def omsim(settings):
# cd to the directory containing the configuration file
os.chdir(settings.directory)
# process input
cmaps = import_input(settings)
print('Imported ' + str(sum(cmaps[iname].count() for iname in cmaps)) + ' nicks in ' + str(sum(cmaps[iname].seq_len() for iname in cmaps)) + 'bp.')
cmaps = KMP(settings, cmaps)
# write processed input
write_processed_input(settings, cmaps)
# filter input for enzymes / files we need
seqs, seq_lens, fns = filter_input(settings, cmaps)
prev = 0
cum_seq_lens = []
for seq_len in seq_lens:
curr = prev + seq_len
cum_seq_lens += [curr]
prev = curr
print('Using ' + str(sum(len(f) for f in fns)) + ' nicks in ' + str(sum(seq_lens)) + 'bp.')
#compute reverse nicking sites
rns = get_rns(settings, fns, seq_lens)
#estimate number of chips based on expected coverage
if settings.chips == 0:
temp = int(sum(seq_lens) * settings.coverage / (settings.scans_per_chip * settings.get_scan_size()))
settings.chips = temp if temp > 1 else 1
#estimate coverage
settings.estimated_coverage = int(settings.get_scan_size() * settings.scans_per_chip * settings.chips / float(sum(seq_lens)))
print('Generating reads on ' + str(settings.chips) + ' chip' + ('' if settings.chips == 1 else 's') + ', estimated coverage: ' + str(settings.estimated_coverage) + 'x.')
noise = Noise(settings)
bnx = BNX(settings, noise)
# generate reads
for chip in range(1, settings.chips + 1):
chip_settings = {'size': 0, 'scans': 0,
'chip_id': '20249,11843,07/17/2014,840014289', 'run_id': str(chip),
'flowcell': 1, 'molecule_count': 0,
'bpp': 425, 'stretch_factor': noise.chip_stretch_factor()}
chip_settings['bpp'] /= chip_settings['stretch_factor']
molecules = {}
for label in settings.labels:
molecules[label] = []
# generate reads
moleculeID = 0
relative_stretch = []
for scan in range(1, settings.scans_per_chip + 1):
chip_settings['scans'] += 1
scan_stretch = noise.scan_stretch_factor(chip_settings['stretch_factor'])
for l, m, meta in noise.generate_scan(seq_lens, cum_seq_lens, fns, rns):
moleculeID += 1
molecule = {}
for label in settings.labels:
molecule[label] = []
for nick in m:
molecule[nick[1]['label']].append(nick[0])
for label in settings.labels:
if settings.min_nicks <= len(molecule[label]):
molecules[label].append((l, molecule[label], chip_settings['scans'], meta))
relative_stretch.append(noise.mol_stretch_factor(scan_stretch) / chip_settings['stretch_factor'])
chip_settings['molecule_count'] += 1
chip_settings['size'] += l
# write output
for label in settings.labels:
moleculeID = 0
ofile = open(settings.prefix + '.' + label + '.' + str(chip) + '.bnx', 'w')
#bedfile = open(settings.prefix + '.' + label + '.' + str(chip) + '.bed', 'w')
bnx.write_bnx_header(ofile, label, chip_settings)
for l, m, s, meta in molecules[label]:
moleculeID += 1
bnx.write_bnx_entry((moleculeID, l, s), m, ofile, chip_settings, relative_stretch[moleculeID - 1])
#for idx, mol in enumerate(meta):
#bedfile.write(seqs[mol[0]] + '\t' + str(mol[1]) + '\t' + str(mol[1] + l) + '\t' + str(moleculeID) + ('.' + str(idx) if len(meta) > 1 else '') + '\n')
ofile.close()
#bedfile.close()
print('Finished chip ' + str(chip) + '/' + str(settings.chips))
print('Finished processing ' + settings.name + '.\n')
def omsim(settings):
# cd to the directory containing the configuration file
os.chdir(settings.directory)
# process input
cmaps = import_input(settings)
print('Imported ' + str(sum(cmaps[iname].count() for iname in cmaps)) +
' nicks in ' + str(sum(cmaps[iname].seq_len()
for iname in cmaps)) + 'bp.')
cmaps = KMP(settings, cmaps)
# write processed input
write_processed_input(settings, cmaps)
# filter input for enzymes / files we need
seqs, seq_lens, fns = filter_input(settings, cmaps)
prev = 0
cum_seq_lens = []
for seq_len in seq_lens:
curr = prev + seq_len
cum_seq_lens += [curr]
prev = curr
print('Using ' + str(sum(len(f) for f in fns)) + ' nicks in ' +
str(sum(seq_lens)) + 'bp.')
#compute reverse nicking sites
rns = get_rns(settings, fns, seq_lens)
#estimate number of chips based on expected coverage
if settings.chips == 0:
temp = int(
sum(seq_lens) * settings.coverage /
(settings.scans_per_chip * settings.get_scan_size()))
settings.chips = temp if temp > 1 else 1
#estimate coverage
settings.estimated_coverage = int(
settings.get_scan_size() * settings.scans_per_chip * settings.chips /
float(sum(seq_lens)))
print('Generating reads on ' + str(settings.chips) + ' chip' +
('' if settings.chips == 1 else 's') + ', estimated coverage: ' +
str(settings.estimated_coverage) + 'x.')
noise = Noise(settings)
bnx = BNX(settings, noise)
# generate reads
for chip in range(1, settings.chips + 1):
chip_settings = {
'size': 0,
'scans': 0,
'chip_id': '20249,11843,07/17/2014,840014289',
'run_id': str(chip),
'flowcell': 1,
'molecule_count': 0,
'bpp': 425,
'stretch_factor': noise.chip_stretch_factor()
}
chip_settings['bpp'] /= chip_settings['stretch_factor']
molecules = {}
for label in settings.labels:
molecules[label] = []
# generate reads
moleculeID = 0
relative_stretch = []
for scan in range(1, settings.scans_per_chip + 1):
chip_settings['scans'] += 1
scan_stretch = noise.scan_stretch_factor(
chip_settings['stretch_factor'])
for l, m, meta in noise.generate_scan(seq_lens, cum_seq_lens, fns,
rns):
moleculeID += 1
molecule = {}
for label in settings.labels:
molecule[label] = []
for nick in m:
molecule[nick[1]['label']].append(nick[0])
for label in settings.labels:
if settings.min_nicks <= len(molecule[label]):
molecules[label].append(
(l, molecule[label], chip_settings['scans'], meta))
relative_stretch.append(
noise.mol_stretch_factor(scan_stretch) /
chip_settings['stretch_factor'])
chip_settings['molecule_count'] += 1
chip_settings['size'] += l
# write output
for label in settings.labels:
moleculeID = 0
ofile = open(
settings.prefix + '.' + label + '.' + str(chip) + '.bnx', 'w')
#bedfile = open(settings.prefix + '.' + label + '.' + str(chip) + '.bed', 'w')
bnx.write_bnx_header(ofile, label, chip_settings)
for l, m, s, meta in molecules[label]:
moleculeID += 1
bnx.write_bnx_entry((moleculeID, l, s), m, ofile,
chip_settings,
relative_stretch[moleculeID - 1])
#for idx, mol in enumerate(meta):
#bedfile.write(seqs[mol[0]] + '\t' + str(mol[1]) + '\t' + str(mol[1] + l) + '\t' + str(moleculeID) + ('.' + str(idx) if len(meta) > 1 else '') + '\n')
ofile.close()
#bedfile.close()
print('Finished chip ' + str(chip) + '/' + str(settings.chips))
print('Finished processing ' + settings.name + '.\n')
