alignCutOff = 0.45
print "alignCutOff wasn't given, assuming 0.5"
try:
coveCutOff = int(sys.argv[6])
print('coveCutOff: %s' % coveCutOff)
except:
coveCutOff = 7
print "coveCutOff wasn't given, assuming 7"
x = geneCheck(genBankReference, resultFile, 0.50, True, blastFolder, organismType, alignCutOff)
print 'Features found: %s' % len(x[0])
print 'Total features: %s' % len(x[1])
print ''
print('Running tRNAscan-SE...')
presentFeatures = x[0]
assemblyCheck = tRNAscanChecker.tRNAscanCheck(resultFile, True, False, organismType, coveCutOff) #returns a Assembly object with statistics and alignment info
tRNAs = assemblyCheck.tRNAs
listOfFeaturesToOutput = []
listOfFoundTRNAs = []
for foundFeature in presentFeatures:
thisFeatureFound = presentFeatures[foundFeature][1]
#comparing tRNAscan-SE results with this, in case tRNAscan-SE was run
if "trn" in thisFeatureFound.seq2.lower():
for tRNAFound in tRNAs:
#down here we update the start and end positions of tRNAs found with Needle, with the
#results outputted by tRNAScan-SE
#tRNAconver = guarantees all tRNA names are in tRNA-Phe format
if 'trna-' + tRNAFound.tRNAtype.lower() == tRNAconvert(thisFeatureFound.seq2.lower()):
thisFeatureFound.startBase = min(tRNAFound.tRNAcoordinates[0],
tRNAFound.tRNAcoordinates[1])
destFile = pathOfFinalResults + args.processName + '.unordered.maf' shutil.copyfile(pathOfMafResult, destFile) destFile = pathOfFinalResults + args.processName + '.unordered.caf' shutil.copyfile(pathOfCafResult, destFile) print '## Final sequence saved to %s' % pathOfFinalResults #from now on, just checking how the build went to output to user and then annotate print '## Now running tRNAscan-SE to check the final build...' if args.skipTrnaScan == True: print '' print '## --skiptrna is turned on, going to ignore this check and move on...' fifthStep = tRNAscanChecker.tRNAscanCheck(resultFile, fourthStep[0], args.skipTrnaScan, args.organismType, args.coveCutOff, args.buildBacteria, args.buildArchea) #returns a Assembly object #with statistics and alignment info if args.skipTrnaScan == False: print '## %s tRNAs were found.' % len(fifthStep) if args.ignoreFirstBuildChecks == False: print '' print '## Procceding to genomic check and annotation...' print '' #time to look for genomic features, searching according to the -o flag #or with the genbank reference that was given organismType = args.organismType module_dir = os.path.dirname(__file__) module_dir = os.path.abspath(module_dir) '''
def checkResults(processName, pathToWork, sizeToLook, refSeqFile = None, cutoffValue = (2500,18000), blasteVal = 10.0,
blastHitSizePercentage = 0.625, usingSOAP = True, numberOfReadGroups = 1, buildCloroplast = False,
skipTrnaScan = False, circularSize = 40, circularOffSet = 220, cutoffEquality = 0.625, organismType = 2,
blastFolder = 'installed', noExtension = False, ignoreFirstBuildChecks = False, coveCutOff = 8,
buildBacteria = False, buildArchea = False, validContigs = 1):
'''
Do checks for main checker function...
Checks for tRNAs, other features like rRNAs, genes, etc and returns a Assembly object, from tRNAscanChecker
that holds this info.
