def loghistogram(data, base=2, ascii=True, title="Counts", summary=False):
"""
bins is a dictionary with key: log(x, base), value: counts.
"""
from jcvi.utils.cbook import percentage
if summary:
unique = len(data)
total = sum(data)
# Print out a distribution
print >> sys.stderr, "Unique: {0}".format(percentage(unique, total))
bins = defaultdict(int)
for d in data:
logd = int(log(d, base))
bins[logd] += 1
x, y = [], []
for size, number in sorted(bins.items()):
lb, ub = base ** size, base ** (size + 1)
x.append((lb, ub))
y.append(number)
asciiplot(x, y, title=title)
def loghistogram(data, base=2, ascii=True, title="Counts", summary=False):
"""
bins is a dictionary with key: log(x, base), value: counts.
"""
from jcvi.utils.cbook import percentage
if summary:
unique = len(data)
total = sum(data)
# Print out a distribution
print >> sys.stderr, "Unique: {0}".format(percentage(unique, total))
bins = defaultdict(int)
for d in data:
logd = int(log(d, base))
bins[logd] += 1
x, y = [], []
for size, number in sorted(bins.items()):
lb, ub = base ** size, base ** (size + 1)
x.append((lb, ub))
y.append(number)
asciiplot(x, y, title=title)
def stem_leaf_plot(data, vmin, vmax, bins, digit=1, title=None):
'''
Generate stem and leaf plot given a collection of numbers
'''
assert bins > 0
range = vmax - vmin
step = range * 1. / bins
if isinstance(range, int):
step = int(ceil(step))
step = step or 1
bins = np.arange(vmin, vmax + step, step)
hist, bin_edges = np.histogram(data, bins=bins)
asciiplot(bin_edges, hist, digit=digit, title=title)
print >> sys.stderr, "Last bin ends in {0}, inclusive.".format(vmax)
def stem_leaf_plot(data, vmin, vmax, bins, digit=1, title=None):
'''
Generate stem and leaf plot given a collection of numbers
'''
assert bins > 0
range = vmax - vmin
step = range * 1. / bins
if isinstance(range, int):
step = int(ceil(step))
step = step or 1
bins = np.arange(vmin, vmax + step, step)
hist, bin_edges = np.histogram(data, bins=bins)
asciiplot(bin_edges, hist, digit=digit, title=title)
print >> sys.stderr, "Last bin ends in {0}, inclusive.".format(vmax)
def stem_leaf_plot(data, vmin, vmax, bins, digit=1, title=None):
"""
Generate stem and leaf plot given a collection of numbers
"""
assert bins > 0
range = vmax - vmin
step = range * 1.0 / bins
if isinstance(range, int):
step = int(ceil(step))
step = step or 1
bins = np.arange(vmin, vmax + step, step)
hist, bin_edges = np.histogram(data, bins=bins)
# By default, len(bin_edges) = len(hist) + 1
bin_edges = bin_edges[: len(hist)]
asciiplot(bin_edges, hist, digit=digit, title=title)
print("Last bin ends in {0}, inclusive.".format(vmax), file=sys.stderr)
return bin_edges, hist
def model(args):
"""
%prog model erate
Model kmer distribution given error rate. See derivation in FIONA paper:
<http://bioinformatics.oxfordjournals.org/content/30/17/i356.full>
"""
from scipy.stats import binom, poisson
p = OptionParser(model.__doc__)
p.add_option("-k", default=23, type="int", help="Kmer size")
p.add_option("--cov", default=50, type="int", help="Expected coverage")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
(erate, ) = args
erate = float(erate)
cov = opts.cov
k = opts.k
xy = []
# Range include c although it is unclear what it means to have c=0
for c in range(0, cov * 2 + 1):
Prob_Yk = 0
for i in range(k + 1):
# Probability of having exactly i errors
pi_i = binom.pmf(i, k, erate)
# Expected coverage of kmer with exactly i errors
mu_i = cov * (erate / 3)**i * (1 - erate)**(k - i)
# Probability of seeing coverage of c
Prob_Yk_i = poisson.pmf(c, mu_i)
# Sum i over 0, 1, ... up to k errors
Prob_Yk += pi_i * Prob_Yk_i
xy.append((c, Prob_Yk))
x, y = zip(*xy)
asciiplot(x, y, title="Model")
def model(args):
"""
%prog model erate
Model kmer distribution given error rate. See derivation in FIONA paper:
<http://bioinformatics.oxfordjournals.org/content/30/17/i356.full>
"""
from scipy.stats import binom, poisson
p = OptionParser(model.__doc__)
p.add_option("-k", default=23, type="int", help="Kmer size")
p.add_option("--cov", default=50, type="int", help="Expected coverage")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
erate, = args
erate = float(erate)
cov = opts.cov
k = opts.k
xy = []
# Range include c although it is unclear what it means to have c=0
for c in xrange(0, cov * 2 + 1):
Prob_Yk = 0
for i in xrange(k + 1):
# Probability of having exactly i errors
pi_i = binom.pmf(i, k, erate)
# Expected coverage of kmer with exactly i errors
mu_i = cov * (erate / 3) ** i * (1 - erate) ** (k - i)
# Probability of seeing coverage of c
Prob_Yk_i = poisson.pmf(c, mu_i)
# Sum i over 0, 1, ... up to k errors
Prob_Yk += pi_i * Prob_Yk_i
xy.append((c, Prob_Yk))
x, y = zip(*xy)
asciiplot(x, y, title="Model")
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 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 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)