def doCreateSBML(self):
try:
print "doNetworkReconstruction"
curDirectory = os.getcwd()
os.chdir(ScriptsDir.ReconstructionScripts)
orgListFile_fh = open(self.networkReconstructionOrgList)
for orgLine in orgListFile_fh:
organismID = orgLine.strip()
print "Network reconstruction for: " + organismID
intAccept2 = "%.9f" % (self.intAaccept)
intReject2 = "%.9f" % (self.intReject)
call = "bash " + ScriptsDir.ReconstructionScripts_reco_dir_postprocess + " " + self.modelTrainingModelDir + " " + intAccept2 + " " + intReject2 + " " + organismID + " " + ScriptsDir.ReconstructionScripts + " " + self.keggDataDir + " " + self.taxonomy + " " + self.bounds + " " + self.ec2rxnFile + " " + "3" +" " + self.rxnNamesFile + " " + self.pathwayFile
NGS_Util.executeCall(call)
orgListFile_fh.close()
os.chdir(curDirectory)
except Exception:
print traceback.print_exc()
return ""
def doNetworkReconstruction(self):
try:
print "doNetworkReconstruction"
curDirectory = os.getcwd()
os.chdir(ScriptsDir.ReconstructionScripts)
orgListFile_fh = open(self.networkReconstructionOrgList)
for orgLine in orgListFile_fh:
organismID = orgLine.strip()
print "Network reconstruction for: " + organismID
call = "bash " + ScriptsDir.ReconstructionScripts_reco_dir + " " + self.modelTrainingModelDir + " " + str(self.intAaccept) + " " + str(self.intReject) + " " + organismID + " " + ScriptsDir.ReconstructionScripts + " " + self.keggDataDir + " " + self.taxonomy
NGS_Util.executeCall(call)
orgListFile_fh.close()
os.chdir(curDirectory)
except Exception:
print traceback.print_exc()
return ""
def makeBlastDB(self, organismName):
try:
print "Make Blast Database: " + organismName
org_fasta = NGS_Util.createFilePath(self.orgFastaDir, organismName+".faa")
org_dust = NGS_Util.createFilePath(self.orgBlastDustDir, organismName+"_dust.asnb")
org_blast_db = NGS_Util.createFilePath(self.orgBlastDBDir, organismName)
if os.path.exists(org_fasta):
if not os.path.exists(org_blast_db + ".phd") and not os.path.exists(org_blast_db + ".psq"):
self.ngsBlast.makeProteinBlastDBFromDustFile(org_fasta,org_dust,org_blast_db)
return org_blast_db
except Exception:
print traceback.print_exc()
return ""
def doMCLClustering(self, pfamID, abcFile, mclClusteringDir):
try:
mciFile, tabFile = self.makeClusterInputFiles(
pfamID, abcFile, mclClusteringDir)
I = 1.2
for index in range(1, 10):
output = NGS_Util.createFilePath(
mclClusteringDir,
pfamID + ".mci." + str(I).replace(".", ""))
call = "mcl " + mciFile + " -I " + str(
I) + " -use-tab " + tabFile + " -o " + output
I += 0.4
print call
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def runClusterIPRScan(self, organismName):
try:
splitFasta = MetabolicReconstructionPipeline_SplitFasta.MetabolicReconstructionPipeline_SplitFasta()
#numberOfFragments = 10
###############################################################################################################################################
org_fasta = NGS_Util.createFilePath(self.orgFastaDir, organismName+".faa")
splitFasta.splitOrganismDataFile(organismName, org_fasta, self.numberOfFragments)
###################################################################################################################################
clusterArrayCall = "qsub -t 1-" + str(self.numberOfFragments) + ":1 " + ScriptsDir.ClusterIprscan
iprscan = NGS_Util.createFilePath(ScriptsDir.IprscanDir,"interproscan.sh ")
splitFile = splitFasta.organismSplitDataDir + organismName
ipr_raw_file_split = NGS_Util.createFilePath(self.orgIPRScanDir, organismName + "_split" )
