@author: karmel
Scatterplots of H3K4me2 peak tag counts by GROseq score
'''
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, 'scatterplots')
data = yzer.import_file(
yzer.get_filename(dirpath, 'me2_peaks_with_transcripts.txt'))
data = data.fillna(0)
data = data.groupby(by='id', as_index=True).mean()
data['transcript_score'] = data['score(2)']
ax = yzer.scatterplot(
data,
xcolname='transcript_score',
ycolname='tag_count',
log=True,
title='H3K4me2 Tag Count as a Function of Transcript Score',
xlabel='Glass Atlas Transcript Score',
ylabel='Normalized H3K4me2 tag count',
show_2x_range=True,
plot_regression=True,
show_count=True,
show_correlation=True,
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]
sets.append(refseq)
@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'] >=
data['tag_count_4'])
ax = None
for show_points in (True, False):
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)
if True:
ax = yzer.scatterplot(merged,
'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Promoters'
dirpath = yzer.get_path(dirpath)
cond, seq, breed = ('naive', 'atac', '')
wt_prefix = sample_name(cond, seq, breed)
ko_prefix = sample_name(cond, seq, 'foxo1_ko_')
wt_dirpath = yzer.get_filename(dirpath, wt_prefix)
ko_dirpath = yzer.get_filename(dirpath, ko_prefix)
wt_filename = yzer.get_filename(wt_dirpath,
wt_prefix + '_promoters.txt')
ko_filename = yzer.get_filename(ko_dirpath,
ko_prefix + '_promoters.txt')
wt_data = yzer.import_file(wt_filename)
wt_data = wt_data.fillna(0)
ko_data = yzer.import_file(ko_filename)
ko_data = ko_data.fillna(0)
min_thresh = get_threshold(seq)
wt_data = wt_data[wt_data['tag_count'] >= min_thresh]
ko_data = ko_data[ko_data['tag_count'] >= min_thresh]
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']) &
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[
enhancers[kla_col] > 2]
sets['No change GRO in KLA {0}'.format(kla_timepoint)] = enhancers[
enhancers[kla_col].abs() <= 1]
sets['1/4 GRO in KLA {0}'.format(kla_timepoint)] = enhancers[
enhancers[kla_col] < -2]
'''
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)
if pu_1: data = data[data['pu_1_kla_tag_count'] + data['pu_1_kla_tag_count'] > 0]
'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')
data = data[data['tag_count'] >= min_thresh]
datasets[sample_prefix] = data
# How many denovo d7 enhancers are also in foxo1 kos?
for celltype in ('hi', 'lo'):
d7 = datasets['klrg{}_d7'.format(celltype)]
de_novo = d7[d7['d0_tag_count'] < min_thresh]
all_shared = d7[
'foxo1_ko_klrg{}_d7_tag_count'.format(celltype)] >= min_thresh
@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/ctcf_across_celltypes'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'figures')
dp = yzer.import_file(
yzer.get_filename(dirpath, 'dp_with_thiomac_ctcf.txt')).fillna(0)
thio = yzer.import_file(
yzer.get_filename(dirpath, 'thiomac_with_dp_ctcf.txt')).fillna(0)
# Get venn-diagram sets
only_dp = dp[dp['thiomac_ctcf_tag_count'] == 0]
only_thio = thio[thio['dp_ctcf_tag_count'] == 0]
shared = dp[dp['thiomac_ctcf_tag_count'] != 0]
shared_check = thio[thio['dp_ctcf_tag_count'] != 0]
print len(only_dp), len(only_thio), len(shared), len(shared_check)
data = shared.append(only_dp, ignore_index=True)
data = data.append(only_thio, ignore_index=True)
data['dp_nonzero'] = nonzero(data['dp_ctcf_tag_count'])
data['thio_nonzero'] = nonzero(data['thiomac_ctcf_tag_count'])
'''
Created on May 10, 2012
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
import os
from matplotlib import pyplot
if __name__ == '__main__':
grapher = SeqGrapher()
dirpath = '/Users/karmel/Desktop/Projects/GlassLab/Notes_and_Reports/ncRNA_josh/'
filename = os.path.join(dirpath, 'refseq_predictions.tsv')
evidence_f = os.path.join(dirpath, 'refseq_evidence.orf')
data = grapher.import_file(filename)
evidence = grapher.import_file(evidence_f)
data['score_orf'] = evidence['score']
data = data[data['score_orf'] < 200]
data_coding = data[data['score'] >= 0]
data_noncoding = data[data['score'] < 0]
ax = grapher.scatterplot(data_coding,
'score_orf',
'score',
log=False,
color='blue',
label='Predicted Coding',
add_noise=False,
show_2x_range=False,
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
interactions = interactions.merge(transcripts, how='left', on='id')
transcripts['id_2'] = transcripts['id']
@author: karmel
'''
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/CD4TCells/Oshea_enhancers/peak_overlaps'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'figures')
peak = 'p300'
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)
th1_with_ctcf_motif = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'th_p300_enhancers_ctcf',
'th1_only_{0}_with_ctcf_motif.txt'.format(peak)))
th2_with_ctcf_motif = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'th_p300_enhancers_ctcf',
'th2_only_{0}_with_ctcf_motif.txt'.format(peak)))
shared_with_ctcf_motif = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'th_p300_enhancers_ctcf',
'th_shared_{0}_with_ctcf_motif.txt'.format(peak)))
# Filter out promoters
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
import random
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_nearby_genes_by_p65')
change_type = 'more' #'less'
for ratio in (1.5, 2, 3):
data = yzer.import_file(
yzer.get_filename(dirpath, 'motifs',
'transcript_vectors_with_nearby_peaks.txt'))
nearby = yzer.import_file(
yzer.get_filename(
img_dirpath,
'nearest_genes_to_enhancer_like_{1}_p65_{0}x.txt'.format(
str(ratio).replace('.', '_'), change_type)))
colname = 'dex_over_kla_1_lfc'
pausing = True
if pausing:
colname = 'pausing_ratio_ratio'
# We want previously calculated bucket scores,
# Joined to old transcripts because we have since updated IDs
bucket_scores = yzer.import_file(
We count the interactions connected to each transcript and
draw a boxplot. In order to most easily pull in all the
zero-interaction enhancers, we load those with a separate query
and use the difference in count.
