def plot_distance_histogram(data_folder,
adaID,
fragment,
counts,
savefig=False):
'''Plot the histogram of distance from consensus'''
from hivwholeseq.sequencing.filenames import get_distance_from_consensus_figure_filename as gff
import matplotlib.pyplot as plt
if savefig:
is_ion = plt.isinteractive()
plt.ioff()
# Linear histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs')
ax.set_title('adaID ' + adaID + ', ' + fragment)
ax.set_xlim(-0.5, 0.5 + counts.nonzero()[0][-1])
ax.plot(np.arange(len(counts)), counts, 'b', lw=2)
if savefig:
outputfile = gff(data_folder, adaID, fragment)
fig.savefig(outputfile)
plt.close(fig)
# Log cumulative histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs < x')
ax.set_title('adaID ' + adaID + ', ' + fragment)
ax.set_xlim(-0.5, 0.5 + counts.nonzero()[0][-1])
ax.set_ylim(1.0 / counts.sum() * 0.9, 1.1)
ax.set_yscale('log')
y = 1.0 - 1.0 * np.cumsum(counts) / counts.sum()
ax.plot(np.arange(len(counts)), y, 'b', lw=2)
if savefig:
outputfile = gff(data_folder,
adaID,
fragment,
cumulative=True,
yscale='log')
fig.savefig(outputfile)
plt.close(fig)
if is_ion:
plt.ion()
def plot_coverage(data_folder,
adaID,
fragment,
counts,
VERBOSE=0,
savefig=False):
'''Plot figure with the coverage'''
from hivwholeseq.sequencing.filenames import get_coverage_figure_filename as gff
if VERBOSE >= 1:
print 'Plotting coverage: ' + adaID + ' ' + fragment
coverage = counts.sum(axis=1).sum(axis=0)
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1, figsize=(15, 8))
ax.plot(coverage + 0.5)
ax.set_yscale('log')
ax.set_xlabel('Position')
ax.set_ylabel('Coverage')
ax.set_title('adaID ' + adaID + ', fragment ' + fragment)
if savefig:
outputfile = gff(data_folder, adaID, fragment)
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_coverage(data_folder, adaID, fragment, counts, VERBOSE=0, savefig=False):
'''Plot figure with the coverage'''
from hivwholeseq.sequencing.filenames import get_coverage_figure_filename as gff
if VERBOSE >= 1:
print 'Plotting coverage: '+adaID+' '+fragment
coverage = counts.sum(axis=1).sum(axis=0)
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1, figsize=(15, 8))
ax.plot(coverage + 0.5)
ax.set_yscale('log')
ax.set_xlabel('Position')
ax.set_ylabel('Coverage')
ax.set_title('adaID '+adaID+', fragment '+fragment)
if savefig:
outputfile = gff(data_folder, adaID, fragment)
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_minor_allele_frequency_filtered(data_folder, adaID, fragments, VERBOSE=0,
savefig=False):
'''Plot minor allele frequency along the genome'''
nus = np.load(get_merged_allele_frequencies_filename(data_folder, adaID, fragments))
nu_min = np.ma.masked_all(nus.shape[-1])
for pos, nutmp in enumerate(nus.T):
try:
if not np.ma.is_masked(nutmp):
nu_min[pos] = np.sort(nutmp)[-2]
except ValueError:
print pos, np.ma.is_masked(nutmp)
import ipdb; ipdb.set_trace()
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1, figsize=(15, 8))
ax.plot(nu_min, lw=1.5, c='k')
ax.scatter(np.arange(len(nu_min)), nu_min, s=30, c='k')
ax.set_yscale('log')
ax.set_xlabel('Position')
ax.set_ylabel(r'$\nu$', fontsize=20)
ax.set_title('adaID '+adaID+', '+'-'.join(fragments))
ax.set_xlim(-100, len(nu_min) + 100)
plt.tight_layout()
if savefig:
from hivwholeseq.sequencing.filenames import \
get_minor_allele_frequency_merged_figure_filename as gff
outputfile = gff(data_folder, adaID, fragments)
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_distance_histogram(data_folder, adaID, fragment, counts, savefig=False):
'''Plot the histogram of distance from consensus'''
from hivwholeseq.sequencing.filenames import get_distance_from_consensus_figure_filename as gff
import matplotlib.pyplot as plt
if savefig:
is_ion = plt.isinteractive()
plt.ioff()
# Linear histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs')
ax.set_title('adaID '+adaID+', '+fragment)
ax.set_xlim(-0.5, 0.5 + counts.nonzero()[0][-1])
ax.plot(np.arange(len(counts)), counts, 'b', lw=2)
if savefig:
outputfile = gff(data_folder, adaID, fragment)
fig.savefig(outputfile)
plt.close(fig)
