'enhancer_lfc': Series(),
'kla_4h_lfc': Series(kla_4h[kla_col], index=range(len(kla_4h))),
'notx_lfc': Series(notx[kla_col], index=range(len(notx))),
}, )
df['enhancer_id'] = group['id_2'].mean()
df['enhancer_lfc'] = group['p65_tag_count_2'].mean()
if f_condition: df = df[f_condition(df)]
return df
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_sets')
img_dirpath = yzer.get_and_create_path(dirpath, 'enhancer_rewiring_lfc',
'p65_tags')
interactions = yzer.import_file(
yzer.get_filename(data_dirpath,
'transcript_pairs_refseq_with_me2.txt'))
interactions = interactions[interactions['count'] > 1]
transcripts = yzer.import_file(
yzer.get_filename(data_dirpath, 'transcript_vectors.txt'))
transcripts['kla_6h_rpbp'] = transcripts['kla_6h_tag_count'] / (
transcripts['length']) * 1000
transcripts['kla_rpbp'] = transcripts['kla_tag_count'] / (
transcripts['length']) * 1000
# Associate gene id
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from matplotlib import pyplot
from glasslab.utils.functions import nonzero
from glasslab.dataanalysis.misc.gr_project_2012.v1.elongation import total_tags_per_run
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/enhancer_classification'
dirpath = yzer.get_path(dirpath)
consistent = False
img_dirpath = yzer.get_and_create_path(
dirpath, 'boxplots_by_expression', consistent and 'consistent'
or 'rep1')
data = yzer.import_file(
yzer.get_filename(dirpath, 'enhancers_with_nearest_gene.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(
lambda s: s.replace('nod_balbc', 'gr_project_2012'))
draw_pies = True
min_tags = 30
ratio = 1.5
# Make sure we have dimethyl
data = data[data.filter(like='h3k4me2').max(axis=1) > min_tags]
data = data[data['minimal_distance'] >= 1000]
transcripts = yzer.import_file(
'''
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 Mar 11, 2013
@author: karmel
Note: Made font.weight = bold and axes.titlesize = 24, font.size = 16 in matplotlibrc
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/Demo-data'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath,
'refseq_to_homer/large_gap_500bp')
data = yzer.import_file(
yzer.get_filename(dirpath, 'refseq_tag_counts_500bp.txt'))
data['sum'] = nonzero(data['sum'].fillna(0))
homer_data = yzer.import_file(
yzer.get_filename(dirpath, 'RNA_GroSeq_CountsGenes.txt'))
homer_data['sequence_identifier'] = homer_data['Gene ID']
homer_data['homer_tag_count'] = nonzero(homer_data[
'ThioMac-GroSeq-notx-110513/ genes (Total: 12166480.0) normFactor 0.82']
.fillna(0))
homer_data = homer_data[['sequence_identifier', 'homer_tag_count']]
merged = data.merge(homer_data, how='inner', on='sequence_identifier')
merged = merged.fillna(1)
@author: karmel
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)
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
from glasslab.dataanalysis.misc.gr_project_2012.v1.enhancer_subsets_for_supershift import ucsc_link_cleanup
import numpy
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
peak_type = 'p65'
img_dirpath = yzer.get_and_create_path(dirpath, 'boxplots_non_refseq_by_{0}'.format(peak_type))
transcripts = yzer.import_file(yzer.get_filename(dirpath, 'motifs', 'transcript_vectors_with_nearby_peaks.txt'))
if True:
pu_1 = False
for ratio in (1.5, 2, 3):
data = transcripts[transcripts['refseq'] == 'f']
data = data[data['has_infrastructure'] == 0]
data = data[data['length'] < 6000]
