'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Enhancers_set2'
dirpath = yzer.get_path(dirpath)
datasets = {}
breed_sets = get_breed_sets()
# Working with only WT for now
sample_names, short_names = breed_sets[0]
# Set up our samples
datasets = {}
for sample_prefix in 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
# Now set up case-specific counts.
# First, how many naive?
print('Naive total:', len(datasets['d0']))
print('Naive not d7:', sum(datasets['d0']['klrghi_d7']))
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']) &
(wt_data['tag_count'] * fold >=
wt_data['foxo1_ko_naive_atac_tag_count'])
]
ko_only = ko_data[
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/' +\
'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Enhancers'
dirpath = yzer.get_path(dirpath)
if True:
atac = yzer.get_filename(
dirpath, 'naive_atac', 'naive_atac_enhancers.txt')
me2 = yzer.get_filename(
dirpath, 'naive_h3k4me2', 'naive_h3k4me2_enhancers.txt')
ac = yzer.get_filename(
dirpath, 'naive_h3k27ac', 'naive_h3k27ac_enhancers.txt')
atac = yzer.import_file(atac).fillna(0)
me2 = yzer.import_file(me2).fillna(0)
atac_thresh = get_threshold('atac')
me2_thresh = get_threshold('h3k4me2')
atac = atac[atac['tag_count'] >= atac_thresh]
me2 = me2[me2['tag_count'] >= me2_thresh]
# Make sure to count each separately, as many ATAC peaks
# can be subsumed by a single H3K4me2 peak
atac_only = atac[(atac['naive_h3k4me2_tag_count'] < me2_thresh)]
atac_me2 = atac[(atac['naive_h3k4me2_tag_count'] >= me2_thresh)]
me2_only = me2[(me2['naive_atac_tag_count'] < atac_thresh)]
me2_atac = me2[(me2['naive_atac_tag_count'] >= atac_thresh)]
print('ATAC only: ', len(atac_only))
print('ATAC with H3K4me2: ', len(atac_me2))
print('H3K4me2 only: ', len(me2_only))
print('H3K4me2 with ATAC: ', len(me2_atac))