call = clusterArrayCall + " " + iprscan + " " + splitFile + " " + ipr_raw_file_split
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
return ""
def rawIPRScan(self, organismName, org_ipr_split_dir):
try:
print "rawIPRScan: " + organismName
for fragment in range(self.numberOfFragments):
org_ipr_split_file = NGS_Util.createFilePath(self.splitFasta.organismSplitDataDir,organismName + "_" + str(fragment+1) )
self.raw_split_IPRScan(organismName, org_ipr_split_file, str(fragment+1))
ipr_raw_file_split = NGS_Util.createFilePath(self.orgIPRScanDir, organismName + "_split_*")
ipr_raw_file = NGS_Util.createFilePath(self.orgIPRScanDir, organismName + ".ipr.raw")
call = "cat " + ipr_raw_file_split + " > " + ipr_raw_file
NGS_Util.executeCall(call)
return ipr_raw_file
except Exception:
print traceback.print_exc()
return ""
def run_Org_vs_Uniprot_ClusterBlast(self, organismName):
try:
splitFasta = MetabolicReconstructionPipeline_SplitFasta.MetabolicReconstructionPipeline_SplitFasta()
###############################################################################################################################################
org_fasta = NGS_Util.createFilePath(self.orgFastaDir, organismName+".faa")
splitFasta.splitOrganismDataFile(organismName, org_fasta, self.numberOfFragments)
###################################################################################################################################
clusterArrayCall = "qsub -t 1-" + str(self.numberOfFragments) + ":1 " + ScriptsDir.ClusterBlast
blastP = NGS_Util.createFilePath(ScriptsDir.BlastDir,"blastp")
outfmt = str(6)
splitFile = splitFasta.organismSplitDataDir + organismName
org_vs_UniprotBlastDB = NGS_Util.createFilePath(self.orgBlastResDir, organismName + "-vs-up" )
call = clusterArrayCall + " " + blastP + " " + self.uniprot_blast_db + " " + splitFile + " " + outfmt + " " + org_vs_UniprotBlastDB + " " + str(self.blastEValue)
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blast_org_vs_nr40_blast_formatted_11(self, organismName):
try:
org_fasta = NGS_Util.createFilePath(self.orgFastaDir, organismName+".faa")
clusterArrayCall = "qsub -t 1-1 " + ScriptsDir.ClusterGTGBlast
blastP = NGS_Util.createFilePath(ScriptsDir.BlastDir,"blastp")
outfmt = str(11)
org_vs_nr40BlastDB_f11 = NGS_Util.createFilePath(self.orgGTGBlastResDir, organismName + ".nrdb40_v2.txt")
call = clusterArrayCall + " " + blastP + " " + self.nrdb40_blast_db + " " + org_fasta + " " + outfmt + " " + org_vs_nr40BlastDB_f11 + " " + str(self.blastEValue)
NGS_Util.executeCall(call)
return org_vs_nr40BlastDB_f11
except Exception:
print traceback.print_exc()
return ""
def makeBlastDB(self, organismName):
try:
print "Make Blast Database: " + organismName
org_fasta = NGS_Util.createFilePath(self.orgFastaDir,
organismName + ".faa")
org_dust = NGS_Util.createFilePath(self.orgBlastDustDir,
organismName + "_dust.asnb")
org_blast_db = NGS_Util.createFilePath(self.orgBlastDBDir,
organismName)
if os.path.exists(org_fasta):
if not os.path.exists(org_blast_db +
".phd") and not os.path.exists(
org_blast_db + ".psq"):
self.ngsBlast.makeProteinBlastDBFromDustFile(
org_fasta, org_dust, org_blast_db)
return org_blast_db
except Exception:
print traceback.print_exc()
return ""
def copySequenceFiles(self, srcDataDir):
try:
print("Copy Fasta Files from %s to %s" %(srcDataDir,self.orgFastaDir))
orgListFile_fh = open(self.orgListFile)
for line in orgListFile_fh:
organismNameID, organismName = line.strip().split()