# Log cumulative histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs < x')
ax.set_title('adaID '+adaID+', '+fragment)
ax.set_xlim(-0.5, 0.5 + counts.nonzero()[0][-1])
ax.set_ylim(1.0 / counts.sum() * 0.9, 1.1)
ax.set_yscale('log')
y = 1.0 - 1.0 * np.cumsum(counts) / counts.sum()
ax.plot(np.arange(len(counts)), y, 'b', lw=2)
if savefig:
outputfile = gff(data_folder, adaID, fragment, cumulative=True, yscale='log')
fig.savefig(outputfile)
plt.close(fig)
if is_ion:
plt.ion()
def plot_minor_allele_frequency_filtered(data_folder,
adaID,
fragments,
VERBOSE=0,
savefig=False):
'''Plot minor allele frequency along the genome'''
nus = np.load(
get_merged_allele_frequencies_filename(data_folder, adaID, fragments))
nu_min = np.ma.masked_all(nus.shape[-1])
for pos, nutmp in enumerate(nus.T):
try:
if not np.ma.is_masked(nutmp):
nu_min[pos] = np.sort(nutmp)[-2]
except ValueError:
print pos, np.ma.is_masked(nutmp)
import ipdb
ipdb.set_trace()
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1, figsize=(15, 8))
ax.plot(nu_min, lw=1.5, c='k')
ax.scatter(np.arange(len(nu_min)), nu_min, s=30, c='k')
ax.set_yscale('log')
ax.set_xlabel('Position')
ax.set_ylabel(r'$\nu$', fontsize=20)
ax.set_title('adaID ' + adaID + ', ' + '-'.join(fragments))
ax.set_xlim(-100, len(nu_min) + 100)
plt.tight_layout()
if savefig:
from hivwholeseq.sequencing.filenames import \
get_minor_allele_frequency_merged_figure_filename as gff
outputfile = gff(data_folder, adaID, fragments)
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_SFS_folded(data_folder,
adaID,
fragment,
nu_filtered,
VERBOSE=0,
savefig=False):
'''Plot the site frequency spectrum (folded)'''
if VERBOSE >= 1:
print 'Plotting folded SFS'
from hivwholeseq.sequencing.filenames import get_SFS_figure_filename as gff
import matplotlib.pyplot as plt
import numpy as np
nu_maj = np.ma.masked_all(nu_filtered.shape[1])
nu_min = np.ma.masked_all(nu_filtered.shape[1])
for pos, nus in enumerate(nu_filtered.T):
if nus[0] == np.ma.masked:
continue
nus = np.sort(nus)
if (nus[-1] < 0.5):
if VERBOSE >= 3:
print pos, 'has 3+ alleles:', nus, 'skipping.'
continue
nu_maj[pos] = nus[-1]
nu_min[pos] = nus[-2]
nu_maj_fold = 1 - nu_maj
nu_mm = np.concatenate([nu_maj_fold, nu_min])
nu_mm = np.array(nu_mm[nu_mm > 1e-5])
nu_mm.sort()
# Cumulative histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel(r'$\nu$', fontsize=20)
ax.set_ylabel('# alleles < x folded')
ax.set_title('adaID ' + adaID + ', ' + fragment)
ax.set_xlim(10**(np.floor(np.log10(nu_mm[0] * 0.9))), 0.6)
ax.set_xscale('log')
ax.set_ylim(1.0 / len(nu_mm) * 0.9, 1.1)
ax.set_yscale('log')
ax.plot(nu_mm,
1.0 - np.linspace(0, 1 - 1.0 / len(nu_mm), len(nu_mm)),
lw=2,
c='b')
if savefig:
outputfile = gff(data_folder,
adaID,
fragment,
cumulative=True,
yscale='log')
fig.savefig(outputfile)
plt.close(fig)
# Histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel(r'$\nu$', fontsize=20)
ax.set_ylabel('SFS folded (density)')
ax.set_title('adaID ' + adaID + ', ' + fragment)
ax.set_xlim(10**(np.floor(np.log10(nu_mm[0] * 0.9))), 0.6)
ax.set_xscale('log')
ax.set_yscale('log')
bins = np.logspace(-4, np.log10(0.5), 50)
h = np.histogram(nu_mm, bins=bins, density=True)
x = np.sqrt(h[1][1:] * h[1][:-1])
y = h[0]
ax.plot(x, y, lw=2, c='b')
ax.scatter(x, y, s=50, edgecolor='none', facecolor='b')
ax.grid()
if savefig:
outputfile = gff(data_folder,
adaID,
fragment,
cumulative=False,
yscale='log')
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_SFS_folded(data_folder, adaID, fragment, nu_filtered, VERBOSE=0, savefig=False):
'''Plot the site frequency spectrum (folded)'''
if VERBOSE >= 1:
print 'Plotting folded SFS'
from hivwholeseq.sequencing.filenames import get_SFS_figure_filename as gff
import matplotlib.pyplot as plt
import numpy as np
nu_maj = np.ma.masked_all(nu_filtered.shape[1])
nu_min = np.ma.masked_all(nu_filtered.shape[1])
for pos, nus in enumerate(nu_filtered.T):
if nus[0] == np.ma.masked:
continue
nus = np.sort(nus)
if (nus[-1] < 0.5):
if VERBOSE >= 3:
print pos, 'has 3+ alleles:', nus, 'skipping.'
