def _classify(self, mode, inputFastaFile, outLog=None):
mothur = os.path.join(os.path.normpath(self._config.get('mothurInstallDir')), 'mothur')
if mode == 16:
extractedRegionsFasta = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16S_rRNA.fna'))
taxonomyFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('16S_rRNA','taxonomyDNA')][0]))
templateFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('16S_rRNA','templateDNA')][0]))
#mothurPredFileName = str(extractedRegionsFasta[0:extractedRegionsFasta.rindex('.')] + '.taxonomy')
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile)
predFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16P'))
#extractedRegionsFasta = str(inputFastaFile + '.16S_rRNA.fna')
#templateFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam16STemplate'))
#taxonomyFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam16STaxonomy'))
#mothurPredFileName = str(inputFastaFile + '.16S_rRNA.bacteria+archaea.taxonomy')
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16S_rRNA.bacteria+archaea.taxonomy'))
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16S_rRNA.fasta.taxonomy'))
#predFileName = str(inputFastaFile + '.16P')
elif mode == 23:
extractedRegionsFasta = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23S_rRNA.fna'))
taxonomyFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('23S_rRNA','taxonomyDNA')][0]))
templateFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('23S_rRNA','templateDNA')][0]))
#mothurPredFileName = str(extractedRegionsFasta[0:extractedRegionsFasta.rindex('.')] + '.taxonomy')
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile)
predFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23P'))
#extractedRegionsFasta = str(inputFastaFile + '.23S_rRNA.fna')
#templateFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam23STemplate'))
#taxonomyFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam23STaxonomy'))
#mothurPredFileName = str(inputFastaFile + '.23S_rRNA.bacteria+archaea.taxonomy')
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23S_rRNA.bacteria+archaea.taxonomy'))
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23S_rRNA.fasta.taxonomy'))
#predFileName = str(inputFastaFile + '.23P')
elif mode == 5:
#extractedRegionsFasta = str(inputFastaFile + '.5S_rRNA.fna')
extractedRegionsFasta = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.5S_rRNA.fna'))
taxonomyFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('5S_rRNA','taxonomyDNA')][0]))
templateFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('5S_rRNA','templateDNA')][0]))
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile)
predFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.5P'))
#templateFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam5STemplate'))
#taxonomyFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam5STaxonomy'))
#mothurPredFileName = os.path.join(self._workingDir,
# str(os.path.basename(inputFastaFile) + '.5S_rRNA.' + os.path.basename(taxonomyFile) + 'onomy'))#.taxonomy
#predFileName = str(inputFastaFile + '.5P')
else:
raise Exception('Wrong branch')
if not os.path.isfile(mothurPredFileName):
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile, suffix='.bayesian.taxonomy')
param = self._config.get('mothurClassifyParamOther')
cmd = str('time ' + mothur + ' "#classify.seqs(fasta=' + extractedRegionsFasta + ', template=' + templateFile
+ ', taxonomy=' + taxonomyFile + ', ' + param + ')"')
if os.name == 'posix':
if outLog is not None:
stdoutLog = open(outLog, 'w')
else:
stdoutLog = subprocess.STDOUT
mothurProc = subprocess.Popen(cmd, shell=True, bufsize=-1, cwd=self._workingDir, stdout=stdoutLog)
print 'run cmd:', cmd
mothurProc.wait()
if outLog is not None:
stdoutLog.close()
print 'mothur return code:', mothurProc.returncode
if mothurProc.returncode != 0:
raise Exception("Command returned with non-zero %s status: %s" % (mothurProc.returncode, cmd))
else:
print 'Cannot run mothur since your system is not "posix" but', str('"' + os.name + '"'), '\n', cmd
#transform mothur prediction files to the tab separated files
self.mothurPredToTabSepPred(mothurPredFileName, predFileName)
def runMarkerGeneAnalysis(self, fastaFileDNA, outLog=None):
"""
Run hmmer HMM and mothur classify (bayesian), same param as for the 16S analysis.
