def mapReads(in_fastq, ref_fasta, out_dir, experiment):
'''use mapPacBio.sh from bbmap to identify reference sequenecs matched by one or more PacBio reads with no substitutions (indels allowed)'''
# mapPacBio path (first part gets path to folder running script)
bbmap_pacbio = (os.path.dirname(
os.path.realpath(__file__))) + '/bbmap_37_28/mapPacBio.sh'
# get sample name from input file
# need to strip off .gz and .fastq extensions sequentially
sample_name = os.path.splitext(
os.path.splitext(os.path.basename(in_fastq))[0])[0]
print('Sample name: ' + sample_name)
# create output genotyping folder if it doesn't exist
sample_dir = utils.createOutputFolder(out_dir + '/genotyping/' +
sample_name)
# create bbmap command
cmd = [
bbmap_pacbio, 'in=' + in_fastq, 'ref=' + ref_fasta,
'covstats=' + sample_dir + '/' + sample_name + '.covstats.tmp.txt',
'outm=' + sample_dir + '/' + sample_name + '.mapped.bam',
'outu=' + sample_dir + '/' + sample_name + '.unmapped.fastq.gz',
'statsfile=' + sample_dir + '/' + sample_name + '.mapping_stats.txt',
'subfilter=0', 'nzo=t', 'ambiguous=all', 'maxlen=1500', 'minid=0.9',
'maxindel=10', 'minratio=0.8', 'twocolumn=t', 'ow=t'
]
# print bbmap command
status.printStatus(' '.join(cmd))
# call bbmap
# suppress stats output (saved to file, no need to clutter stderr)
# FNULL = open(os.devnull, 'w')
subprocess.call(cmd)
# FNULL.close()
# add descriptors to covstats output
with open(sample_dir + '/' + sample_name + '.covstats.tmp.txt', 'r') as f:
with open(sample_dir + '/' + sample_name + '.covstats.txt', 'w') as g:
for idx, line in enumerate(f):
# print header in first line, otherwise value of sample_name
if idx == 0:
g.write('sample_name' + '\t' + line.rstrip('\n') + '\t' +
'ref_fasta\tanalysis_path\texperiment\n')
else:
g.write(sample_name + '\t' + line.rstrip('\n') + '\t' +
ref_fasta + '\t' + out_dir + '\t' + experiment +
'\n')
# remove temporary covstats.tmp.txt file after covstats.txt with sample ID prepared
if os.path.exists(sample_dir + '/' + sample_name + '.covstats.tmp.txt'):
os.remove(sample_dir + '/' + sample_name + '.covstats.tmp.txt')
# copy reference file to output folder
copyfile(ref_fasta, out_dir + '/genotyping/' + os.path.basename(ref_fasta))
# return covstats file
return sample_dir + '/' + sample_name + '.covstats.txt'
def mapReadsFolder(fastq_folder, ref_fasta, out_dir, experiment):
'''map FASTQ reads to reference for all files in folder and make pivottable from results'''
# create list to store covstats paths
covstats = []
# count number of fastq files that will be processed
fastq_count = 0
for filename in os.listdir(fastq_folder):
if filename.endswith(".fastq.gz"):
fastq_count += 1
# run mapReads on FASTQ files in specific folder
for idx, filename in enumerate(os.listdir(fastq_folder)):
if filename.endswith(".fastq.gz"):
# run mapReads for each file
# return covstats file path - add to covstats list
status.printStatus('Genotyping FASTQ file ' + str(idx + 1) +
' of ' + str(fastq_count))
covstats.append(
mapReads(fastq_folder + '/' + filename, ref_fasta, out_dir,
experiment))
continue
else:
continue
status.printStatus('Make pivot table from: ' + ', '.join(covstats))
# create pivottable
pivotTable(covstats, out_dir)
def makeFastq(ccs_bam):
'''use smrtlink bam2fq to produce gzip compressed FASTQ file from CCS bam'''
'''/slipstream/oc/pacbio/smrtlink_v6/smrtcmds/bin/'''
# path to smrtlink bam2fastq
smrtlink_bam2fastq_path = '/slipstream/oc/pacbio/smrtlink_v6/smrtcmds/bin/bam2fastq'
# create fastq output file name
ccs_basename = os.path.splitext(os.path.basename(ccs_bam))[0]
fastq_output = os.path.dirname(ccs_bam) + '/' + ccs_basename
print(fastq_output)
# call bam2fastq
cmd = [
smrtlink_bam2fastq_path,
ccs_bam,
'-o',
fastq_output,
]
status.printStatus('bam2fastq command: ' + ' '.join(cmd))
status.printStatus('bam2fastq processing of ' + ccs_bam + ' started')
subprocess.call(cmd)
status.printStatus('bam2fastq processing of ' + ccs_bam + ' completed')
status.printStatus('gzip compressed FASTQ file saved to ' + fastq_output +
'.fastq.gz')
# return path to output fastq file
return fastq_output + '.fastq.gz'
def importLabkey(df):
'''import tabular genotypes into https://dholk.primate.wisc.edu/list/dho/gs/grid.view?listId=1630'''
# make list of records from tabular dataframe
labkey_data = df.to_dict('records')
# add to labkey
x = labkeyInteract.LabkeyInsertRows()
x.serverContext('/dho/gs/')
x.labkey_schema = 'lists'
x.labkey_table = 'pacbio_genotypes'
x.insertRows(x.labkey_schema, x.labkey_table, labkey_data)
# log
status.printStatus(
str(len(labkey_data)) + ' sample genotypes added to dholk')
def makeCcs(subreads,
out_dir,
minPredictedAccuracy='0.9',
minLength='1000',
maxLength='1500'):
'''use smrtlink ccs to produce consensus sequence'''
# path to smrtlink ccs
smrtlink_ccs_path = '/slipstream/SMRT4/SMRT/smrtcmds/bin/ccs'
# check that subreads file exists
if os.path.exists(subreads) == False:
status.printStatus(
'Error: Specified subread file does not exist. Check your file path and try again.'
