def plot_cumulative_histogram(data_folder, adaID, fragment, insert_sizes,
title=None,
ax=None,
show=False, savefig=False,
**kwargs):
'''Plot cumulative histogram of insert sizes'''
import matplotlib.pyplot as plt
if ax is None:
fig, ax = plt.subplots(1, 1)
ax.plot(insert_sizes, np.linspace(0, 1, len(insert_sizes)), **kwargs)
ax.set_xlabel('Insert size')
ax.set_ylabel('Cumulative fraction')
ax.set_xlim(-1, 1000)
ax.set_ylim(-0.02, 1.02)
if title is not None:
ax.set_title(title)
plt.tight_layout()
if show:
plt.ion()
plt.show()
if savefig:
output_filename = get_insert_size_distribution_cumulative_filename(data_folder,
adaID,
fragment)
from hivwholeseq.utils.generic import mkdirs
from hivwholeseq.sequencing.filenames import get_figure_folder
mkdirs(get_figure_folder(data_folder, adaID))
fig.savefig(output_filename)
def report_insert_size(data_folder, adaID, seq_run, VERBOSE=0, summary=True):
'''Produce figures of the insert size distribution'''
from hivwholeseq.sequencing.check_insert_distribution import get_insert_size_distribution, \
plot_cumulative_histogram, plot_histogram
bins = np.linspace(0, 1000, 100)
isz, h = get_insert_size_distribution(
data_folder,
adaID,
'premapped',
bins=bins,
maxreads=10000,
VERBOSE=VERBOSE)
plot_cumulative_histogram(
data_folder,
adaID,
'premapped',
isz,
savefig=True,
title='run ' + str(seq_run) + ', adaID ' + str(adaID) + ', premap',
lw=2,
c='b')
plot_histogram(
data_folder,
adaID,
'premapped',
h,
savefig=True,
title='run ' + str(seq_run) + ', adaID ' + str(adaID) + ', premap',
lw=2,
color='b')
if summary:
with open(get_premap_summary_filename(data_folder, adaID), 'a') as f:
f.write('\nInsert size distribution plotted:\n')
f.write(
get_insert_size_distribution_cumulative_filename(
data_folder, adaID, 'premapped') + '\n')
f.write(
get_insert_size_distribution_filename(data_folder, adaID,
'premapped') + '\n')
def report_insert_size(data_folder, adaID, seq_run, VERBOSE=0, summary=True):
'''Produce figures of the insert size distribution'''
from hivwholeseq.sequencing.check_insert_distribution import get_insert_size_distribution, \
plot_cumulative_histogram, plot_histogram
bins = np.linspace(0, 1000, 100)
isz, h = get_insert_size_distribution(data_folder,
adaID,
'premapped',
bins=bins,
maxreads=10000,
VERBOSE=VERBOSE)
plot_cumulative_histogram(data_folder,
adaID,
'premapped',
isz,
savefig=True,
title='run ' + str(seq_run) + ', adaID ' +
str(adaID) + ', premap',
lw=2,
c='b')
plot_histogram(data_folder,
adaID,
'premapped',
h,
savefig=True,
title='run ' + str(seq_run) + ', adaID ' + str(adaID) +
', premap',
lw=2,
color='b')
if summary:
with open(get_premap_summary_filename(data_folder, adaID), 'a') as f:
f.write('\nInsert size distribution plotted:\n')
f.write(
get_insert_size_distribution_cumulative_filename(
data_folder, adaID, 'premapped') + '\n')
f.write(
get_insert_size_distribution_filename(data_folder, adaID,
'premapped') + '\n')