continue
nu_maj[pos] = nus[-1]
nu_min[pos] = nus[-2]
nu_maj_fold = 1 - nu_maj
nu_mm = np.concatenate([nu_maj_fold, nu_min])
nu_mm = np.array(nu_mm[nu_mm > 1e-5])
nu_mm.sort()
# Cumulative histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel(r'$\nu$', fontsize=20)
ax.set_ylabel('# alleles < x folded')
ax.set_title('adaID '+adaID+', '+fragment)
ax.set_xlim(10**(np.floor(np.log10(nu_mm[0] * 0.9))), 0.6)
ax.set_xscale('log')
ax.set_ylim(1.0 / len(nu_mm) * 0.9, 1.1)
ax.set_yscale('log')
ax.plot(nu_mm, 1.0 - np.linspace(0, 1 - 1.0 / len(nu_mm), len(nu_mm)), lw=2, c='b')
if savefig:
outputfile = gff(data_folder, adaID, fragment, cumulative=True, yscale='log')
fig.savefig(outputfile)
plt.close(fig)
# Histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel(r'$\nu$', fontsize=20)
ax.set_ylabel('SFS folded (density)')
ax.set_title('adaID '+adaID+', '+fragment)
ax.set_xlim(10**(np.floor(np.log10(nu_mm[0] * 0.9))), 0.6)
ax.set_xscale('log')
ax.set_yscale('log')
bins = np.logspace(-4, np.log10(0.5), 50)
h = np.histogram(nu_mm, bins=bins, density=True)
x = np.sqrt(h[1][1:] * h[1][:-1])
y = h[0]
ax.plot(x, y, lw=2, c='b')
ax.scatter(x, y, s=50, edgecolor='none', facecolor='b')
ax.grid()
if savefig:
outputfile = gff(data_folder, adaID, fragment, cumulative=False, yscale='log')
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_distance_histogram_sliding_window(data_folder,
adaID,
fragment,
lref,
counts,
binsize=200,
savefig=False):
'''Plot the distance histogram along the genome'''
from hivwholeseq.sequencing.filenames import get_distance_from_consensus_figure_filename as gff
import matplotlib.pyplot as plt
from matplotlib import cm
if savefig:
is_ion = plt.isinteractive()
plt.ioff()
# Figure max x
xmax = counts.nonzero()[1].max()
# Linear histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs')
ax.set_title('adaID ' + adaID + ', ' + fragment)
ax.set_xlim(-0.5, 0.5 + xmax)
for i, count in enumerate(counts):
color = cm.jet(int(255.0 * i / counts.shape[0]))
start = binsize * i
end = min(binsize * (i + 1), lref)
ax.plot(np.arange(counts.shape[1]),
count,
lw=2,
color=color,
label=str(start) + ' to ' + str(end))
ax.legend(loc=1)
if savefig:
outputfile = gff(data_folder, adaID, fragment, sliding_window=True)
fig.savefig(outputfile)
plt.close(fig)
# Log cumulative histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs')
ax.set_title('adaID ' + adaID + ', ' + fragment)
ax.set_xlim(-0.5, 0.5 + xmax)
ax.set_ylim(1.0 / counts.sum(axis=1).max() * 0.9, 1.1)
ax.set_yscale('log')
for i, count in enumerate(counts):
color = cm.jet(int(255.0 * i / counts.shape[0]))
start = binsize * i
end = min(binsize * (i + 1), lref)
y = 1.0 - 1.0 * np.cumsum(count) / count.sum()
ax.plot(np.arange(counts.shape[1]),
y,
lw=2,
color=color,
label=str(start) + ' to ' + str(end))
ax.legend(loc=1)
if savefig:
outputfile = gff(data_folder,
adaID,
fragment,
cumulative=True,
sliding_window=True)
fig.savefig(outputfile)
plt.close(fig)
if is_ion:
plt.ion()
def plot_distance_histogram_sliding_window(data_folder, adaID, fragment,
lref,
counts, binsize=200,
savefig=False):
'''Plot the distance histogram along the genome'''
