def get_allele_frequency_trajectories(pname,
samples,
fragment,
qual_min=30,
VERBOSE=0):
'''Scan the reads of all samples and write to a single file'''
if VERBOSE >= 1:
print 'Getting allele frequency trajectories:', pname, fragment
from hivwholeseq.patients.filenames import get_initial_reference_filename, \
get_mapped_to_initial_filename, get_allele_frequency_trajectories_filename, \
get_allele_count_trajectories_filename
from hivwholeseq.utils.one_site_statistics import get_allele_counts_insertions_from_file, \
get_allele_counts_insertions_from_file_unfiltered, \
filter_nus
refseq = SeqIO.read(get_initial_reference_filename(pname, fragment),
'fasta')
# Prepare output data structures
cos_traj = np.zeros((len(samples), len(alpha), len(refseq)), int)
nus_traj = np.zeros((len(samples), len(alpha), len(refseq)))
for it, sample in enumerate(samples):
if VERBOSE >= 2:
print pname, it, sample
input_filename = get_mapped_to_initial_filename(pname,
sample,
fragment,
type='bam')
(counts, inserts) = get_allele_counts_insertions_from_file_unfiltered(
input_filename, len(refseq), qual_min=qual_min, VERBOSE=VERBOSE)
# Take the total counts, blending in the read types
cou = counts.sum(axis=0)
cos_traj[it] = cou
# Take the filtered frequencies, blending in the read types
nu = filter_nus(counts)
nus_traj[it] = nu
#FIXME: test, etc.
return (cos_traj, nus_traj)
summary=summary)
continue
# Get coverage and counts
counts = np.load(
get_allele_counts_filename(data_folder, adaID, fragment))
if len(counts.shape) == 2:
import warnings
warnings.warn(
'Counts not divided by read type: will normalize instead of filter!'
)
nu_filtered = 1.0 * counts / counts.sum(axis=0)
else:
# Filter the minor frequencies by comparing the read types
nu_filtered = filter_nus(counts)
# Write output
write_frequency_files(data_folder,
adaID,
fragment,
nu_filtered,
VERBOSE=VERBOSE)
if summary:
import matplotlib.pyplot as plt
was_interactive = plt.isinteractive()
plt.ioff()
plot_SFS_folded(data_folder,
adaID,
fragment,
# Iterate over all requested samples
for samplename, sample in samples.iterrows():
sample = SampleSeq(sample)
adaID = sample.adapter
if not fragments:
fragments_sample = sample.regions_generic
else:
fragments_sample = sorted(set(fragments) & set(sample.regions_generic))
for fragment in fragments_sample:
# Submit to the cluster self if requested
if submit:
fork_self(seq_run, adaID, fragment, VERBOSE=VERBOSE)
continue
counts, inserts = get_allele_counts(data_folder, adaID, fragment, VERBOSE=VERBOSE)
write_counts_files(data_folder, adaID, fragment, counts, inserts, VERBOSE=VERBOSE)
if summary:
plot_coverage(data_folder, adaID, fragment, counts, VERBOSE=VERBOSE, savefig=True)
if write_frequencies:
nu_filtered = filter_nus(counts)
write_frequency_files(data_folder, adaID, fragment, nu_filtered, VERBOSE=VERBOSE)
if summary:
plot_SFS_folded(data_folder, adaID, fragment, nu_filtered, VERBOSE=VERBOSE, savefig=True)
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()
