def write_counts_files(data_folder, adaID, fragment, counts, inserts, coverage=None, VERBOSE=0):
"""Write allele counts, inserts, and coverage to file"""
if VERBOSE >= 1:
print "Write to file: " + adaID + " " + fragment
if coverage is None:
coverage = counts.sum(axis=1)
# Save counts and coverage
counts.dump(get_allele_counts_filename(data_folder, adaID, fragment))
coverage.dump(get_coverage_filename(data_folder, adaID, fragment))
# Convert inserts to normal nested dictionary for pickle
inserts_dic = {k: dict(v) for (k, v) in inserts.iteritems()}
with open(get_insert_counts_filename(data_folder, adaID, fragment), "w") as f:
pickle.dump(inserts_dic, f, protocol=-1)
def write_counts_files(data_folder,
adaID,
fragment,
counts,
inserts,
coverage=None,
VERBOSE=0):
'''Write allele counts, inserts, and coverage to file'''
if VERBOSE >= 1:
print 'Write to file: ' + adaID + ' ' + fragment
if coverage is None:
coverage = counts.sum(axis=1)
# Save counts and coverage
counts.dump(get_allele_counts_filename(data_folder, adaID, fragment))
coverage.dump(get_coverage_filename(data_folder, adaID, fragment))
# Convert inserts to normal nested dictionary for pickle
inserts_dic = {k: dict(v) for (k, v) in inserts.iteritems()}
with open(get_insert_counts_filename(data_folder, adaID, fragment),
'w') as f:
pickle.dump(inserts_dic, f, protocol=-1)
if not fragments:
fragments = ['F' + str(i) for i in xrange(1, 7)]
if VERBOSE >= 3:
print 'fragments', fragments
# Iterate over samples and fragments
for adaID in adaIDs:
for fragment in fragments:
consensus = SeqIO.read(
get_consensus_filename(data_folder, adaID, fragment), 'fasta')
cmat = np.array(consensus)
counts = np.load(
get_allele_counts_filename(data_folder, adaID, fragment))
coverage = np.load(
get_coverage_filename(data_folder, adaID, fragment))
nu = filter_nus(counts, coverage, VERBOSE=VERBOSE)
# Note: not-covered positions are filtered, but argmax cannot work
# with masked arrays
cmat_af = alpha[nu.argmax(axis=0)]
if hasattr(nu, 'mask'):
cmat_af[nu.mask.all(axis=0)] = 'N'
# Check for consistency first
if len(cmat) != len(cmat_af):
print 'Consensus has a different length from allele frequency \
matrix... WTF?'
# Do not actually align, it makes a huge mess (we miss mistakes)
ali = [cmat, cmat_af]
def check_overlap_allele_frequencies(data_folder, adaID, frag1, frag2, overlap,
VERBOSE=0, ax=None):
'''Check biases in allele frequencies in the overlap'''
(start_s2, end_s1, ali) = overlap
# Get allele counts and coverage
cou1 = np.load(get_allele_counts_filename(data_folder, adaID, frag1))
cov1 = np.load(get_coverage_filename(data_folder, adaID, frag1))
cou2 = np.load(get_allele_counts_filename(data_folder, adaID, frag2))
cov2 = np.load(get_coverage_filename(data_folder, adaID, frag2))
# Cut the counts and coverage to the overlap region
cou1 = cou1[:, :, start_s2:]
cov1 = cov1[:, start_s2:]
cou2 = cou2[:, :, :end_s1]
cov2 = cov2[:, :end_s1]
# Reduce the allele counts (fwd and rev have different status on most overlaps,
# because of the uneven coverage)
nu1 = filter_nus(cou1, cov1)
nu2 = filter_nus(cou2, cov2)
# FIXME
if nu1.shape != nu2.shape:
return
# Print table of called polymorphisms
print 'adaID', adaID, frag1, frag2, 'polymorphism matrix (NO | YES)'
print 3 * ' ', '|', '{:^10s}'.format(frag1)
print 15 * '-'
print 3 * ' ', '|', \
'{:3d}'.format(((nu1 < 1e-6) & (nu2 < 1e-6)).sum()), '|', \
'{:3d}'.format(((nu1 > 3e-3) & (nu2 < 1e-6)).sum())
print '{:3s}'.format(frag2), '+'+(5*'-')+'+'+(4*'-')
print 3 * ' ', '|', \
'{:3d}'.format(((nu1 < 1e-6) & (nu2 > 3e-3)).sum()), '|', \
'{:3d}'.format(((nu1 > 3e-6) & (nu2 > 3e-3)).sum())
# Plot scatter
import matplotlib.pyplot as plt
from matplotlib import cm
if ax is None:
show_plot = True
fig, ax = plt.subplots(1, 1, figsize=(6, 6))
ax.set_title('allele frequencies, adaID '+str(adaID)+', '+\
str(frag1)+' - '+str(frag2),
fontsize=18)
else:
show_plot = False
ax.set_title(str(frag1)+' - '+str(frag2), fontsize=18)
ax.scatter(np.abs(nu1 - 1e-5), np.abs(nu2 - 1e-5), s=30,
c=cm.jet([int(255.0 * i / len(nu1)) for i in xrange(len(nu1))]))
# Plot diagonal
ax.plot([1e-7, 2], [1e-7, 2], lw=1, c='k', ls='--')
ax.set_xlabel(r'$\nu_1$', fontsize=20)
ax.set_ylabel(r'$\nu_2$', fontsize=20)
ax.set_xscale('log')
ax.set_yscale('log')
ax.set_xlim(0.7e-5, 1.2)
ax.set_ylim(0.7e-5, 1.2)
if show_plot:
plt.tight_layout(w_pad=0.05)
plt.ion()
plt.show()
# If the script is called with no fragment, iterate over all
if not fragments:
fragments = ['F'+str(i) for i in xrange(1, 7)]
if VERBOSE >= 3:
print 'fragments', fragments
# Iterate over samples and fragments
for adaID in adaIDs:
for fragment in fragments:
consensus = SeqIO.read(get_consensus_filename(data_folder, adaID, fragment),
'fasta')
cmat = np.array(consensus)
counts = np.load(get_allele_counts_filename(data_folder, adaID, fragment))
coverage = np.load(get_coverage_filename(data_folder, adaID, fragment))
nu = filter_nus(counts, coverage, VERBOSE=VERBOSE)
# Note: not-covered positions are filtered, but argmax cannot work
# with masked arrays
cmat_af = alpha[nu.argmax(axis=0)]
if hasattr(nu, 'mask'):
cmat_af[nu.mask.all(axis=0)] = 'N'
# Check for consistency first
if len(cmat) != len(cmat_af):
print 'Consensus has a different length from allele frequency \
matrix... WTF?'