from hivwholeseq.sequencing.filenames import get_distance_from_consensus_figure_filename as gff
import matplotlib.pyplot as plt
from matplotlib import cm
if savefig:
is_ion = plt.isinteractive()
plt.ioff()
# Figure max x
xmax = counts.nonzero()[1].max()
# Linear histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs')
ax.set_title('adaID '+adaID+', '+fragment)
ax.set_xlim(-0.5, 0.5 + xmax)
for i, count in enumerate(counts):
color = cm.jet(int(255.0 * i / counts.shape[0]))
start = binsize * i
end = min(binsize * (i+1), lref)
ax.plot(np.arange(counts.shape[1]), count, lw=2,
color=color, label=str(start)+' to '+str(end))
ax.legend(loc=1)
if savefig:
outputfile = gff(data_folder, adaID, fragment, sliding_window=True)
fig.savefig(outputfile)
plt.close(fig)
# Log cumulative histogram
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('Hamming distance')
ax.set_ylabel('# read pairs')
ax.set_title('adaID '+adaID+', '+fragment)
ax.set_xlim(-0.5, 0.5 + xmax)
ax.set_ylim(1.0 / counts.sum(axis=1).max() * 0.9, 1.1)
ax.set_yscale('log')
for i, count in enumerate(counts):
color = cm.jet(int(255.0 * i / counts.shape[0]))
start = binsize * i
end = min(binsize * (i+1), lref)
y = 1.0 - 1.0 * np.cumsum(count) / count.sum()
ax.plot(np.arange(counts.shape[1]), y, lw=2,
color=color, label=str(start)+' to '+str(end))
ax.legend(loc=1)
if savefig:
outputfile = gff(data_folder, adaID, fragment, cumulative=True,
sliding_window=True)
fig.savefig(outputfile)
plt.close(fig)
if is_ion:
plt.ion()
def plot_minor_allele_frequency(data_folder, adaID, fragments, VERBOSE=0,
savefig=False):
'''Plot minor allele frequency along the genome'''
from hivwholeseq.sequencing.filenames import get_minor_allele_frequency_figure_filename as gff
import matplotlib
params = {'axes.labelsize': 20,
'text.fontsize': 20,
'legend.fontsize': 8,
'xtick.labelsize': 16,
'ytick.labelsize': 16,
'text.usetex': False}
matplotlib.rcParams.update(params)
from matplotlib import cm
import matplotlib.pyplot as plt
plot_grid = [(1, 1), (1, 2), (1, 3), (2, 2), (1, 5), (2, 3)]
# Store in globals structures
covs = {}
nus_minor = {}
alls_minor = {}
nus_filtered = {}
nus_minor_filtered = {}
for fragment in fragments:
coverage = np.load(get_coverage_filename(data_folder, adaID, fragment))
covs[fragment] = coverage
counts = np.load(get_allele_counts_filename(data_folder, adaID, fragment))
(counts_major,
counts_minor,
counts_minor2) = get_minor_allele_counts(counts, n_minor=2)
# Get minor allele frequencies and identities
nu_minor = 1.0 * counts_minor[:, :, 1] / (coverage + 1e-6)
nus_minor[fragment] = nu_minor
all_minor = counts_minor[:, :, 0]
alls_minor[fragment] = all_minor
# Filter the minor frequencies by comparing the read types
try:
nu_filtered = np.load(get_allele_frequencies_filename(data_folder, adaID, fragment))
except IOError:
nu_filtered = filter_nus(counts, coverage)
nut = np.zeros(nu_filtered.shape[-1])
for pos, nupos in enumerate(nu_filtered.T):
nut[pos] = np.sort(nupos)[-2]
nus_filtered[fragment] = nu_filtered
nus_minor_filtered[fragment] = nut
# Plot them
(n_plots_y, n_plots_x) = plot_grid[len(fragments) - 1]
fig, axs = plt.subplots(n_plots_y, n_plots_x, figsize=(13, 8))
if len(fragments) > 1:
axs = axs.ravel()
else:
axs = [axs]
