def prepare_plot_data(samples):
bar_plot_data = {}
for sample in samples:
in_file = prepare_file_name(sample, pt, 'sample_', '.bam')
st = pysam.AlignmentFile(in_file, "rb")
uniq_dist, multi_dist, _ = umi_dist(st)
x1, y1 = bar_prep(uniq_dist)
x2, y2 = bar_prep(multi_dist)
bar_plot_data.update({sample: (x1, y1, x2, y2)})
unique_savers_dist(savers, mm_hashtable, uniq_hashtable, draw_bar=True)
'''
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
logger.info('Call to rank1 multimap solver package.')
path = '/data/UMI/data/MUS/R1/'
pt = '/data/UMI/data/MUS/'
file_names = []
samples = ['GACCGC']
for sample in samples:
f1 = prepare_file_name(sample, pt, 'sample_', '.bam')
f2 = prepare_file_name(sample, path, 'u_tab_', '.pkl')
f3 = prepare_file_name(sample, path, 'u_map_', '.pkl')
f4 = prepare_file_name(sample, path, 'm_tab_', '.pkl')
file_names.append((sample, f1, f2, f3, f4))
for sample, f1, f2, f3, f4 in file_names:
st = pysam.AlignmentFile(f1, "rb")
u_tab = pickle.load(open(f2, 'r'))
u_map = pickle.load(open(f3, 'r'))
m_tab = pickle.load(open(f4, 'r'))
'''
m_tab = build_multimapping_hashtable(st, sample)
logger.info('Call to UMI distribution report module. \n')
logger.info('UMI distribution report for %d samples.' % len(samples))
logger.info('Organism : %s\n' % organism)
sample_counter = 1
for sample in samples:
logger.info('\n')
logger.info('-' * 100)
logger.info('Sample no. %d, cellular barcode : %s' %
(sample_counter, sample))
logger.info('-' * 100)
logger.info('\n')
f1 = prepare_file_name(sample, path, 'summ_ut_', '.pkl')
f2 = prepare_file_name(sample, path, 'summ_mt_', '.pkl')
f3 = prepare_file_name(sample, path, 'summ_cnt_', '.pkl')
uniq_summary = pickle.load(open(f1, 'r'))
multi_summary = pickle.load(open(f2, 'r'))
multi_stat_summary = pickle.load(open(f3, 'r'))
logger.info('UMI distribution among unique reads:\n')
logger.info('-' * 40)
distribution_report(uniq_summary)
logger.info('\n')
logger.info('UMI distribution among multi reads:\n')
logger.info('-' * 40)
multi_read_stats_report(multi_stat_summary)
distribution_report(multi_summary)
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
fh = logging.FileHandler('/data/UMI/data/MUS/DT/isoDmappedReport.log')
fh.setLevel(logging.INFO)
logger.addHandler(fh)
logger.info('Call to double_mapped solver module. \n')
logger.info('Double_mapped multi reads report for %d samples.' %
len(samples))
logger.info('Organism : %s\n' % organism)
samples = ['CCGGAC']
sample_counter = 1
for sample in samples:
logger.info('\n')
logger.info('-' * 100)
logger.info('Sample no. %d, cellular barcode : %s' %
(sample_counter, sample))
logger.info('-' * 100)
logger.info('\n')
in_file = prepare_file_name(sample, path, 'sample_', '.bam')
pysam_iter = pysam.AlignmentFile(in_file, "rb")
iso_report(pysam_iter)
sample_counter += 1
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
fh = logging.FileHandler('/data/UMI/data/MUS/RP/RepeatDistReport.log')
fh.setLevel(logging.INFO)
logger.addHandler(fh)
logger.info('Call to Repeat Solver Library.')
logger.info('Repeat distribution report for %d samples.' % len(samples))
logger.info('Organism : %s\n' % organism)
file_names = []
for sample in samples:
f1 = prepare_file_name(sample, pt, 'sample_', '.bam')
f2 = prepare_file_name(sample, path, 'r2r_', '.pkl')
file_names.append((f1, f2))
counter = 1
for in_file, out_file in file_names:
logger.info('\n')
logger.info('-' * 100)
logger.info('Sample no. %d : %s' % (counter, in_file))
logger.info('-' * 100)
logger.info('\n')
start_time = time.time()
st = pysam.AlignmentFile(in_file, "rb")