def fitnesscost_distribution(regions, minor_af, synnonsyn, synnonsyn_uc, mut_rates, fname=None, ref=None):
'''
produce figure of distribution of selection coefficients separately for
synonymous, nonsynonymous sites, and synonymous sites in reading frame overlaps.
FIGURE 4 of the manuscript
'''
from util import add_panel_label
if ref is not None:
if not hasattr(ref, 'fitness_cost'):
ref.fitness_cost = np.zeros_like(ref.entropy)
fig, axs = plt.subplots(1, 3, sharey=True, figsize=(10,6))
if type(regions)==str: # if only one region is passed as string
regions = [regions]
for ni,ax,label_str in ((0, axs[0], 'synonymous'),
(1, axs[1], 'syn-overlaps'),
(2, axs[2], 'nonsyn')):
slist = []
for region in regions:
if label_str=='synonymous':
ind = synnonsyn[region]
elif label_str=='syn-overlaps':
ind = synnonsyn_uc[region]&(~synnonsyn[region])
else:
ind = ~synnonsyn_uc[region]
ind = ind&(~np.isnan(minor_af[region]))
slist.extend(mut_rates[region][ind]/(minor_af[region][ind]+af_cutoff))
s = np.array(slist)
s[s>=0.1] = 0.1
s[s<=0.001] = 0.001
if ref is not None:
bg = ref.annotation[region].location.start
ed = ref.annotation[region].location.end
ref.fitness_cost[bg:ed][ind] = s
if len(s):
ax.hist(s, color=cols[ni],
weights=np.ones(len(s), dtype=float)/len(s), bins=np.logspace(-3,-1,11), label=label_str+', n='+str(len(s)))
ax.set_xscale('log')
ax.tick_params(labelsize=fs*0.8)
ax.text(0.1, 0.8, 'position: '+str(ni))
if ni==0:
ax.set_ylabel('fraction of sites', fontsize=fs)
ax.set_yscale('linear')
ax.set_xlabel('fitness cost', fontsize=fs)
ax.set_xticks([0.001, 0.01, 0.1])
ax.set_xticklabels([r'$<10^{-3}$', r'$10^{-2}$', r'$>10^{-1}$'])
ax.legend(loc=2, fontsize=fs*0.8)
add_panel_label(ax, ['A', 'B', 'C'][ni],
x_offset=-0.2 - 0.1 * (ni == 0))
plt.tight_layout()
if fname is not None:
for ext in ['png', 'svg', 'pdf']:
plt.savefig(fname+'.'+ext)
def plot_figure_1(data, mu, dmulog10, muA, dmuAlog10,suffix=''):
'''Plot figure 1 of the paper'''
print('Plot Figure 1')
fig = plt.figure(figsize=(12, 11))
ax1 = plt.subplot2grid((2,2), (0,0))
ax2 = plt.subplot2grid((2,2), (0,1))
ax3 = plt.subplot2grid((2,2), (1, 0), colspan=2)
# plot linear regression
plot_mutation_increase(data, mu=mu, axs=[ax1, ax2])
mu_all = pd.DataFrame({'mu': mu,
'muA': muA,
'dmulog10': dmulog10,
'dmuAlog10': dmuAlog10,
})
# plot matrix of arrows
plot_mutation_rate_graph(mu_all,
ax=ax3)
plt.tight_layout()
# Add labels
from util import add_panel_label
add_panel_label(ax1, 'A', x_offset=-0.2)
add_panel_label(ax2, 'B', x_offset=-0.2)
add_panel_label(ax3, 'C', x_offset=-0.08)
plt.ion()
plt.show()
for ext in ['svg', 'png', 'pdf']:
fig.savefig('../figures/figure_1'+suffix+'.'+ext)
def plot_figure_1(data, mu, dmulog10, muA, dmuAlog10, suffix=''):
'''Plot figure 1 of the paper'''
print('Plot Figure 1')
fig = plt.figure(figsize=(12, 11))
ax1 = plt.subplot2grid((2, 2), (0, 0))
ax2 = plt.subplot2grid((2, 2), (0, 1))
ax3 = plt.subplot2grid((2, 2), (1, 0), colspan=2)
# plot linear regression
plot_mutation_increase(data, mu=mu, axs=[ax1, ax2])
mu_all = pd.DataFrame({
'mu': mu,
'muA': muA,
'dmulog10': dmulog10,
'dmuAlog10': dmuAlog10,
})
# plot matrix of arrows
plot_mutation_rate_graph(mu_all, ax=ax3)
plt.tight_layout()
# Add labels
from util import add_panel_label
add_panel_label(ax1, 'A', x_offset=-0.2)
add_panel_label(ax2, 'B', x_offset=-0.2)
add_panel_label(ax3, 'C', x_offset=-0.08)
plt.ion()
plt.show()
for ext in ['svg', 'png', 'pdf']:
fig.savefig('../figures/figure_1' + suffix + '.' + ext)
def plot_to_away(data, fig_filename=None, figtypes=['.png', '.svg', '.pdf'],
sequence_type='nuc'):
'''Makes a two panel figure summarizing the results on reversion
Args:
data (dict): data to be plotted (see below)
'''
import seaborn as sns
from matplotlib import pyplot as plt
plt.ion()
sns.set_style('darkgrid')
figpath = 'figures/'
fs=fig_fontsize
fig_size = (1.0*fig_width, 0.6*fig_width)
fig, axs = plt.subplots(1, 2, figsize=fig_size)
nbs=100 # number of bootstrap replicates
# set the colors for the plots, both panels use the same color scheme
cols = HIVEVO_colormap()
colors = [cols(x) for x in [0.0, 0.33, 0.66, 0.99]]
####################################################################################
# make panel divergence vs entropy
####################################################################################
ax=axs[1]
if sequence_type == 'nuc':
Sbins = np.array([0, 0.02, 0.08, 0.25, 2])
else:
Sbins = np.array([0, 0.1, 0.3, 3])
Sbinc = 0.5*(Sbins[1:]+Sbins[:-1])
def get_Sbin_mean(df): # regroup and calculate mean in entropy bins
return df.groupby(by=['S_bin'], as_index=False).mean()
color_count = 0
for lblstr, subtype, ls in [('subtype', 'patient', '--'), ('group M', 'any', '-')]:
mv = data[subtype]['minor_variants']
# subset to a specific time interval
mv = mv.loc[(mv.loc[:,'time'] > 1500)&(mv.loc[:,'time'] < 2500),:]
print "average time:", mv.loc[:,'time'].mean() / 365.25
mv.loc[:,['af_away_minor', 'af_away_derived', 'af_to_minor', 'af_to_derived']] = \
mv.loc[:,['af_away_minor', 'af_away_derived', 'af_to_minor', 'af_to_derived']].astype(float)
mean_to_away =get_Sbin_mean(mv)
bs = boot_strap_patients(mv,
eval_func=get_Sbin_mean,
n_bootstrap=nbs,
columns=['af_away_minor',
'af_away_derived',
'af_to_minor',
'af_to_derived',
'S_bin'])
print mean_to_away
col = 'af_away_derived'
ax.errorbar(Sbinc,
mean_to_away.loc[:,col],
replicate_func(bs, col, np.std, bin_index='S_bin'),
ls=ls,
lw=3,
label='founder = '+lblstr,
c=colors[color_count])
color_count+=1
col = 'af_to_derived'
ax.errorbar(Sbinc, mean_to_away.loc[:,col],
replicate_func(bs, col, np.std, bin_index='S_bin'), ls=ls,
lw = 3, label = u'founder \u2260 '+lblstr, c=colors[color_count])
color_count+=1
ax.set_yscale('log')
ax.set_xscale('log')
ax.set_ylabel('Divergence from founder', fontsize = fig_fontsize)
ax.set_xlabel('Variability [bits]', fontsize = fig_fontsize)
add_panel_label(ax, 'B', x_offset=-0.32)
for item in ax.get_yticklabels()+ax.get_xticklabels():
item.set_fontsize(fs-2)
ax.set_xlim([0.005, 2])
####################################################################################
# print reversion statistics
####################################################################################
def get_time_bin_means(df): # get mean of divergence, reversion divergence and time for each time bin
