def variation(args):
"""
%prog variation P1.bed P2.bed F1.bed
Associate IES in parents and progeny.
"""
p = OptionParser(variation.__doc__)
p.add_option("--diversity",
choices=("breakpoint", "variant"),
default="variant",
help="Plot diversity")
opts, args, iopts = p.set_image_options(args, figsize="6x6")
if len(args) != 3:
sys.exit(not p.print_help())
pfs = [op.basename(x).split('-')[0] for x in args]
P1, P2, F1 = pfs
newbedfile = "-".join(pfs) + ".bed"
if need_update(args, newbedfile):
newbed = Bed()
for pf, filename in zip(pfs, args):
bed = Bed(filename)
for b in bed:
b.accn = "-".join((pf, b.accn))
b.score = None
newbed.append(b)
newbed.print_to_file(newbedfile, sorted=True)
neworder = Bed(newbedfile).order
mergedbedfile = mergeBed(newbedfile, nms=True)
bed = Bed(mergedbedfile)
valid = 0
total_counts = Counter()
F1_counts = []
bp_diff = []
novelbedfile = "novel.bed"
fw = open(novelbedfile, "w")
for b in bed:
accns = b.accn.split(',')
pfs_accns = [x.split("-")[0] for x in accns]
pfs_counts = Counter(pfs_accns)
if len(pfs_counts) != 3:
print(b, file=fw)
continue
valid += 1
total_counts += pfs_counts
F1_counts.append(pfs_counts[F1])
# Collect breakpoint positions between P1 and F1
P1_accns = [x for x in accns if x.split("-")[0] == P1]
F1_accns = [x for x in accns if x.split("-")[0] == F1]
if len(P1_accns) != 1:
continue
ri, ref = neworder[P1_accns[0]]
P1_accns = [neworder[x][-1] for x in F1_accns]
bp_diff.extend(x.start - ref.start for x in P1_accns)
bp_diff.extend(x.end - ref.end for x in P1_accns)
print("A total of {0} sites show consistent deletions across samples.".\
format(percentage(valid, len(bed))), file=sys.stderr)
for pf, count in total_counts.items():
print("{0:>9}: {1:.2f} deletions/site".\
format(pf, count * 1. / valid), file=sys.stderr)
F1_counts = Counter(F1_counts)
# Plot the IES variant number diversity
from jcvi.graphics.base import plt, savefig, set_ticklabels_helvetica
fig = plt.figure(1, (iopts.w, iopts.h))
if opts.diversity == "variant":
left, height = zip(*sorted(F1_counts.items()))
for l, h in zip(left, height):
print("{0:>9} variants: {1}".format(l, h), file=sys.stderr)
plt.text(l,
h + 5,
str(h),
color="darkslategray",
size=8,
ha="center",
va="bottom",
rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Identified number of IES per site")
plt.ylabel("Counts")
plt.title("IES variation in progeny pool")
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".counts.pdf")
# Plot the IES breakpoint position diversity
else:
bp_diff = Counter(bp_diff)
bp_diff_abs = Counter()
for k, v in bp_diff.items():
bp_diff_abs[abs(k)] += v
plt.figure(1, (iopts.w, iopts.h))
left, height = zip(*sorted(bp_diff_abs.items()))
for l, h in zip(left, height)[:21]:
plt.text(l,
h + 50,
str(h),
color="darkslategray",
size=8,
ha="center",
va="bottom",
rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Progeny breakpoint relative to SB210")
plt.ylabel("Counts")
plt.xlim(-.5, 20.5)
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".breaks.pdf")
# Serialize the data to a file
fw = open("Breakpoint-offset-histogram.csv", "w")
for k, v in sorted(bp_diff.items()):
print("{0},{1}".format(k, v), file=fw)
fw.close()
total = sum(height)
zeros = bp_diff[0]
within_20 = sum([v for i, v in bp_diff.items() if -20 <= i <= 20])
print("No deviation: {0}".format(percentage(zeros, total)),
file=sys.stderr)
print(" Within 20bp: {0}".format(percentage(within_20, total)),
file=sys.stderr)
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 variation(args):
"""
%prog variation P1.bed P2.bed F1.bed
Associate IES in parents and progeny.
