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')
Created on Mar 23, 2012
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
import os
if __name__ == '__main__':
grapher = SeqGrapher()
dirpath = '/Users/karmel/Desktop/Projects/GlassLab/Notes_and_Reports/NOD_BALBc/BMDCs/Analysis/'
filename = os.path.join(dirpath, 'balbc_nod_vectors.txt')
data = grapher.import_file(filename)
# vs balbc counterpart
data = grapher.normalize(data, 'nod_notx_0h_tag_count', 2.790489)
data = grapher.normalize(data, 'diabetic_nod_notx_0h_tag_count', 1.083990)
data = grapher.normalize(data, 'slow_diabetic_nod_notx_0h_tag_count',
0.349747)
# Vs nod notx
data = grapher.normalize(data,
'diabetic_nod_notx_0h_tag_count',
0.483232,
suffix='_norm_2')
data = grapher.normalize(data,
'slow_diabetic_nod_notx_0h_tag_count',
0.276080,
suffix='_norm_2')
refseq = grapher.get_refseq(data)
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/CD4TCells_Finland_2012/Analysis_2013_02'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'with_me3',
'basic_scatterplots')
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data = data.fillna(0)
data = data[data['naive_me3_tag_count'] + data['act_me3_tag_count'] > 0]
for key1, key2, norm_factor in comparison_sets:
name1 = pretty_names[key1[:-1]] + key1[-1:]
name2 = pretty_names[key2[:-1]] + key2[-1:]
data_normed = yzer.normalize(data, key2 + '_tag_count', norm_factor)
ax = yzer.scatterplot(
data_normed,
key1 + '_tag_count',
key2 + '_tag_count_norm',
log=True,
color='blue',
title='{0} versus {1} Normalized Tag Counts'.format(name1, name2),
xlabel='{0} tags in RefSeq transcripts'.format(name1),
ylabel='{0} tags in RefSeq transcripts, normalized'.format(name2),
add_noise=False,
show_2x_range=True,
show_legend=False,
plot_regression=False,
show_count=True,
show_correlation=True,
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
if __name__ == '__main__':
yzer = SeqGrapher()
yzer.fig_size = 15
yzer.disable_show_plot = True
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/NOD_BALBc/ThioMacs/Analysis_2013_02/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'refseq_expression')
data = yzer.import_file(yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data = data.fillna(0)
data = yzer.normalize(data, 'nod_notx_1h_tag_count', 1.095436)
data = yzer.normalize(data, 'nod_kla_1h_tag_count', 0.652898)
#data = yzer.normalize(data, 'nonplated_diabetic_nod_notx_tag_count', 0.885427)
#data = yzer.normalize(data, 'nonplated_diabetic_balb_notx_tag_count', 0.645579)
data['balb_notx_1h_reads_per_base'] = data['balb_notx_1h_tag_count']/data['length']
data['balb_kla_1h_reads_per_base'] = data['balb_kla_1h_tag_count']/data['length']
data['balb_notx_1h_tag_count'] = nonzero(data['balb_notx_1h_tag_count'])
data['nod_notx_1h_tag_count_norm'] = nonzero(data['nod_notx_1h_tag_count_norm'])
data['balb_kla_1h_tag_count'] = nonzero(data['balb_kla_1h_tag_count'])
data['nod_kla_1h_tag_count_norm'] = nonzero(data['nod_kla_1h_tag_count_norm'])
data = data[data['transcript_score'] >= 4]
data = data[data[['balb_notx_1h_tag_count','nod_notx_1h_tag_count_norm',
'balb_kla_1h_tag_count','nod_kla_1h_tag_count_norm']].max(axis=1) >= 10]
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
import os
from scipy.stats.stats import ttest_ind
if __name__ == '__main__':
grapher = SeqGrapher()
dirpath = '/Volumes/karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Inbred strains/Peak comparisons/Compared with NOD/'
filename = os.path.join(dirpath, 'bl6_gt_balb_with_nod_pu_1_unique.txt')
data = grapher.import_file(filename)
data = data.fillna(0) # For easy log graphing
wt_peaks, balb_peaks, nod_peaks, balb2_peaks = 67074, 79353, 107716, 94199
data = grapher.normalize(data, 'balb_pu_1_tag_count',
1) #balb_peaks/wt_peaks)
data = grapher.normalize(data, 'nod_pu_1_tag_count',
1) #nod_peaks/wt_peaks)
data = grapher.normalize(data, 'balb2_pu_1_tag_count',
1) #balb2_peaks/wt_peaks)
for i, row in data[data['wt_pu_1_tag_count'] < 20].iterrows():
data['wt_pu_1_tag_count'][i] = 0
for i, row in data[data['balb_pu_1_tag_count_norm'] < 20].iterrows():
data['balb_pu_1_tag_count_norm'][i] = 0
for i, row in data[data['nod_pu_1_tag_count_norm'] < 20].iterrows():
data['nod_pu_1_tag_count_norm'][i] = 0
data[
'wt_to_balb'] = data['wt_pu_1_tag_count'] / data['balb_pu_1_tag_count']
data['nod_to_balb'] = data['nod_pu_1_tag_count'] / data[
if __name__ == '__main__':
grapher = SeqGrapher()
dirpath = grapher.get_path(
'/karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Inbred strains/Groseq comparisons/'
)
filename = os.path.join(dirpath, 'groseq_with_h3k4me2.txt')
data = grapher.import_file(filename)
data = data.fillna(0)
nod_norm, balb_norm = 0.393529, 0.359488
nod_to_balb_norm = 1.102844
data = grapher.normalize(data, 'balb_tag_count', nod_norm)
data = grapher.normalize(data, 'nod_tag_count', balb_norm)
print len(data)
data['nod_with_bl6'] = data['nod_sv_id'] <= .1
nod_with_bl6 = data[data['nod_with_bl6'] == True]
nod_with_balb = data[data['nod_with_bl6'] == False]
nod_with_bl6 = grapher.collapse_strands(nod_with_bl6)
nod_with_balb = grapher.collapse_strands(nod_with_balb)
nod_with_bl6 = nod_with_bl6[nod_with_bl6['wt_peak_tag_count'] > 2 *
nod_with_bl6['balb_peak_tag_count']]
nod_with_balb = nod_with_balb[nod_with_balb['wt_peak_tag_count'] > 2 *
nod_with_balb['balb_peak_tag_count']]
