def write_all_wiggles(f5_dirs1, f5_dirs2, corrected_group, basecall_subgroups,
stats_fn, wig_base, wig_types):
if any(stat_name in wig_types
for stat_name in ['stat', 'mt_stat', 'fraction']):
if VERBOSE: sys.stderr.write('Loading statistics from file.\n')
all_stats, stat_type = ts.parse_stats(stats_fn)
if f5_dirs1 is not None:
raw_read_coverage1 = th.parse_fast5s(f5_dirs1, corrected_group,
basecall_subgroups)
if len(raw_read_coverage1) == 0:
sys.stderr.write(
'*' * 60 + '\nERROR: No reads present in --fast5-basedirs.\n' +
'*' * 60 + '\n')
sys.exit()
group1_name = '' if f5_dirs2 is None else GROUP1_NAME
if f5_dirs2 is not None:
raw_read_coverage2 = th.parse_fast5s(f5_dirs2, corrected_group,
basecall_subgroups)
chrm_sizes = th.get_chrm_sizes(raw_read_coverage1, raw_read_coverage2)
if VERBOSE: sys.stderr.write('Writing wiggles.\n')
if 'coverage' in wig_types:
write_cov_wig(raw_read_coverage2, wig_base, GROUP2_NAME)
if 'signal_sd' in wig_types:
write_signal_sd_wig(raw_read_coverage2, chrm_sizes, wig_base,
GROUP2_NAME)
if 'length' in wig_types:
write_length_wig(raw_read_coverage2, chrm_sizes, wig_base,
GROUP2_NAME)
# need to do signal and difference call once either with or
# w/o second set of files (unlike coverage, sds and length
if 'signal' in wig_types or 'difference' in wig_types:
write_signal_and_diff_wigs(raw_read_coverage1, raw_read_coverage2,
chrm_sizes, wig_base, group1_name,
'signal' in wig_types, 'difference'
in wig_types)
elif f5_dirs1 is not None:
chrm_sizes = th.get_chrm_sizes(raw_read_coverage1)
if VERBOSE: sys.stderr.write('Writing wiggles.\n')
if 'signal' in wig_types:
write_signal_and_diff_wigs(raw_read_coverage1, None, chrm_sizes,
wig_base, group1_name, 'signal'
in wig_types, False)
if 'coverage' in wig_types:
write_cov_wig(raw_read_coverage1, wig_base, group1_name)
if 'signal_sd' in wig_types:
write_signal_sd_wig(raw_read_coverage1, chrm_sizes, wig_base,
group1_name)
if 'length' in wig_types:
write_length_wig(raw_read_coverage1, chrm_sizes, wig_base, group1_name)
if any(stat_name in wig_types
for stat_name in ['stat', 'mt_stat', 'fraction']):
write_stat_wigs(all_stats, wig_base, 'stat' in wig_types, 'mt_stat'
in wig_types, 'fraction' in wig_types, stat_type)
return
def model_resquiggle(
f5_dirs1, corr_group, bc_subgrps,
tb_model_fn, z_trans_lag, p_value_thresh, reg_context, base_reg_context,
max_base_shift, b_max_base_shift, min_obs_per_base, base_space_iters,
compute_sd, new_corr_grp, num_processes, overwrite, in_place=True):
z_thresh = ts.p_value_to_z_score(p_value_thresh)
raw_read_coverage = th.parse_fast5s(
f5_dirs1, corr_group, bc_subgrps, new_corr_grp)
if tb_model_fn is None:
tb_model_fn = ts.get_default_standard_ref_from_files(fast5_fns)
# load reads into Queue
manager = mp.Manager()
reads_q = manager.Queue()
failed_reads_q = manager.Queue()
# group reads by filename so slot is not deleted in 2D reads
fn_grouped_reads = defaultdict(list)
for cs_reads in raw_read_coverage.itervalues():
for r_data in cs_reads:
fn_grouped_reads[r_data.fn].append(r_data)
num_reads = 0
for fn_reads in fn_grouped_reads.itervalues():
reads_q.put(fn_reads)
num_reads += 1
mod_rsqgl_args = (
reads_q, failed_reads_q, tb_model_fn, z_trans_lag, z_thresh,
reg_context, base_reg_context, max_base_shift, b_max_base_shift,
min_obs_per_base, base_space_iters, new_corr_grp, compute_sd,
overwrite, in_place, corr_group)
mod_rsqgl_ps = []
for p_id in xrange(num_processes):
p = mp.Process(target=model_resquiggle_worker, args=mod_rsqgl_args)
p.start()
mod_rsqgl_ps.append(p)
if VERBOSE: sys.stderr.write(
'Correcting ' + str(num_reads) + ' files with ' +
str(len(bc_subgrps)) + ' subgroup(s)/read(s) ' +
'each (Will print a dot for each ' + str(PROGRESS_INTERVAL) +
' reads completed).\n')
failed_reads = defaultdict(list)
while any(p.is_alive() for p in mod_rsqgl_ps):
try:
errorType, fn = failed_reads_q.get(block=False)
failed_reads[errorType].append(fn)
except Queue.Empty:
sleep(1)
continue
while not failed_reads_q.empty():
errorType, fn = failed_reads_q.get(block=False)
failed_reads[errorType].append(fn)
# print newline after read progress dots
if VERBOSE: sys.stderr.write('\n')
return dict(failed_reads)
def write_most_signif(f5_dirs, fasta_fn, num_regions, qval_thresh,
corrected_group, basecall_subgroups, seqs_fn, num_bases,
stat_order, stats_fn):
if VERBOSE: sys.stderr.write('Loading statistics from file.\n')
all_stats, stat_type = ts.parse_stats(stats_fn)
plot_intervals = ts.get_most_signif_regions(all_stats,
num_bases,
num_regions,
qval_thresh,
fraction_order=not stat_order)
# get each regions sequence either from reads or fasta index
if fasta_fn is None:
raw_read_coverage = th.parse_fast5s(f5_dirs, corrected_group,
basecall_subgroups)
all_reg_data = th.get_region_sequences(plot_intervals,
raw_read_coverage)
else:
fasta_records = th.parse_fasta(fasta_fn)
all_reg_data = [
th.intervalData(int_i.reg_id, int_i.chrm, int_i.start, int_i.end,
int_i.strand, int_i.reg_text, int_i.reads,
fasta_records[int_i.chrm][int_i.start:int_i.end])
for int_i in plot_intervals if int_i.chrm in fasta_records
]
if VERBOSE: sys.stderr.write('Outputting region seqeuences.\n')
with open(seqs_fn, 'w') as seqs_fp:
for int_i in all_reg_data:
reg_seq = int_i.seq
if int_i.strand == '-':
reg_seq = th.rev_comp(reg_seq)
seqs_fp.write('>{0}:{1:d}:{2} {3}\n{4}\n'.format(
int_i.chrm, int(int_i.start + (num_bases / 2)), int_i.strand,
int_i.reg_text, ''.join(reg_seq)))
return