return df.loc[:,['divergence', 'reversion','time_bin']].groupby(by=['time_bin'], as_index=False).mean()
for subtype in ['patient', 'any']:
to_away = data[subtype]['to_away']
time_bins = np.array([0, 500, 1000, 1500, 2500, 3500])
binc = 0.5*(time_bins[1:]+time_bins[:-1])
add_binned_column(to_away, time_bins, 'time')
to_away.loc[:,['reversion', 'divergence']] = \
to_away.loc[:,['reversion', 'divergence']].astype(float)
rev_div = get_time_bin_means(to_away)
bs = boot_strap_patients(to_away, get_time_bin_means, n_bootstrap = nbs,
columns = ['reversion','divergence','time_bin'])
reversion_std = replicate_func(bs, 'reversion', np.std, bin_index='time_bin')
total_div_std = replicate_func(bs, 'divergence', np.std, bin_index='time_bin')
fraction = rev_div.loc[:,'reversion']/rev_div.loc[:,'divergence']
print "Comparison:", subtype
print "Reversions:\n", rev_div.loc[:,'reversion']
print "Divergence:\n", rev_div.loc[:,'divergence']
# print the fraction of divergence that is due to reversion at different times
# gives errors as standard deviations over patient bootstraps
print "Fraction:"
for frac, total, num_std, denom_std in zip(fraction, rev_div.loc[:,'divergence'],reversion_std, total_div_std):
print frac, '+/-', np.sqrt(num_std**2/total**2 + denom_std**2*frac**2/total**2)
print "Consensus!=Founder:",np.mean(data[subtype]['consensus_distance'].values())
####################################################################################
# make panel divergence vs time
####################################################################################
to_histogram=data['to_histogram']
away_histogram=data['away_histogram']
time_bins=data['time_bins']
af_bins=data['af_bins']
af_binc=0.5*(af_bins[1:]+af_bins[:-1])
def bin_time(freq_arrays, time_bins):
'''sum up allele frequency histgrams corresponding to the same time bin'''
binned_hists = [np.zeros_like(af_binc) for ti in time_bins[1:]]
for hists in freq_arrays.values():
for t, y in hists.iteritems():
ti = np.searchsorted(time_bins, t)
if ti>0 and ti<len(time_bins):
binned_hists[ti-1]+=y
return binned_hists
def get_div(afhist, fixed=False):
'''return the fraction of fixed alleles or the mean divergence'''
if fixed:
return afhist[0]/afhist.sum()
else:
return np.array(afhist[:-1]*(1-af_binc[:-1])).sum()/afhist.sum()
from random import choice
ax = axs[0]
time_binc = 0.5*(time_bins[1:]+time_bins[:-1])
sym='o'
fs = fig_fontsize
color_count=0
for subtype, ls in [('patient', '--'), ('any','-')]:
for toaway, H in [(u'founder = '+('group M' if subtype=='any' else 'subtype'), away_histogram[subtype]),
(u'founder \u2260 '+('group M' if subtype=='any' else 'subtype'), to_histogram[subtype])]:
mean_hists = bin_time(H,time_bins)
div = [get_div(mean_hists[ti]) for ti in range(len(time_bins)-1)]
# make replicates and calculate bootstrap confidence intervals
replicates = []
all_keys = H.keys()
for ri in xrange(nbs):
bootstrap_keys = [all_keys[ii] for ii in np.random.randint(len(all_keys), size=len(all_keys))]
tmp = bin_time({key:H[key] for key in bootstrap_keys}, time_bins)
replicates.append([get_div(tmp[ti]) for ti in range(len(time_bins)-1)])
std_dev = np.array(replicates).std(axis=0)
ax.errorbar(time_binc/365.25, div, std_dev, ls = ls, lw=3, c=colors[color_count])
ax.plot(time_binc/365.25, div, label = toaway, ls = ls, lw=3, c=colors[color_count]) # plot again with label to avoid error bars in legend
color_count+=1
if sequence_type == 'nuc':
ax.set_ylim([0,0.16])
ax.set_yticks([0, 0.04, 0.08, 0.12])
else:
ax.set_ylim([0,0.32])
ax.set_yticks([0, 0.08, 0.16, 0.24])
ax.set_xlabel('ETI [years]', fontsize=fs)
ax.set_ylabel('Divergence from founder', fontsize=fs)
ax.legend(loc=2, fontsize=fs-2, labelspacing=0)
add_panel_label(ax, 'A', x_offset=-0.32)
ax.tick_params(axis='both', labelsize=fs-2)
plt.tight_layout(pad=0.3, h_pad=0.5) #rect=(0.0, 0.02, 0.98, 0.98), pad=0.05, h_pad=0.5, w_pad=0.4)
for ext in figtypes:
fig.savefig(fig_filename+ext)
def plot_divdiv(data, fig_filename=None, figtypes=['.png', '.svg', '.pdf']):
'''
plot divergence and diversity of synonymous and nonsynonymous mutations
includes:
- a panel that compares syn diversity/nonsyn divergence
'''
n_bootstrap = 50
####### plotting ###########
import seaborn as sns
from matplotlib import pyplot as plt
plt.ion()
sns.set_style('darkgrid')
figpath = 'figures/'
fs = fig_fontsize
fig_size = (fig_width, 1.0 * fig_width)
cols = HIVEVO_colormap()
fig, axs = plt.subplots(2, 2, figsize=fig_size)
divdiv = data['divdiv']
# in rough the order in which they most dominantly appear in the plot
regions = ['envelope', 'accessory', 'structural', 'enzymes']
time_bins = np.array([0, 200, 500, 1000, 1500, 2000, 4000])
time_binc = 0.5 * (time_bins[:-1] + time_bins[1:])
add_binned_column(divdiv, time_bins, 'time')
# map the regions to rough genomic order to match the genome color map in panel C
colors = {
reg: c
for reg, c in zip(regions, [cols(x) for x in [0.66, 0.99, 0.01, 0.33]])
}
def get_time_bin_mean(df):
return df.loc[:, ['time_bin', 'diversity', 'divergence']].groupby(
by=['time_bin'], as_index=False).mean()
def label_func(
mutclass, region, divordiv
): # assign labels to Panels A and B separately to make a combinatorial legend (regions vs syn/nonsyn)
if divordiv == 'divergence' and mutclass == 'nonsyn':
return region
elif divordiv == 'diversity' and region == 'accessory':
return mutclass
else:
return None
########## panel A and B #####################
csv_out = open(fig_filename + '_AB.tsv', 'w')
for ax, dtype in izip(axs[0, :], ['divergence', 'diversity']):
add_panel_label(ax,
'A' if dtype == 'divergence' else 'B',
x_offset=-0.3)
for mutclass in ['nonsyn', 'syn']:
for region in regions:
ind = (divdiv.loc[:, 'region']
== region) & (divdiv.loc[:, 'mutclass'] == mutclass)
tmp = divdiv.loc[
ind, ['time_bin', 'diversity', 'divergence', 'pcode']]
avg_divdiv = get_time_bin_mean(tmp)
bs = boot_strap_patients(tmp,
eval_func=get_time_bin_mean,
n_bootstrap=n_bootstrap)
# plot the same line with and without error bars, labels for legend without
ax.plot(time_binc / 365.25,
avg_divdiv.loc[:, dtype],
ls='-' if mutclass == 'nonsyn' else '--',
c=colors[region],
lw=3,
label=label_func(mutclass, region, dtype))
ax.errorbar(time_binc / 365.25,
avg_divdiv.loc[:, dtype],
replicate_func(bs,
dtype,
np.std,
bin_index='time_bin'),