if not os.path.exists( NGS_Util.createFilePath(self.orgFastaDir, organismName + ".faa") ):
orgFasta = NGS_Util.createFilePath(srcDataDir, organismName + ".faa")
NGS_Util.copyFile(orgFasta, self.orgFastaDir)
print("Copied fasta file for %s" % (organismName))
else:
print("\tDoing nothing (files already copied) for %s" % (organismName))
orgListFile_fh.close()
except Exception:
print traceback.print_exc()
def concatenate_Org_vs_Uniprot_ClusterBlast_results(self, organismName):
try:
clusterProcessing = True
for fragment in range(self.numberOfFragments):
org_vs_UniprotBlastDB = NGS_Util.createFilePath(self.orgBlastResDir, organismName + "-vs-up_" + str(fragment+1) + ".blast" )
if not os.path.exists(org_vs_UniprotBlastDB):
clusterProcessing = False
break
if (clusterProcessing):
org_vs_UniprotBlastDB = NGS_Util.createFilePath(self.orgBlastResDir, organismName + "-vs-up.blast" )
call = "cat " + NGS_Util.createFilePath(self.orgBlastResDir, organismName + "-vs-up_*") + " > " + org_vs_UniprotBlastDB
NGS_Util.executeCall(call)
return org_vs_UniprotBlastDB
else:
print organismName + "-vs-Uniprot BLAST incomplete"
except Exception:
print traceback.print_exc()
return ""
def moveGTGResults(self):
try:
print "moveGTGResults"
orgListFile_fh = open(self.orgListFile)
NGS_Util.zipDirectory(self.orgGTGBlastResDir)
NGS_Util.moveDirectoryFiles(self.orgGTGBlastResDir,self.moveToDir_orgGTGBlastResDir)
NGS_Util.zipDirectory(self.GTGBestHitsDir)
NGS_Util.moveDirectoryFiles(self.GTGBestHitsDir,self.moveToDir_GTGBestHitsDir)
for line in orgListFile_fh:
organismNameID, organismName = line.strip().split()
org_gtg_knn_final = NGS_Util.createFilePath(self.GTGKNNDir, organismNameID + ".gtg.knn")
moveto_org_gtg_knn_final = NGS_Util.createFilePath(self.moveToDir_GTGKNNDir, organismNameID + ".gtg.knn")
self.moveFile_createLink(org_gtg_knn_final,moveto_org_gtg_knn_final)
orgListFile_fh.close()
except Exception:
print traceback.print_exc()
def runModelTrainingAlgo(self):
try:
print "runModelTrainingAlgo"
curDirectory = os.getcwd()
os.chdir(ScriptsDir.ModelTrainingScripts)
self.extract_IPR_EC_Values()
self.computeBlastPvalues()
self.computeMergedScores()
self.computeECscores()
self.computeProbabilityDensityScores()
self.combineProbabilityDensityScores()
self.computeTreeProbabilityDensityScore()
self.runBashScript()
NGS_Util.executeCall("rm *.Rout")
NGS_Util.executeCall("rm *.RData")
os.chdir(curDirectory)
except Exception:
print traceback.print_exc()
def makeProteinBlastDB(self, inputFasta,blastDB):
try:
call = self.makeblastdb + " -in " + inputFasta + " -input_type fasta -dbtype prot -parse_seqids -hash_index " + " -out " + blastDB
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def convert_raw_xml(self, inputFile, outputFile):
try:
call = self.converter + " -format xml -input " + inputFile + " -output " + outputFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def protein_iprscan5_to_xml_output(self, inputFile, outputFile):
try:
call = self.iprscan5 + " -i " + inputFile + " -o " + outputFile + " -f XML -goterms -iprlookup "
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def convert_iprscan5_xml_raw(self, inputFile, outputFile):
try:
call = self.iprscan5 + " -mode convert -i " + inputFile + " -f RAW -o " + outputFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blastP_with_Database_Size(self, blastDB, queryFastaFile, outfmt, blastResultFile, eValue, uniprotDBSize ):
try:
call = self.blastp + " -db " + blastDB + " -query " + queryFastaFile + " -outfmt " + str(outfmt) + " -out " + blastResultFile + " -evalue " + str(eValue) + " " + self.numThreads + " -dbsize " + str(uniprotDBSize)