data = data[data['dex_1_lfc'] < 1]
data = data[data['kla_1_lfc'] >= 1]
data = data[data['gr_kla_dex_tag_count'] > 0]
data = data[data['gr_fa_kla_dex_tag_count'] == 0]
print len(data)
'''
Created on Oct 26, 2012
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from matplotlib import pyplot
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/enhancer_classification'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'piecharts_for_genes_by_mechanism')
data = yzer.import_file(yzer.get_filename(dirpath, 'enhancers_with_nearest_gene.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(lambda s: s.replace('nod_balbc','gr_project_2012'))
draw_pies = True
min_tags = 30
ratio = 1.5
# Make sure we have dimethyl
data = data[data.filter(like='h3k4me2').max(axis=1) > min_tags]
data = data[data['minimal_distance'] >= 1000]
#data = yzer.collapse_strands(data)
transcripts = yzer.import_file(yzer.get_filename(dirpath, 'transcript_vectors.txt'))
transcripts['nearest_refseq_transcript_id'] = transcripts['id']
# Join, keeping all transcripts
data = data.merge(transcripts, how='left', on='nearest_refseq_transcript_id', suffixes=['','_trans'])
from random import shuffle
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/hic_domains'
dirpath = yzer.get_path(dirpath)
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(
lambda s: s.replace('nod_balbc', 'gr_project_2012'))
data = data.fillna(0)
for rep in (4, 3, 1):
img_dirpath = yzer.get_and_create_path(dirpath,
'fold_change_per_domain',
'all_transcripts',
'rep{0}'.format(rep))
kla_key = 'kla_{0}_lfc'.format(rep)
dex_kla_key = 'dex_over_kla_{0}_lfc'.format(rep)
shuffled = data['domain_id'].values.copy()
shuffle(shuffled)
data['shuffled_domain_id'] = shuffled
data['up_in_kla'] = data[kla_key] > 1
data['repressed'] = data[dex_kla_key] <= -.58
data['transrepressed'] = (data[kla_key] > 1) & (data[dex_kla_key] <=
-.58)
data['count'] = ~data[kla_key].isnull()
For those, we will sort genes in each condition by number
of interactions, and allow for null values when there is a number
mismatch.
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
import numpy
kla_col = 'kla_6h_lfc'
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_sets')
img_dirpath = yzer.get_and_create_path(dirpath,
'genes_to_average_enhancer_lfc')
keys = ('all', 'notx', 'kla', 'notx_only', 'kla_only', 'shared_enh')
if True:
interactions = yzer.import_file(
yzer.get_filename(data_dirpath,
'transcript_pairs_refseq_with_me2.txt'))
interactions = interactions[interactions['count'] > 1]
all_transcripts = yzer.import_file(
yzer.get_filename(data_dirpath, 'transcript_vectors.txt'))
transcripts = all_transcripts[['id', 'kla_lfc', 'kla_6h_lfc']]
# Associate gene id
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
def ucsc_link_cleanup(data):
data['ucsc_link_nod'] = data['ucsc_link_nod'].map(
lambda x: '<a href={0} target="_blank">UCSC</a>'.format(
x.replace('nod_balbc', 'gr_project_2012')))
return data
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
save_dirpath = yzer.get_and_create_path(dirpath,
'subgroups_for_supershift')
transcripts = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'transcript_vectors.txt'))
data = transcripts[transcripts['refseq'] == 'f']
data = data[data['has_infrastructure'] == 0]
data = data[data['length'] < 6000]
data = data[data['dex_1_lfc'] < 1]
data = data[data['kla_1_lfc'] >= 1]