ls='-' if mutclass == 'nonsyn' else '--',
c=colors[region],
lw=3)
csv_out.write('\t'.join(
map(str, [dtype, mutclass, region] +
list(avg_divdiv.loc[:, dtype]))) + '\n')
ax.legend(loc=2, fontsize=fs - 1, numpoints=2, labelspacing=0)
ax.set_xticks([0, 2, 4, 6, 8])
if dtype == 'divergence':
ax.set_yticks([0, .02, .04])
ax.set_ylim([0, .048])
else:
ax.set_yticks([0, .01, .02])
ax.set_ylim([0, .028])
ax.set_xlim([0, 8.5])
ax.set_ylabel(dtype)
ax.tick_params(labelsize=fs - 2)
ax.set_xlabel('Years since EDI', fontsize=fs)
csv_out.close()
########## panel C: anti correlation of syn diversity and nonsyn divergence #############
csv_out = open(fig_filename + '_C.tsv', 'w')
(avg_nonsyn_divg, avg_nonsyn_divs, avg_syn_divs) = data['divdiv_corr']
ax = axs[1, 0]
add_panel_label(ax, 'C', x_offset=-0.3)
x_data, y_data = avg_nonsyn_divg[::500], avg_syn_divs[::500]
ax.scatter(x_data,
y_data,
c=[cols(p) for p in np.linspace(0, 1, len(x_data))],
s=50)
csv_out.write('\t'.join(map(str, ["nonsyn_divergence"] + list(x_data))) +
'\n')
csv_out.write('\t'.join(map(str, ["syn_diversity"] + list(y_data))) + '\n')
csv_out.close()
ax.set_xlabel('nonsyn divergence', fontsize=fig_fontsize)
ax.set_ylabel('syn diversity', fontsize=fig_fontsize)
ax.set_ylim([0, 0.028])
ax.set_xlim([0, 0.012])
ax.set_xticks([0, 0.005, 0.01])
ax.set_yticks([0, 0.01, 0.02])
ax.tick_params(labelsize=fig_fontsize - 2)
########## sfs in panel D ##############
csv_out = open(fig_filename + '_D.tsv', 'w')
sfs = data['sfs']
ax = axs[1, 1]
add_panel_label(ax, 'D', x_offset=-0.3)
colors = sns.color_palette(n_colors=2)
binc = binc = 0.5 * (sfs['bins'][1:] + sfs['bins'][:-1])
ax.bar(binc - 0.045,
sfs['syn'] / np.sum(sfs['syn']),
width=0.04,
label='syn',
color=colors[0])
ax.bar(binc,
sfs['nonsyn'] / np.sum(sfs['nonsyn']),
width=0.04,
label='nonsyn',
color=colors[1])
csv_out.write('\t'.join(map(str, ["bin_centers"] + list(binc))) + '\n')
csv_out.write('\t'.join(
map(str, ["sfs_nonsyn"] +
list(sfs['nonsyn'] / np.sum(sfs['nonsyn'])))) + '\n')
csv_out.write('\t'.join(
map(str, ["sfs_syn"] + list(sfs['syn'] / np.sum(sfs['syn'])))) + '\n')
csv_out.close()
ax.set_ylim([0.005, 2.0])
ax.set_yscale('log')
ax.set_xlabel('Frequency', fontsize=fs)
ax.set_ylabel('Fractions of SNPs', fontsize=fs)
ax.legend(loc=1, fontsize=fs - 2)
ax.tick_params(labelsize=fig_fontsize - 2)
# finalize and save the figure
plt.tight_layout(rect=(0.0, 0.02, 0.98, 0.98),
pad=0.05,
h_pad=0.5,
w_pad=0.4)
if fig_filename is not None:
for ext in figtypes:
fig.savefig(fig_filename + ext)
else:
plt.ion()
plt.show()
def plot_allele_frequency_overlap(data, title='', VERBOSE=0, use_logit=False,
fig_filename=None,
separate_axes=False):
'''Plot allele frequency in the overlap regions'''
if VERBOSE >= 2:
print 'Plot allele frequency in overlaps'
import matplotlib.pyplot as plt
import seaborn as sns
from util import add_panel_label
sns.set_style('darkgrid')
colors = sns.color_palette('Set1', 5)
fs = fig_fontsize
xmin = 1e-3
if not separate_axes:
fig, ax = plt.subplots(figsize=(fig_width, 0.8 * fig_width))
axs = [ax]
else:
fig = plt.figure(figsize=(1.5 * fig_width, 1.5 * 0.8 * fig_width))
fun = fig.add_axes
lpad = 0.07
hpad = 0.05
vpad = 0.05
width = (1.0 - lpad - 3 * hpad) / 3
height = (1.0 - 4 * vpad) / 2
axs = [fun([lpad, 0.5 + vpad, width, height]),
fun([lpad + hpad + width, 0.5 + vpad, width, height]),
fun([lpad + 2 * hpad + 2 * width, 0.5 + vpad, width, height]),
fun([0.5 * (1 - hpad) - width, vpad, width, height]),
fun([0.5 * (1 + hpad), vpad, width, height]),
]
# NOTE (Fabio): my logit patch has made it to matplotlib master but now there
# is a weird bug here that crashes the figure. If I manually call
# plt.yscale('logit')
# it works, so I don't quite understand. Anyway, this is only aesthetics and
# does not affect any data.
if use_logit:
for iax, ax in enumerate(axs):
ax.set_xlim(xmin, 1 - xmin)
ax.set_ylim(xmin, 1 - xmin)
ax.set_xscale('logit')
ax.set_yscale('logit')
ax.xaxis.set_tick_params(labelsize=fs)
ax.yaxis.set_tick_params(labelsize=fs)
if iax not in (0, 3):
ax.set_yticklabels([])
for ida, datum in enumerate(data):
if separate_axes:
ax = axs[ida]
afjoint = datum['af']
color = colors[datum['io']]
x = afjoint[0].ravel()
y = afjoint[1].ravel()
ind = ~(x.mask | y.mask)
x = x[ind]
y = y[ind]
ind = (x >= xmin) & (x <= 1 - xmin) & (y >= xmin) & (y <= 1 - xmin)
x = x[ind]
y = y[ind]
ax.scatter(x, y,
s=50,
color=color,
alpha=0.7,
edgecolor='none')
## Plot stddev in Poisson sampling
#n = datum['n']
#x = np.linspace(np.log10(xmin), 0, 1000)
#x = 1.0 / (1 + 10**(-x))
#y = x - np.sqrt(x / n)
#ax.plot(np.concatenate([x, 1 - y[::-1]]), np.concatenate([y, 1 - x[::-1]]),
# lw=3, c=color, alpha=0.5)
#ax.plot(np.concatenate([y, 1 - x[::-1]]), np.concatenate([x, 1 - y[::-1]]),
# lw=3, c=color, alpha=0.5,
# label=datum['overlap'])
if separate_axes or (ida == len(data) - 1):
ax.plot([xmin, 1 - xmin], [xmin, 1 - xmin], lw=2, color='k', alpha=0.5)
#ax.set_xlabel('SNP frequency leading fragment', fontsize=fs)
#ax.set_ylabel('SNP frequency trailing fragment', fontsize=fs)
if not separate_axes:
add_panel_label(ax, 'C', x_offset=-0.22)
if title:
ax.set_title(title)
if not separate_axes:
plt.tight_layout()
if fig_filename is not None:
for ext in ['.pdf','.svg', '.png']:
fig.savefig(fig_filename+ext)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_allele_frequency_overlap(data,
title='',
VERBOSE=0,
use_logit=False,
fig_filename=None,
separate_axes=False):
'''Plot allele frequency in the overlap regions'''
if VERBOSE >= 2:
print 'Plot allele frequency in overlaps'
import matplotlib.pyplot as plt
import seaborn as sns
from util import add_panel_label
sns.set_style('darkgrid')
colors = sns.color_palette('Set1', 5)
fs = fig_fontsize
xmin = 1e-3
if not separate_axes:
fig, ax = plt.subplots(figsize=(fig_width, 0.8 * fig_width))
axs = [ax]
else:
fig = plt.figure(figsize=(1.5 * fig_width, 1.5 * 0.8 * fig_width))
fun = fig.add_axes
lpad = 0.07
hpad = 0.05
vpad = 0.05
width = (1.0 - lpad - 3 * hpad) / 3
height = (1.0 - 4 * vpad) / 2
axs = [
fun([lpad, 0.5 + vpad, width, height]),
fun([lpad + hpad + width, 0.5 + vpad, width, height]),
fun([lpad + 2 * hpad + 2 * width, 0.5 + vpad, width, height]),
fun([0.5 * (1 - hpad) - width, vpad, width, height]),
fun([0.5 * (1 + hpad), vpad, width, height]),
]
# NOTE (Fabio): my logit patch has made it to matplotlib master but now there
# is a weird bug here that crashes the figure. If I manually call
# plt.yscale('logit')
# it works, so I don't quite understand. Anyway, this is only aesthetics and
# does not affect any data.
if use_logit:
for iax, ax in enumerate(axs):
ax.set_xlim(xmin, 1 - xmin)
ax.set_ylim(xmin, 1 - xmin)
ax.set_xscale('logit')
ax.set_yscale('logit')
ax.xaxis.set_tick_params(labelsize=fs)
ax.yaxis.set_tick_params(labelsize=fs)
if iax not in (0, 3):
ax.set_yticklabels([])
for ida, datum in enumerate(data):
if separate_axes:
ax = axs[ida]
afjoint = datum['af']
color = colors[datum['io']]
x = afjoint[0].ravel()
y = afjoint[1].ravel()
ind = ~(x.mask | y.mask)
x = x[ind]
y = y[ind]
ind = (x >= xmin) & (x <= 1 - xmin) & (y >= xmin) & (y <= 1 - xmin)
x = x[ind]
y = y[ind]
ax.scatter(x, y, s=50, color=color, alpha=0.7, edgecolor='none')
## Plot stddev in Poisson sampling
#n = datum['n']
#x = np.linspace(np.log10(xmin), 0, 1000)
#x = 1.0 / (1 + 10**(-x))
#y = x - np.sqrt(x / n)
#ax.plot(np.concatenate([x, 1 - y[::-1]]), np.concatenate([y, 1 - x[::-1]]),
# lw=3, c=color, alpha=0.5)
#ax.plot(np.concatenate([y, 1 - x[::-1]]), np.concatenate([x, 1 - y[::-1]]),
# lw=3, c=color, alpha=0.5,
# label=datum['overlap'])
if separate_axes or (ida == len(data) - 1):
ax.plot([xmin, 1 - xmin], [xmin, 1 - xmin],
lw=2,
color='k',
alpha=0.5)
#ax.set_xlabel('SNP frequency leading fragment', fontsize=fs)
#ax.set_ylabel('SNP frequency trailing fragment', fontsize=fs)
if not separate_axes:
add_panel_label(ax, 'C', x_offset=-0.22)
if title:
ax.set_title(title)
if not separate_axes:
plt.tight_layout()
if fig_filename is not None:
for ext in ['.pdf', '.svg', '.png']:
fig.savefig(fig_filename + ext)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_subtype_correlation(data, fig_filename=None, figtypes=['.png', '.svg', '.pdf']):
'''Plot results'''
import seaborn as sns
from matplotlib import pyplot as plt
plt.ion()
sns.set_style('darkgrid')
figpath = 'figures/'
fs=fig_fontsize
fig_size = (fig_width, 0.5*fig_width)
fig, axs = plt.subplots(1, 2, figsize=fig_size)
ax=axs[0]
add_panel_label(ax, 'A', x_offset=-0.15)
patients = sorted(data['correlations']['pcode'].unique(), key=lambda x:int(x[1:]))
colors = patient_colors
# calculate mean and variance across regions for each time point and patient
mean_rho = data['correlations'].groupby(by=['time', 'pcode'], as_index=False).mean().groupby('pcode')
var_rho = data['correlations'].groupby(by=['time', 'pcode'], as_index=False).var().groupby('pcode')
# loop over patients and plot the mean/std of the previously grouped data
for pat in patients:
ax.errorbar(np.array(mean_rho.get_group(pat)['time']/365.25),
np.array(mean_rho.get_group(pat)['rho']),
yerr=np.array(np.sqrt(var_rho.get_group(pat)['rho'])),
color=colors[pat], ls="none",
markersize=8, marker='o', label=pat)
ax.legend(loc=2, fontsize=fs-3, ncol=2, labelspacing=0.1, columnspacing=0.1)
ax.set_yticks([0,0.25,0.5])
ax.set_xticks([0,2,4,6,8])
ax.set_xlim([-2,8.5])
ax.set_ylim([-0.1, 0.8])
ax.set_xlabel('ETI [years]', fontsize=fs)
ax.set_title(r"Spearman's $\rho$", fontsize=fs)
for item in ax.get_xticklabels()+ax.get_yticklabels():
item.set_fontsize(fs)
# add a second plot that shows the fraction of variable sites by entropy bin
ax=axs[1]
add_panel_label(ax, 'B', x_offset=-0.15)
div = data['diverse_fraction']
colors = sns.color_palette(n_colors=4)
# add a time bin column
time_bins = np.arange(0,4000,500)
binc = 0.5*(time_bins[1:] + time_bins[:-1])
div.loc[:,'time_bin'] = np.minimum(len(time_bins)-2, np.maximum(0,np.searchsorted(time_bins, div["time"])-1))
for i in range(4):
ent = 'S'+str(i+1)
div.loc[:,ent] = div.loc[:,ent].astype(float)
# calculate mean and variance over regions and patients and samples within a time bin
mean_div = div.loc[:,[ent, 'time_bin']].groupby(by=['time_bin'], as_index=False).mean()
var_div = div.loc[:,[ent, 'time_bin']].groupby(by=['time_bin'], as_index=False).var()
ax.errorbar(np.array(binc/365.25),
np.array(mean_div.loc[:,ent]),
yerr=np.array(np.sqrt(var_div.loc[:,ent])),
label='Q'+str(i+1),
c=colors[i])
ax.set_ylim([0,0.35])
ax.set_yticks([0, 0.1, 0.2, 0.3])
ax.set_xticks([0,2,4,6,8])
ax.set_title('Fraction of SNPs > 0.01')
ax.set_xlabel('ETI [years]', fontsize=fs)
for item in ax.get_xticklabels()+ax.get_yticklabels():
item.set_fontsize(fs)
ax.legend(loc=2, ncol=2,fontsize=fs-3, title='Conservation',
labelspacing=0.1, columnspacing=0.5)
# plot output
plt.tight_layout(rect=(0.0, 0.02, 0.98, 0.98), pad=0.05, h_pad=0.5, w_pad=0.4)
if fig_filename is not None:
for ext in figtypes:
fig.savefig(fig_filename+ext)
else:
plt.ion()
plt.show()
aa_mutation_rates, total_nonsyn_mutation_rates = calc_amino_acid_mutation_rates()
selcoeff = {}
for region in regions:
s = fitness_costs_per_site(region, data, total_nonsyn_mutation_rates)
s[s>1] = 1
selcoeff[region] = s
aa_ref = 'NL4-3'
global_ref = HIVreference(refname=aa_ref, subtype=args.subtype)
### FIGURE 5
fig,axs = plt.subplots(1,2, figsize=(10,5))
#fitness_costs_in_optimal_epis(['gag', 'nef'], selcoeff, ax=axs[0])
#add_panel_label(axs[0], 'A', x_offset=-0.15)
plot_fraction_associated(regions, selcoeff, associations, axs=axs, slope=2.0)
add_panel_label(axs[0], 'A', x_offset=-0.15)
region='nef'
reference = HIVreferenceAminoacid(region, refname=aa_ref, subtype = args.subtype)
tmp, rho, pval = fitness_scatter(region, selcoeff, associations, reference, ax=axs[0])
add_panel_label(axs[1], 'B', x_offset=-0.15)
axs[0].legend(loc=3, fontsize=fs)
axs[0].set_ylim([0.03,3])
plt.tight_layout()
for fmt in ['pdf', 'png', 'svg']:
plt.savefig('../figures/figure_5_'+region+'_st_'+args.subtype+'.'+fmt)
# calculate corrleations between fitness costs and phenotypes
phenotype_correlations = {}
erich = np.zeros((2,2,2))
for region in regions:
def plot_fit(data_sat, data_pooled):
from matplotlib import cm
from util import add_panel_label
palette = sns.color_palette('colorblind')
fig_width = 5
fs = 16
fig, axs = plt.subplots(1, 2,
figsize=(2 * fig_width, fig_width))
data_to_fit = data_sat['data_to_fit']
mu = data_sat['mu']
s = data_sat['s']
fun = lambda x, s: mu / s * (1.0 - np.exp(-s * x))
# PANEL A: data and fits
ax = axs[0]
for iS, (S, datum) in enumerate(data_to_fit.iterrows()):
x = np.array(datum.index)
y = np.array(datum)
color = cm.jet(1.0 * iS / data_to_fit.shape[0])
# Most conserved group is dashed
if iS == 0:
ls = '--'
else:
ls = '-'
ax.scatter(x, y,
s=70,
color=color,
)
xfit = np.linspace(0, 3000)
yfit = fun(xfit, s.loc[S, 's'])
ax.plot(xfit, yfit,
lw=2,
color=color,
ls=ls,
)
ax.set_xlabel('days since EDI', fontsize=fs)
ax.set_ylabel('average SNP frequency', fontsize=fs)
ax.set_xlim(-200, 3200)
ax.set_ylim(-0.0005, 0.025)
ax.set_xticks(np.linspace(0, 0.005, 5))
ax.set_xticks([0, 1000, 2000, 3000])
ax.xaxis.set_tick_params(labelsize=fs)
ax.yaxis.set_tick_params(labelsize=fs)
ax.text(0, 0.023,
r'$\mu = 1.2 \cdot 10^{-5}$ per day',
fontsize=16)
ax.plot([200, 1300], [0.007, 0.007 + (1300 - 200) * mu], lw=1.5, c='k')
# PANEL B: costs
ax = axs[1]
# B1: Saturation fit
x = np.array(s.index)
y = np.array(s['s'])
dy = np.array(s['ds'])
ymin = 0.1
x = x[1:]
y = y[1:]
dy = dy[1:]
ax.errorbar(x, y,
yerr=dy,
ls='-',