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blastFormatter(self, archive, outfmt, formattedFile):
try:
call = self.blast_formatter + " -archive " + archive + " -outfmt " + str(outfmt) + " -out " + formattedFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blastP(self, blastDB, queryFastaFile, outfmt, blastResultFile, eValue ):
try:
call = self.blastp + " -db " + blastDB + " -query " + queryFastaFile + " -outfmt " + str(outfmt) + " -out " + blastResultFile + " -evalue " + str(eValue) + " " + self.numThreads
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def hmmpress(self, pfamFile):
try:
call = "hmmpress " + pfamFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blastP(self, blastDB, queryFastaFile, outfmt, blastResultFile, eValue ):
try:
call = self.blastp + " -db " + blastDB + " -query " + queryFastaFile + " -outfmt " + str(outfmt) + " -out " + blastResultFile + " -evalue " + str(eValue) + " " + self.numThreads
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blastFormatter(self, archive, outfmt, formattedFile):
try:
call = self.blast_formatter + " -archive " + archive + " -outfmt " + str(outfmt) + " -out " + formattedFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def blastP_with_Database_Size(self, blastDB, queryFastaFile, outfmt, blastResultFile, eValue, uniprotDBSize ):
try:
call = self.blastp + " -db " + blastDB + " -query " + queryFastaFile + " -outfmt " + str(outfmt) + " -out " + blastResultFile + " -evalue " + str(eValue) + " " + self.numThreads + " -dbsize " + str(uniprotDBSize)
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def makeProteinBlastDBFromDustFile(self, inputFasta, dustFile, blastDB):
try:
call = self.segmasker + " -in " + inputFasta + " -infmt fasta -parse_seqids -outfmt maskinfo_asn1_bin -out " + dustFile
call = self.makeblastdb + " -in " + inputFasta + " -input_type fasta -dbtype prot -parse_seqids -mask_data " + dustFile + " -out " + blastDB
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def convert_raw_xml(self, inputFile, outputFile):
try:
call = self.converter + " -format xml -input " + inputFile + " -output " + outputFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def getBlastScore(self, mode):
try:
print "getBlastScores"
orgListFile_fh = open(self.orgListFile)
for line in orgListFile_fh:
organismNameID, organismName = line.strip().split()
orgJointBlast = NGS_Util.createFilePath(self.orgBlastResDir, organismName + ".joint.blast")
orgRectifyBlast = NGS_Util.createFilePath(self.jointBlastDir, organismName + ".joint.blast")
print "getBlastScore:" + organismName
if not os.path.exists(orgRectifyBlast):
if os.path.exists(orgJointBlast):
orgRectifyBlast = self.rectifyBlast(organismName, orgJointBlast)
else:
if (mode == 1):
org_blast_db = self.makeBlastDB(organismName)
self.run_Org_vs_Uniprot_ClusterBlast(organismName)
time.sleep(1800) #wait for 15 minutes
self.run_Uniprot_vs_Org_ClusterBlast(organismName)
time.sleep(2400) #wait for 20 minutes
elif (mode == 2):
org_vs_UniprotBlastDB = self.concatenate_Org_vs_Uniprot_ClusterBlast_results(organismName)
Uniprot_vs_orgBlastDB = self.concatenate_Uniprot_vs_Org_ClusterBlast_results(organismName)
if (org_vs_UniprotBlastDB != "" and Uniprot_vs_orgBlastDB != ""):
orgJointBlast = self.combineBlast(organismName, org_vs_UniprotBlastDB, Uniprot_vs_orgBlastDB)
if (orgJointBlast != ""):
orgRectifyBlast = self.rectifyBlast(organismName, orgJointBlast)
orgListFile_fh.close()