data = data.fillna(0)
data = ucsc_link_cleanup(data)
if False:
'''
Created on Oct 1, 2012
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'boxplots_from_p65_gr')
if True:
for main, compare, basal_cond in (('p65', 'GR', 'KLA'), ('GR', 'p65',
'Dex')):
data = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'from_peaks',
'{0}_kla_dex_vectors.txt'.format(main)))
data = data.fillna(0)
data = data.groupby(['id', 'chr_name'], as_index=False).mean()
data = data[data['tag_count_2'] > 0]
colname = 'tag_count_diff'
data[colname] = (data['tag_count'] -
data['tag_count_2']) / data['tag_count']
cond_1 = (data['tag_count_3'] == 0)
cond_2 = (data['tag_count_3'] > 0) & (data['tag_count_3'] <
'''
Created on Apr 19, 2013
@author: karmel
Note: Made font.weight = bold and axes.titlesize = 24 in matplotlibrc
'''
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/Demo-data'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'figure_4_pie_charts')
yzer.legend_location = 'lower left'
pie1 = '''Annotated by RefSeq and/or ncRNA.org 16,945
Unannotated 36,578'''
pie1 = [row.split(' ') for row in pie1.split('\n')]
pie1 = zip(*pie1)
yzer.piechart(map(lambda s: int(s.replace(',', '')), pie1[1]),
pie1[0],
title='Transcripts with Score >= 2',
save_dir=img_dirpath,
show_plot=True)
pie2 = '''Promoter-associated RNA 6,314
Antisense of RefSeq 5,604
Post-TTS, same-strand 6,940
Other RefSeq Proximal 3,119
'''
Created on Oct 26, 2012
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from matplotlib import pyplot
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/enhancer_classification'
dirpath = yzer.get_path(dirpath)
consistent = True
img_dirpath = yzer.get_and_create_path(
dirpath, 'piecharts_by_mechanism', consistent and 'consistent'
or 'by_genes')
data = yzer.import_file(
yzer.get_filename(dirpath, 'enhancers_with_nearest_gene.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(
lambda s: s.replace('nod_balbc', 'gr_project_2012'))
draw_pies = True
min_tags = 30
ratio = 1.5
# Make sure we have dimethyl
data = data[data.filter(like='h3k4me2').max(axis=1) > min_tags]
data = data[data['minimal_distance'] >= 1000]
#data = yzer.collapse_strands(data)
'''
Created on Sep 27, 2014
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.dataanalysis.misc.rodrigo.samples import get_threshold,\
get_breed_sets
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/' +\
'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Enhancers_set2'
dirpath = yzer.get_path(dirpath)
save_path = yzer.get_and_create_path(
dirpath, 'Figures', 'Enhancer_counts')
datasets = {}
breed_sets = get_breed_sets()
for i, (samples, short_names) in enumerate(breed_sets):
oth_breed = breed_sets[1 - i]
for j, sample_prefix in enumerate(short_names):
sample_dirpath = yzer.get_filename(dirpath, sample_prefix)
filename = yzer.get_filename(sample_dirpath,
sample_prefix + '_enhancers.txt')
data = yzer.import_file(filename)
data = data.fillna(0)
min_thresh = get_threshold('atac')
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from random import shuffle
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/hic_domains'
dirpath = yzer.get_path(dirpath)
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(
lambda s: s.replace('nod_balbc', 'gr_project_2012'))
data = data.fillna(0)
for rep in (4, 3, 1):
img_dirpath = yzer.get_and_create_path(dirpath, 'lfc_histograms',
'rep{0}'.format(rep))