marker='o',
lw=2,
color=palette[0],
label='Sat',
)
# B2: pooled
x = data_pooled['all'][:-1, 0]
y = data_pooled['all'][:-1, 1]
dy = data_pooled['all_std'][:-1, 1]
ax.errorbar(x, y, yerr=dy,
ls='-',
marker='o',
lw=2,
color=palette[2],
label='Pooled',
)
ax.legend(loc='upper right', fontsize=16)
ax.set_xlabel('variability in group M [bits]', fontsize=fs)
ax.set_ylabel('fitness cost', fontsize=fs)
ax.set_xlim(0.9e-3, 2.5)
ax.set_ylim(9e-5, 0.11)
ax.set_xscale('log')
ax.set_yscale('log')
ax.xaxis.set_tick_params(labelsize=fs)
ax.yaxis.set_tick_params(labelsize=fs)
# Panel labels
add_panel_label(axs[0], 'A', x_offset=-0.27)
add_panel_label(axs[1], 'B', x_offset=-0.21)
plt.tight_layout()
plt.ion()
plt.show()
from hivevo.hivevo.patients import Patient
from hivevo.hivevo.samples import all_fragments
from util import store_data, load_data, draw_genome, fig_width, fig_fontsize, add_panel_label
# Script
if __name__ == "__main__":
patients = ['p' + str(i) for i in range(1, 12) if i not in [4, 7]]
# make two figures, each showing one method of template quantification
sns.set_style('darkgrid')
fs = fig_fontsize
fig1, ax1 = plt.subplots(figsize=(fig_width, 0.8 * fig_width))
fig2, ax2 = plt.subplots(figsize=(fig_width, 0.8 * fig_width))
add_panel_label(ax1, 'A', x_offset=-0.15)
add_panel_label(ax2, 'B', x_offset=-0.15)
# define colors for patients and fragments
pat_colors = sns.color_palette(
sns.color_palette([
'#a6cee3', '#1f78b4', '#b2df8a', '#33a02c', '#fb9a99', '#e31a1c',
'#fdbf6f', '#ff7f00', '#cab2d6'
],
n_colors=len(patients)))
frag_colors = sns.color_palette(n_colors=6)
depth_estimates = []
total_viral_load_dilutions_list = []
overlap_dilution_list = {i: [] for i in range(6)}
for pi, pcode in enumerate(patients):
def plot_divdiv(data, fig_filename=None, figtypes=['.png', '.svg', '.pdf']):
'''
plot divergence and diversity of synonymous and nonsynonymous mutations
includes:
- a panel that compares syn diversity/nonsyn divergence
'''
n_bootstrap=50
####### plotting ###########
import seaborn as sns
from matplotlib import pyplot as plt
plt.ion()
sns.set_style('darkgrid')
figpath = 'figures/'
fs=fig_fontsize
fig_size = (fig_width, 1.0*fig_width)
cols = HIVEVO_colormap()
fig, axs = plt.subplots(2, 2,figsize=fig_size)
divdiv = data['divdiv']
# in rough the order in which they most dominantly appear in the plot
regions = ['envelope', 'accessory', 'structural','enzymes']
time_bins = np.array([0, 200, 500, 1000, 1500, 2000, 4000])
time_binc = 0.5*(time_bins[:-1]+time_bins[1:])
add_binned_column(divdiv, time_bins, 'time')
# map the regions to rough genomic order to match the genome color map in panel C
colors = {reg:c for reg, c in zip(regions, [cols(x) for x in [0.66, 0.99, 0.01, 0.33]])}
def get_time_bin_mean(df):
return df.loc[:,['time_bin', 'diversity', 'divergence']].groupby(by=['time_bin'], as_index=False).mean()
def label_func(mutclass, region, divordiv): # assign labels to Panels A and B separately to make a combinatorial legend (regions vs syn/nonsyn)
if divordiv=='divergence' and mutclass=='nonsyn':
return region
elif divordiv=='diversity' and region=='accessory':
return mutclass
else:
return None
########## panel A and B #####################
csv_out = open(fig_filename+'_AB.tsv', 'w')
for ax, dtype in izip(axs[0,:], ['divergence', 'diversity']):
add_panel_label(ax, 'A' if dtype=='divergence' else 'B', x_offset = -0.3)
for mutclass in ['nonsyn', 'syn']:
for region in regions:
ind = (divdiv.loc[:,'region']==region) & (divdiv.loc[:,'mutclass']==mutclass)
tmp = divdiv.loc[ind,['time_bin', 'diversity', 'divergence', 'pcode']]
avg_divdiv = get_time_bin_mean(tmp)
bs = boot_strap_patients(tmp, eval_func = get_time_bin_mean, n_bootstrap=n_bootstrap)
# plot the same line with and without error bars, labels for legend without
ax.plot(time_binc/365.25, avg_divdiv.loc[:,dtype], ls='-' if mutclass=='nonsyn' else '--',
c=colors[region], lw=3, label=label_func(mutclass, region, dtype))
ax.errorbar(time_binc/365.25, avg_divdiv.loc[:,dtype], replicate_func(bs, dtype, np.std, bin_index='time_bin'),
ls='-' if mutclass=='nonsyn' else '--', c=colors[region], lw=3)
csv_out.write('\t'.join(map(str,[dtype, mutclass, region]+list(avg_divdiv.loc[:,dtype])))+'\n')
ax.legend(loc=2, fontsize=fs-1, numpoints=2, labelspacing = 0)
ax.set_xticks([0,2,4,6,8])
if dtype=='divergence':
ax.set_yticks([0,.02,.04])
ax.set_ylim([0,.048])
else:
ax.set_yticks([0,.01,.02])
ax.set_ylim([0,.028])
ax.set_xlim([0,8.5])
ax.set_ylabel(dtype)
ax.tick_params(labelsize=fs-2)
ax.set_xlabel('Years since EDI', fontsize=fs)
csv_out.close()
########## panel C: anti correlation of syn diversity and nonsyn divergence #############
csv_out = open(fig_filename+'_C.tsv', 'w')
(avg_nonsyn_divg, avg_nonsyn_divs, avg_syn_divs) = data['divdiv_corr']
ax = axs[1,0]
add_panel_label(ax, 'C', x_offset = -0.3)
x_data, y_data = avg_nonsyn_divg[::500], avg_syn_divs[::500]
ax.scatter(x_data, y_data, c=[cols(p) for p in np.linspace(0,1,len(x_data))], s=50)
csv_out.write('\t'.join(map(str, ["nonsyn_divergence"]+list(x_data)))+'\n')
csv_out.write('\t'.join(map(str, ["syn_diversity"]+list(y_data)))+'\n')
csv_out.close()
ax.set_xlabel('nonsyn divergence', fontsize = fig_fontsize)
ax.set_ylabel('syn diversity', fontsize = fig_fontsize)
ax.set_ylim([0,0.028])
ax.set_xlim([0,0.012])
ax.set_xticks([0, 0.005,0.01])
ax.set_yticks([0, 0.01, 0.02])
ax.tick_params(labelsize=fig_fontsize-2)
########## sfs in panel D ##############
csv_out = open(fig_filename+'_D.tsv', 'w')
sfs=data['sfs']
ax = axs[1,1]
add_panel_label(ax, 'D', x_offset = -0.3)
colors = sns.color_palette(n_colors=2)
binc = binc = 0.5*(sfs['bins'][1:]+sfs['bins'][:-1])
ax.bar(binc-0.045, sfs['syn']/np.sum(sfs['syn']),width = 0.04, label='syn', color=colors[0])
ax.bar(binc, sfs['nonsyn']/np.sum(sfs['nonsyn']),width = 0.04, label='nonsyn', color=colors[1])
csv_out.write('\t'.join(map(str, ["bin_centers"]+list(binc)))+'\n')
csv_out.write('\t'.join(map(str, ["sfs_nonsyn"]+list(sfs['nonsyn']/np.sum(sfs['nonsyn']))))+'\n')
csv_out.write('\t'.join(map(str, ["sfs_syn"]+list(sfs['syn']/np.sum(sfs['syn']))))+'\n')
csv_out.close()
ax.set_ylim([0.005,2.0])
ax.set_yscale('log')
ax.set_xlabel('Frequency',fontsize=fs)
ax.set_ylabel('Fractions of SNPs',fontsize=fs)
ax.legend(loc=1, fontsize=fs-2)
ax.tick_params(labelsize=fig_fontsize-2)
# finalize and save the figure
plt.tight_layout(rect=(0.0, 0.02, 0.98, 0.98), pad=0.05, h_pad=0.5, w_pad=0.4)
if fig_filename is not None:
for ext in figtypes:
fig.savefig(fig_filename+ext)
else:
plt.ion()
plt.show()
from util import store_data, load_data, draw_genome, fig_width, fig_fontsize, add_panel_label
# Script
if __name__=="__main__":
patients = ['p'+str(i) for i in range(1,12) if i not in [4,7]]
# make two figures, each showing one method of template quantification
sns.set_style('darkgrid')
fs=fig_fontsize
fig1, ax1 = plt.subplots(figsize=(fig_width, 0.8*fig_width))
fig2, ax2 = plt.subplots(figsize=(fig_width, 0.8*fig_width))
add_panel_label(ax1, 'A', x_offset=-0.15)
add_panel_label(ax2, 'B', x_offset=-0.15)
# define colors for patients and fragments
pat_colors = sns.color_palette(sns.color_palette(['#a6cee3', '#1f78b4',
'#b2df8a', '#33a02c',
'#fb9a99', '#e31a1c',
'#fdbf6f', '#ff7f00',
