def make_single_joyplot(self,
sorted_clusters,
annotations,
repertoire_size,
plotdir,
plotname,
plot_high_mutation=False,
cluster_indices=None,
title=None,
debug=False):
def gety(minval, maxval, xmax, x):
slope = (maxval - minval) / xmax
return slope * x + minval
def getnmutelist(cluster):
return annotations[':'.join(cluster)]['n_mutations']
colors = ['#006600', '#3399ff', '#ffa500']
# goldenrod '#daa520'
# red '#cc0000',
# dark red '#990012'
# purple '#a821c7'
# grey '#808080'
dpi = 80
xpixels = 450
ypixels = max(400, 10 * len(sorted_clusters))
fig, ax = self.plotting.mpl_init(figsize=(xpixels / dpi,
ypixels / dpi))
min_linewidth = 0.3
max_linewidth = 12
# min_alpha = 0.1
# max_alpha = 1.
# linewidth = 7
alpha = 0.55
ymin, ymax = 9999, 0
iclust_global = 0 # index within this plot
yticks, yticklabels = [], []
high_mutation_clusters = []
biggest_n_mutations = None
if debug:
print ' %s %d x %d %s' % (plotname, xpixels, ypixels,
utils.color('red', 'high mutation')
if plot_high_mutation else '')
print ' size frac yval median mean'
for csize, cluster_group in itertools.groupby(sorted_clusters,
key=lambda c: len(c)):
cluster_group = sorted(list(cluster_group),
key=lambda c: numpy.median(getnmutelist(c)))
n_clusters = len(cluster_group)
repfracstr = self.get_repfracstr(csize, repertoire_size)
for iclust in range(len(
cluster_group)): # index within the clusters of this size
cluster = cluster_group[iclust]
nmutelist = sorted(getnmutelist(cluster))
nmedian = numpy.median(nmutelist)
nmean = numpy.mean(
nmutelist) # maybe should use this instead of the median?
if biggest_n_mutations is None or nmutelist[
-1] > biggest_n_mutations:
biggest_n_mutations = nmutelist[-1]
if nmedian > self.n_max_mutations and not plot_high_mutation:
high_mutation_clusters.append(cluster)
continue
yval = len(sorted_clusters) - iclust_global
if yval < ymin:
ymin = yval
if yval > ymax:
ymax = yval
yticks.append(yval)
# yticklabels.append('%d' % csize)
yticklabels.append(repfracstr)
base_color = colors[iclust_global % len(colors)]
qti_n_muted = {}
if self.args.queries_to_include is not None:
queries_to_include_in_this_cluster = set(cluster) & set(
self.args.queries_to_include)
if len(queries_to_include_in_this_cluster) > 0:
unsorted_nmutelist = getnmutelist(cluster)
qti_n_muted = {
uid: unsorted_nmutelist[cluster.index(uid)]
for uid in queries_to_include_in_this_cluster
} # add a red line for each of 'em (i.e. color that hist bin red)
if plot_high_mutation:
xtext = 1.1
elif float(nmedian) / self.n_max_mutations < 0.5:
xtext = 0.75
else:
xtext = 0.1
ax.text(xtext * self.n_max_mutations,
yval,
' '.join(
sorted(queries_to_include_in_this_cluster,
key=lambda q: qti_n_muted[q])),
color='red',
fontsize=8)
if debug:
print ' %5s %-10s %4.1f %6.1f %6.1f' % (
'%d' % csize if iclust == 0 else '', repfracstr
if iclust == 0 else '', yval, nmedian, nmean)
nbins = nmutelist[-1] - nmutelist[0] + 1
hist = Hist(nbins, nmutelist[0] - 0.5, nmutelist[-1] + 0.5)
for nm in nmutelist:
hist.fill(nm)
assert hist.overflow_contents() == 0. # includes underflows
xmax = max(
hist.bin_contents) # NOTE no relation to <ymax> above
for ibin in range(1, hist.n_bins + 1):
linewidth = gety(min_linewidth, max_linewidth, xmax,
hist.bin_contents[ibin])
color = base_color
# alpha = gety(min_alpha, max_alpha, xmax, hist.bin_contents[ibin])
for nmuted in qti_n_muted.values():
if hist.find_bin(nmuted) == ibin:
color = 'red'
if hist.bin_contents[ibin] == 0.:
color = 'grey'
linewidth = min_linewidth
alpha = 0.4
ax.plot([hist.low_edges[ibin], hist.low_edges[ibin + 1]],
[yval, yval],
color=color,
linewidth=linewidth,
alpha=alpha,
solid_capstyle='butt')
if cluster_indices is not None:
xtext = nmutelist[
-1] if plot_high_mutation else self.n_max_mutations # NOTE reuse of <xtext> (arg)
xwidth = ax.get_xlim()[1] - ax.get_xlim(
)[0] if plot_high_mutation else self.n_max_mutations
ax.text(0.05 * xwidth + xtext,
yval,
str(cluster_indices[':'.join(cluster)]),
color=base_color,
fontsize=6,
alpha=alpha,
fontdict={'weight': 'bold'})
ax.text(0.12 * xwidth + xtext,
yval,
str(csize),
color=base_color,
fontsize=6,
alpha=alpha,
fontdict={'weight': 'bold'})
iclust_global += 1
xbounds = [-0.2, self.n_max_mutations] if not plot_high_mutation else [
self.n_max_mutations, biggest_n_mutations
]
ybounds = [0.95 * ymin, 1.05 * ymax]
n_ticks = 5
if len(yticks) > n_ticks:
yticks = [
yticks[i] for i in range(0, len(yticks),
int(len(yticks) / float(n_ticks - 1)))
]
yticklabels = [
yticklabels[i]
for i in range(0, len(yticklabels),
int(len(yticklabels) / float(n_ticks - 1)))
]
self.plotting.mpl_finish(
ax,
plotdir,
plotname,
xlabel='N mutations',
ylabel='fraction of repertoire',
title=title, # ylabel = 'clonal family size'
xbounds=xbounds,
ybounds=ybounds,
yticks=yticks,
yticklabels=yticklabels,
adjust={'left': 0.25})
return high_mutation_clusters
def make_single_size_vs_shm_plot(self,
sorted_clusters,
annotations,
repertoire_size,
base_plotdir,
plotname,
n_max_mutations=100,
plot_high_mutation=False,
title=None,
debug=False):
import plotting
def gety(minval, maxval, xmax, x):
slope = (maxval - minval) / xmax
return slope * x + minval
def getnmutelist(cluster):
return annotations[':'.join(cluster)]['n_mutations']
colors = ['#006600', '#3399ff', '#ffa500']
# goldenrod '#daa520'
# red '#cc0000',
# dark red '#990012'
# purple '#a821c7'
# grey '#808080'
dpi = 80
xpixels = 450
ypixels = max(400, 10 * len(sorted_clusters))
fig, ax = plotting.mpl_init(figsize=(xpixels / dpi, ypixels / dpi))
