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,
'Frequency',
'Tandem Duplications by Min Dist to %s' %genomedat_startcolname,
plot_output_fname,
autoxlim=autoxlim)
largest_tss_dic = {}
for k, l in all_tandem_dupes.iteritems():
largest_tss_dic[k] = max(l)
print 'Largest distances by chromosome: '
print largest_tss_dic
if __name__ == '__main__':
if len(sys.argv) < 2:
print('Tandem data must be given on the command line.')
sys.exit()
tandem_fname = sys.argv[1]
tandem_path = os.path.join(_input_dir, tandem_fname)
gc_chr_pairlist = tandem_data.calculate_tandem_gc_content(tandem_path,
'sequence',
'chromosome_1',
save_output,
output_gc_content_colname,
output_seq_length_colname)
just_gc = [i[0] for i in gc_chr_pairlist]
seq_lengths = [i[2] for i in gc_chr_pairlist]
jplots.plot_binned_bar_graph(seq_lengths, 20, None, None,
'length_of_sequence (bases)',
'frequency',
'seq_length_across_tandem_dupes',
save_path_length, autoxlim=True)
jplots.plot_binned_bar_graph(just_gc, 30, 0, 1,
'gc_content',
'frequency',
'gc_content_across_tandem_dupes',
save_path_gc)
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:
outwriter.writerow(dist)
'''
jplots.plot_binned_bar_graph(tss_distances_list, bins_in_plot,
xmin,
xmax,
'distance from %s' %genome_startcolname,
'frequency',
'Random distribution of Distances from %s'\
'across genome\n%s points per chromosome'\
%(genome_startcolname, numb_rands_per_chr),
plot_output_fname,
autoxlim=autoxlim)
print('Done for %s' %chromosome)
print distances_dict
print coordinates_dict
print locations_dict
# Convert dictionary to list
distances = []
for dist_list in distances_dict.values():
distances.append(dist_list)
# Flatten list
distances = list_tools.flatten_list(distances)
# Plot results
jplots.plot_binned_bar_graph(distances, 100, -100000, 100000,
'Distance from Exon', 'Frequency',
'Title', save_path_name,
autoxlim=True)
print('Plot saved in %s' %save_path_name)
merged_tss_list = []
for chromosome in chromosome_list:
genome_tss = genome_info.get_tss_locations(genome_path, 'chrom', 'txStart',
chromosome, chromosome_list)
dist_from_tss_list = tandem_data.get_tandem_tss_distribution(tandem_path,
'start_1',
'chromosome_1',
genome_tss,
chromosome,
chromosome_list)
merged_tss_list.extend(dist_from_tss_list)
jplots.plot_binned_bar_graph(merged_tss_list, 100,
'Distance from a known TSS',
'Frequency',
'Distribution of filtered tandem duplications by TSS',
os.path.join(_plot_dir, plot_output_fname))
total = len(merged_tss_list)
abs_merged_tss_list = [abs(i) for i in merged_tss_list]
print abs_merged_tss_list
print len(abs_merged_tss_list)
chunked_list = list_tools.chunks(sorted(abs_merged_tss_list), 48)
print chunked_list
print len(chunked_list)
print [[min(i), max(i)] for i in chunked_list]