kla_key = 'kla_{0}_lfc'.format(rep)
dex_kla_key = 'dex_over_kla_{0}_lfc'.format(rep)
data = data[data[kla_key] >= 1]
shuffled = data['domain_id'].values.copy()
shuffle(shuffled)
data['shuffled_domain_id'] = shuffled
grouped = data.groupby(by='domain_id', as_index=False).mean()
shuffled_grouped = data.groupby(by='shuffled_domain_id',
as_index=False).mean()
grouped = grouped[grouped['domain_id'] != 0]
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
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_sets')
kla_col = 'kla_lfc'
tss_only = False
img_dirpath = yzer.get_and_create_path(
dirpath, 'novel_me2_sites', tss_only and 'genic' or 'all_interactions',
'ratio_10')
if False:
enhancers = yzer.import_file(
yzer.get_filename(data_dirpath,
'all_distal_enhancers_inc_me2.txt'))
all_transcripts = yzer.import_file(
yzer.get_filename(data_dirpath, 'transcript_vectors.txt'))
transcripts = all_transcripts[['id', kla_col]]
enhancers = enhancers.merge(transcripts, how='left', on='id')
if tss_only:
interactions = yzer.import_file(
yzer.get_filename(data_dirpath,
'''
Created on Feb 15, 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 = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'srf_ko_targets')
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data = data.fillna(0)
data = data[data[['nod_notx_1h_tag_count', 'balb_notx_1h_tag_count']].max(
axis=1) >= 10]
data = data[(data['has_refseq'] == 1) & (data['transcript_score'] >= 4)]
# From Amy Sullivan SRF paper
down_in_srf_ko = [
'Cnn2', 'Srf', 'Lima1', 'Rhoj', 'Coro1a', 'Il1rn', 'Lsp1', 'LOC277203',
'Vcl', 'Card11', 'Cbr2', 'Cd83', 'Acta2', 'Actb', 'Tspan7', 'Ebi2',
'Gpr162', 'Ckb', 'Dhcr24', 'LOC638632', 'Actg2', 'Trim29', 'Ppap2b',
'Klk1b11', 'Actc1', 'Pcp4l1', 'LOC621324', 'Cdkn1c', 'Slco2b1',
'Cd24a', 'Pdgfa', 'Lrrc58', 'Dnmt3a', 'Slamf9', '1100001H23Rik',
'Aldoc', 'Cd28', '1500003O03Rik', 'Rab15', 'Pld4', 'Pilra', 'Xlr',
'Tgm1', 'Lcp1', 'Fstl1', 'Slc40a1', 'Usp24', 'Jup', 'Cd74', 'Tpm4',
'''
Created on Feb 12, 2013
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/CD4TCells/Oshea_enhancers/peak_overlaps'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'figures')
peak_pretty = 'p300'
peak = peak_pretty.lower()
th1 = yzer.import_file(
yzer.get_filename(dirpath,
'th1_with_th2_{0}.txt'.format(peak))).fillna(0)
th2 = yzer.import_file(
yzer.get_filename(dirpath,
'th2_with_th1_{0}.txt'.format(peak))).fillna(0)
# Filter out promoters
th1 = th1[th1['tss_id'] == 0]
th2 = th2[th2['tss_id'] == 0]
# Get venn-diagram sets
def get_filters_transcript(subdata, xcol, ycol):
down_in_kla = subdata['kla_1_lfc'] <= -1
nc_in_kla = subdata['kla_1_lfc'].abs() < 1
up_in_kla = subdata['kla_1_lfc'] >= 1 & (subdata['dex_over_kla_1_lfc'] >
-.58)
trans = up_in_kla & (subdata['dex_over_kla_1_lfc'] <= -.58)
return down_in_kla, nc_in_kla, up_in_kla, trans
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'bargraphs_from_p65_gr')
transcripts = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'transcript_vectors.txt'))
transcripts['glass_transcript_id'] = transcripts['id']
if True:
for main, compare, basal_cond in (('p65', 'GR', 'KLA'), ('GR', 'p65',
'Dex')):
data = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'from_peaks',
'{0}_kla_dex_vectors.txt'.format(main)))
data = data.merge(transcripts,
how='left',
on='glass_transcript_id',
@author: karmel
Do novel interactions gain or lose me2?
