'''
Created on Sep 7, 2012
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
grapher = SeqGrapher()
base_dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
base_dirpath = grapher.get_path(base_dirpath)
dirpath = grapher.get_filename(base_dirpath, 'motifs')
filename = grapher.get_filename(dirpath, 'transcript_vectors.txt')
data = grapher.import_file(filename)
# Boxplots for gr_dex peaks by lfc in Dex
if False:
#data = data[data['distal'] == 't']
data = data[data['has_refseq'] == 1]
down = data[data['dex_1_lfc'] <= -1]
up = data[data['dex_1_lfc'] >= 1]
nc = data[abs(data['dex_1_lfc']) < 1]
key = 'p65_kla_tag_count'
datasets = [down[key],nc[key],up[key]]
datasets = [d['p65_kla_dex_tag_count'] - d[key] for d in [down, nc, up]]
'''
Created on Jan 30, 2013
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from collections import OrderedDict
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/'
dirpath = yzer.get_path(dirpath)
data_dirpath = yzer.get_filename(dirpath, 'enhancer_rewiring_lfc')
transcripts = yzer.import_file(
yzer.get_filename(dirpath, 'enhancer_sets', 'transcript_vectors.txt'))
sets = OrderedDict((
('all',
yzer.import_file(yzer.get_filename(data_dirpath, 'all_vectors.cdt'))),
#('all_6h', yzer.import_file(yzer.get_filename(data_dirpath,'kla_6h','all_vectors.cdt'))),
('rewired',
yzer.import_file(
yzer.get_filename(data_dirpath, 'rewired_vectors.cdt'))),
#('rewired_6h', yzer.import_file(yzer.get_filename(data_dirpath,'kla_6h','rewired_vectors.cdt'))),
('shared',
yzer.import_file(yzer.get_filename(data_dirpath,
'shared_vectors.cdt'))),
))
for key, val in sets.items():
'''
Created on Mar 4, 2013
@author: karmel
'''
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/NOD_BALBc/ThioMacs/Analysis_2013_02/'
dirpath_bmdc = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/NOD_BALBc/BMDCs/Analysis_2013_03/'
dirpath = yzer.get_path(dirpath)
dirpath_bmdc = yzer.get_path(dirpath_bmdc)
img_dirpath = yzer.get_and_create_path(dirpath, 'bmdc_vs_thiomac')
thio = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
bmdc = yzer.import_file(
yzer.get_filename(dirpath_bmdc, 'transcript_vectors.txt'))
sets = []
for data in (thio, bmdc):
data = data.fillna(0)
refseq = yzer.get_refseq(data)
# Remove low tag counts
#refseq = refseq[refseq['transcript_score'] >= 4]
'''
Created on Jun 26, 2012
@author: karmel
'''
from glasslab.dataanalysis.misc.gr_project_2012.elongation import set_up_sequencing_run_ids, \
get_sequencing_run_id_sets, get_rep_string, total_tags_per_run
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer
if __name__ == '__main__':
grapher = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = grapher.get_path(dirpath)
filename = grapher.get_filename(dirpath, 'transcript_vectors.txt')
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)),
'''
Created on Jul 2, 2014
@author: karmel
We want to compare acetylation at various subsets of me2 enhancers.
'''
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/AND_TCR/Analysis/Chips1_2_3/Motifs'
dirpath = yzer.get_path(dirpath)
savepath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/AND_TCR/Analysis/Chips1_2_3/Figures/Acetyl_box_plots'
savepath = yzer.get_path(savepath)
if False:
peptide, ab = 'PCC', 'me2'
pep_dirpath = yzer.get_filename(dirpath, '{}_{}'.format(peptide, ab))
filename = yzer.get_filename(
pep_dirpath, '{}_{}_enhancers_with_ac.txt'.format(peptide, ab))
data = yzer.import_file(filename)
data = data.fillna(0)
de_novo = data[data['no_pep_tag_count'] == 0]
established = data[data['no_pep_tag_count'] > 0]
'''
Created on Apr 3, 2012
@author: karmel
'''
from __future__ import division
import os
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = yzer.get_path('/karmel/Desktop/Projects/Classes/Rotations/Winter 2012/Endpoint analysis/for_minna/')
filename = os.path.join(dirpath, 'merged_h3k4me2_notx.txt')
data = yzer.import_file(filename)
data['rpkm'] = 1000*data['trans']/data['width']
data = data.fillna(0)
data = data[data['refseq'] == 0]
me2_tf = data[(data['pu_1'] + data['cebpa'] + data['p65'] > 0) &
(data['ctcf'] == 0) &
(data['k27'] == 0) & (data['me2'] > 0) ]
ctcf_tf = data[(data['pu_1'] + data['cebpa'] + data['p65'] > 0) &
(data['ctcf'] > 0) &
(data['k27'] == 0) & (data['me2'] == 0) ]
'''
Created on Mar 23, 2012
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
import os
from scipy.stats.stats import ttest_ind
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