)
return
# filename of input file
subreads_basename = os.path.splitext(os.path.basename(subreads))[0]
print(subreads_basename)
# create output directory if it doesn't exist
utils.createOutputFolder(out_dir)
# call ccs
cmd = [
smrtlink_ccs_path, '--minPredictedAccuracy', minPredictedAccuracy,
'--minLength', minLength, '--maxLength', maxLength, subreads,
out_dir + '/' + subreads_basename + '.ccs.bam'
]
status.printStatus('CCS command: ' + ' '.join(cmd))
status.printStatus('CCS processing of ' + subreads + ' started')
subprocess.call(cmd)
status.printStatus('CCS processing of ' + subreads + ' completed')
status.printStatus('Output CCS file saved to ' + out_dir + '/' +
subreads_basename + '.ccs.bam')
# create fastq file
fastq_path = makeFastq(out_dir + '/' + subreads_basename + '.ccs.bam')
return fastq_path
def extractSequenceNames(gzip_fastq):
'''convert FASTQ to FASTA and then extract sequence names to new file'''
# path to reformat.sh, update as needed
bbmap_reformat_sh = '/slipstream/oc/jrcanalysisdata/mhcAnalysis/bbmap/reformat.sh'
# create temporary whitelist sequence path
whitelist_sequences = gzip_fastq + '.whitelist.tmp.txt'
print(whitelist_sequences)
# create reformat.sh command to convert fastq to fasta
cmd = [
bbmap_reformat_sh, 'in=' + gzip_fastq,
'out=' + whitelist_sequences + '.tmp.fasta'
]
# print bbmap command
status.printStatus(' '.join(cmd))
# call reformat.sh
subprocess.call(cmd)
# need to remove trailing /ccs from FASTA file
# use code from https://stackoverflow.com/questions/17140886/how-to-search-and-replace-text-in-a-file-using-python
with fileinput.FileInput(whitelist_sequences + '.tmp.fasta',
inplace=True) as file:
for line in file:
print(line.replace('/ccs', ''), end='')
# extract sequence names to new file
with open(whitelist_sequences, 'w') as the_file:
for seq_record in SeqIO.parse(whitelist_sequences + '.tmp.fasta',
"fasta"):
the_file.write(seq_record.id + '\n')
# return path to fasta_output
return whitelist_sequences
def getSamples(pacbio_id):
'''retrieve sample information from genotyping Samples table'''
# get runId corresponding to pacbio_id
runId = getRunId(pacbio_id)
# get samples from specified PacBio run
pacbio_samples = labkeyInteract.LabkeySelectRows()
pacbio_samples.serverContext('dho/pacbio')
pacbio_samples.set_filters('run_id', runId)
result = pacbio_samples.selectRows(labkey_schema='genotyping', labkey_table='Samples')
# log count of samples in pacbio_id
status.printStatus(str(result['rowCount']) + ' samples detected in ' + pacbio_id)
status.printStatus('Barcode configuration')
# log information on each sample
print('OC_ID\tForward Barcode\tReverse Barcode')
samples = {} # initialize samples dictionary
for i in result['rows']:
# use oc_id if it exists, otherwise use animal_id to identify sample name
if i['oc_animal_id'] == None:
sample_name = i['animal_id']
else:
sample_name = i['oc_animal_id']
# run normalizeBarcodes to create PacBio standard identifiers
renamed_barcodes = normalizeBarcodes(i)
# print samples
print(sample_name + '\t' + renamed_barcodes[0]+ '\t' + renamed_barcodes[1])
# create dictionary with sample name and barcodes
samples[sample_name] = [renamed_barcodes[0], renamed_barcodes[1]]
return samples
def getRunId(pacbio_id):
'''inherit pacbio_id (e.g., PacBio48) from parent function and retrieve run identifier'''
# get Pacbio run ID for specified run
# necessary because Samples table stores run_id as foreign key lookup to runs table
# debug modification by JRC 09202018
pacbio_run_id = labkeyInteract.LabkeySelectRows()
pacbio_run_id.serverContext('dho/pacbio')
pacbio_run_id.set_filters('pacbio_id', pacbio_id)