"""
#read list of marker genes
mgFiles = forEachLine(self.markerGeneListFile, _MgFiles(self.markerGeneListFileDir))
#translate DNA to protein sequences
fastaFileProt = os.path.join(self.markerGeneWorkingDir, str(os.path.basename(fastaFileDNA) + '.PROT'))
dnaToProt(fastaFileDNA, fastaFileProt)
#read DNA fasta file
try:
handle = open(fastaFileDNA, "rU")
dnaSeqDict = SeqIO.to_dict(SeqIO.parse(handle, "fasta"))
handle.close()
except Exception:
sys.stderr.write(str('Cannot read file: ' + str(fastaFileDNA)))
raise
#to output all predictions in one file
outPredAllFileName = os.path.join(self.markerGeneWorkingDir,
str(os.path.basename(fastaFileDNA) + '_all.mP'))
outAllBuffer = OutFileBuffer(outPredAllFileName)
#run HMM search
mgList = mgFiles.getGeneNameList()
if outLog is not None:
stdoutLog = open(outLog,'w')
else:
stdoutLog = subprocess.STDOUT
#for each gene perform the analysis separately
for geneName in mgList:
domFileArray = [os.path.join(self.markerGeneWorkingDir, str(geneName + '_1.dom')),
os.path.join(self.markerGeneWorkingDir, str(geneName + '_2.dom'))]
outFileArray = [os.path.join(self.markerGeneWorkingDir, str(geneName + '_1.out')),
os.path.join(self.markerGeneWorkingDir, str(geneName + '_2.out'))]
hmmFileArray = [mgFiles.getFilePath(geneName, 'hmmPROTPrim'),
mgFiles.getFilePath(geneName, 'hmmPROTSec')]
cmdArray = list([])
#define cmd
for i in range(2):
if hmmFileArray[i] is not None:
cmdArray.append(str(os.path.join(self.hmmerBinDir, 'hmmsearch') + ' --domtblout ' + domFileArray[i] + ' -E 0.01'
+ ' -o ' + outFileArray[i] + ' ' + hmmFileArray[i] + ' ' + fastaFileProt))
else:
cmdArray.append(None)
#run cmd
for cmd in cmdArray:
if cmd is not None and os.name == 'posix':
hmmProc = subprocess.Popen(cmd, shell=True, bufsize=-1, cwd=self.hmmInstallDir, stdout=stdoutLog)
print 'run cmd:', cmd
hmmProc.wait()
print 'HMM return code:', hmmProc.returncode
if hmmProc.returncode != 0:
raise Exception("Command returned with non-zero %s status: %s" % (hmmProc.returncode, cmd))
else:
print 'Marker genes analysis, doesn`t run (no posix): ', cmd
#get regions that match to the HMM profile ()
entryDictList = []
for i in range(2):
if cmdArray[i] is not None:
entryDictList.append(forEachLine(domFileArray[i], _MgRegions()).getEntryDict())
else:
entryDictList.append(None)
entryDict1 = entryDictList[0]
entryDict2 = entryDictList[1]
#extract regions found in the protein sequences that were found by the HMM and generate corresponding DNA sequences
regionDnaFasta = os.path.join(self.markerGeneWorkingDir, str(geneName + '_dna.gff'))
outFileBuffer = OutFileBuffer(regionDnaFasta)
for seqName in entryDict1:
i = -1
for e in entryDict1[seqName]:
i += 1
from1 = entryDict1[seqName][i][0]
to1 = entryDict1[seqName][i][1]
assert ((from1 != None) and (to1 != None))
#compare the results found by the primary and secondary HMM profiles
if (entryDict2 != None) and (seqName in entryDict2):
if len(entryDict2[seqName]) >= (i+1):
from2 = entryDict2[seqName][i][0]
to2 = entryDict2[seqName][i][1]
#if from1 != from2 or to1 != to2:
# print str('Different positions in' + seqName + ' from1:' + str(from1) + ' from2:' + str(from2)
# + ' to1:' + str(to1) + ' to2:' + str(to2))
#extract regions from the DNA sequences (consider 3 ORF and reverse complements)
#name of the whole sequence
dnaSeqName = re.sub(r'([0-9]+_[0-9]+)_[pr]+[012]', r'\1', seqName)
#whole DNA sequence
dnaSeq = dnaSeqDict[dnaSeqName].seq
#reverse complement (contains "pr")
tagRev = 'p'
if re.match(r'[0-9]+_[0-9]+_pr[012]', seqName):
dnaSeq = dnaSeq.reverse_complement()
tagRev = 'pr'
#shift "0"
if re.match(r'[0-9]+_[0-9]+_[pr]+0', seqName):
tagFrom = ((from1 - 1)*3)
tagTo = (to1*3)
tagRev += '0'
dnaSeq = dnaSeq[tagFrom:tagTo]
#shift "1"
elif re.match(r'[0-9]+_[0-9]+_[pr]+1', seqName):
tagFrom = (((from1 - 1)*3) + 1)
tagTo = ((to1*3) + 1)
tagRev += '1'
dnaSeq = dnaSeq[tagFrom:tagTo]
#shift "2"
elif re.match(r'[0-9]+_[0-9]+_[pr]+2', seqName):
tagFrom = (((from1 - 1)*3) + 2)
tagTo = ((to1*3) + 2)
tagRev += '2'
dnaSeq = dnaSeq[tagFrom:tagTo]
#error
else:
sys.stderr.write('Wrong seq name: ' + seqName + ' \n')
dnaSeq = None
tag = str(str(tagFrom) + '_' + str(tagTo) + '_' + tagRev)
outFileBuffer.writeText(str('>' + dnaSeqName + '_' + tag + '\n' + dnaSeq + '\n'))
outFileBuffer.close()
#if no marker gene found
if outFileBuffer.isEmpty():
continue
#run mothur classify (bayesian? the same as for the 16S analysis)
templateFile = mgFiles.getFilePath(geneName, 'templateDNA')
taxonomyFile = mgFiles.getFilePath(geneName, 'taxonomyDNA')
assert ((templateFile is not None) and (taxonomyFile is not None))
cmd = str('time ' + self.mothur + ' "#classify.seqs(fasta=' + regionDnaFasta + ', template=' + templateFile
+ ', taxonomy=' + taxonomyFile + ', ' + self.mothurParam + ')"')
if os.name == 'posix':
mothurProc = subprocess.Popen(cmd, shell=True, bufsize=-1, cwd=self.markerGeneWorkingDir, stdout=stdoutLog)
print 'run cmd:', cmd
mothurProc.wait()
print 'mothur return code:', mothurProc.returncode
if mothurProc.returncode != 0:
raise Exception("Command returned with non-zero %s status: %s" % (mothurProc.returncode, cmd))
else:
print 'Cannot run mothur since your system is not "posix" but', str('"' + os.name + '"'), '\n', cmd
#transform the mothur output to a simple output (name, ncbid, weight)
#mothurPredFileName = os.path.join(self.markerGeneWorkingDir,
# str(geneName + '_dna.' + os.path.basename(taxonomyFile) + 'onomy')) # taxonomy
#!!!!!!!!!!!!!
mothurPredFileName = common.getMothurOutputFilePath(regionDnaFasta, taxonomyFile)
if not os.path.isfile(mothurPredFileName):
mothurPredFileName = common.getMothurOutputFilePath(regionDnaFasta, taxonomyFile, suffix='.bayesian.taxonomy')
if not os.path.isfile(mothurPredFileName):
print("Can't open file: %s" % mothurPredFileName)
outPredFileName = os.path.join(self.markerGeneWorkingDir,
str(os.path.basename(fastaFileDNA) + '_' + geneName + '.mP'))
outBuffer = OutFileBuffer(outPredFileName, bufferText=True)
forEachLine(mothurPredFileName, _MothurOutFileParser(outBuffer, geneName))
if not outAllBuffer.isEmpty():
outAllBuffer.writeText('\n')
outAllBuffer.writeText(outBuffer.getTextBuffer())
if outLog is not None:
stdoutLog.close()
outAllBuffer.close()
def runMarkerGeneAnalysis(self, fastaFileDNA, outLog=None):
"""
Run hmmer HMM and mothur classify (bayesian), same param as for the 16S analysis.
"""
#read list of marker genes
mgFiles = forEachLine(self.markerGeneListFile, _MgFiles(self.markerGeneListFileDir))
#translate DNA to protein sequences
fastaFileProt = os.path.join(self.markerGeneWorkingDir, str(os.path.basename(fastaFileDNA) + '.PROT'))
dnaToProt(fastaFileDNA, fastaFileProt)
#read DNA fasta file
try:
handle = open(fastaFileDNA, "rU")
dnaSeqDict = SeqIO.to_dict(SeqIO.parse(handle, "fasta"))
handle.close()
except Exception:
sys.stderr.write(str('Cannot read file: ' + str(fastaFileDNA)))
raise
#to output all predictions in one file
outPredAllFileName = os.path.join(self.markerGeneWorkingDir,
str(os.path.basename(fastaFileDNA) + '_all.mP'))
outAllBuffer = OutFileBuffer(outPredAllFileName)
#run HMM search
mgList = mgFiles.getGeneNameList()
if outLog is not None:
stdoutLog = open(outLog, 'w')
else:
stdoutLog = subprocess.STDOUT
#for each gene perform the analysis separately
for geneName in mgList:
domFileArray = [os.path.join(self.markerGeneWorkingDir, str(geneName + '_1.dom'))] #,
# os.path.join(self.markerGeneWorkingDir, str(geneName + '_2.dom'))]
outFileArray = [os.path.join(self.markerGeneWorkingDir, str(geneName + '_1.out'))] #,
# os.path.join(self.markerGeneWorkingDir, str(geneName + '_2.out'))]
hmmFileArray = [mgFiles.getFilePath(geneName, 'hmmPROTPrim')] #,
# mgFiles.getFilePath(geneName, 'hmmPROTSec')]
cmdArray = list([])
#define cmd
for i in range(1):
if hmmFileArray[i] is not None:
cmdArray.append(str(os.path.join(self.hmmerBinDir, 'hmmsearch') + ' --domtblout ' + domFileArray[i] + ' -E 0.01' + self.processorsHmm
+ ' -o ' + outFileArray[i] + ' ' + hmmFileArray[i] + ' ' + fastaFileProt))
else:
cmdArray.append(None)
#run cmd
for cmd in cmdArray:
if cmd is not None and os.name == 'posix':
cwd = self.hmmInstallDir
if parallel.reportFailedCmd(parallel.runCmdSerial([parallel.TaskCmd(cmd, cwd)])) is not None:
sys.exit(-1)
# hmmProc = subprocess.Popen(cmd, shell=True, bufsize=-1, cwd=self.hmmInstallDir, stdout=stdoutLog)
# print 'run cmd:', cmd
# hmmProc.wait()
# print 'HMM return code:', hmmProc.returncode
# if hmmProc.returncode != 0:
# raise Exception("Command returned with non-zero %s status: %s" % (hmmProc.returncode, cmd))
else:
print 'Marker genes analysis, doesn`t run (no posix): ', cmd
#get regions that match to the HMM profile ()
entryDictList = []
for i in range(1):
if cmdArray[i] is not None:
entryDictList.append(forEachLine(domFileArray[i], _MgRegions()).getEntryDict())
else:
entryDictList.append(None)
entryDict1 = entryDictList[0]
# entryDict2 = entryDictList[1]
#extract regions found in the protein sequences that were found by the HMM and generate corresponding DNA sequences
regionDnaFasta = os.path.join(self.markerGeneWorkingDir, str(geneName + '_dna.gff'))
outFileBuffer = OutFileBuffer(regionDnaFasta)
for seqName in entryDict1:
i = -1
for e in entryDict1[seqName]:
i += 1
from1 = entryDict1[seqName][i][0]
to1 = entryDict1[seqName][i][1]
assert ((from1 != None) and (to1 != None))
#compare the results found by the primary and secondary HMM profiles
# if (entryDict2 != None) and (seqName in entryDict2):
# if len(entryDict2[seqName]) >= (i+1):
# from2 = entryDict2[seqName][i][0]
# to2 = entryDict2[seqName][i][1]
#if from1 != from2 or to1 != to2:
# print str('Different positions in' + seqName + ' from1:' + str(from1) + ' from2:' + str(from2)
# + ' to1:' + str(to1) + ' to2:' + str(to2))
#extract regions from the DNA sequences (consider 3 ORF and reverse complements)
#name of the whole sequence
dnaSeqName = re.sub(r'([0-9]+_[0-9]+)_[pr]+[012]', r'\1', seqName)
#whole DNA sequence
dnaSeq = dnaSeqDict[dnaSeqName].seq
#reverse complement (contains "pr")
tagRev = 'p'
if re.match(r'[0-9]+_[0-9]+_pr[012]', seqName):
dnaSeq = dnaSeq.reverse_complement()
tagRev = 'pr'
#shift "0"
if re.match(r'[0-9]+_[0-9]+_[pr]+0', seqName):
tagFrom = ((from1 - 1)*3)
tagTo = (to1*3)
tagRev += '0'
dnaSeq = dnaSeq[tagFrom:tagTo]
#shift "1"
elif re.match(r'[0-9]+_[0-9]+_[pr]+1', seqName):
tagFrom = (((from1 - 1)*3) + 1)
tagTo = ((to1*3) + 1)
tagRev += '1'
dnaSeq = dnaSeq[tagFrom:tagTo]
#shift "2"
elif re.match(r'[0-9]+_[0-9]+_[pr]+2', seqName):
tagFrom = (((from1 - 1)*3) + 2)
tagTo = ((to1*3) + 2)
tagRev += '2'
dnaSeq = dnaSeq[tagFrom:tagTo]
#error
else:
sys.stderr.write('Wrong seq name: ' + seqName + ' \n')
dnaSeq = None
tag = str(str(tagFrom) + '_' + str(tagTo) + '_' + tagRev)
outFileBuffer.writeText(str('>' + dnaSeqName + '_' + tag + '\n' + dnaSeq + '\n'))
outFileBuffer.close()
#if no marker gene found
if outFileBuffer.isEmpty():
continue
#run mothur classify (bayesian? the same as for the 16S analysis)
templateFile = mgFiles.getFilePath(geneName, 'templateDNA')
taxonomyFile = mgFiles.getFilePath(geneName, 'taxonomyDNA')
assert ((templateFile is not None) and (taxonomyFile is not None))
cmd = str('' + self.mothur + ' "#classify.seqs(fasta=' + regionDnaFasta + ', template=' + templateFile
+ ', taxonomy=' + taxonomyFile + ', ' + self.mothurParam + ')"')
if os.name == 'posix':
print('Mothur processing: %s' % os.path.basename(templateFile).split('_', 1)[0])
cwd = self.markerGeneWorkingDir
if parallel.reportFailedCmd(parallel.runCmdSerial([parallel.TaskCmd(cmd, cwd, stdout=stdoutLog)])) is not None:
sys.exit(-1)
# mothurProc = subprocess.Popen(cmd, shell=True, bufsize=-1, cwd=self.markerGeneWorkingDir, stdout=stdoutLog)
# print 'run cmd:', cmd
# mothurProc.wait()
# print 'mothur return code:', mothurProc.returncode
# if mothurProc.returncode != 0:
# raise Exception("Command returned with non-zero %s status: %s" % (mothurProc.returncode, cmd))
else:
print 'Cannot run mothur since your system is not "posix" but', str('"' + os.name + '"'), '\n', cmd
#transform the mothur output to a simple output (name, ncbid, weight)
#mothurPredFileName = os.path.join(self.markerGeneWorkingDir,
# str(geneName + '_dna.' + os.path.basename(taxonomyFile) + 'onomy')) # taxonomy
#!!!!!!!!!!!!!
mothurPredFileName = common.getMothurOutputFilePath(regionDnaFasta, taxonomyFile)
if not os.path.isfile(mothurPredFileName):
mothurPredFileName = common.getMothurOutputFilePath(regionDnaFasta, taxonomyFile, suffix='.bayesian.taxonomy')
if not os.path.isfile(mothurPredFileName):
print("Can't open file: %s" % mothurPredFileName)
outPredFileName = os.path.join(self.markerGeneWorkingDir,
str(os.path.basename(fastaFileDNA) + '_' + geneName + '.mP'))
outBuffer = OutFileBuffer(outPredFileName, bufferText=True)
forEachLine(mothurPredFileName, _MothurOutFileParser(outBuffer, geneName))
if not outAllBuffer.isEmpty():
outAllBuffer.writeText('\n')
outAllBuffer.writeText(outBuffer.getTextBuffer())
if outLog is not None:
stdoutLog.close()
outAllBuffer.close()
def _classify(self, mode, inputFastaFile, outLog=None):
mothur = os.path.join(os.path.normpath(self._config.get('mothurInstallDir')), 'mothur')
if mode == 16:
extractedRegionsFasta = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16S_rRNA.fna'))
taxonomyFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('16S_rRNA','taxonomyDNA')][0]))
templateFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('16S_rRNA','templateDNA')][0]))
#mothurPredFileName = str(extractedRegionsFasta[0:extractedRegionsFasta.rindex('.')] + '.taxonomy')
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile)
predFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16P'))
#extractedRegionsFasta = str(inputFastaFile + '.16S_rRNA.fna')
#templateFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam16STemplate'))
#taxonomyFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam16STaxonomy'))
#mothurPredFileName = str(inputFastaFile + '.16S_rRNA.bacteria+archaea.taxonomy')
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16S_rRNA.bacteria+archaea.taxonomy'))
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.16S_rRNA.fasta.taxonomy'))
#predFileName = str(inputFastaFile + '.16P')
elif mode == 23:
extractedRegionsFasta = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23S_rRNA.fna'))
taxonomyFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('23S_rRNA','taxonomyDNA')][0]))
templateFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('23S_rRNA','templateDNA')][0]))
#mothurPredFileName = str(extractedRegionsFasta[0:extractedRegionsFasta.rindex('.')] + '.taxonomy')
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile)
predFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23P'))
#extractedRegionsFasta = str(inputFastaFile + '.23S_rRNA.fna')
#templateFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam23STemplate'))
#taxonomyFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam23STaxonomy'))
#mothurPredFileName = str(inputFastaFile + '.23S_rRNA.bacteria+archaea.taxonomy')
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23S_rRNA.bacteria+archaea.taxonomy'))
#mothurPredFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.23S_rRNA.fasta.taxonomy'))
#predFileName = str(inputFastaFile + '.23P')
elif mode == 5:
#extractedRegionsFasta = str(inputFastaFile + '.5S_rRNA.fna')
extractedRegionsFasta = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.5S_rRNA.fna'))
taxonomyFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('5S_rRNA', 'taxonomyDNA')][0]))
templateFile = os.path.join(self._refDir, os.path.normpath(self._refDict[('5S_rRNA', 'templateDNA')][0]))
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile)
predFileName = os.path.join(self._workingDir, str(os.path.basename(inputFastaFile) + '.5P'))
#templateFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam5STemplate'))
#taxonomyFile = os.path.normpath(self._configRRNA16S.get('mothurClassifyParam5STaxonomy'))
#mothurPredFileName = os.path.join(self._workingDir,
# str(os.path.basename(inputFastaFile) + '.5S_rRNA.' + os.path.basename(taxonomyFile) + 'onomy'))#.taxonomy
#predFileName = str(inputFastaFile + '.5P')
else:
raise Exception('Wrong branch')
if not os.path.isfile(mothurPredFileName):
mothurPredFileName = common.getMothurOutputFilePath(extractedRegionsFasta, taxonomyFile, suffix='.bayesian.taxonomy')
param = self._config.get('mothurClassifyParamOther')
cmd = str(mothur + ' "#classify.seqs(fasta=' + extractedRegionsFasta + ', template=' + templateFile
+ ', taxonomy=' + taxonomyFile + ', ' + param + ')"')
if os.name == 'posix':
print('Mothur processing: %s' % os.path.basename(templateFile).split('_', 1)[0])
cwd = self._workingDir
if outLog is not None:
stdoutLog = open(outLog, 'w')
else:
stdoutLog = subprocess.STDOUT
if parallel.reportFailedCmd(parallel.runCmdSerial([parallel.TaskCmd(cmd, cwd, stdout=stdoutLog)])) is not None:
sys.exit(-1)
if outLog is not None:
stdoutLog.close()
# mothurProc = subprocess.Popen(cmd, shell=True, bufsize=-1, cwd=self._workingDir, stdout=stdoutLog)
# print 'run cmd:', cmd
# mothurProc.wait()
# if outLog is not None:
# stdoutLog.close()
# print 'mothur return code:', mothurProc.returncode
# if mothurProc.returncode != 0:
# raise Exception("Command returned with non-zero %s status: %s" % (mothurProc.returncode, cmd))
else:
print 'Cannot run mothur since your system is not "posix" but', str('"' + os.name + '"'), '\n', cmd
#transform mothur prediction files to the tab separated files
self.mothurPredToTabSepPred(mothurPredFileName, predFileName)
