def makeNanoporeRead(f5_path):
# here we load the NanoporeRead and write it to a file
np = NanoporeRead(fast_five_file=f5_path, twoD=False) # make this a config arg
ok = np.Initialize(job)
if not ok:
return None
_l = np.read_label
tF = job.fileStore.getLocalTempFile()
fH = open(tF, "w")
ok = np.Write(job, fH, initialize=False)
if not ok:
fH.close()
return None
fH.close()
# then we gzip it and deliver it to the readstore and return the ledger line
fn = LocalFile(workdir=workdir, filename="%s.np.gz" % _l)
fH = open(tF, "rb")
gz = gzip.open(fn.fullpathGetter(), "wb")
shutil.copyfileobj(fH, gz)
fH.close()
gz.close()
try:
deliverOutput(job, fn, readstore_dir)
except RuntimeError:
job.fileStore.logToMaster("[makeNanoporeReadsJobFunction]Read %s failed to upload" % _l)
return None
return (_l, "%s%s\n" % (readstore_dir, fn.filenameGetter()))
def _SignalMachine(read_label, cigar, nanopore_read):
guide_aln = LocalFile(workdir=workdir)
_handle = open(guide_aln.fullpathGetter(), "w")
_handle.write(cigar)
_handle.close()
require(os.path.exists(guide_aln.fullpathGetter()),
"NO guide aln file")
signalMachine_args = [
"--sm3Hdp",
"-s",
"1",
"-o",
"%s" % degenerate_enum,
"-L",
"%s" % read_label,
"-T",
"%s%s" % (DOCKER_DIR, models.localFileName(hmmfid)),
"-q",
"%s%s" % (DOCKER_DIR, nanopore_read.filenameGetter()),
"-f",
"%s%s" % (DOCKER_DIR, fw_seqfile.filenameGetter()),
"-b",
"%s%s" % (DOCKER_DIR, bw_seqfile.filenameGetter()),
"-p",
"%s%s" % (DOCKER_DIR, guide_aln.filenameGetter()),
"-u",
"%s%s" % (DOCKER_DIR, posteriors.filenameGetter()),
"-v",
"%s%s" % (DOCKER_DIR, models.localFileName(hdpfid)),
]
try:
docker_call(job=job,
tool=signalMachine_image,
parameters=signalMachine_args,
work_dir=(workdir + "/"))
except subprocess.CalledProcessError:
pass
def getFastqFromBam(job,
bam_sample,
samtools_image="quay.io/ucsc_cgl/samtools"):
# n.b. this is NOT a jobFunctionWrappingJob, it just takes the parent job as
# an argument to have access to the job store
# download the BAM to the local directory, use a uid to aviod conflicts
uid = uuid.uuid4().hex
work_dir = job.fileStore.getLocalTempDir()
local_bam = LocalFile(workdir=work_dir, filename="bam_{}.bam".format(uid))
fastq_reads = LocalFile(workdir=work_dir,
filename="fastq_reads{}.fq".format(uid))
urlDownload(parent_job=job,
source_url=bam_sample.URL,
destination_file=local_bam)
require(not os.path.exists(fastq_reads.fullpathGetter()),
"[getFastqFromBam]fastq file already exists")
# run samtools to get the reads from the BAM
# TODO use DOCKER_DIR and clean this up. idea: make globls.py or something
samtools_parameters = [
"fastq", "/data/{}".format(local_bam.filenameGetter())
]
with open(fastq_reads.fullpathGetter(), 'w') as fH:
docker_call(job=job,
tool=samtools_image,
parameters=samtools_parameters,
work_dir=work_dir,
outfile=fH)
require(os.path.exists(fastq_reads.fullpathGetter()),
"[getFastqFromBam]didn't generate reads")
# upload fastq to fileStore
return job.fileStore.writeGlobalFile(fastq_reads.fullpathGetter())