result = pacbio_run_id.selectRows(labkey_schema='lists', labkey_table='runs')
# debug modification by JRC 09202018
print('result is')
print(result)
time.sleep(5)
# extract run number from result
runNumber = result['rows'][0]['run_num']
# log whether pacbio_id corresponding to run_id is found
if runNumber != '':
status.printStatus(pacbio_id + ' found in dholk.primate.wisc.edu')
return runNumber
def makeFastq(ccs_bam):
'''use smrtlink bam2fq to produce gzip compressed FASTQ file from CCS bam'''
# path to smrtlink bam2fastq
smrtlink_bam2fastq_path = '/slipstream/SMRT4/SMRT/smrtcmds/bin/bam2fastq'
# create fastq output file name
ccs_basename = os.path.splitext(os.path.basename(ccs_bam))[0]
fastq_output = os.path.dirname(ccs_bam) + '/' + ccs_basename
# call bam2fastq
cmd = [
smrtlink_bam2fastq_path,
ccs_bam,
'-o',
fastq_output,
]
status.printStatus('bam2fastq command: ' + ' '.join(cmd))
status.printStatus('bam2fastq processing of ' + ccs_bam + ' started')
subprocess.call(cmd)
status.printStatus('bam2fastq processing of ' + ccs_bam + ' completed')
status.printStatus('gzip compressed FASTQ file saved to ' + fastq_output +
'.fastq.gz')
# return path to output fastq file
return fastq_output + '.fastq.gz'
# if __name__ == '__main__': # if run directly from the command line
# # command line parameters
# import argparse
# parser = argparse.ArgumentParser()
# parser.add_argument("out_dir", help='Folder that will store all output files')
# parser.add_argument("--subreads", required=True,
# help='Path to file of PacBio subreads. Will be converted to CCS file.')
# parser.add_argument("--ccsMinAccuracy", required=False,
# help='Set minPredicted accuracy (from 0-1) for retaining CCS reads. Default=0.9. Recommend 0.999 for de novo allele discovery.')
# parser.add_argument("--ccsMinLength", required=False,
# help='Set minLength in bp for retaining CCS reads. Default=1000. Set to minimum expected amplicon size.')
# parser.add_argument("--ccsMaxLength", required=False,
# help='Set maxLength in bp for retaining CCS reads. Default=1500. Set to minimum expected amplicon size.')
# args = parser.parse_args()
#
# # make output folder if it doesn't exist
# utils.createOutputFolder(args.out_dir)
#
# # configure log to stdout
# logging.basicConfig(filename=args.out_dir + '/log.txt', filemode='w', level=logging.DEBUG,
# format='%(asctime)s %(message)s', datefmt='%Y-%m-%d %I:%M:%S')
#
# # run with command line parameters
# d = {}
# d['subreads'] = args.subreads
# d['out_dir'] = args.out_dir
# if args.ccsMinAccuracy is not None: d['minPredictedAccuracy'] = args.ccsMinAccuracy
# if args.ccsMinLength is not None: d['minLength'] = args.ccsMinLength
# if args.ccsMaxLength is not None: d['maxLength'] = args.ccsMaxLength
#
# # log command line
# status.printStatus('Command line statment: ' + ' '.join(sys.argv))
#
# # run makeCcs function
# makeCcs(**d)
# # test invokation
# d = {}
# d['subreads'] = '/slipstream/pacbio/pacbio_raw/pacbio48/3_C01/m54178_170519_124037.subreads.bam'
# d['out_dir'] = '/slipstream/shared_data/19070/pacbio48-default-minQuality/11'
# d['minPredictedAccuracy'] = '0.9'
# d['minLength'] = '1000'
# d['maxLength'] = '1500'
#
# # log command line
# status.printStatus('CCS paramaeters: ' + d)
#
# # run makeCcs function
# makeCcs(**d)
# test bam2fastq
# makeFastq('/slipstream/shared_data/19070/pacbio48//20170604082124/ccs//m54178_170519_124037.subreads.ccs.bam')
env["TEXTTEST_TMP"] = os.path.join(options.rootDir, env["FILEPREFIX"]+"texttesttmp")
env["TEXTTEST_HOME"] = os.path.join(options.rootDir, options.testsDir)
if "SUMO_HOME" not in env:
env["SUMO_HOME"] = os.path.join(os.path.dirname(__file__), '..', '..')
