'''
from glasslab.dataanalysis.misc.rodrigo.samples import get_breed_sets
from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer
from glasslab.utils.database import get_engine, dataframe_from_query
if __name__ == '__main__':
yzer = MotifAnalyzer()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/' +\
'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Enhancers_set2'
dirpath = yzer.get_path(dirpath)
# Get DB engine
engine = get_engine(uri='ec2-23-20-125-153.compute-1.amazonaws.com',
password='******')
breed_sets = get_breed_sets()
# Run and save output from sql queries
for k, (samples, short_names) in enumerate(breed_sets):
oth_breed = breed_sets[1 - k]
for i, sample in enumerate(samples):
curr_name = short_names[i]
others = samples[:i] + samples[i + 1:]
oth_names = short_names[:i] + short_names[i + 1:]
sql = '''-- {}
select distinct on (p1.id)
chr."name" as chr_name, p1."start", p1."end", p1.tag_count,
p1.*,
'''.format(sample)
selects, joins = [], []
for j, other_sample in enumerate(others):
Created on Oct 6, 2014
@author: karmel
'''
from glasslab.dataanalysis.misc.rodrigo.samples import get_threshold,\
get_breed_sets
from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer
if __name__ == '__main__':
yzer = MotifAnalyzer()
dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/' +\
'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Enhancers_set2'
dirpath = yzer.get_path(dirpath)
datasets = {}
samples, short_names = get_breed_sets()[0]
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