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/novel_enhancers'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'boxplots_by_me2_in_notx')
data = {}
data['all_enhancers_with_less_me2'] = yzer.import_file(
yzer.get_filename(dirpath, 'all_enhancers_with_less_me2_in_notx.txt'))
data['all_enhancers_with_me2'] = yzer.import_file(
yzer.get_filename(dirpath, 'all_enhancers_with_me2_in_notx.txt'))
data['interacting_in_notx_with_less_me2'] = yzer.import_file(
yzer.get_filename(
dirpath,
'interacting_in_notx_enhancers_with_less_me2_in_notx.txt'))
data['interacting_in_notx_with_me2'] = yzer.import_file(
yzer.get_filename(
dirpath, 'interacting_in_notx_enhancers_with_me2_in_notx.txt'))
data['interacting_in_kla_30m_with_less_me2'] = yzer.import_file(
yzer.get_filename(
dirpath,
'interacting_in_kla_30m_enhancers_with_less_me2_in_notx.txt'))
data['interacting_in_kla_30m_with_me2'] = yzer.import_file(
yzer.get_filename(
if __name__ == '__main__':
enhancer_counts = True # Are we looking at enhancer interactions (False) or counts (True)?
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/enhancers_by_gene_length'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots')
counted = enhancer_counts and 'enhancer' or 'interaction'
# The first set has length with interaction counts;
# the second has length for all transcripts, even those without interactions.
# We want to merge such that we add the interaction-less genes with a count of 0.
data = yzer.import_file(yzer.get_filename(dirpath,'{0}_counts_by_refseq.txt'.format(counted)))
all_data = yzer.import_file(yzer.get_filename(dirpath,'refseq_all.txt'))
all_data = all_data[~all_data['id'].isin(data['id'])]
data = pandas.concat([data, all_data])
data = data.reset_index().fillna(0)
notx = data[data['sequencing_run_id'] == 765]
kla_30m = data[data['sequencing_run_id'] == 766]
kla_4h = data[data['sequencing_run_id'] == 773]
no_intxns = data[data['sequencing_run_id'] == 0]
# Zero won't show up in a log plot, so add one.
no_intxns['count'] = 1
ax = yzer.scatterplot(no_intxns,
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:
# First get sets for Negative controls
tfs = ['p65', 'pu_1', 'gr', 'gr_fa']
for tf in tfs:
@author: karmel
Note: Made font.weight = normal and axes.titlesize = 24 in matplotlibrc
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.dataanalysis.misc.demoatlas.rpkm_to_score import PrettyAxisGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/NAR_review_data/Post-gene'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots')
data = yzer.import_file(
yzer.get_filename(dirpath, 'post_gene_transcripts.txt'))
refseq = yzer.import_file(
yzer.get_filename(dirpath, 'all_expressed_refseq.txt'))
refseq_with_runoff = refseq[refseq['id'].isin(data['gene_id'])]
refseq_no_runoff = refseq[~refseq['id'].isin(data['gene_id'])]
if False:
print len(refseq_no_runoff)
print refseq_no_runoff.tail(100).to_string()