shutil.rmtree(env["TEXTTEST_TMP"], True)
if not os.path.exists(env["SUMO_REPORT"]):
os.makedirs(env["SUMO_REPORT"])
for name in ["dfrouter", "duarouter", "jtrrouter", "netconvert", "netgenerate", "od2trips", "sumo", "polyconvert", "sumo-gui", "activitygen"]:
binary = os.path.join(options.rootDir, options.binDir, name + programSuffix + ".exe")
if name == "sumo-gui":
if os.path.exists(binary):
env["GUISIM_BINARY"] = binary
elif os.path.exists(binary):
env[name.upper()+"_BINARY"] = binary
log = open(testLog, 'w')
# provide more information than just the date:
nameopt = " -name %sr%s" % (date.today().strftime("%d%b%y"), svnrev)
if options.sumoExe == "meso":
runInternalTests.runInternal(programSuffix, "-b "+env["FILEPREFIX"]+nameopt, log)
else:
subprocess.call("texttest.py -b "+env["FILEPREFIX"]+nameopt, stdout=log, stderr=subprocess.STDOUT, shell=True)
subprocess.call("texttest.py -a sumo.gui -b "+env["FILEPREFIX"]+nameopt, stdout=log, stderr=subprocess.STDOUT, shell=True)
subprocess.call("texttest.py -b "+env["FILEPREFIX"]+" -coll", stdout=log, stderr=subprocess.STDOUT, shell=True)
ago = datetime.datetime.now() - datetime.timedelta(50)
subprocess.call('texttest.py -s "batch.ArchiveRepository session='+env["FILEPREFIX"]+' before=%s"' % ago.strftime("%d%b%Y"),
stdout=log, stderr=subprocess.STDOUT, shell=True)
log.close()
log = open(statusLog, 'w')
status.printStatus(makeLog, makeAllLog, env["TEXTTEST_TMP"], env["SMTP_SERVER"], log)
log.close()
def main(options, platform="x64"):
env["FILEPREFIX"] = options.msvc_version + options.suffix + platform
prefix = os.path.join(options.remoteDir, env["FILEPREFIX"])
makeLog = prefix + "Release.log"
makeAllLog = prefix + "Debug.log"
testLog = prefix + "Test.log"
testDebugLog = prefix + "DebugTest.log"
statusLog = prefix + "status.log"
log_handler = status.set_rotating_log(makeLog)
status.killall(("", "D"), BINARIES)
toClean = []
for ext in ("*.exe", "*.ilk", "*.pdb", "*.py", "*.pyd", "*.dll", "*.lib", "*.exp", "*.jar", "*.manifest", "*.fmu"):
toClean += glob.glob(os.path.join(SUMO_HOME, "bin", ext))
toClean += glob.glob(os.path.join(SUMO_HOME, "tools", "lib*", "*lib*"))
toClean += glob.glob(os.path.join(SUMO_HOME, "share", "*", "*"))
for f in toClean:
try:
os.remove(f)
except Exception:
pass
for d in (glob.glob(os.path.join(SUMO_HOME, "bin", "osgPlugins*")) +
glob.glob(os.path.join(SUMO_HOME, "tools", "*.egg-info"))):
shutil.rmtree(d, ignore_errors=True)
for d in glob.glob(os.path.join(SUMO_HOME, "docs", "*")):
if os.path.basename(d) in ('examples', 'javadoc', 'man', 'pydoc', 'tutorial', 'userdoc'):
shutil.rmtree(d, ignore_errors=True)
status.printLog("Running %s build using python %s." % (options.msvc_version, sys.version))
gitrev = repositoryUpdate(options)
generator = "Visual Studio " + ("12 2013" if options.msvc_version == "msvc12" else "16 2019")
buildDir = generateCMake(generator, platform, options.suffix == "extra", options.python)
ret = status.log_subprocess(["cmake", "--build", ".", "--config", "Release"], cwd=buildDir)
status.log_subprocess(["cmake", "--build", ".", "--config", "Release", "--target", "lisum"], cwd=buildDir)
status.log_subprocess(["cmake", "--build", ".", "--config", "Release", "--target", "userdoc", "examples"],
cwd=buildDir)
status.log_subprocess(["cmake", "--install", "."], cwd=buildDir)
plat = platform.lower().replace("x", "win")
if options.msvc_version != "msvc16":
plat += options.msvc_version
for d in glob.glob(os.path.join(buildDir, "sumo-*")):
if os.path.isdir(d):
installDir = d
installBase = os.path.basename(installDir)
binaryZip = os.path.join(buildDir, "sumo-%s%s-%s" % (plat, options.suffix, installBase[5:]))
if ret == 0:
try:
for f in (glob.glob(os.path.join(SUMO_HOME, "*.md")) +
[os.path.join(SUMO_HOME, n) for n in ("AUTHORS", "ChangeLog", "LICENSE")]):
shutil.copy(f, installDir)
if options.suffix == "extra":
shutil.copy(os.path.join(SUMO_HOME, "build", "wix", "gpl-2.0.txt"), os.path.join(installDir, "LICENSE"))
for f in glob.glob(os.path.join(SUMO_HOME, "bin", "*.jar")):
shutil.copy(f, os.path.join(installDir, "bin"))
shutil.copytree(os.path.join(SUMO_HOME, "docs"), os.path.join(installDir, "docs"),
ignore=shutil.ignore_patterns('web'))
shutil.copy(os.path.join(buildDir, "src", "version.h"), os.path.join(installDir, "include"))
status.printLog("Creating sumo.zip.")
