, yy, str(i))
# Bites
ystart = .24
ytip = .05
bites = (("Bite(40=>-15)", True),
("Bite(50=>35)", False),
("Bite(70=>120)", False),
("Bite(100=>3)", True))
for i, (bite, selected) in enumerate(bites):
xx = .15 if (i % 2 == 0) else .55
yy = ystart - i / 2 * ytip
i += 1
TextCircle(root, xx, yy, str(i))
color = "k" if selected else "gray"
root.text(xx + ytip, yy, bite, size=10, color=color, va="center")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
figname = fname() + ".pdf"
savefig(figname, dpi=300)
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--pdf", default=False, action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
soap = False
for row in fp:
if len(row.split()) == 1:
soap = True
break
fp.seek(0)
for rowno, row in enumerate(fp):
if soap:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = counts
history = ["drop"]
for a, b in pairwise(sorted(hist.items())):
Ka, ca = a
Kb, cb = b
if ca <= cb:
status = "rise"
else:
status = "drop"
if history[-1] != status:
history.append(status)
if history == ["drop", "rise", "drop"]:
break
Total_Kmers = int(totalKmers)
Kmer_coverage = Ka
Genome_size = Total_Kmers * 1. / Ka / 1e6
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size)
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() if a <= 100)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
return asciiplot(x, y, title=title)
fig = plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
ax.text(.5, .9, _(Total_Kmers_msg),
ha="center", color='b', transform=ax.transAxes)
ax.text(.5, .8, _(Kmer_coverage_msg),
ha="center", color='b', transform=ax.transAxes)
ax.text(.5, .7, _(Genome_size_msg),
ha="center", color='b', transform=ax.transAxes)
ax.set_title(_(title), color='r')
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(_(xlabel), color='r')
ax.set_ylabel(_(ylabel), color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
plt.savefig(imagename, dpi=100)
print >> sys.stderr, "Image saved to `{0}`.".format(imagename)
def bites(args):
"""
%prog bites
Illustrate the pipeline for automated bite discovery.
"""
p = OptionParser(__doc__)
opts, args = p.parse_args()
fig = plt.figure(1, (6, 6))
root = fig.add_axes([0, 0, 1, 1])
# HSP pairs
hsps = (
((50, 150), (60, 180)),
((190, 250), (160, 235)),
((300, 360), (270, 330)),
((430, 470), (450, 490)),
((570, 620), (493, 543)),
((540, 555), (370, 385)), # non-collinear hsps
)
titlepos = (0.9, 0.65, 0.4)
titles = ("Compare orthologous region", "Find collinear HSPs",
"Scan paired gaps")
ytip = 0.01
mrange = 650.0
m = lambda x: x / mrange * 0.7 + 0.1
for i, (ya, title) in enumerate(zip(titlepos, titles)):
yb = ya - 0.1
plt.plot((0.1, 0.8), (ya, ya), "-", color="gray", lw=2, zorder=1)
plt.plot((0.1, 0.8), (yb, yb), "-", color="gray", lw=2, zorder=1)
RoundLabel(root, 0.5, ya + 4 * ytip, title)
root.text(0.9, ya, "A. thaliana", ha="center", va="center")
root.text(0.9, yb, "B. rapa", ha="center", va="center")
myhsps = hsps
if i >= 1:
myhsps = hsps[:-1]
for (a, b), (c, d) in myhsps:
a, b, c, d = [m(x) for x in (a, b, c, d)]
r1 = Rectangle((a, ya - ytip),
b - a,
2 * ytip,
fc="r",
lw=0,
zorder=2)
r2 = Rectangle((c, yb - ytip),
d - c,
2 * ytip,
fc="r",
lw=0,
zorder=2)
r3 = Rectangle((a, ya - ytip),
b - a,
2 * ytip,
fill=False,
zorder=3)
r4 = Rectangle((c, yb - ytip),
d - c,
2 * ytip,
fill=False,
zorder=3)
r5 = Polygon(
((a, ya - ytip), (c, yb + ytip), (d, yb + ytip),