'#cab2d6'],
n_colors=len(patients)))
frag_colors = sns.color_palette(n_colors=6)
depth_estimates = []
total_viral_load_dilutions_list = []
overlap_dilution_list = {i:[] for i in range(6)}
for pi, pcode in enumerate(patients):
def plot_subtype_correlation(data,
fig_filename=None,
figtypes=['.png', '.svg', '.pdf']):
'''Plot results'''
import seaborn as sns
from matplotlib import pyplot as plt
plt.ion()
sns.set_style('darkgrid')
figpath = 'figures/'
fs = fig_fontsize
fig_size = (fig_width, 0.5 * fig_width)
fig, axs = plt.subplots(1, 2, figsize=fig_size)
ax = axs[0]
add_panel_label(ax, 'A', x_offset=-0.15)
patients = sorted(data['correlations']['pcode'].unique(),
key=lambda x: int(x[1:]))
colors = patient_colors
# calculate mean and variance across regions for each time point and patient
mean_rho = data['correlations'].groupby(
by=['time', 'pcode'], as_index=False).mean().groupby('pcode')
var_rho = data['correlations'].groupby(
by=['time', 'pcode'], as_index=False).var().groupby('pcode')
# loop over patients and plot the mean/std of the previously grouped data
for pat in patients:
ax.errorbar(np.array(mean_rho.get_group(pat)['time'] / 365.25),
np.array(mean_rho.get_group(pat)['rho']),
yerr=np.array(np.sqrt(var_rho.get_group(pat)['rho'])),
color=colors[pat],
ls="none",
markersize=8,
marker='o',
label=pat)
ax.legend(loc=2,
fontsize=fs - 3,
ncol=2,
labelspacing=0.1,
columnspacing=0.1)
ax.set_yticks([0, 0.25, 0.5])
ax.set_xticks([0, 2, 4, 6, 8])
ax.set_xlim([-2, 8.5])
ax.set_ylim([-0.1, 0.8])
ax.set_xlabel('ETI [years]', fontsize=fs)
ax.set_title(r"Spearman's $\rho$", fontsize=fs)
for item in ax.get_xticklabels() + ax.get_yticklabels():
item.set_fontsize(fs)
# add a second plot that shows the fraction of variable sites by entropy bin
ax = axs[1]
add_panel_label(ax, 'B', x_offset=-0.15)
div = data['diverse_fraction']
colors = sns.color_palette(n_colors=4)
# add a time bin column
time_bins = np.arange(0, 4000, 500)
binc = 0.5 * (time_bins[1:] + time_bins[:-1])
div.loc[:, 'time_bin'] = np.minimum(
len(time_bins) - 2,
np.maximum(0,
np.searchsorted(time_bins, div["time"]) - 1))
for i in range(4):
ent = 'S' + str(i + 1)
div.loc[:, ent] = div.loc[:, ent].astype(float)
# calculate mean and variance over regions and patients and samples within a time bin
mean_div = div.loc[:,
[ent, 'time_bin']].groupby(by=['time_bin'],
as_index=False).mean()
var_div = div.loc[:, [ent, 'time_bin']].groupby(by=['time_bin'],
as_index=False).var()
ax.errorbar(np.array(binc / 365.25),
np.array(mean_div.loc[:, ent]),
yerr=np.array(np.sqrt(var_div.loc[:, ent])),
label='Q' + str(i + 1),
c=colors[i])
ax.set_ylim([0, 0.35])
ax.set_yticks([0, 0.1, 0.2, 0.3])
ax.set_xticks([0, 2, 4, 6, 8])
ax.set_title('Fraction of SNPs > 0.01')
ax.set_xlabel('ETI [years]', fontsize=fs)
for item in ax.get_xticklabels() + ax.get_yticklabels():
item.set_fontsize(fs)
ax.legend(loc=2,
ncol=2,
fontsize=fs - 3,
title='Conservation',
labelspacing=0.1,
columnspacing=0.5)
# plot output
plt.tight_layout(rect=(0.0, 0.02, 0.98, 0.98),
pad=0.05,
h_pad=0.5,
w_pad=0.4)
if fig_filename is not None:
for ext in figtypes:
fig.savefig(fig_filename + ext)
else:
plt.ion()
plt.show()
def plot_non_coding_figure(data, minor_af, synnonsyn, reference, fname=None):
'''Plot fitness cost at noncoding features'''
from util import add_panel_label
ymax = 0.25
ymin = 0.0005
y_second_gene = 1.18
fig, axs = plt.subplots(1, 4, sharey=True, figsize =(10,5),
gridspec_kw={'width_ratios':[4, 1, 2.5, 1]})
# plot the 5' region
start, stop = 500, 900
feature_names = ['polyA', 'U5', 'U5 stem', 'PBS', 'PSI SL1-4']
ax = plot_fitness_costs_along_genome(start, stop, feature_names, data,
minor_af, reference, pheno=None,
synnonsyn=synnonsyn['genomewide'],
ws=8, ws_syn=4, ax=axs[0])
# add label and dimension to left-most axis, all other are tied to this one
ax.set_ylabel('fitness cost [1/day]', fontsize=fs)
ax.set_ylim(ymin, ymax)
add_panel_label(ax, 'B', x_offset=-0.15)
ax.plot([start,reference.annotation["LTR5'"].location.end],
ax.get_ylim()[0]*np.ones(2), lw=10, c='k', alpha=0.7)
ax.text(start, ax.get_ylim()[0]*1.17, "LTR5'", fontsize=fs*0.8, horizontalalignment='left')
ax.plot([reference.annotation['gag'].location.start, stop],
ax.get_ylim()[0]*np.ones(2), lw=10, c='k', alpha=0.7)
ax.text(stop, ax.get_ylim()[0]*1.17, 'gag', fontsize=fs*0.8, horizontalalignment='right')
ax.set_ylim(ymin, ymax)
# frame shift region -- no syn fitness cost here since this is in an overlap
start, stop = 2050, 2150
feature_names = ['frameshift']
ax = plot_fitness_costs_along_genome(start, stop, feature_names, data,
minor_af, reference, pheno=None,
ws=8, ws_syn=4, ax=axs[1])
ax.plot([start, reference.annotation['gag'].location.end],
ax.get_ylim()[0]*np.ones(2), lw=10, c='k', alpha=0.7)
ax.text(start, ax.get_ylim()[0]*1.17, 'gag', fontsize=fs*0.8, horizontalalignment='left')
ax.plot([reference.annotation['pol'].location.start,stop],
y_second_gene*ax.get_ylim()[0]*np.ones(2), lw=5, c='k', alpha=0.7)
ax.text(stop, ax.get_ylim()[0]*(y_second_gene+0.17), 'pol', fontsize=fs*0.8, horizontalalignment='right')
ax.set_xticks([2050, 2150])
ax.set_ylim(ymin, ymax)
# plot the cPPT region
start, stop = 4750, 5000
feature_names = ['A1','D2', 'cPPT']
ax = plot_fitness_costs_along_genome(start, stop, feature_names, data,
minor_af, reference, pheno=None,
synnonsyn=synnonsyn['genomewide'],
ws=8, ws_syn=4, ax=axs[2])
# add label and dimension to left-most axis, all other are tied to this one
ax.set_ylim(ymin, ymax)
ax.plot([start,reference.annotation["IN"].location.end],
ax.get_ylim()[0]*np.ones(2), lw=10, c='k', alpha=0.7)
ax.text(start, ax.get_ylim()[0]*1.17, "IN", fontsize=fs*0.8, horizontalalignment='left')
ax.plot([reference.annotation['vif'].location.start, stop],
y_second_gene*ax.get_ylim()[0]*np.ones(2), lw=10, c='k', alpha=0.7)
ax.text(stop, ax.get_ylim()[0]*(y_second_gene+0.17), 'vif', fontsize=fs*0.8, horizontalalignment='right')
ax.set_xticks([4800, 4900])
ax.set_ylim(ymin, ymax)
# plot the 3' region
start, stop = 9050, 9150
feature_names = ['PPT']
ax = plot_fitness_costs_along_genome(start, stop, feature_names, data,
minor_af, reference, pheno=None,
synnonsyn=synnonsyn['genomewide'],
ws=8, ws_syn=4, ax=axs[3])
ax.plot([start, reference.annotation['nef'].location.end],
ax.get_ylim()[0]*np.ones(2), lw=10, c='k', alpha=0.7)
ax.text(start, ax.get_ylim()[0]*1.17, 'nef', fontsize=fs*0.8, horizontalalignment='left')
ax.plot([reference.annotation["LTR3'"].location.start,stop],
y_second_gene*ax.get_ylim()[0]*np.ones(2), lw=5, c='k', alpha=0.7)
ax.text(stop, ax.get_ylim()[0]*(y_second_gene+0.17), "LTR3'", fontsize=fs*0.8, horizontalalignment='right')
ax.set_xticks([9050, 9100,9150])
ax.set_ylim(ymin, ymax)
fig.text(0.5, 0.01, 'Position in HIV-1 reference (HXB2) [bp]',
ha='center',
fontsize=fs)
plt.tight_layout(rect=(0, 0.04, 1, 1),w_pad=-1)
if fname is not None:
for ext in ['.png', '.svg', '.pdf']:
plt.savefig(fname+ext)
def plot_fitness_cost_along_genome(regions, data, minor_af, synnonsyn, reference, ws=30):
'''Plot the fitness costs along the genome
We have the fitness costs per site, but we only plot a running average over
30 bp as a smoothing, for visual clarity. Later on we export the actual
per-site fitness costs to file.