except Exception:
print traceback.print_exc()
return ""
def hmmfetch(self, pfamFile, pfam, output):
try:
call = "hmmfetch " + pfamFile + " " + pfam + " > " + output
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def protein_iprscan_to_xml_output(self, inputFile, outputFile):
try:
call = self.iprscan + " -i " + inputFile + " -o " + outputFile + " -goterms -iprlookup "
NGS_Util.executeCall(call)
# NGS_Util.executeThreadedCall(call)
except Exception:
print traceback.print_exc()
def protein_iprscan_to_raw_output(self, inputFile, outputFile):
try:
call = self.iprscan + " -i " + inputFile + " -o " + outputFile + " -format raw -goterms -iprlookup "
NGS_Util.executeCall(call)
# NGS_Util.executeThreadedCall(call)
except Exception:
print traceback.print_exc()
def computeProbabilityDensityScores(self):
try:
print "computeProbabilityDensityScores"
call = "python " + ScriptsDir.ModelTrainingScripts_estimate_cpds_wrapper + " " + self.seq_org_list + " " + self.modelTraining_EC_Scores_Dir + " " + self.modelTraining_IPR_EC_Dir + " " + self.modelTrainingProbabilityDensityScoreDir
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def combineProbabilityDensityScores(self):
try:
print "combineProbabilityDensityScores"
call = "python " + ScriptsDir.ModelTrainingScripts_combined_density + " " + self.modelTrainingProbabilityDensityScoreDir
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def computeECscores(self):
try:
print "computeECscores"
call = "python " + ScriptsDir.ModelTrainingScripts_computeECscores + " " + self.modelTraining_EC_Scores_Dir
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def extract_IPR_EC_Values(self):
try:
print "extract_IPR_EC_Values"
call = "python " + ScriptsDir.ModelTrainingScripts_extract_ecs_from_iprscan + " " + self.fungi_InterProScan_result + " " + self.modelTraining_IPR_EC_Dir
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def computeBlastPvalues(self):
try:
print "computeBlastPvalues"
call = "python " + ScriptsDir.ModelTrainingScripts_computeBlastPvalues + " " + self.jointBlastDir + " " + self.modelTrainingBlastPVDir
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def computeTreeProbabilityDensityScore(self):
try:
print "computeTreeProbabilityDensityScore"
call = "python " + ScriptsDir.ModelTrainingScripts_estimate_mutation_probability + " " + self.modelTraining_IPR_EC_Dir + " " + self.phylogeneticTreeFile + " " + self.modelTrainingTreeDir
NGS_Util.executeCall(call)
self.treeCPDS = NGS_Util.createFilePath(self.modelTrainingTreeDir,"tree.cpds")
except Exception:
print traceback.print_exc()
def moveIPRScanResults(self):
try:
print "moveIPRScanResults"
orgListFile_fh = open(self.orgListFile)
NGS_Util.zipDirectory(self.orgIPRScanDir)
NGS_Util.moveDirectoryFiles(self.orgIPRScanDir,self.moveToDir_orgIPRScanDir)
for line in orgListFile_fh:
organismNameID, organismName = line.strip().split()
organism_raw_final = NGS_Util.createFilePath(self.InterProScan_EC_RAW_results, organismName + ".faa.raw.txt")
moveto_organism_raw_final = NGS_Util.createFilePath(self.moveToDir_InterProScan_EC_RAW_results, organismName + ".faa.raw.txt")
self.moveFile_createLink(organism_raw_final,moveto_organism_raw_final)
organism_IPR_final = NGS_Util.createFilePath(self.InterProScan_EC_RAW_results, organismName + ".faa.IPR.final.txt")
moveto_organism_IPR_final = NGS_Util.createFilePath(self.moveToDir_InterProScan_EC_RAW_results, organismName + ".faa.IPR.final.txt")
self.moveFile_createLink(organism_IPR_final,moveto_organism_IPR_final)