min_linewidth = 0.3
max_linewidth = 12
# min_alpha = 0.1
# max_alpha = 1.
# linewidth = 7
alpha = 0.55
ymin, ymax = 9999, 0
iclust_global = 0
yticks, yticklabels = [], []
high_mutation_clusters = []
biggest_n_mutations = None
if debug:
print ' %s %d x %d' % (
plotname, xpixels, ypixels
) #, utils.color('red', 'high mutation') if plot_high_mutation else '')
print ' size frac yval median mean'
for csize, cluster_group in itertools.groupby(sorted_clusters,
key=lambda c: len(c)):
cluster_group = sorted(list(cluster_group),
key=lambda c: numpy.median(getnmutelist(c)))
n_clusters = len(cluster_group)
repfracstr = self.get_repfracstr(csize, repertoire_size)
for iclust in range(len(cluster_group)):
cluster = cluster_group[iclust]
nmutelist = sorted(getnmutelist(cluster))
nmedian = numpy.median(nmutelist)
nmean = numpy.mean(
nmutelist) # maybe should use this instead of the median?
if biggest_n_mutations is None or nmutelist[
-1] > biggest_n_mutations:
biggest_n_mutations = nmutelist[-1]
yval = len(sorted_clusters) - iclust_global
if yval < ymin:
ymin = yval
if yval > ymax:
ymax = yval
yticks.append(yval)
yticklabels.append('%d' % csize)
# yticklabels.append(repfracstr)
base_color = colors[iclust_global % len(colors)]
if self.args.queries_to_include is not None:
queries_to_include_in_this_cluster = set(cluster) & set(
self.args.queries_to_include)
if len(queries_to_include_in_this_cluster) > 0:
base_color = 'red'
if plot_high_mutation:
xtext = 1.1
elif float(nmedian) / n_max_mutations < 0.5:
xtext = 0.75
else:
xtext = 0.1
ax.text(xtext * n_max_mutations,
yval,
' '.join(queries_to_include_in_this_cluster),
color='red',
fontsize=8)
if debug:
print ' %5s %-10s %4.1f %6.1f %6.1f' % (
'%d' % csize if iclust == 0 else '', repfracstr
if iclust == 0 else '', yval, nmedian, nmean),
if nmedian > n_max_mutations and not plot_high_mutation:
if debug:
print '%s' % utils.color('red', 'high mutation')
high_mutation_clusters.append(cluster)
continue
if debug:
print ''
nbins = nmutelist[-1] - nmutelist[0] + 1
hist = Hist(nbins, nmutelist[0] - 0.5, nmutelist[-1] + 0.5)
for nm in nmutelist:
hist.fill(nm)
assert hist.overflow_contents() == 0. # includes underflows
xmax = max(hist.bin_contents) # float(csize)
for ibin in range(1, hist.n_bins + 1):
linewidth = gety(min_linewidth, max_linewidth, xmax,
hist.bin_contents[ibin])
color = base_color
# alpha = gety(min_alpha, max_alpha, xmax, hist.bin_contents[ibin])
if hist.bin_contents[ibin] == 0.:
color = 'grey'
linewidth = min_linewidth
alpha = 0.4
ax.plot([hist.low_edges[ibin], hist.low_edges[ibin + 1]],
[yval, yval],
color=color,
linewidth=linewidth,
alpha=alpha,
solid_capstyle='butt')
iclust_global += 1
xbounds = [-0.2, n_max_mutations] if not plot_high_mutation else [
n_max_mutations, biggest_n_mutations
]
ybounds = [0.95 * ymin, 1.05 * ymax]
n_ticks = 5
if len(yticks) > n_ticks:
yticks = [
yticks[i] for i in range(0, len(yticks),
int(len(yticks) / float(n_ticks - 1)))
]
yticklabels = [
yticklabels[i]
for i in range(0, len(yticklabels),
int(len(yticklabels) / float(n_ticks - 1)))
]
plotting.mpl_finish(ax,
base_plotdir + '/overall',
plotname,
xlabel='N mutations',
ylabel='clonal family size',
title=title,
xbounds=xbounds,
ybounds=ybounds,
yticks=yticks,
yticklabels=yticklabels,
adjust={'left': 0.18})
return high_mutation_clusters