'''
from util import add_panel_label
all_sel_coeff = []
# Fitness costs along the genome
fig, axs = plt.subplots(2, 1, sharex=True,
gridspec_kw={'height_ratios':[6, 1]})
for ni,label_str in ((1,'nonsynonymous'), (0,'synonymous')):
for ri, region in enumerate(regions):
ind = synnonsyn[region] if label_str=='synonymous' else ~synnonsyn[region]
ind = ind&(~np.isnan(minor_af[region]))
#axs[0].plot([x for x in reference.annotation[region] if x%3==0], 1.0/np.convolve(np.ones(ws, dtype=float)/ws, 1.0/sc[region], mode='same'), c=cols[ri])
sc = (data['mut_rate'][region]/(af_cutoff+minor_af[region]))
sc[sc>0.1] = 0.1
sc[sc<0.001] = 0.001
axs[0].plot(running_average(np.array(list(reference.annotation[region]))[ind], ws),
np.exp(running_average(np.log(sc[ind]), ws)),
c=cols[ri%len(cols)],
ls='--' if label_str=='synonymous' else '-',
label=label_str if region=='gag' else None)
if ni and region not in ['vpr', 'vpu']:
all_sel_coeff.extend([(region, pos, np.log10(sc[pos]), synnonsyn[region][pos]) for pos in range(len(sc))])
axs[0].legend(loc=1, fontsize=fs*0.8)
axs[0].set_yscale('log')
axs[0].set_ylabel('fitness cost [1/day]', fontsize=fs)
axs[0].set_ylim(0.002, 0.25)
axs[0].tick_params(labelsize=fs*0.8)
# The genome annotations
regs = ['p17', 'p6', 'p7', 'p24',
'PR', 'RT', 'IN', 'p15',
'nef',
'gp120', 'gp41',
'vif', 'vpu', 'vpr', 'rev', 'tat',
'V1', 'V2', 'V3', 'V5']
annotations = {k: val for k, val in reference.annotation.iteritems() if k in regs}
annotations = draw_genome(annotations, axs[1])
axs[1].set_axis_off()
feas = ['p17', 'p24', 'PR', 'RT', 'p15', 'IN', 'vif', 'gp120', 'gp41', 'nef']
vlines = np.unique(annotations.loc[annotations['name'].isin(feas), ['x1', 'x2']])
for xtmp in vlines:
axs[0].axvline(xtmp, lw=1, color='0.8')
plt.tight_layout()
add_panel_label(axs[0], 'A', x_offset=-0.1)
for ext in ['png', 'svg', 'pdf']:
fig.savefig('../figures/figure_3A_st_' + reference.subtype + '.'+ext)
# Violin plots of the fitness cost distributions for syn and nonsyn
all_sel_coeff = pd.DataFrame(data=all_sel_coeff, columns=['gene', 'position', 'selection', 'synonymous'])
all_sel_coeff.loc[all_sel_coeff['synonymous'] == True, 'synonymous'] = 'synonymous'
all_sel_coeff.loc[all_sel_coeff['synonymous'] == False, 'synonymous'] = 'nonsynonymous'
fig = plt.figure()
ax = sns.violinplot(x='gene', y='selection', hue='synonymous', data=all_sel_coeff,
inner='quartile', split=True, cut=0, scale='area')
ax.set_yticks([-3,-2,-1])
ax.set_yticklabels([r'$10^{'+str(i)+'}$' for i in [-3,-2,-1]])
ax.tick_params(labelsize=0.8*fs)
ax.set_ylabel('fitness cost [1/day]', fontsize=fs)
ax.set_xlabel('')
ax.set_ylim(-3, -0.5)
ax.legend(loc=1, fontsize=fs, title=None)
plt.tight_layout()
#add_panel_label(ax, 'B', x_offset=-0.1)
for ext in ['png', 'svg', 'pdf']:
fig.savefig('../figures/figure_S6_st_' + reference.subtype +'.'+ext)
def plot_minor_allele_example(data, title='', VERBOSE=0, fig_filename=None):
'''Plot minor allele in a typical sample'''
import matplotlib.pyplot as plt
import seaborn as sns
from util import add_panel_label
plt.ioff()
if VERBOSE:
print 'Plot minor alleles of example sample'
fig_size = (fig_width, 0.8*fig_width)
fig, axs = plt.subplots(1, 2,
figsize=fig_size,
sharey=True,
gridspec_kw={'width_ratios': [3, 1]})
sns.set_style('darkgrid')
labels = ['control', 'patient']
alphas = [0.6, 1]
colors = [sns.color_palette()[i] for i in [2, 0]]
shapes = ['s', 'o']
for idat, datum in enumerate(data):
y = datum['freq_minor']
x = np.arange(len(y))
#axs[0].plot(x, y, lw=1.5, alpha=0.8)
axs[0].scatter(x, y,
marker=shapes[idat],
lw=1.5, edgecolor='none',
facecolor=colors[idat],
zorder=idat+1)
h = np.histogram(y, bins=np.logspace(-4, 0, 27))
axs[1].barh(h[1][:-1], h[0], (h[1][1:] - h[1][:-1]),
color=colors[idat],
alpha=alphas[idat],
zorder=2 - idat)
axs[0].set_xlabel('Position [bp]', fontsize=fig_fontsize)
axs[0].set_ylabel('SNP frequency', fontsize=fig_fontsize)
axs[0].set_yscale('log')
axs[0].set_ylim(10**(-4), 1)
axs[0].set_xlim(-20, y.nonzero()[0][-1] + 21)
axs[0].grid(True)
axs[0].tick_params(axis='both', labelsize=fig_fontsize)
axs[1].set_xlabel('Number of positions', fontsize=fig_fontsize)
axs[1].grid(True)
axs[1].set_yscale('log')
axs[1].set_xlim(0.8, 2 * h[0].max())
axs[1].set_xscale('log')
axs[1].tick_params(axis='x', labelsize=fig_fontsize)
add_panel_label(axs[0], 'C', x_offset=-0.22)
plt.tight_layout(pad=0.1, h_pad=0.001, w_pad=0.001)
if title:
fig.suptitle(title)
if fig_filename is not None:
for ext in ['.pdf','.svg', '.png']:
fig.savefig(fig_filename+ext)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_fit(data_sat, data_pooled, bins_sat):
from matplotlib import cm
from util import add_panel_label
palette = sns.color_palette('colorblind')
fig_width = 5
fs = 16
fig, axs = plt.subplots(1, 2, figsize=(2 * fig_width, fig_width))
data_to_fit = data_sat['data_to_fit']
mu = data_sat['mu']
s = data_sat['s']
fun = lambda x, s: mu / s * (1.0 - np.exp(-s * x))
# PANEL A: data and fits
ax = axs[0]
for iS, (S, datum) in enumerate(data_to_fit.iterrows()):
x = np.array(datum.index)
y = np.array(datum)
color = cm.jet(1.0 * iS / data_to_fit.shape[0])
# Most conserved group is dashed
if iS == 0:
ls = '--'
else:
ls = '-'
ax.scatter(
x,
y,
s=70,
color=color,
)
xfit = np.linspace(0, 3000)
yfit = fun(xfit, s.loc[S, 's'])
ax.plot(
xfit,
yfit,
lw=2,
color=color,
ls=ls,
)
ax.set_xlabel('days since EDI', fontsize=fs)
ax.set_ylabel('divergence', fontsize=fs)
ax.set_xlim(-200, 3200)
ax.set_ylim(-0.0005, 0.025)
ax.set_xticks(np.linspace(0, 0.005, 5))
ax.set_xticks([0, 1000, 2000, 3000])
ax.xaxis.set_tick_params(labelsize=fs)
ax.yaxis.set_tick_params(labelsize=fs)
ax.text(0, 0.023, r'$\mu = 1.2 \cdot 10^{-5}$ per day', fontsize=16)
ax.plot([200, 1300], [0.007, 0.007 + (1300 - 200) * mu], lw=1.5, c='k')
# PANEL B: costs
ax = axs[1]
# B1: Saturation fit
x = np.array(s.index)
y = np.array(s['s'])
dy = np.array(s['ds'])
ymin = 0.1
x = x[1:]
y = y[1:]
dx = np.array((x - bins_sat[1:-1], bins_sat[2:] - x))
dy = dy[1:]
ax.errorbar(
x,
y,
yerr=dy,
xerr=dx,
ls='-',
marker='o',
lw=2,
color=palette[0],
label='Sat',
)
# Annotate with colors from panel A
#ax.scatter(x, y,
# marker='o',
# s=130,
# edgecolor=cm.jet(1.0 * np.arange(1, data_to_fit.shape[0]) / data_to_fit.shape[0]),
# facecolor='none',
# lw=2,
# zorder=5,
# )
for iS in xrange(1, data_to_fit.shape[0]):
ax.annotate(
'',
xy=(x[iS - 1],
y[iS - 1] * 0.7 if iS != data_to_fit.shape[0] - 1 else 1e-4),
xytext=(x[iS - 1], y[iS - 1] * 1.0 /