orgListFile_fh.close()
except Exception:
print traceback.print_exc()
return ""
def makeProteinBlastDBFromDustFile(self, inputFasta, dustFile, blastDB):
try:
if not os.path.exists(dustFile):
call = self.segmasker + " -in " + inputFasta + " -infmt fasta -parse_seqids -outfmt maskinfo_asn1_bin -out " + dustFile
NGS_Util.executeCall(call)
call = self.makeblastdb + " -in " + inputFasta + " -input_type fasta -dbtype prot -parse_seqids -hash_index -mask_data " + dustFile + " -out " + blastDB
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def computeMergedScores(self):
try:
print "computeMergedScores"
call = "python " + ScriptsDir.ModelTrainingScripts_computeMergedScores + " " + self.seq_org_list + " " + self.modelTrainingBlastPVDir + " " + self.GTGFungiKNNDir + " " + self.modelTraining_EC_Scores_Dir
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def preprocess_EC_UniprotSprot_data_files(self):
try:
print "preprocess_EC_UniprotSprot_data_files"
if not os.path.exists(self.ec_files) and os.path.exists(
self.uniprot_sprot_dat):
call = "python " + ScriptsDir.BlastScripts_getEcs + " " + self.uniprot_sprot_dat + " " + self.ec_files + ": AC, ID, EC"
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def runBashScript(self):
try:
print "runBashScript"
call = "bash " + ScriptsDir.ModelTrainingScripts_run_job + " " + self.modelTrainingDir + " " + self.modelTrainingModelDir + " " + self.modelTraining_EC_Scores_Dir + " " + self.modelTrainingProbabilityDensityScoreDir+"all" + " " + self.seq_org_list + " " + self.phylogeneticTreeFile + " " + self.modelTraining_IPR_EC_Dir + " " + self.treeCPDS
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def preprocess_EC_UniprotSprot_data_files(self):
try:
print "preprocess_EC_UniprotSprot_data_files"
if not os.path.exists( self.ec_files ) and os.path.exists(self.uniprot_sprot_dat):
call = "python " + ScriptsDir.BlastScripts_getEcs + " " + self.uniprot_sprot_dat+ " " + self.ec_files +": AC, ID, EC"
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def generateKeggData(self):
try:
print "generateKeggData"
if not os.path.exists(self.keggAtomMapsDataDir):
call = "bash " + ScriptsDir.keggParsingScripts_build_kegg_no_general
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def generateKeggData(self):
try:
print "generateKeggData"
if not os.path.exists(self.keggAtomMapsDataDir):
call = "bash " + ScriptsDir.keggParsingScripts_build_kegg_no_general
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
def gettNormalizedBlastBitScoreMatrix(self, pfamID, bitScoreMatrix, blastResultFile):
try:
print "gettNormalizedBlastBitScoreMatrix"
normalizedBitScoreMatrix = self.createBlastBitScoreMatrix(blastResultFile)
for sequenceId, matchingSequenceIDsList in bitScoreMatrix.iteritems():
for matchingSequenceID in matchingSequenceIDsList:
sum = bitScoreMatrix[sequenceId][sequenceId] + bitScoreMatrix[matchingSequenceID][matchingSequenceID] - bitScoreMatrix[sequenceId][matchingSequenceID]
normalizedBitScoreMatrix[sequenceId][matchingSequenceID] = bitScoreMatrix[sequenceId][matchingSequenceID] / sum
normalizedBitScoreMatrixFile = NGS_Util.createFilePath(self.pfamBlastStaticticsDir, pfamID + "_NormalizedBitScores.txt")
self.writeMatrixToFile(normalizedBitScoreMatrix, normalizedBitScoreMatrixFile)
return normalizedBitScoreMatrix
except Exception:
print traceback.print_exc()
return ""
def combineBlast(self, organismName, org_vs_UniprotBlastDB, Uniprot_vs_orgBlastDB):
try:
print "Combine Blast: " + organismName
orgJointBlast = NGS_Util.createFilePath(self.orgBlastResDir, organismName + ".joint.blast")
org_vs_UniprotBlastDB_fh = open(org_vs_UniprotBlastDB)
Uniprot_vs_orgBlastDB_fh = open(Uniprot_vs_orgBlastDB)
ec_files_fh = open(self.ec_files)
orgJointBlast_fh = open(orgJointBlast, "w")
combineBlasts(ec_files_fh, org_vs_UniprotBlastDB_fh, Uniprot_vs_orgBlastDB_fh, orgJointBlast_fh)
org_vs_UniprotBlastDB_fh.close()
Uniprot_vs_orgBlastDB_fh.close()
ec_files_fh.close()
orgJointBlast_fh.close()
return orgJointBlast
except Exception:
print traceback.print_exc()
return ""
def generatePics(currentRunDir):
try:
print "generatePics"
call = "cat " + projectBinDir + "r_analyseClustering.R | R --slave --args " + currentRunDir
NGS_Util.executeCall(call)
picsDir = NGS_Util.createDirectoryPath(currentRunDir, "PicsTables")
epsFile = NGS_Util.createFilePath(picsDir, "SenSpeVsInfAll.eps")
pngFile = NGS_Util.createFilePath(picsDir, "SenSpeVsInfAll.png")
call = "convert " + epsFile + " " + pngFile
NGS_Util.executeCall(call)
except Exception:
print traceback.print_exc()
return ""
def makeClusterInputFiles(self, pfamID, abcFile, mclClusteringDir):
try:
mciFile = NGS_Util.createFilePath(mclClusteringDir,
pfamID + ".mci")
tabFile = NGS_Util.createFilePath(mclClusteringDir,
pfamID + ".tab")
call = "mcxload -abc " + abcFile + " --stream-mirror --stream-neg-log10 -stream-tf 'ceil(200)' -o " + mciFile + " -write-tab " + tabFile
NGS_Util.executeCall(call)
return mciFile, tabFile
except Exception:
print traceback.print_exc()
def map_ipr_to_specific_ecs(self,organismName, organism_ipr2go):
try:
print "map_ipr_to_specific_ecs: " + organismName
organism_ipr2ec = NGS_Util.createFilePath(self.orgIPRScanDir, organismName + "_ipr2ec.txt")
call = "python " + ScriptsDir.IPRScanScripts_get_interpro_ecs + " " + self.ec2go + " " + organism_ipr2go + " " + organism_ipr2ec
NGS_Util.executeCall(call)
return organism_ipr2ec
except Exception:
print traceback.print_exc()
return ""
def reform_knn(self, organismName, org_gtg_knn): # (9) Add org and ecs
try:
print "reform_knn: " + organismName
org_gtg_knn_final = NGS_Util.createFilePath(self.GTGKNNDir, organismName + ".gtg.knn")
call = "python " + ScriptsDir.GTGScripts_reform_knn + " " +self.seq_org_list + " " + self.ec_files + " " + org_gtg_knn + " " + org_gtg_knn_final
NGS_Util.executeCall(call)
return org_gtg_knn_final
except Exception:
print traceback.print_exc()
return ""
def extract_combine_seq_start_len_fmt11(self, organismName, org_vs_nr40BlastDB_f11_part1, org_vs_nr40BlastDB_f11_part2): #(4) combine the result from previous two steps
try:
print "extract_combine_seq_start_len_fmt11: " + organismName
org_vs_nr40BlastDB_f11_part1_part2_result = NGS_Util.createFilePath(self.orgGTGBlastResDir, organismName + ".nrdb40_v2.part1.part2.result")
call = "python " + ScriptsDir.GTGScripts_extract_combine_seq_start_len_fmt11 + " " + org_vs_nr40BlastDB_f11_part1 + " " + org_vs_nr40BlastDB_f11_part2 + " " + org_vs_nr40BlastDB_f11_part1_part2_result
NGS_Util.executeCall(call)
return org_vs_nr40BlastDB_f11_part1_part2_result
except Exception:
print traceback.print_exc()
return ""
def extract_ipr2go_based_on_xml(self,organismName, ipr_xml_file):
try:
print "extract_ipr2go_based_on_xml: " + organismName
organism_ipr2go = NGS_Util.createFilePath(self.orgIPRScanDir, organismName + "_ipr2go.txt")
call = "python " + ScriptsDir.IPRScanScripts_ipr2go + " " + ipr_xml_file + " " + organism_ipr2go
NGS_Util.executeCall(call)
return organism_ipr2go
except Exception:
print traceback.print_exc()
return ""