shutil.make_archive(binaryZip, 'zip', buildDir, installBase)
shutil.copy(binaryZip + ".zip", options.remoteDir)
status.printLog("Creating sumo.msi.")
if options.suffix == "extra":
wix.buildMSI(binaryZip + ".zip", binaryZip + ".msi",
license=os.path.join(SUMO_HOME, "build", "wix", "gpl-2.0.rtf"))
else:
wix.buildMSI(binaryZip + ".zip", binaryZip + ".msi")
shutil.copy(binaryZip + ".msi", options.remoteDir)
except Exception as ziperr:
status.printLog("Warning: Could not zip to %s.zip (%s)!" % (binaryZip, ziperr))
gameZip = os.path.join(buildDir, "sumo-game-%s%s-%s.zip" % (plat, options.suffix, installBase[5:]))
status.printLog("Creating sumo-game.zip.")
try:
status.log_subprocess(["cmake", "--build", ".", "--target", "game"], cwd=buildDir)
shutil.move(os.path.join(buildDir, "sumo-game.zip"), gameZip)
shutil.copy(gameZip, options.remoteDir)
except Exception as e:
status.printLog("Warning: Could not create nightly sumo-game.zip! (%s)" % e)
debug_handler = status.set_rotating_log(makeAllLog, log_handler)
ret = status.log_subprocess(["cmake", "--build", ".", "--config", "Debug"], cwd=buildDir)
if ret == 0:
debugZip = os.path.join(buildDir, "sumo-%s%sDebug-%s.zip" % (plat, options.suffix, installBase[5:]))
status.printLog("Creating sumoDebug.zip.")
try:
with zipfile.ZipFile(debugZip, 'w', zipfile.ZIP_DEFLATED) as zipf:
for ext in ("*D.exe", "*.dll", "*D.pdb"):
for f in glob.glob(os.path.join(SUMO_HOME, "bin", ext)):
zipf.write(f, os.path.join(installBase, "bin", os.path.basename(f)))
shutil.copy(debugZip, options.remoteDir)
except IOError as ziperr:
status.printLog("Warning: Could not zip to %s (%s)!" % (debugZip, ziperr))
log_handler = status.set_rotating_log(testLog, debug_handler)
status.printLog("Running tests.")
runTests(options, env, gitrev)
with open(statusLog, 'w') as log:
status.printStatus(makeLog, makeAllLog, env["SMTP_SERVER"], log, testLog=testLog)
if not options.x64only:
debug_handler = status.set_rotating_log(testDebugLog, log_handler)
status.printLog("Running debug tests.")
runTests(options, env, gitrev, "D")
with open(prefix + "Dstatus.log", 'w') as log:
status.printStatus(makeAllLog, testDebugLog, env["SMTP_SERVER"], log, testLog=testDebugLog)
# provide more information than just the date:
nameopt = " -name %sr%s" % (date.today().strftime("%d%b%y"), svnrev)
if options.sumoExe == "meso":
runInternalTests.runInternal(programSuffix,
"-b " + env["FILEPREFIX"] + nameopt, log)
else:
subprocess.call("texttest.py -b " + env["FILEPREFIX"] + nameopt,
stdout=log,
stderr=subprocess.STDOUT,
shell=True)
subprocess.call("texttest.py -a sumo.gui -b " + env["FILEPREFIX"] +
nameopt,
stdout=log,
stderr=subprocess.STDOUT,
shell=True)
subprocess.call("texttest.py -b " + env["FILEPREFIX"] + " -coll",
stdout=log,
stderr=subprocess.STDOUT,
shell=True)
ago = datetime.datetime.now() - datetime.timedelta(50)
subprocess.call('texttest.py -s "batch.ArchiveRepository session=' +
env["FILEPREFIX"] + ' before=%s"' % ago.strftime("%d%b%Y"),
stdout=log,
stderr=subprocess.STDOUT,
shell=True)
log.close()
log = open(statusLog, 'w')
status.printStatus(makeLog, makeAllLog, env["TEXTTEST_TMP"],
env["SMTP_SERVER"], log)
log.close()
#!/usr/bin/env python
import json, yaml, argparse, httpd, status
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Check status script')
parser.add_argument('--json', const='json', default='print', dest='output_format', action='store_const', help='return the status as json')
parser.add_argument('--www', const=True, default=False, dest='start_httpd', action='store_const', help='return the status as json')
args = parser.parse_args()
if args.start_httpd:
print 'Starting webserver...'
