genome_path = os.path.join(_input_dir, genome_fname)
all_tss = genome_info.get_all_tss_locations(genome_path,
genomedat_chrcolname,
genomedat_startcolname,
chromosome_list)
all_tandem_dupes = tandem_data.tandem_dupes_all(tandem_path,
tandem_position_colname,
tandem_chrcolname,
all_tss,
chromosome_list)
min_dists, closest_tss = integrate_data.calc_tss_dist(all_tandem_dupes,
all_tss,
chromosome_list,
text_output_path)
min_dists_list = []
for min_dists_chr_list in min_dists.values():
min_dists_list.extend(min_dists_chr_list)
lessthan2kb, btwn2kb10kb, grtrthan10kb = \
integrate_data.bin_distances(min_dists_list)
# print len(lessthan2kb), len(btwn2kb10kb), len(grtrthan10kb)
jplots.plot_binned_bar_graph(min_dists_list, bins_in_plot,
xmin,
xmax,
'Min Distance to %s' %genomedat_startcolname,
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
'''
with open(os.path.join(_output_dir, output_filename), 'wb') as writefile:
outwriter = csv.writer(writefile, delimiter='\t')
for dist in tss_distances_list:
