Plot supplementary figure showing Hah et al error rates
against MAX EDGE values when Vespucci is built without knowledge
of RefSeq boundaries.
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/NAR_review_data/no_refseq'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'plots')
ax = yzer.set_up_plot()
title = 'Benchmarking without Foreknowledge of RefSeq'
yzer.add_title(title, ax)
yzer.add_axis_labels('MAX_EDGE value',
'Error rate defined by Hah et al. (%)')
max_edges = [100, 500, 1000, 4000, 5000, 5500, 6000, 10000]
error_rates = [
0.388551822833, 0.372390444765, 0.263807982126, 0.124663089396,
0.121784970634, 0.121807917409, 0.123263849815, 0.142530838464
]
error_pcts = [e * 100 for e in error_rates]
yzer.plot(max_edges, error_pcts, '-o')
yzer.save_plot_with_dir(save_dir=img_dirpath, title=title)
yzer.show_plot()
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/NAR_review_data/parameters'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'success_rates')
multipliers = [1000, 10000, 20000, 50000, 100000]
datasets = OrderedDict()
for m in multipliers:
datasets[m] = pandas.read_csv(yzer.get_filename(
dirpath, 'vs_gro5', 'gro5_count_dm_{}.txt'.format(m)),
header=0,
sep='\t')
success_rates = []
for m, data in datasets.iteritems():
print 'Stats for DENSITY_MULTIPLIER = {}'.format(m)
exactly_1 = sum(data['count'] == 1)
greater_than_1 = sum(data['count'] > 1)
success_rate = (exactly_1 - greater_than_1) / len(data)
success_rates.append(success_rate)
print success_rate
ax = yzer.set_up_plot()
title = 'Transcript initiation recapture versus DENSITY_MULTIPLIER'
yzer.add_title(title, ax)
yzer.add_axis_labels('DENSITY_MULTIPLIER value',
'Initiation recapture rate')
yzer.plot(multipliers, success_rates, '-o')
yzer.save_plot_with_dir(save_dir=img_dirpath, title=title)
yzer.show_plot()
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/NAR_review_data/parameters'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'success_rates')
edges = [100, 200, 500, 800, 1000, 1500, 2000, 5000]
datasets = OrderedDict()
for e in edges:
datasets[e] = pandas.read_csv(yzer.get_filename(
dirpath, 'vs_gro5', 'gro5_count_me_{}.txt'.format(e)),
header=0,
sep='\t')
success_rates = []
for e, data in datasets.iteritems():
print 'Stats for MAX_EDGE = {}'.format(e)
exactly_1 = sum(data['count'] == 1)
greater_than_1 = sum(data['count'] > 1)
success_rate = (exactly_1 - greater_than_1) / len(data)
success_rates.append(success_rate)
print success_rate
ax = yzer.set_up_plot()
title = 'Transcript initiation recapture versus MAX_EDGE'
yzer.add_title(title, ax)
yzer.add_axis_labels('MAX_EDGE value', 'Initiation recapture rate')
yzer.plot(edges, success_rates, '-o')
yzer.save_plot_with_dir(save_dir=img_dirpath, title=title)
yzer.show_plot()
x_labels = [5] + range(11, 22)
x_vals = range(len(x_labels))
ctl_y = [
100, 100, 100, 100, 87.5, 87.5, 87.5, 87.5, 75, 75, 75, 75, 62.5, 62.5,
37.5, 37.5
]
ctl_x = [0, 1, 2, 3, 3, 4, 5, 6, 6, 7, 8, 9, 9, 10, 10, 11]
low_y = [100, 100, 75, 75, 75, 75, 75, 50, 50, 50, 50, 50, 50, 50]
low_x = [0, 1, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 10, 11]
med_y = [100, 100, 100, 75, 75, 50, 50, 50, 50, 25, 25, 25, 25, 25, 25]
med_x = [0, 1, 2, 2, 3, 3, 4, 5, 6, 6, 7, 8, 9, 10, 11]
high_y = [100, 100, 100, 100, 75, 75, 50, 50, 50, 50, 50, 50, 25, 25, 25]
high_x = [0, 1, 2, 3, 3, 4, 4, 5, 6, 7, 8, 9, 9, 10, 11]
ax = yzer.set_up_plot()
yzer.add_axis_labels('Week', 'Percent Normoglycemic')
title = 'Diabetes Induction with In Vivo TDB Treatment'
yzer.add_title(title, ax)
pyplot.plot(ctl_x,
ctl_y,
'o-',
color='black',
label='Control (n=8)',
linewidth=8)
pyplot.plot(low_x,
low_y,
'o-',
color='blue',
label='Low Dose TDB (107 ug, n=4)',
linewidth=6)