'''
genBankReference = False
#Let's set the default gene checking genbank file according to the organismType flag
#and if a genbank reference was given in the -r flag, it will be changed
module_dir = os.path.dirname(__file__)
module_dir = os.path.abspath(module_dir)
'''
1. The Standard Code
2. The Vertebrate Mitochondrial Code
3. The Yeast Mitochondrial Code
4. The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code
5. The Invertebrate Mitochondrial Code
6. The Ciliate, Dasycladacean and Hexamita Nuclear Code
9. The Echinoderm and Flatworm Mitochondrial Code
10. The Euplotid Nuclear Code
11. The Bacterial, Archaeal and Plant Plastid Code
12. The Alternative Yeast Nuclear Code
13. The Ascidian Mitochondrial Code
14. The Alternative Flatworm Mitochondrial Code
16. Chlorophycean Mitochondrial Code
21. Trematode Mitochondrial Code
22. Scenedesmus obliquus Mitochondrial Code
23. Thraustochytrium Mitochondrial Code
24. Pterobranchia Mitochondrial Code
25. Candidate Division SR1 and Gracilibacteria Code
'''
if buildCloroplast == True:
refSeqFileForGenes = os.path.join(module_dir, 'references/cloroplast.gb')
elif organismType == 11: #plant plastid or bacterial or archea
refSeqFileForGenes = os.path.join(module_dir, 'references/magnolia.gb')
if buildBacteria == True:
refSeqFileForGenes = os.path.join(module_dir, 'references/bacteria.gb') #some bacterial DNA
elif buildArchea == True:
refSeqFileForGenes = os.path.join(module_dir, 'references/archea.gb') #some archea DNA
elif organismType == 3: #yeast
refSeqFileForGenes = os.path.join(module_dir, 'references/yeast.gb')
elif organismType == 5: #invertebrate, insect
refSeqFileForGenes = os.path.join(module_dir, 'references/beetle.gb')
elif organismType == 6: #ciliate
refSeqFileForGenes = os.path.join(module_dir, 'references/paramecium.gb')
elif organismType != 1: #human, 2(vertebrate), also the default option
refSeqFileForGenes = os.path.join(module_dir, 'references/human.gb')
#we don't need a sequence reference for this check
if refSeqFile != None: #if user gave a reference file not in fasta, let's consider it to look for features
if refSeqFile[-6:] != '.fasta':
genBankReference = True
refSeq = SeqIO.read(refSeqFile, "genbank", generic_dna)
refSeqFileForGenes = refSeqFile
circularCheck = circularizationCheck.circularizationCheck("best_query.fasta", circularSize, circularOffSet, blastFolder) #returns a tuple with True or False and coordinates
if circularCheck[0] == True:
print('Circularization was found.')
else:
print('Circularization was not found.')
if skipTrnaScan == False: #user did not want to skip tRNAscanChecker
print("Checking for tRNAs...")
else:
print("Checking for genomic features...")
checktRNA = tRNAscanChecker.tRNAscanCheck("best_query.fasta", circularCheck, skipTrnaScan, organismType, coveCutOff, buildBacteria,
buildArchea)
#add to the assembly object the number of contigs concatenated to create this super contig
checktRNA.validContigs = validContigs
'''
let's check for it's features to see if everything was built,
if a .gb reference was given we check against that, if not, we check against
our own database inside references/ folder according to -o flag
'''
if ignoreFirstBuildChecks == False:
checktRNA.checkFeatures = geneChecker.geneCheck(refSeqFileForGenes, "best_query.fasta", cutoffEquality, genBankReference, blastFolder,
organismType = organismType)
presentFeatures = checktRNA.checkFeatures[0]
importantFeatures = checktRNA.checkFeatures[1]
splitFeatures = checktRNA.checkFeatures[2]
print 'Features found: %s / %s' % (len(presentFeatures) - len(splitFeatures), len(importantFeatures))
else:
checktRNA.checkFeatures = ([],[])
presentFeatures = checktRNA.checkFeatures[0]
importantFeatures = checktRNA.checkFeatures[1]
print 'Ignoring genomic checks, since --relaxed is on.'
print "Assessing checks..."
if (len(checktRNA) == 21 and buildCloroplast == False) or (len(checktRNA) == 37 and buildCloroplast == True):
print 'All ' + str(len(checktRNA)) + ' tRNAs were found!'
if circularCheck[0] == True:
print 'And this build is circular.'
if len(presentFeatures) == len(importantFeatures):
print 'And all genes, tRNAs and rRNAs were found.'
if skipTrnaScan == True:
return True
elif len(presentFeatures) >= len(importantFeatures):
print 'And all genes, tRNAs and rRNAs were found, but some were split or duplicated.'
else:
print 'But not all genes, tRNAs and rRNAs were found, storing info and rebuilding...'
print ''
return checktRNA
print ''
#if all tRNAs were found, all features were found and it's circular, just return true and stop the recursive part
return True
else:
print 'But circularization could not be found yet, storing this info...'
if len(presentFeatures) == len(importantFeatures):
print 'And all genes, tRNAs and rRNAs were found.'
elif len(presentFeatures) >= len(importantFeatures):
print 'And all genes, tRNAs and rRNAs were found, but some were split or duplicated.'
else:
print 'But not all genes, tRNAs and rRNAs were found, storing info...'
print 'Rebuilding...'
print ''
return checktRNA
else:
print str(len(checktRNA)) + ' tRNAs were built.'
if len(presentFeatures) == len(importantFeatures):
print 'And all genes and rRNAs were found.'
elif len(presentFeatures) >= len(importantFeatures):
print 'And all genes, tRNAs and rRNAs were found, but some were split or duplicated.'
else:
print 'But not all genes and rRNAs were found, storing info...'
print ''
return checktRNA