httpd.LocalStatusHttpd()
else:
if args.output_format == 'json':
print status.getServicesStatus()
else:
data = json.loads(status.getServicesStatus())
for svc in data:
print "{} ({}): {}".format(svc['service'], svc['port'], status.printStatus(svc['status']))
def runLongAmpliconAnalysis(subreadsetXML,
whitelistSequences,
outputPrefix,
minLength='1000',
maxLength='1500',
maxReads='20000',
maxClusteringReads='5000'):
'''run SMRT Link v5 long amplicon analysis'''
# runs LAA to generate amplicon sequences from PacBio Sequel data
# subreadsetXML can be from a single dataset, or merged datasets where new XML files are created using dataset create
# whitelistFasta is a file containing sequences that will be analyzed by LAA, typically sequences from a single sample
# defaults are set for typical MHC class I genotyping and should be adjusted depending on target
# note: LAA default minLength=3000 will cause most of our analyses to fail so minLength should almost always be set
# increasing maxClusteringReads will allow more alleles to be detected at the expense of speed:
# LAA default of 500 clustering reads runs each sample in ~2 minutes, MHC class I default of 10000 takes ~30 minutes
# but detects more alleles. Setting even higher values like 100,000 clustering reads causes runtimes of several hours.
# maxReads can be set very high to ensure that all reads are used to accurately define clusters. This doesn't significantly
# impact runtime.
# use outputPrefix to specify the folder and prefix for output files
# eg '/slipstream/shared_data/19364/09/'
# eg '/slipstream/shared_data/19364/09/BM115.
# path to SMRT Link v6.0 LAA
laa_path = '/slipstream/oc/pacbio/smrtlink_v6/smrtcmds/bin/laa'
# create output folder if it doesn't exist
utils.createOutputFolder(os.path.dirname(outputPrefix))
# create laa command
laa_cmd = [
laa_path, '--whitelist=' + whitelistSequences,
'--logFile=' + outputPrefix + '.log.txt',
'--resultFile=' + outputPrefix + '.amplicon_analysis.fastq',
'--junkFile=' + outputPrefix +
'.amplicon_analysis_chimeras_noise.fastq',
'--reportFile=' + outputPrefix + '.amplicon_analysis_summary.csv',
'--inputReportFile=' + outputPrefix + '.amplicon_analysis_input.csv',
'--subreadsReportPrefix=' + outputPrefix +
'.amplicon_analysis_subreads', subreadsetXML
]
print(laa_cmd)
# '--minLength=' + minLength,
# '--maxLength=' + maxLength,
# '--maxReads=' + maxReads,
# '--maxClusteringReads=' + maxClusteringReads,'--whitelist=' + whitelistSequences,
# '--logFile=' + outputPrefix + '.log.txt',
# '--resultFile=' + outputPrefix + '.amplicon_analysis.fastq',
# '--junkFile=' + outputPrefix + '.amplicon_analysis_chimeras_noise.fastq',
# '--reportFile=' + outputPrefix + '.amplicon_analysis_summary.csv',
# '--inputReportFile=' + outputPrefix + '.amplicon_analysis_input.csv',
# '--subreadsReportPrefix=' + outputPrefix + '.amplicon_analysis_subreads',
# subreadsetXML]
# laa_cmd = [laa_path,
# '--minLength=' + minLength,
# '--maxLength=' + maxLength,
# '--maxReads=' + maxReads,
# '--maxClusteringReads=' + maxClusteringReads,
# '--whitelist=' + whitelistSequences,
# '--logFile=' + outputPrefix + '.log.txt',
# '--resultFile=' + outputPrefix + '.amplicon_analysis.fastq',
# '--junkFile=' + outputPrefix + '.amplicon_analysis_chimeras_noise.fastq',
# '--reportFile=' + outputPrefix + '.amplicon_analysis_summary.csv',
# '--inputReportFile=' + outputPrefix + '.amplicon_analysis_input.csv',
# '--subreadsReportPrefix=' + outputPrefix + '.amplicon_analysis_subreads',
# subreadsetXML]
# print laa command
status.printStatus(' '.join(laa_cmd))
# call laa
subprocess.call(laa_cmd)
# return path to LAA fastq output
return outputPrefix + 'amplicon_analysis.fastq'
def parseBarcodes(samples, input_ccs_fastq, out_dir):
'''parse barcodes from gzip-compressed FASTQ of PacBio CCS reads'''
# create output directory if it doesn't exist
utils.createOutputFolder(out_dir)
# create PacBio barcode dictionary to lookup against
pacbioLookup = pacbioBarcodeDict()
# create dictionary of sample IDs and barcode sequences
searchDict = {}
for seq_name, barcode_seqs in samples.items():
searchDict[seq_name] = [pacbioLookup[barcode_seqs[0]], pacbioLookup[barcode_seqs[1]]]
# open gzip-compressed FASTQ
with gzip.open(input_ccs_fastq, "rt") as handle:
# make dictionary to hold barcode-split seq records
perBarcodeDict = {}
# initialize dictionary with names of each sample
for j in searchDict:
perBarcodeDict[j]=[]