# Do not actually align, it makes a huge mess (we miss mistakes)
ali = [cmat, cmat_af]
def check_overlap_allele_frequencies(data_folder, adaID, frag1, frag2, overlap, VERBOSE=0, ax=None):
"""Check biases in allele frequencies in the overlap"""
(start_s2, end_s1, ali) = overlap
# Get allele counts and coverage
cou1 = np.load(get_allele_counts_filename(data_folder, adaID, frag1))
cov1 = np.load(get_coverage_filename(data_folder, adaID, frag1))
cou2 = np.load(get_allele_counts_filename(data_folder, adaID, frag2))
cov2 = np.load(get_coverage_filename(data_folder, adaID, frag2))
# Cut the counts and coverage to the overlap region
cou1 = cou1[:, :, start_s2:]
cov1 = cov1[:, start_s2:]
cou2 = cou2[:, :, :end_s1]
cov2 = cov2[:, :end_s1]
# Reduce the allele counts (fwd and rev have different status on most overlaps,
# because of the uneven coverage)
nu1 = filter_nus(cou1, cov1)
nu2 = filter_nus(cou2, cov2)
# FIXME
if nu1.shape != nu2.shape:
return
# Print table of called polymorphisms
print "adaID", adaID, frag1, frag2, "polymorphism matrix (NO | YES)"
print 3 * " ", "|", "{:^10s}".format(frag1)
print 15 * "-"
print 3 * " ", "|", "{:3d}".format(((nu1 < 1e-6) & (nu2 < 1e-6)).sum()), "|", "{:3d}".format(
((nu1 > 3e-3) & (nu2 < 1e-6)).sum()
)
print "{:3s}".format(frag2), "+" + (5 * "-") + "+" + (4 * "-")
print 3 * " ", "|", "{:3d}".format(((nu1 < 1e-6) & (nu2 > 3e-3)).sum()), "|", "{:3d}".format(
((nu1 > 3e-6) & (nu2 > 3e-3)).sum()
)
# Plot scatter
import matplotlib.pyplot as plt
from matplotlib import cm
if ax is None:
show_plot = True
fig, ax = plt.subplots(1, 1, figsize=(6, 6))
ax.set_title("allele frequencies, adaID " + str(adaID) + ", " + str(frag1) + " - " + str(frag2), fontsize=18)
else:
show_plot = False
ax.set_title(str(frag1) + " - " + str(frag2), fontsize=18)
ax.scatter(
np.abs(nu1 - 1e-5), np.abs(nu2 - 1e-5), s=30, c=cm.jet([int(255.0 * i / len(nu1)) for i in xrange(len(nu1))])
)
# Plot diagonal
ax.plot([1e-7, 2], [1e-7, 2], lw=1, c="k", ls="--")
ax.set_xlabel(r"$\nu_1$", fontsize=20)
ax.set_ylabel(r"$\nu_2$", fontsize=20)
ax.set_xscale("log")
ax.set_yscale("log")
ax.set_xlim(0.7e-5, 1.2)
ax.set_ylim(0.7e-5, 1.2)
if show_plot:
plt.tight_layout(w_pad=0.05)
plt.ion()
plt.show()
if reads[0].isize < 300:
continue
for read in reads:
if read.seq.find(primer_new) != -1:
cov_new += 1
if read.seq.find(primer_old) != -1:
cov_old += 1
print 'old:', cov_old, 'new:', cov_new
bamfile.close()
# Get coverage and see
covfn = get_coverage_filename(data_folder, adaID, fragment)
cov = np.load(covfn)
import matplotlib.pyplot as plt
import matplotlib.cm as cm
for js, read_type in enumerate(read_types):
plt.plot(np.arange(cov.shape[1]), cov[js], lw=2,
c=cm.jet(int(255.0 * js / len(read_types))))
plt.xlabel('Position [bases]')
plt.title(str(adaID)+' '+fragment)
plt.ylabel('Coverage')
plt.ion()
plt.show()
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()