def analyseRecombindationResults(self,oligoReport,featureList,outputFile="oligo_recomb_analysis.txt"):
result = Report()
result.extend(oligoReport)
rowNames = oligoReport.returnRowNames()
recordAlignment = SeqRecord(Seq(""))
recordAlignment.features = featureList
for rName in rowNames:
output.write(rName + "\n")
start = float(oligoReport["genomic_start"][rName])
end = float(oligoReport["genomic_end"][rName])
oligo = oligoReport["best"][rName]
keyString = "\n(%s,%s) %s\n\n" % (start,end,oligo)
output.write(keyString)
subFeatures = self._selectFeatures(featureList,start,end)
index = 0
for feature in subFeatures:
matchName = "match_" + str(index)
id = feature.id
qValue = feature.qualifiers["query"]
sValue = feature.qualifiers["subject"]
matchString = feature.qualifiers["alignment"]
output.write(id + "\n")
output.write(matchString + "\n\n")
result.add(rName,matchName,qValue)
index += 1
output.close()
return result
def geneControlReport(self,model,controlMap,outputName):
report = Report()
geneMap = model.controlMap
for (target,controls) in geneMap.keys():
for control in controls:
report.add(target,control,"control")
writer = ReportWriter()
writer.setFile(outputName)
writer.write(report)
writer.closeFile()
return None
def parseGenericReport(self, fileName, keyTag=None, header = None, unique = True):
'''
@var fileName: name of flat (delimited) in text format to be parsed
@type fileName: String
@var keyTag: ID of column to be used for report key row
@type keyTag: String
@summary:
Primary Function
Parses flat file returns report object.
'''
result = Report()
kIndex = None
lines = open( fileName, 'r' )
index = 0
for line in lines:
if self.isComment( line ):
pass
elif self.endLine < index < self.startLine:
index += 1
continue
elif index == self.headerLine:
header = self.parseHeader( line, unique )
if keyTag in header:
kIndex = header.index(keyTag)
elif self.endLine > index > self.startLine:
line = line.replace('\n','')
sLine =self._safeSplit(line)
if kIndex != None:
rName = sLine[kIndex]
else:
rName = str(index)
for i in range(len(sLine)):
if i != kIndex:
cName = header[i]
value = sLine[i]
result.add(rName,cName,value)
index += 1
lines.close()
return result
def enzymeBoundaryControl(model,targets,bounds,objectiveName,productionName,searchSize):
targets = bounds.keys()
controlNames = model.getControlsForNames(targets)
eControlMap = model.getEnzymeControlMap()
controlSubSets = combinations(controlNames,searchSize)
xcontrolSubSets = set(controlSubSets)
result = Report()
iter = 0
for icontrolNames in xcontrolSubSets:
ibounds = {}
controlTag = ''
ienzymeNames = model.annotateGeneList(list(icontrolNames))
ienzymeNames.sort()
for ieName in ienzymeNames:
controlTag += "(%s)" % (ieName)
for icontrolName in icontrolNames:
itargets = eControlMap[icontrolName]
for itarget in itargets:
if itarget in bounds.keys():
ibound = bounds[itarget]
ibounds[itarget] = ibound
#print ("control %s => [%s]") % (icontrolName,ibounds)
pass
if len(ibounds) == 0:
continue
(fluxMap,oflux,pflux) = findBoundaryProduction(model, ibounds, None, objectiveName, productionName)
print "[%s] objective %s => production %s" % (controlTag, oflux, pflux)
iter += 1
#iEnzymeNames = model.annotateGeneList(icontrolNames)
#for icontrolName in iEnzymeNames:
# result.add(iter, icontrolName, "active")
result.add(controlTag,"natural",oflux)
result.add(controlTag,"production",pflux)
return result
def parseAlignments(self,records,featureLocations):
result = Report()
index = 0
logFile = open("oligoLog.txt","w")
targetMap = {}
for r in records:
id = r.id
features = featureLocations[index]
hits = len(features)
genomicStart = features[0].location.start.position
genomicEnd = features[0].location.end.position
genomicStrand = features[0].strand
laggingComplementStrand = self.strandChooser(features[0])
if "alignment" in features[0].qualifiers.keys():
aMatch = features[0].qualifiers["alignment"]
else:
aMatch = ''
targetMap[id] = (genomicStart + genomicEnd)/2
logFile.write(id+"\n")
logFile.write(aMatch+"\n")
#if self.verbose: print aMatch
s = str(r.seq)
originalString = s
result.add(id,"original", originalString)
result.add(id,"hits", hits)
result.add(id,"genomic_start", genomicStart)
result.add(id,"genomic_end", genomicEnd)