"""
p = OptionParser(variation.__doc__)
p.add_option("--diversity", choices=("breakpoint", "variant"),
default="variant", help="Plot diversity")
opts, args, iopts = p.set_image_options(args, figsize="6x6")
if len(args) != 3:
sys.exit(not p.print_help())
pfs = [op.basename(x).split('-')[0] for x in args]
P1, P2, F1 = pfs
newbedfile = "-".join(pfs) + ".bed"
if need_update(args, newbedfile):
newbed = Bed()
for pf, filename in zip(pfs, args):
bed = Bed(filename)
for b in bed:
b.accn = "-".join((pf, b.accn))
b.score = None
newbed.append(b)
newbed.print_to_file(newbedfile, sorted=True)
neworder = Bed(newbedfile).order
mergedbedfile = mergeBed(newbedfile, nms=True)
bed = Bed(mergedbedfile)
valid = 0
total_counts = Counter()
F1_counts = []
bp_diff = []
novelbedfile = "novel.bed"
fw = open(novelbedfile, "w")
for b in bed:
accns = b.accn.split(',')
pfs_accns = [x.split("-")[0] for x in accns]
pfs_counts = Counter(pfs_accns)
if len(pfs_counts) != 3:
print >> fw, b
continue
valid += 1
total_counts += pfs_counts
F1_counts.append(pfs_counts[F1])
# Collect breakpoint positions between P1 and F1
P1_accns = [x for x in accns if x.split("-")[0] == P1]
F1_accns = [x for x in accns if x.split("-")[0] == F1]
if len(P1_accns) != 1:
continue
ri, ref = neworder[P1_accns[0]]
P1_accns = [neworder[x][-1] for x in F1_accns]
bp_diff.extend(x.start - ref.start for x in P1_accns)
bp_diff.extend(x.end - ref.end for x in P1_accns)
print >> sys.stderr, \
"A total of {0} sites show consistent deletions across samples.".\
format(percentage(valid, len(bed)))
for pf, count in total_counts.items():
print >> sys.stderr, "{0:>9}: {1:.2f} deletions/site".\
format(pf, count * 1. / valid)
F1_counts = Counter(F1_counts)
# Plot the IES variant number diversity
from jcvi.graphics.base import plt, savefig, set_ticklabels_helvetica
fig = plt.figure(1, (iopts.w, iopts.h))
if opts.diversity == "variant":
left, height = zip(*sorted(F1_counts.items()))
for l, h in zip(left, height):
print >> sys.stderr, "{0:>9} variants: {1}".format(l, h)
plt.text(l, h + 5, str(h), color="darkslategray", size=8,
ha="center", va="bottom", rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Identified number of IES per site")
plt.ylabel("Counts")
plt.title("IES variation in progeny pool")
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".counts.pdf")
# Plot the IES breakpoint position diversity
else:
bp_diff = Counter(bp_diff)
bp_diff_abs = Counter()
for k, v in bp_diff.items():
bp_diff_abs[abs(k)] += v
plt.figure(1, (iopts.w, iopts.h))
left, height = zip(*sorted(bp_diff_abs.items()))
for l, h in zip(left, height)[:21]:
plt.text(l, h + 50, str(h), color="darkslategray", size=8,
ha="center", va="bottom", rotation=90)
plt.bar(left, height, align="center")
plt.xlabel("Progeny breakpoint relative to SB210")
plt.ylabel("Counts")
plt.xlim(-.5, 20.5)
ax = plt.gca()
set_ticklabels_helvetica(ax)
savefig(F1 + ".breaks.pdf")
# Serialize the data to a file
fw = open("Breakpoint-offset-histogram.csv", "w")
for k, v in sorted(bp_diff.items()):
print >> fw, "{0},{1}".format(k, v)
fw.close()
total = sum(height)
zeros = bp_diff[0]
within_20 = sum([v for i, v in bp_diff.items() if -20 <= i <= 20])
print >> sys.stderr, "No deviation: {0}".format(percentage(zeros, total))
print >> sys.stderr, " Within 20bp: {0}".format(percentage(within_20, total))