data['length_5_utr'] = (data['utr_start'] - data['utr_end']).apply(abs)
ids = grouped[
grouped['relevant_sets'] >= thresh]['glass_transcript_id']
repr_data = data[data['glass_transcript_id'].isin(ids)]
rest_data = data[data['glass_transcript_id'].isin(
grouped[grouped['relevant_sets'] < thresh]['glass_transcript_id'])]
all_data = data[data['glass_transcript_id'].isin(
grouped['glass_transcript_id'])]
if False:
yzer.prep_files_for_homer(
all_data,
'all_transcripts_preceding'.format(thresh),
yzer.get_filename(dirpath, 'from_genes'),
center=False,
reverse=False,
preceding=True,
size=200)
yzer.prep_files_for_homer(
all_data,
'all_transcripts_promoter'.format(thresh),
yzer.get_filename(dirpath, 'from_genes'),
center=False,
reverse=False,
preceding=False,
size=200)
if False:
yzer.prep_files_for_homer(
repr_data,
'repressed_in_{0}_kla_{1}_promoter_200'.format(
print grapher.get_gene_names(refseq[(refseq['kla_1_lfc'] >= 1)],
add_quotes=True)
print grapher.get_gene_names(
refseq[(refseq['kla_1_lfc'] >= 1)
& (refseq['dex_over_kla_1_lfc'] < -.58)])
if False:
yzer = MotifAnalyzer()
motif_dirpath = yzer.get_filename(dirpath, 'motifs/size_200')
distal = data[data['distal'] == 't']
dataset = distal[(distal['kla_lfc'] >= 1)]
yzer.prep_files_for_homer(dataset,
'distal_up_in_kla_all',
motif_dirpath,
center=False,
reverse=False,
preceding=True,
size=200)
dataset = distal[(distal['kla_1_lfc'] >= 1)]
yzer.prep_files_for_homer(dataset,
'distal_up_in_kla_1',
motif_dirpath,
center=False,
reverse=False,
preceding=True,
size=200)
dataset = distal[(distal['kla_2_lfc'] >= 1)]
yzer.prep_files_for_homer(dataset,
pausing_data = yzer.import_file(
yzer.get_filename(dirpath, 'feature_vectors.txt'))
data = yzer.import_file(
yzer.get_filename(dirpath, 'transcript_vectors.txt'))
try:
min_ratio = float(sys.argv[1])
except IndexError:
min_ratio = 1.5
if False:
yzer.prep_files_for_homer(data,
'all_transcripts_promoter',
dirpath,
center=False,
reverse=False,
preceding=True,
size=200)
for replicate_id in ('', 1, 2, 3, 4):
rep_str = get_rep_string(replicate_id)
key = 'kla_dex_{0}pausing_ratio'.format(rep_str)
pausing_data[key] = pausing_data['kla_dex_{0}bucket_score'.format(rep_str)] \
/pausing_data['kla_{0}bucket_score'.format(rep_str)]
pausing_data = pausing_data.fillna(0)
pausing_ids = pausing_data[
pausing_data[key] >= min_ratio]['glass_transcript_id']
dataset = data[data['id'].isin(pausing_ids)]
data = yzer.import_file(
yzer.get_filename(
dirpath,
'from_peaks/{0}_promoter_vectors.txt'.format(peak_type)))
data['id'] = data['peak_id']
thresh = 2
ids = grouped[
grouped['relevant_sets_primary'] >= thresh]['glass_transcript_id']
dataset = data[data['glass_transcript_id'].isin(ids)]
if True:
yzer.prep_files_for_homer(data,
'all_{0}_200'.format(peak_type),
yzer.get_and_create_path(
dirpath, 'from_peaks', peak_type),
center=True,
reverse=False,
preceding=False,
size=200)
yzer.prep_files_for_homer(
dataset,
'paused_in_{0}_at_least_{1}_min_{2}_down_in_dex_{3}_200'.format(
thresh, min_ratio, secondary_min_ratio, peak_type),
yzer.get_and_create_path(dirpath, 'from_peaks', peak_type),
center=True,
reverse=False,
preceding=False,
size=200)
