args = parser.parse_args()
inputFile = args.i
outputRaw = args.rawout
outputThreshold = args.tout
threshold = args.threshold
kmerSize = args.k
# Read in JSON-Bead file
#Calculate kmer pools for all beads
kmerPool = []
beadCount = 0
with open(inputFile, 'r') as f:
for line in f:
b = bead.beadSequence(json.loads(line))
kmerPool.append(kmer.kmerCount(b, kmerSize))
beadCount += 1
print('Found {0} beads.'.format(beadCount))
# Calculate kmer distance for all pairs
edge = []
edgeThreshold = []
n1 = 0
n2 = 0
for pair in combinations(kmerPool, 2):
D = kmer.kmerDistance((pair[0].set, pair[1].set)).mashDistance()
edge.append((pair[0].barcode, pair[1].barcode, D))
if threshold[0] <= D <= threshold[1]:
edgeThreshold.append((pair[0].barcode, pair[1].barcode, D))
n2 += 1
n1 += 1
default='kmerReport.tsv',
help='Report file on Kmers.')
args = parser.parse_args()
inputFile = args.i
outputFile = args.o
kmerSize = args.k
reportFile = args.report
kmerPool = []
report = {}
kmerFrag = []
with open(inputFile, 'r') as f:
for line in f:
b = bead.beadSequence(json.loads(line))
kmers = kmer.kmerCount(b, kmerSize)
barcode = b.barcode
kmerPool.append({barcode: kmers.kmers})
kmerNumber = len(kmers.kmers)
fragNumber = len(b.fragments)
kmerFrag.append((kmerNumber, fragNumber))
report[kmerNumber] = report.get(kmerNumber, 1) + 1
with open(outputFile, 'w') as f:
for line in kmerPool:
f.write('{0}\n'.format(json.dumps(line)))
report = sorted([x for x in report.items()], key=lambda i: i[0])
with open(reportFile, 'w') as f:
f.write('KmerNumber\tCount\n')
for line in report:
def main():
# Read in JSON-Bead file
#Calculate kmer pools for all beads
kmerPool = []
beadCount = 0
with open(inputFile, 'r') as f:
for line in f:
b = bead.beadSequence(json.loads(line))
kmerPool.append(kmer.kmerCount(b, kmerSize))
beadCount += 1
print('Found {0} beads.'.format(beadCount))
# Setup the parallel enviroment
# Create shared list for store edge list and progress counter
manager = Manager()
edge = manager.list([[]] * job) # n list for edge list
count = manager.list([0] * job) # n list for count
print('Starting mash distance ...')
# Divide the kmer pair pool
pairPool = []
for pair in combinations(kmerPool, 2):
pairPool.append(pair)
size = len(pairPool)
print('Total is {0} pairs.'.format(size))
step = size // job
print('Step is {0}'.format(step))
start = 0
workers = []
print(len(pairPool))
for i in range(job):
if i + 1 < job: # not the last job
workers.append(
Process(target=kmerDistanceWorker,
args=(pairPool[start:start + step], edge, i, count)))
start += step
print('Start change to {0}'.format(start))
else:
workers.append(
Process(target=kmerDistanceWorker,
args=(pairPool[start:], edge, i, count)))
print('Starting %i jobs ...' % job)
count_worker = 1
for j in workers:
j.start()
print('Starting thread No. %i ...' % count_worker)
count_worker += 1
job_alive = True
while job_alive:
time.sleep(0.01)
job_alive = False
for j in workers:
if j.is_alive():
job_alive = True
progress = str(sum(count) / size * 100) + "\r"
sys.stderr.write(progress)
#print(len(edge[0]))
for j in workers:
j.join()
print('Finished dereplicating.')
with open(outputRaw, 'w') as f:
f.write('Source\tTarget\tDistance\n')
for item in edge:
for line in item:
f.write('{0}\t{1}\t{2}\n'.format(line[0], line[1], line[2]))
default='kmerReport.tsv',
help='A report on kmer distribuion on Kmers.')
args = parser.parse_args()
inputFile = args.i
outputFile = args.o
k = args.k
reportFile = args.report
kmerPool = []
report = {}
kmerFrag = []
with open(inputFile, 'r') as f:
for line in f:
b = bead.beadSequence(json.loads(line))
kmers = kmer.kmerCount(b, k)
barcode = b.barcode
kmerPool.append({barcode: kmers.kmers})
kmerNumber = len(kmers.kmers)
fragNumber = len(b.fragments)
kmerFrag.append((kmerNumber, fragNumber))
report[kmerNumber] = report.get(kmerNumber, 1) + 1
with open(outputFile, 'w') as f:
for line in kmerPool:
f.write('{0}\n'.format(json.dumps(line)))
report = sorted([x for x in report.items()], key=lambda i: i[0])
with open(reportFile, 'w') as f:
f.write('KmerNumber\tCount\n')
for line in report: