data = grapher.import_file(filename)
run_ids = set_up_sequencing_run_ids()
dmso, kla, kla_dex, all_dmso, all_kla, all_kla_dex = get_sequencing_run_id_sets(
)
total_tags = total_tags_per_run()
# Norm sum scalars listed for all, group 1, group 2, group 3, group 4
kla_scalars = [1.223906, 1.281572, 1.118363, 1.104860, 1.503260]
kla_dex_scalars = [1.182574, 1.147695, 1.248636, 1.069588, 1.388871]
dex_over_kla_scalars = [1.069073, 0.967659, 1.122628, 1.008758, 0.927466]
for i, scalar in enumerate(kla_scalars):
data = grapher.normalize(data,
'kla_{0}tag_count'.format(get_rep_string(i)),
scalar)
for i, scalar in enumerate(kla_dex_scalars):
data = grapher.normalize(
data, 'kla_dex_{0}tag_count'.format(get_rep_string(i)), scalar)
for i, scalar in enumerate(dex_over_kla_scalars):
data = grapher.normalize(data,
'kla_dex_{0}tag_count'.format(
get_rep_string(i)),
scalar,
suffix='_norm_2')
refseq = data[data['has_refseq'] != 0]
refseq = refseq[refseq['transcript_score'] >= 10]
scatter_dirpath = grapher.get_filename(dirpath, 'scatterplots')
# Minimal ratio in KLA+Dex vs. KLA pausing
try:
min_ratio = float(sys.argv[1])
except IndexError:
min_ratio = -1
try:
thresh = int(sys.argv[3])
except IndexError:
thresh = 4
grouped['relevant_sets'] = 0
rep_ids = (1, 2, 3, 4)
for replicate_id in rep_ids:
rep_str = get_rep_string(replicate_id)
primary_min = grouped['kla_{0}gene_body_lfc'.format(
rep_str)] <= min_ratio
repressed_set = grouped.ix[primary_min][
'glass_transcript_id'].values.tolist()
grouped['relevant_sets'] += primary_min.apply(int)
repressed.append(repressed_set)
print 'Genes with rep {0} KLA LFC <= {1}:'.format(
rep_str, min_ratio), len(repressed_set)
print 'Repressed in at least 4 reps:', sum(
grouped['relevant_sets'] >= 4)
def draw_elongation_profile(data,
grapher,
dirpath,
show_moving_average=True,
show_count=False):
run_ids = set_up_sequencing_run_ids()
total_tags = total_tags_per_run()
lfcs = ( #('Special', 'group_{0}'),
#('KLA','kla_{0}gene_body_lfc'),# ('KLA+Dex','kla_dex_{0}gene_body_lfc'),
('KLA+Dex over KLA', 'dex_over_kla_{0}gene_body_lfc'), )
for desc, lfc in lfcs:
for replicate_id in ('', 1, 2, 3, 4):
rep_str = get_rep_string(replicate_id)
lfc_str = lfc.format(rep_str)
# Include all transcripts at once, but only do it once.
if desc == 'Special':
datasets = [
('All RefSeq', data),
('Up > 2x in KLA, Down > 1.5x from that in Dex',
data[(data['kla_{0}gene_body_lfc'.format(rep_str)] >= 1)
& (data['dex_over_kla_{0}gene_body_lfc'.format(
rep_str)] <= -1)]),
]
else:
datasets = [
('No change in {0}'.format(desc),
data[data[lfc_str].abs() < 1]),
('Up in {0}'.format(desc), data[data[lfc_str] >= 1]),
('Down in {0}'.format(desc), data[data[lfc_str] <= -1]),
]
for label, dataset in datasets:
slug_label = label.lower().replace(' ', '_')
group_by_cols = ['basepair', 'sequencing_run_id']
data_grouped = dataset.groupby(group_by_cols,
as_index=False).sum()
groups = [
data_grouped[data_grouped['sequencing_run_id'].isin(
run_ids['dmso'][replicate_id or 0])],
data_grouped[data_grouped['sequencing_run_id'].isin(
run_ids['kla'][replicate_id or 0])],
data_grouped[data_grouped['sequencing_run_id'].isin(
run_ids['kla_dex'][replicate_id or 0])]
]
# Combine for sequencing runs now
for i, group in enumerate(groups):
groups[i] = group.groupby(['basepair'],
as_index=False).sum()
totals = zip(*total_tags.values())[replicate_id or 0]
tag_scalars = grapher.get_tag_scalars(totals)
ax = grapher.plot_tags_per_basepair(
groups,
labels=['DMSO', 'KLA', 'KLA+Dex'],
title='Tag localization for RefSeq: {0}, {1}'.format(
label,
replicate_id and 'Group {0}'.format(replicate_id)
or 'overall'),
tag_scalars=tag_scalars,
show_moving_average=show_moving_average,
show_count=show_count)
grapher.save_plot(
grapher.get_filename(
dirpath, '{0}_refseq_by_run_type_{1}.png'.format(
slug_label,
replicate_id and 'group_{0}'.format(replicate_id)
or 'all')))