(b, ya - ytip)),
fc="r",
alpha=0.2,
)
rr = (r1, r2, r3, r4, r5)
if i == 2:
rr = rr[:-1]
for r in rr:
root.add_patch(r)
# Gap pairs
hspa, hspb = zip(*myhsps)
gapa, gapb = [], []
for (a, b), (c, d) in pairwise(hspa):
gapa.append((b + 1, c - 1))
for (a, b), (c, d) in pairwise(hspb):
gapb.append((b + 1, c - 1))
gaps = zip(gapa, gapb)
tpos = titlepos[-1]
yy = tpos - 0.05
for i, ((a, b), (c, d)) in enumerate(gaps):
i += 1
a, b, c, d = [m(x) for x in (a, b, c, d)]
xx = (a + b + c + d) / 4
TextCircle(root, xx, yy, str(i))
# Bites
ystart = 0.24
ytip = 0.05
bites = (
("Bite(40=>-15)", True),
("Bite(50=>35)", False),
("Bite(70=>120)", False),
("Bite(100=>3)", True),
)
for i, (bite, selected) in enumerate(bites):
xx = 0.15 if (i % 2 == 0) else 0.55
yy = ystart - i / 2 * ytip
i += 1
TextCircle(root, xx, yy, str(i))
color = "k" if selected else "gray"
root.text(xx + ytip, yy, bite, size=10, color=color, va="center")
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
figname = fname() + ".pdf"
savefig(figname, dpi=300)
def histogram(args):
"""
%prog histogram meryl.histogram species K
Plot the histogram based on meryl K-mer distribution, species and N are
only used to annotate the graphic. Find out totalKmers when running
kmer.meryl().
"""
p = OptionParser(histogram.__doc__)
p.add_option("--pdf",
default=False,
action="store_true",
help="Print PDF instead of ASCII plot [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 3:
sys.exit(not p.print_help())
histfile, species, N = args
ascii = not opts.pdf
fp = open(histfile)
hist = {}
totalKmers = 0
# Guess the format of the Kmer histogram
soap = False
for row in fp:
if len(row.split()) == 1:
soap = True
break
fp.seek(0)
for rowno, row in enumerate(fp):
if soap:
K = rowno + 1
counts = int(row.strip())
else: # meryl histogram
K, counts = row.split()[:2]
K, counts = int(K), int(counts)
Kcounts = K * counts
totalKmers += Kcounts
hist[K] = counts
history = ["drop"]
for a, b in pairwise(sorted(hist.items())):
Ka, ca = a
Kb, cb = b
if ca <= cb:
status = "rise"
else:
status = "drop"
if history[-1] != status:
history.append(status)
if history == ["drop", "rise", "drop"]:
break
Total_Kmers = int(totalKmers)
Kmer_coverage = Ka
Genome_size = Total_Kmers * 1. / Ka / 1e6
Total_Kmers_msg = "Total {0}-mers: {1}".format(N, Total_Kmers)
Kmer_coverage_msg = "{0}-mer coverage: {1}".format(N, Kmer_coverage)
Genome_size_msg = "Estimated genome size: {0:.1f}Mb".format(Genome_size)
for msg in (Total_Kmers_msg, Kmer_coverage_msg, Genome_size_msg):
print >> sys.stderr, msg
counts = sorted((a, b) for a, b in hist.items() if a <= 100)
x, y = zip(*counts)
title = "{0} genome {1}-mer histogram".format(species, N)
if ascii:
return asciiplot(x, y, title=title)
fig = plt.figure(1, (6, 6))
plt.plot(x, y, 'g-', lw=2, alpha=.5)
ax = plt.gca()
ax.text(.5,
.9,
_(Total_Kmers_msg),
ha="center",
color='b',
transform=ax.transAxes)
ax.text(.5,
.8,
_(Kmer_coverage_msg),
ha="center",
color='b',
transform=ax.transAxes)
ax.text(.5,
.7,
_(Genome_size_msg),
ha="center",
color='b',
transform=ax.transAxes)
ax.set_title(_(title), color='r')
xlabel, ylabel = "Coverage (X)", "Counts"
ax.set_xlabel(_(xlabel), color='r')
ax.set_ylabel(_(ylabel), color='r')
set_human_axis(ax)
imagename = histfile.split(".")[0] + ".pdf"
plt.savefig(imagename, dpi=100)
print >> sys.stderr, "Image saved to `{0}`.".format(imagename)