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
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_sets')
img_dirpath = yzer.get_and_create_path(dirpath,
'novel_enhancer_me2_change',
'all_interactions')
interactions = yzer.import_file(
yzer.get_filename(
data_dirpath,
'transcript_pairs_enhancer_with_anything_with_me2_inc_me2_counts.txt'
))
interactions = interactions[interactions['count'] > 1]
interactions = interactions.fillna(0)
# Key on peak id, not enhancer id, which could be bidirectional
#interactions['id_2'] = interactions['h3k4me2_id']
interactions['hash'] = interactions.apply(
lambda row: '{0}.{1}'.format(row['id'], row['id_2']), axis=1)
'''
Created on Oct 1, 2012
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from matplotlib import pyplot
import numpy
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'piecharts_from_p65_gr')
if True:
for main, compare, basal_cond in (
('GR', 'p65', 'Dex'),
('p65', 'GR', 'KLA'),
):
data = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'from_peaks',
'{0}_kla_dex_vectors.txt'.format(main)))
# Get nearby peaks first
ids_with_nearby = data[
(data['distance_to_tss_2'].isnull() == False)
& (data['distance_to_peak_2'] <= 1000)]['id']
data = data.fillna(0)
@author: karmel
Do novel interactions gain or lose me2?
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
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_sets')
img_dirpath = yzer.get_and_create_path(dirpath,
'novel_interactions_kla_lfc',
'all_interactions')
interactions = yzer.import_file(
yzer.get_filename(
data_dirpath,
'transcript_pairs_enhancer_with_anything_with_me2_inc_me2_counts.txt'
))
interactions = interactions[interactions['count'] > 1]
all_transcripts = yzer.import_file(
yzer.get_filename(data_dirpath, 'transcript_vectors.txt'))
kla_col = 'kla_lfc'
transcripts = all_transcripts[['id', kla_col]]
@author: karmel
Do the gene groups outlined in Ramirez-Carrozzi 2006 and 2009 correlate
with expression changes in Dex+KLA?
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/cpg_island_promoters'
dirpath = yzer.get_path(dirpath)
for rep in (4, 3, 1):
img_dirpath = yzer.get_and_create_path(dirpath,
'boxplots_by_expression',
'genes_with_gr',
'rep{0}'.format(rep),
'transrepressed')
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(
lambda s: s.replace('nod_balbc', 'gr_project_2012'))
data = data.fillna(0)
data = data[(data['kla_{0}_lfc'.format(rep)] >= 1)
& (data['dex_over_kla_{0}_lfc'.format(rep)] <= -.58)]
# 2006
secondary_response = data[data['gene_names'].isin([
'{Il12b}', '{Il6}', '{Nos2}', '{Mx1}', '{Mx2}', '{Marco}',
'''
Created on Feb 12, 2013
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer
if __name__ == '__main__':
yzer = SeqGrapher()
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, 'srf_binding')
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
data = data.fillna(0)
data = data[data[['nod_notx_1h_tag_count', 'balb_notx_1h_tag_count']].max(
axis=1) >= 10]
subsets = [
data,
data[(data['has_refseq'] == 1) & (data['transcript_score'] >= 4)],
data[(data['distal'] == 't') & (data['h3k4me2_tag_count'] > 10)]
]
# Add in nearest genes for enhancers
enh = subsets[2].copy()
nearest_genes = yzer.import_file(
wt_only = wt_data[
wt_data['foxo1_ko_naive_atac_tag_count'] < min_thresh]
fold = 2
both = wt_data[
(wt_data['foxo1_ko_naive_atac_tag_count']
* fold >= wt_data['tag_count']) &
(wt_data['tag_count'] * fold >=
wt_data['foxo1_ko_naive_atac_tag_count'])
]
ko_only = ko_data[
ko_data['naive_atac_tag_count'] < min_thresh]
save_path = yzer.get_and_create_path(
dirpath, 'Figures', 'Foxo1_group_promoters_overlaps')