# log every 1000 sequences processed
log_every_n = 1000
# iterate through generator containing FASTQ sequences
for idx, i in enumerate(SeqIO.parse(handle, "fastq")):
# print status message every 1000 sequences processed
if (idx % log_every_n) == 0:
status.printStatus(str(idx) + ' FASTQ reads demultiplexed')
# for each sequence, look for the presence of barcodes at the start and end
for j in searchDict:
# redo to use re.search to find barcodes not at very end of sequence
# if i.seq.startswith(searchDict[j][0]) and i.seq.endswith(searchDict[j][1]):
# regular expression to find barcodes in forward orientation
prog = re.compile(searchDict[j][0] + ('.*') + searchDict[j][1])
# test if regular expression is found in sequence
# need to cast i.seq to string to use re.search
if prog.search(str(i.seq)):
# write matching barcodes to perBarcodeDict - store in memory
x = perBarcodeDict[j]
x.append(i)
perBarcodeDict[j]= x
# handle inserts in the opposite orientation
# create Biopython sequence object containing barcode sequences
forward_seq = Seq(searchDict[j][0])
reverse_seq = Seq(searchDict[j][1])
# reverse complement
forward_seq_rc = forward_seq.reverse_complement()
reverse_seq_rc = reverse_seq.reverse_complement()
# find FASTQ sequences matching reverse complemented barcodes
# if i.seq.startswith(forward_seq_rc) and i.seq.endswith(reverse_seq_rc):
# because of the SMRTBell orientation, second barcode gets listed first in reverse complement orientation
prog = re.compile(str(reverse_seq_rc) + '.*' + str(forward_seq_rc))
# need to cast i.seq to string to use re.search
if prog.search(str(i.seq)):
# store matches in dictionary
x = perBarcodeDict[j]
x.append(i)
perBarcodeDict[j]= x
# write output files containing reads matching each barcode
for i in perBarcodeDict:
count = SeqIO.write(perBarcodeDict[i], out_dir + '/' + i + '.fastq', 'fastq')
# compress fastq file and remove uncompressed version
with open(out_dir + '/' + i + '.fastq', 'rb') as f_in:
with gzip.open(out_dir + '/' + i + '.fastq.gz', 'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
os.remove(out_dir + '/' + i + '.fastq') # remove uncompressed
# log
status.printStatus(str(count) + ' barcoded reads saved from sample ' + i )
status.printStatus('gzip-compressed demultipled FASTQ file saved to ' + out_dir + '/' + i + '.fastq.gz')
print("Warning: Could not create nightly sumo-game.zip! (%s)" % e, file=log)
log.close()
with open(makeAllLog, 'a') as log:
subprocess.call(["cmake", "--build", ".", "--config", "Debug"],
cwd=buildDir, stdout=log, stderr=subprocess.STDOUT)
if sumoAllZip:
try:
debugZip = sumoAllZip.replace("-all-", "Debug-%s-" % env["FILEPREFIX"])
zipf = zipfile.ZipFile(debugZip, 'w', zipfile.ZIP_DEFLATED)
debugDllPath = os.path.join(options.rootDir, "..", "debugDll")
if platform == "x64":
debugDllPath += "64"
for dllPath in (os.path.join(options.rootDir, dllDir), debugDllPath):
for f in glob.glob(os.path.join(dllPath, "*.dll")) + glob.glob(os.path.join(dllPath, "*", "*.dll")):
zipf.write(f, os.path.join(binDir, f[len(dllPath) + 1:]))
for f in (glob.glob(os.path.join(options.rootDir, options.binDir, "*D.exe")) +
glob.glob(os.path.join(options.rootDir, options.binDir, "*D.pdb"))):
zipf.write(f, os.path.join(binDir, os.path.basename(f)))
zipf.close()
except IOError as ziperr:
(errno, strerror) = ziperr.args
print("Warning: Could not zip to %s!" % binaryZip, file=log)
print("I/O error(%s): %s" % (errno, strerror), file=log)
runTests(options, env, gitrev, options.extended_tests and platform == "x64")
with open(statusLog, 'w') as log:
status.printStatus(makeLog, makeAllLog, env["SMTP_SERVER"], log)
if options.extended_tests:
runTests(options, env, gitrev, True, "D")
with open(prefix + "Dstatus.log", 'w') as log:
status.printStatus(makeAllLog, makeAllLog, env["SMTP_SERVER"], log)
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("out_dir",
help='Folder that will store all output files')
parser.add_argument(
"fastq_folder",
help='Path to folder containing FASTQ files to genotype')
parser.add_argument(
"ref_fasta", help='Path to reference FASTA file to map reads against')
parser.add_argument("experiment", help='Experiment number')
args = parser.parse_args()
# make output folder if it doesn't exist
utils.createOutputFolder(args.out_dir)
# configure log to stdout
logging.basicConfig(filename=args.out_dir + '/log.txt',
filemode='w',
level=logging.DEBUG,
format='%(asctime)s %(message)s',
