if __name__ == '__main__':
if len(sys.argv) < 2:
print('TSS data must be given on the command line.')
sys.exit()
genome_fname = sys.argv[1]
genome_path = os.path.join(_input_dir, genome_fname)
chromosome_list = chr_tools.get_chr_list()
all_tss = genome_info.get_all_tss_locations(genome_path,
genome_chrcolname,
genome_startcolname,
chromosome_list)
random_locs = random_genome_locs.generate_random_chr_pos(numb_rands_per_chr)
tss_distances_dict, _ = integrate_data.calc_tss_dist(random_locs, all_tss,
chromosome_list,
os.path.join(_output_dir, output_filename))
''
tss_distances_list = []
for dist_list in tss_distances_dict.values(): # Each value is a list
tss_distances_list.extend(dist_list)
lessthan2kb, btwn2kb10kb, grtrthan10kb = \
integrate_data.bin_distances(tss_distances_list)
# print lessthan2kb, btwn2kb10kb, grtrthan10kb
'''
output_dist_colname = 'distance_to_exon'
output_exonstart_colname = 'closest_exon_start'
output_exonend_colname = 'closest_exon_end'
output_event_colname = 'exon_or_nonexon'
if __name__ == '__main__':
if len(sys.argv) < 2:
print('Reference genome info must be given on the command line.')
sys.exit()
ref_fname = sys.argv[1]
chromosome_list = chr_tools.get_chr_list()
# Create randomized tandem distribution file.
random_genome_locs = random_genome_locs.generate_random_chr_pos(nrandopms_per_chr)
# Create a mock textfile with appropriate rownames
with open(os.path.join(outputdir, tandem_fname), 'wb') as randomfile:
randomwriter = csv.writer(randomfile, delimiter='\t')
# Writer colnames
header = [tandem_chr_colname, tandem_start_colname]
randomwriter.writerow(header)
for c in chromosome_list:
for pos in random_genome_locs[c]:
randomwriter.writerow([c, pos])
# Initialize rf_data class, using tandem_path we just created above.
rf_data = ref_and_tandem.data(ref_path=mydirs.joinpath(inputdir,
ref_fname),
tandem_path=os.path.join(outputdir, tandem_fname),
tandem_output_path=mydirs.joinpath(outputdir,