groups = [wt_only, both, ko_only]
labels = ['WT only', 'WT and KO', 'Foxo1 KO only']
if True:
yzer.boxplot([gp['naive_foxo1_tag_count'] for gp in groups],
labels,
title='Foxo1 tags in ATAC-seq regions by group',
ylabel='Foxo1 peak tag count', save_dir=save_path,
show_plot=False)
yzer.boxplot([gp['lcmv_d12_foxo1_tag_count'] for gp in groups],
labels,
title='LCMV d12 Foxo1 tags in ATAC-seq regions by group',
ylabel='Foxo1 peak tag count', save_dir=save_path,
show_plot=False)
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
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_sets')
kla_col = 'kla_lfc'
tss_only = False
img_dirpath = yzer.get_and_create_path(
dirpath, 'interactions_by_kla_lfc', tss_only and 'genic'
or 'all_interactions', 'lfc_2')
# File generated in novel_me2_sites
enhancers = yzer.import_file(
yzer.get_filename(
data_dirpath,
'all_enhancers_with_me2_and_{0}interaction_stats.txt'.format(
tss_only and 'tss_' or '')))
for kla_timepoint in ('1h', ):
enhancers['me2_ratio'] = nonzero(enhancers['me2_kla_6h_tag_count_2'])/\
nonzero(enhancers['me2_notx_tag_count_2'])
sets = OrderedDict()
sets['4x GRO in KLA {0}'.format(kla_timepoint)] = enhancers[
'''
Created on Apr 19, 2013
@author: karmel
Note: Made font.weight = bold and axes.titlesize = 24 in matplotlibrc
'''
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/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'hg19_mcf7_pie_charts')
yzer.legend_location = 'lower left'
pie1 = '''Annotated by RefSeq and/or ncRNA.org 14,022
Unannotated 67,046'''
pie1 = [row.split(' ') for row in pie1.split('\n')]
pie1 = zip(*pie1)
yzer.piechart(map(lambda s: int(s.replace(',', '')), pie1[1]),
pie1[0],
title='Hah et al MCF-7 Transcripts\nwith Score >= 1',
save_dir=img_dirpath,
show_plot=True)
pie2 = '''Promoter-associated RNA 7,055
Antisense of RefSeq 7,539
Other RefSeq Proximal 13,664
Distal with H3K4me2 2,352
Created on Jan 3, 2013
@author: karmel
Plot gen-enhancer me2 LFC; do we see correlation?
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import nonzero
import numpy
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_sets')
img_dirpath = yzer.get_and_create_path(dirpath, 'gene_enhancer_me2_lfc',
'scatterplots')
interactions = yzer.import_file(
yzer.get_filename(
data_dirpath,
'transcript_pairs_enhancer_with_anything_with_me2_inc_me2_counts.txt'
))
interactions = interactions[interactions['count'] > 1]
all_transcripts = yzer.import_file(
yzer.get_filename(data_dirpath, 'transcript_vectors.txt'))
for me2_timepoint in ('6h', '24h'):
me2_col = 'me2_{0}_ratio'.format(me2_timepoint)
kla_col = 'kla_lfc'
col_set = [me2_col + '_2', kla_col + '_2', kla_col, me2_col]
'''
Created on Jul 11, 2012
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'peak_scatterplots')
if True:
for main, compare, basal_cond in (('p65', 'GR', 'KLA'), ('GR', 'p65',
'Dex')):
data = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'from_peaks',
'{0}_kla_dex_vectors.txt'.format(main)))
data = data.fillna(0)
data = data.groupby(['id', 'chr_name'], as_index=False).mean()
xcolname, ycolname = 'tag_count_2', 'tag_count' #'p65_kla_tag_count', 'p65_kla_dex_tag_count',
data = data[data[ycolname] >= 10]
cond_1 = (data['tag_count_3'] == 0)
cond_2 = (data['tag_count_3'] > 0) & (data['tag_count_3'] <
data['tag_count_4'])
cond_3 = (data['tag_count_3'] > 0) & (data['tag_count_3'] >=
'''
Created on Nov 7, 2012
@author: karmel
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.dataanalysis.misc.cd4tcell_finland_2012.resources import comparison_sets,\
pretty_names
if __name__ == '__main__':
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',
