def separatePairsAndSingles(cf):
"""In an array of runs, separate the paired end reads into two separate files, and
the singles into a third."""
fastqfiles = get_array(cf, 'fastqfiles')
srafetchxml = cf.get_input('srafetchxml')
leftfh = open(cf.get_output('left'), 'w')
rightfh = open(cf.get_output('right'), 'w')
singlefh = open(cf.get_output('single'), 'w')
for accession, fastqfile in fastqfiles:
fqp = FastqParser()
fastqfh = open(fastqfile, 'U')
if isPaired(srafetchxml, accession):
iter = fqp.parse(fastqfh)
#paired end run
while True:
try:
pe1 = iter.next()
pe2 = iter.next()
leftfh.write(str(pe1) + '\n')
rightfh.write(str(pe2) + '\n')
except StopIteration:
break
else:
#single end run
for rec in fqp.parse(fastqfh):
singlefh.write(str(rec) + '\n')
leftfh.close()
rightfh.close()
singlefh.close()
return constants.OK
def getOverRepClusters(cf):
"""Identify over represented clusters in a fastqfile and write the cluster seed
to a file."""
fastqfile = cf.get_input('fastqfile')
resultsuc = cf.get_input('resultsuc')
resultsfa = cf.get_input('resultsfa')
percRep = cf.get_parameter('percRep', 'float')
output = cf.get_output('resultsfa')
totalSeqs = 0
fqp = FastqParser()
for rec in fqp.parse(open(fastqfile, 'rb')):
totalSeqs += 1
clusterCounts = {}
reader = csv.reader(open(resultsuc, 'rb'), quoting=csv.QUOTE_NONE, delimiter='\t')
for row in reader:
if row[0] == 'H':
if not clusterCounts.has_key(row[-1]):
clusterCounts[row[-1]] = 0
clusterCounts[row[-1]] += 1
outfh = open(output, 'wb')
for rec in fasta_itr(resultsfa):
if not clusterCounts.has_key(rec.header):
continue
clusterRep = (float(clusterCounts[rec.header]) / float(totalSeqs)) * 100
if clusterRep >= percRep:
outfh.write(str(rec) + '\n')
outfh.close()
return constants.OK
def getNamesFromFastQ(cf):
"""Write the headers of a fastqfile to an outputfile."""
outfh = open(cf.get_output("namelist"), "w")
fqp = FastqParser()
for rec in fqp.parse(open(cf.get_input("fastqfile"), "U")):
outfh.write("%s\n" % rec.header)
outfh.close()
return constants.OK
def fastq_merge(cf):
"""Merge an array of fastqfiles."""
outfh = open(cf.get_output('output'), 'w')
fastqfiles = get_array(cf, 'in_array')
cf.write_log(str(fastqfiles))
fqp = FastqParser()
for key, fastqfile in fastqfiles:
for rec in fqp.parse(open(fastqfile, 'U')):
outfh.write(str(rec) + '\n')
outfh.close()
return constants.OK
inputfile = cf.get_input('srafile')
srafetchxml = cf.get_input('srafetchxml')
accession = cf.get_parameter('accession', 'string')
outputfile = cf.get_output('fastqfile')
params = []
if isPaired(srafetchxml, accession):
cf.write_log('Run is paired end.')
params.append('--split-spot')
outfh = open(outputfile + '.tmp', 'wb')
try:
params.append('-Z')
params.append(inputfile)
subprocess.check_call(['fastq-dump'] + params, stdout=outfh)
except subprocess.CalledProcessError, e:
cf.write_log("Error running fastq-dump.")
cf.write_log("Error: %s" % str(e))
return constants.GENERIC_ERROR
finally:
outfh.close()
#format the fastq headers
outfh = open(outputfile, 'wb')
fqp = FastqParser()
for rec in fqp.parse(open(outputfile + '.tmp', 'U')):
rec.header = rec.header.split(' ')[1]
outfh.write(str(rec) + '\n')
outfh.close()
return constants.OK
anduril.main(sra2fastq)