datefmt='%Y-%m-%d %I:%M:%S')
# log command line
status.printStatus('Command line statment: ' + ' '.join(sys.argv))
# map reads and summarize results
mapReadsFolder(args.fastq_folder, args.ref_fasta, args.out_dir,
args.experiment)
# example invokation
# anaconda3/bin/python /slipstream/shared_data/pycharm/dhogal/19070/genotyping.py /slipstream/shared_data/19070/pacbio48-default-minQuality/16/ /slipstream/shared_data/19070/pacbio48-default-minQuality/12/fastq/ /slipstream/shared_data/19070/pacbio48-default-minQuality/ipd-mhc-20170523.fasta
for f in glob.glob(os.path.join(dllPath, "*.dll")) + glob.glob(
os.path.join(dllPath, "*", "*.dll")):
zipf.write(f, os.path.join(binDir, f[len(dllPath) + 1:]))
buildDir = os.path.dirname(
os.path.join(options.rootDir, options.project))
for f in glob.glob(
os.path.join(options.rootDir, options.binDir, "*D.exe")):
exe = os.path.basename(f)
pdb = exe[:-3] + "pdb"
zipf.write(f, os.path.join(binDir, exe))
if platform == "x64":
pdbPath = os.path.join(buildDir, exe[:-5], "x64", "Debug",
pdb)
else:
pdbPath = os.path.join(buildDir, exe[:-5], "Debug", pdb)
if os.path.exists(pdbPath):
zipf.write(pdbPath, os.path.join(binDir, pdb))
zipf.close()
except IOError as ziperr:
(errno, strerror) = ziperr.args
print("Warning: Could not zip to %s!" % binaryZip, file=log)
print("I/O error(%s): %s" % (errno, strerror), file=log)
runTests(options, env, gitrev)
log = open(statusLog, 'w')
status.printStatus(makeLog, makeAllLog, env["SMTP_SERVER"], log)
log.close()
runTests(options, env, gitrev, "D")
log = open(prefix + "Dstatus.log", 'w')
status.printStatus(makeAllLog, makeAllLog, env["SMTP_SERVER"], log)
log.close()
def main():
runLog.logger.info("Starting GCO.py")
egpg = easygopigo3.EasyGoPiGo3(
use_mutex=True) # Create an instance of the EasyGoPiGo3 class
# Adjust GOPIGO3 CONSTANTS to my bot default EasyGoPiGo3.WHEEL_DIAMETER = 66.5 mm
myconfig.setParameters(egpg)
ds = myDistSensor.init(egpg)
tp = tiltpan.TiltPan(egpg)
tp.tiltpan_center()
dist_list_mm = []
at_angle_list = []
scan360speed = 150
safe_distance = 20.32 # cm 8 inches wheels to wall/object
ds_to_wheels = 7 # cm distance sensor is 2.75 inches in front of wheels
try:
# spin360 taking distance measurement
print("\n360 degree scan at speed={}".format(scan360speed))
dist_list_mm, at_angle_list = scan360.spin_and_scan(
egpg, ds, tp, 360,
speed=scan360speed) # spin taking distance readings
range_list_cm = [dist / 10 for dist in dist_list_mm]
printmaps.view360(
range_list_cm,
at_angle_list) # print view (all r positive, theta 0=left
print("Readings:{}".format(len(at_angle_list)))
sleep(3)
# spin to face closest object
dist_to_target, scan_angle_to_target = closest_obj(
range_list_cm, at_angle_list)
angle_to_target = scan_angle_to_target - 90 # adjust for 0=left
print("\nClosest object is {:.1f} cm at {:.0f} degrees".format(
dist_to_target, angle_to_target))
sleep(3)
print("\nTurning {:.0f} at {} dps to face closest object".format(
angle_to_target, egpg.get_speed()))
egpg.turn_degrees(angle_to_target)
sleep(3)
# travel to point where wheels are 10 inches from object (will back up if too close)
dist_to_guard_spot = dist_to_target + ds_to_wheels - safe_distance
print("\nMoving {:.0f} cm to guard spot".format(dist_to_guard_spot))
egpg.drive_cm(dist_to_guard_spot)
sleep(3)
# perform a 160 degree scan with obj in the center
# spin 180 to face away from object
print("\nTurning 180 to guard direction")
egpg.turn_degrees(180)
sleep(3)
# loop
# perform a quick 160 degree scan
# if something gets closer, wag head and announce "I saw that."
while True:
dist_l, angl_l = servoscan.ds_map(ds, tp, num_of_readings=72)
printmaps.view180(dist_l,
angl_l,
grid_width=80,
units="cm",
ignore_over=230)
# turn distance sensor (eyes) to face closest object
dist_to_closest, scan_angle_to_closest = closest_obj(
dist_l, angl_l)
angle_to_closest = scan_angle_to_closest # - 90 # adjust for 0=left
print("\nClosest object is {:.1f} cm at {:.0f} degrees".format(
dist_to_closest, angle_to_closest))
print("\nPointing {:.0f} to face closest object".format(
angle_to_closest))
tp.pan(angle_to_closest)
sleep(2)
status.printStatus(egpg, ds)
sleep(30)
tp.tiltpan_center()
# status.batterySafetyCheck()
except KeyboardInterrupt: # except the program gets interrupted by Ctrl+C on the keyboard.
egpg.stop() # stop motors
runLog.logger.info("Exiting GCO.py")
print("Ctrl-C detected - Finishing up")
egpg.stop()