# Calculate length of runoff
data[
'length'] = data['transcription_end'] - data['transcription_start'] + 1
data['gene_length'] = data['gene_end'] - data['gene_start'] + 1
# What might be correlated with length of runoff?
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
interactions = interactions.merge(transcripts, how='left', on='id')
transcripts['id_2'] = transcripts['id']
transcripts = transcripts.drop(['id'], axis=1)
interactions = interactions.merge(transcripts,
how='left',
'''
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]
interactions[me2_col] = numpy.log2(nonzero(interactions['me2_kla_{0}_tag_count'.format(me2_timepoint)])/\
nonzero(interactions['me2_notx_tag_count']))
interactions[me2_col + '_2'] = numpy.log2(nonzero(interactions['me2_kla_{0}_tag_count_2'.format(me2_timepoint)])/\
nonzero(interactions['me2_notx_tag_count_2']))
@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/NAR_review_data/vs_homer'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots')
data = yzer.import_file(
yzer.get_filename(dirpath, 'tag_count_by_refseq.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)
if True:
ax = yzer.scatterplot(merged,
Created on Oct 8, 2012
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from matplotlib import pyplot
from glasslab.dataanalysis.misc.gr_project_2012.boxplots_redistribution_pairs import get_high_quality_pairs
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/'
dirpath = yzer.get_path(dirpath)
motif_dirpath = yzer.get_filename(dirpath, 'motifs', 'from_peaks')
transcripts = yzer.import_file(
yzer.get_filename(dirpath, 'motifs', 'transcript_vectors.txt'))
transcripts['glass_transcript_id'] = transcripts['id']
if True:
all_data = yzer.import_file(
yzer.get_filename(
dirpath, 'redistribution',
'p65_peaks_bigger_in_kla_dex_with_nearby_bigger_kla_peaks.txt')
)
data = get_high_quality_pairs(all_data, transcripts)
data = data.groupby(['id', 'chr_name'], as_index=False).mean()
gr_dex_gt_kla_dex = sum(
data['tag_count_3'] * 1.5 < data['tag_count_4'])
Created on Feb 14, 2013
@author: karmel
'''
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/CD4TCells/Oshea_enhancers/ctcf_stat1_overlap'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'figures')
data = yzer.import_file(
yzer.get_filename(dirpath, 'ctcf_with_stat1_binding.txt')).fillna(0)
with_stat1 = data[data['p2_tag_count'] > 0]
without_stat1 = data[data['p2_tag_count'] == 0]
if True:
ax = yzer.piechart(
[len(with_stat1), len(without_stat1)],
['CTCF sites with STAT1', 'CTCF sites without STAT1'],
title='DP Thymocyte CTCF Sites with STAT1 in Th1 Cells',
save_dir=img_dirpath,
show_plot=True)
data['tag_count_nonzero'] = nonzero(data['tag_count'])
data['p2_tag_count_nonzero'] = nonzero(data['p2_tag_count'])
ax = yzer.scatterplot(
data,
'tag_count_nonzero',
'''
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}',
'{Cmpk2}', '{Rsad2}'
])]
delayed = data[data['gene_names'].isin([
'{Ccl5}', '{Saa3}', '{Ifnb1}', '{Ccl2}', '{Ifit1}', '{Ifit3}',
'{Peli1}', '{Cxcl10}', '{Traf1}'
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,
'transcript_pairs_refseq_with_me2.txt'))
else:
interactions = yzer.import_file(
yzer.get_filename(
data_dirpath,
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(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
transcripts['nearest_refseq_transcript_id'] = transcripts['id']
data = data.merge(transcripts,
how='left',
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
only_th1 = th1[th1['p2_id'] == 0]
only_th2 = th2[th2['p2_id'] == 0]
shared = th1[th1['p2_id'] != 0]
shared_check = th2[th2['p2_id'] != 0]
print len(only_th1), len(only_th2), len(shared), len(shared_check)
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]]
Note: Made font.weight = bold and axes.titlesize = 24 in matplotlibrc
'''
from __future__ import division
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
from glasslab.utils.functions import pandas_min
from glasslab.dataanalysis.misc.demoatlas.rpkm_to_score import PrettyAxisGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/Post_gene_transcripts'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots')
data = yzer.import_file(yzer.get_filename(dirpath,'within_1kb_gap_500bp_with_nc.txt'))
refseq = yzer.import_file(yzer.get_filename(dirpath,'expressed_refseq_gap_500bp.txt'))
refseq_with_runoff = refseq[refseq['id'].isin(data['gene_id'])]
refseq_no_runoff = refseq[~refseq['id'].isin(data['gene_id'])]
if True:
print len(refseq_no_runoff)
print refseq_no_runoff.tail(100).to_string()
# Calculate length of runoff
data['length'] = data['transcription_end'] - data['transcription_start'] + 1
data['gene_length'] = data['gene_end'] - data['gene_start'] + 1
# What might be correlated with length of runoff?
if False:
yzer.scatterplot(data, 'gene_length', 'length', log=True)
'''
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 Oct 26, 2012
@author: karmel
'''
from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher
if __name__ == '__main__':
yzer = SeqGrapher()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/'
dirpath = yzer.get_path(dirpath)
img_dirpath = yzer.get_and_create_path(dirpath, 'cpg_island_promoters',
'piecharts', 'by_genes_with_gr')
data = yzer.import_file(
yzer.get_filename(dirpath, 'enhancer_classification',
'enhancers_with_nearest_gene.txt'))
data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(
lambda s: s.replace('nod_balbc', 'gr_project_2012'))
min_tags = 30
# 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, 'cpg_island_promoters',
'transcript_vectors.txt'))
transcripts['nearest_refseq_transcript_id'] = transcripts['id']