fig.suptitle('adapterID '+adaID, fontsize=20)
labss = {'read1 f': 'read1 fwd', 'read1 r': 'read1 rev',
'read2 f': 'read2 fwd', 'read2 r': 'read2 rev'}
for i, fragment in enumerate(fragments):
ax = axs[i]
ax.set_yscale('log')
ax.set_title(fragment)
if i in [0, 3]:
ax.set_ylabel(r'$\nu$')
if i > 2:
ax.set_xlabel('Position')
# Plot divided by readtype
for js, nu_minorjs in enumerate(nus_minor[fragment]):
color = cm.jet(int(255.0 * js / len(read_types)))
ax.plot(nu_minorjs, lw=1.5, c=color, label=labss[read_types[js]])
ax.scatter(np.arange(len(nu_minorjs)), nu_minorjs, lw=1.5,
color=color)
# Plot filtered
ax.plot(nus_minor_filtered[fragment], lw=1.5, c='k',
alpha=0.5, label='Filtered')
ax.scatter(np.arange(len(nus_minor_filtered[fragment])),
nus_minor_filtered[fragment], lw=1.5, c='k',
alpha=0.5)
# Plot 1/max(coverage)
coverage = covs[fragment]
cov_tot = coverage.sum(axis=0)
ax.plot(1.0 / cov_tot, lw=1.2, c='r', label='Detection limit')
ax.set_xlim(-100, len(nu_minorjs) + 100)
plt.grid()
plt.legend(loc='upper right')
plt.tight_layout(rect=(0, 0, 1, 0.95))
if savefig:
outputfile = gff(data_folder, adaID, fragment)
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
def plot_minor_allele_frequency_filtered(data_folder, adaID, fragments, VERBOSE=0,
savefig=False):
'''Plot minor allele frequency along the genome'''
from hivwholeseq.sequencing.filenames import get_minor_allele_frequency_figure_filename as gff
import matplotlib
params = {'axes.labelsize': 20,
'text.fontsize': 20,
'legend.fontsize': 8,
'xtick.labelsize': 16,
'ytick.labelsize': 16,
'text.usetex': False}
matplotlib.rcParams.update(params)
from matplotlib import cm
import matplotlib.pyplot as plt
# Store in globals structures
covs = {}
nus_minor_filtered = {}
for fragment in fragments:
coverage = np.load(get_coverage_filename(data_folder, adaID, fragment))
covs[fragment] = coverage
try:
nu_filtered = np.load(get_allele_frequencies_filename(data_folder,
adaID, fragment))
except IOError:
counts = np.load(get_allele_counts_filename(data_folder, adaID, fragment))
nu_filtered = filter_nus(counts)
nut = np.zeros(nu_filtered.shape[-1])
for pos, nupos in enumerate(nu_filtered.T):
nut[pos] = np.sort(nupos)[-2]
nus_minor_filtered[fragment] = nut
# Plot them
plot_grid = [(1, 1), (1, 2), (1, 3), (2, 2), (1, 5), (2, 3)]
(n_plots_y, n_plots_x) = plot_grid[len(fragments) - 1]
fig, axs = plt.subplots(n_plots_y, n_plots_x, figsize=(13, 8))
if len(fragments) > 1:
axs = axs.ravel()
else:
axs = [axs]
fig.suptitle('adapterID '+adaID, fontsize=20)
for i, fragment in enumerate(fragments):
ax = axs[i]
ax.set_yscale('log')
ax.set_title(fragment)
if i in [0, 3]:
ax.set_ylabel(r'$\nu$')
if i > 2:
ax.set_xlabel('Position')
# Plot filtered
ax.plot(nus_minor_filtered[fragment], lw=1.5, c='k',
alpha=0.5, label='Filtered')
ax.scatter(np.arange(len(nus_minor_filtered[fragment])),
nus_minor_filtered[fragment], lw=1.5, c='k',
alpha=0.5)
ax.set_xlim(-100, len(nus_minor_filtered[fragment]) + 100)
#plt.legend(loc='upper right')
plt.tight_layout(rect=(0, 0, 1, 0.95))
if savefig:
outputfile = gff(data_folder, adaID, fragment, only_filtered=True)
fig.savefig(outputfile)
plt.close(fig)
else:
plt.ion()
plt.show()