3 if iS != data_to_fit.shape[0] - 1 else 2e-4),
arrowprops={
'facecolor': cm.jet(1.0 * iS / data_to_fit.shape[0]),
'edgecolor': 'none',
'shrink': 0.05
},
)
# B2: pooled
x = data_pooled['all'][:-1, 0]
y = data_pooled['all'][:-1, -1]
dy = data_pooled['all_std'][:-1, -1]
dx = np.array(
(x - data_pooled['all'][:-1, 1], data_pooled['all'][:-1, 2] - x))
ax.errorbar(
x,
y,
yerr=dy,
xerr=dx,
ls='-',
marker='o',
lw=2,
color=palette[2],
label='Pooled',
)
ax.legend(loc='upper right', fontsize=16)
ax.set_xlabel('variability in group M [bits]', fontsize=fs)
ax.set_ylabel('fitness cost [1/day]', fontsize=fs)
ax.set_xlim(0.9e-3, 2.5)
ax.set_ylim(9e-5, 0.11)
ax.set_xscale('log')
ax.set_yscale('log')
ax.xaxis.set_tick_params(labelsize=fs)
ax.yaxis.set_tick_params(labelsize=fs)
# Panel labels
add_panel_label(axs[0], 'A', x_offset=-0.27)
add_panel_label(axs[1], 'B', x_offset=-0.21)
plt.tight_layout()
plt.ion()
plt.show()
def plot_non_coding_figure(data, minor_af, synnonsyn, reference, fname=None):
'''Plot fitness cost at noncoding features'''
from util import add_panel_label
ymax = 0.25
ymin = 0.0005
y_second_gene = 1.18
fig, axs = plt.subplots(1,
4,
sharey=True,
figsize=(10, 5),
gridspec_kw={'width_ratios': [4, 1, 2.5, 1]})
# plot the 5' region
start, stop = 500, 900
feature_names = ['polyA', 'U5', 'U5 stem', 'PBS', 'PSI SL1-4']
ax = plot_fitness_costs_along_genome(start,
stop,
feature_names,
data,
minor_af,
reference,
pheno=None,
synnonsyn=synnonsyn['genomewide'],
ws=8,
ws_syn=4,
ax=axs[0])
# add label and dimension to left-most axis, all other are tied to this one
ax.set_ylabel('fitness cost [1/day]', fontsize=fs)
ax.set_ylim(ymin, ymax)
add_panel_label(ax, 'B', x_offset=-0.15)
ax.plot([start, reference.annotation["LTR5'"].location.end],
ax.get_ylim()[0] * np.ones(2),
lw=10,
c='k',
alpha=0.7)
ax.text(start,
ax.get_ylim()[0] * 1.17,
"LTR5'",
fontsize=fs * 0.8,
horizontalalignment='left')
ax.plot([reference.annotation['gag'].location.start, stop],
ax.get_ylim()[0] * np.ones(2),
lw=10,
c='k',
alpha=0.7)
ax.text(stop,
ax.get_ylim()[0] * 1.17,
'gag',
fontsize=fs * 0.8,
horizontalalignment='right')
ax.set_ylim(ymin, ymax)
# frame shift region -- no syn fitness cost here since this is in an overlap
start, stop = 2050, 2150
feature_names = ['frameshift']
ax = plot_fitness_costs_along_genome(start,
stop,
feature_names,
data,
minor_af,
reference,
pheno=None,
ws=8,
ws_syn=4,
ax=axs[1])
ax.plot([start, reference.annotation['gag'].location.end],
ax.get_ylim()[0] * np.ones(2),
lw=10,
c='k',
alpha=0.7)
ax.text(start,
ax.get_ylim()[0] * 1.17,
'gag',
fontsize=fs * 0.8,
horizontalalignment='left')
ax.plot([reference.annotation['pol'].location.start, stop],
y_second_gene * ax.get_ylim()[0] * np.ones(2),
lw=5,
c='k',
alpha=0.7)
ax.text(stop,
ax.get_ylim()[0] * (y_second_gene + 0.17),
'pol',
fontsize=fs * 0.8,
horizontalalignment='right')
ax.set_xticks([2050, 2150])
ax.set_ylim(ymin, ymax)
# plot the cPPT region
start, stop = 4750, 5000
feature_names = ['A1', 'D2', 'cPPT']
ax = plot_fitness_costs_along_genome(start,
stop,
feature_names,
data,
minor_af,
reference,
pheno=None,
synnonsyn=synnonsyn['genomewide'],
ws=8,
ws_syn=4,
ax=axs[2])
# add label and dimension to left-most axis, all other are tied to this one
ax.set_ylim(ymin, ymax)
ax.plot([start, reference.annotation["IN"].location.end],
ax.get_ylim()[0] * np.ones(2),
lw=10,
c='k',
alpha=0.7)
ax.text(start,
ax.get_ylim()[0] * 1.17,
"IN",
fontsize=fs * 0.8,
horizontalalignment='left')
ax.plot([reference.annotation['vif'].location.start, stop],
y_second_gene * ax.get_ylim()[0] * np.ones(2),
lw=10,
c='k',
alpha=0.7)
ax.text(stop,
ax.get_ylim()[0] * (y_second_gene + 0.17),
'vif',
fontsize=fs * 0.8,
horizontalalignment='right')
ax.set_xticks([4800, 4900])
ax.set_ylim(ymin, ymax)
# plot the 3' region
start, stop = 9050, 9150
feature_names = ['PPT']
ax = plot_fitness_costs_along_genome(start,
stop,
feature_names,
data,
minor_af,
reference,
pheno=None,
synnonsyn=synnonsyn['genomewide'],
ws=8,
ws_syn=4,
ax=axs[3])
ax.plot([start, reference.annotation['nef'].location.end],
ax.get_ylim()[0] * np.ones(2),
lw=10,
c='k',
alpha=0.7)
ax.text(start,
ax.get_ylim()[0] * 1.17,
'nef',
fontsize=fs * 0.8,
horizontalalignment='left')
ax.plot([reference.annotation["LTR3'"].location.start, stop],
y_second_gene * ax.get_ylim()[0] * np.ones(2),
lw=5,
c='k',
alpha=0.7)
ax.text(stop,
ax.get_ylim()[0] * (y_second_gene + 0.17),
"LTR3'",
fontsize=fs * 0.8,
horizontalalignment='right')
ax.set_xticks([9050, 9100, 9150])
ax.set_ylim(ymin, ymax)
fig.text(0.5,
0.01,
'Position in HIV-1 reference (HXB2) [bp]',
ha='center',
fontsize=fs)
plt.tight_layout(rect=(0, 0.04, 1, 1), w_pad=-1)
if fname is not None:
for ext in ['.png', '.svg', '.pdf']:
plt.savefig(fname + ext)
def plot_minor_allele_example(data, title='', VERBOSE=0, fig_filename=None):
'''Plot minor allele in a typical sample'''
import matplotlib.pyplot as plt
import seaborn as sns
from util import add_panel_label
plt.ioff()
if VERBOSE:
print 'Plot minor alleles of example sample'
fig_size = (fig_width, 0.8 * fig_width)
fig, axs = plt.subplots(1,
2,
figsize=fig_size,
sharey=True,
gridspec_kw={'width_ratios': [3, 1]})
sns.set_style('darkgrid')
labels = ['control', 'patient']
alphas = [0.6, 1]
colors = [sns.color_palette()[i] for i in [2, 0]]
shapes = ['s', 'o']
for idat, datum in enumerate(data):
y = datum['freq_minor']
x = np.arange(len(y))
#axs[0].plot(x, y, lw=1.5, alpha=0.8)
axs[0].scatter(x,
y,
marker=shapes[idat],
lw=1.5,
edgecolor='none',
facecolor=colors[idat],
zorder=idat + 1)
h = np.histogram(y, bins=np.logspace(-4, 0, 27))
axs[1].barh(h[1][:-1],
h[0], (h[1][1:] - h[1][:-1]),
color=colors[idat],
alpha=alphas[idat],
zorder=2 - idat)
axs[0].set_xlabel('Position [bp]', fontsize=fig_fontsize)
axs[0].set_ylabel('SNP frequency', fontsize=fig_fontsize)
axs[0].set_yscale('log')
axs[0].set_ylim(10**(-4), 1)
axs[0].set_xlim(-20, y.nonzero()[0][-1] + 21)
axs[0].grid(True)
axs[0].tick_params(axis='both', labelsize=fig_fontsize)
axs[1].set_xlabel('Number of positions', fontsize=fig_fontsize)
axs[1].grid(True)
axs[1].set_yscale('log')
axs[1].set_xlim(0.8, 2 * h[0].max())
axs[1].set_xscale('log')
axs[1].tick_params(axis='x', labelsize=fig_fontsize)
add_panel_label(axs[0], 'C', x_offset=-0.22)
plt.tight_layout(pad=0.1, h_pad=0.001, w_pad=0.001)
if title:
fig.suptitle(title)
if fig_filename is not None:
for ext in ['.pdf', '.svg', '.png']:
fig.savefig(fig_filename + ext)
plt.close(fig)
else:
plt.ion()
plt.show()