result.add(id,"genomic_strand", genomicStrand)
result.add(id,"match", aMatch)
return result
def getControlReport(self,genes,targetRecord,sequence,boundary=0,range=1000):
'''
Create report of control regions for listed genes
'''
result = Report()
seqProp = RecombinationOligoFactory()
sdata = str(sequence).lower()
promoters = {}
locations = {}
arrow= ["<-","-","->"]
if self.verbose: print "finding local features"
localFeatures = self.localFeatures(genes,targetRecord,range=range)
if self.verbose: print "features found, creating report"
for feature in genes:
name = feature.qualifiers["gene"][0]
locTag = feature.qualifiers["locus_tag"][0]
start = feature.location.start.position
end = feature.location.end.position
strand = feature.strand
result.add(name,"locus_tag",locTag)
result.add(name,"gene_start",start)
result.add(name,"gene_end",end)
result.add(name,"gene_strand",strand)
if strand == 1:
loc = start
if strand == -1:
loc = end
rbsSeq = self.getSequenceRegion(sdata, loc, 3, boundary, strand)
oligoStrandRbs = seqProp.strandChooser(feature)
result.add(name,"rbs_start",loc)
result.add(name,"rbs_region",rbsSeq)
result.add(name,"rbs_Oligo_Strand",str(oligoStrandRbs))
iLocalFeatures = localFeatures[name]
count = 0
for tFeature in iLocalFeatures:
count = count + 1
tName = tFeature.qualifiers["gene"][0]
tStart = tFeature.location.start.position
tEnd = tFeature.location.end.position
tStrand = tFeature.strand
oligoStrand = seqProp.strandChooser(tFeature)
iArrow = arrow[tStrand + 1]
if tStrand == strand:
tSize = -1*tStrand
pSeq = self.getSequenceRegion(sdata, tStart, tSize, boundary, strand)
tag = "%s:[%s %s %s] t[%s] = %s" % (tName,tStart,iArrow,tEnd,oligoStrand,pSeq)
colName = "promoter_%s" % (count)
result.add(name,colName,tag)
return result
def findPrimers(self,seq,targetMap,boundary,oligoSize,searchSize,targetTm):
'''
@input targetMap: a list of genomic locations with sequence names
find a list of sequencing primers for a list of target locations
usage:
set boundary and oligo size
read in report, list of locations
run find sequence primers.
write report of result
'''
result = Report()
for k in targetMap.keys():
targetLocation = targetMap[k]
upLocation = targetLocation - boundary
upStart = targetLocation - boundary - searchSize - oligoSize
upEnd = targetLocation - boundary + searchSize
upSeq = seq[upStart:upEnd]
downLocation = targetLocation + boundary
downStart = targetLocation + boundary - searchSize
downEnd = targetLocation + boundary + searchSize + oligoSize
downSeq = seq[downStart:downEnd]
downSeq = downSeq.reverse_complement()
start = searchSize
(uTm,uAdjust,oUpSeq) = self.scanOligoTm(upSeq,start,oligoSize,searchSize,targetTm)
(dTm,dAdjust,oDownSeq) = self.scanOligoTm(downSeq,start,oligoSize,searchSize,targetTm)
dAdjust = -dAdjust
ucLocation = upLocation + uAdjust
dcLocation = downLocation + dAdjust
result.add(k,"sequencing location",targetLocation)
result.add(k,"foward primer",oUpSeq)
result.add(k,"foward adjust",uAdjust)
result.add(k,"foward location",ucLocation)
result.add(k,"foward TM",uTm)
result.add(k,"reverse primer",oDownSeq)
result.add(k,"reverse adjust",dAdjust)
result.add(k,"reverse location",dcLocation + dAdjust)
result.add(k,"reverse TM",dTm)
return result
def generateTargetingOligos(self, records, featureLocations, tagRE, boundary, searchSize, cutOff):
'''
Generate a list of oligos for recombination in target locations
and return report with the targets and sequencing oligos
All oligos printed 5' -> 3'
Control upstream will be to the left if strands are preserved and to the right
if strands are switched when matching lagging complement
oligos are selected discovered as an optimized subsection of the presented sequences
@records: sequences from which to select oligos
@featureLocations: a list of locations that place the features in a genome
@tagRE: regular expression for finding taged sequence with in feature sequences.
@bounary: oligo flanking region size
@searchSize: distance in base pairs to search for optimal oligo
@cutOff: limit of viable fold change energy for chose oligos.
'''
result = Report()
index = 0
logFile = open("oligoLog.txt","w")
targetMap = {}
sRegions = []
for r in records:
id = r.id
features = featureLocations[index]
hits = len(features)
genomicStart = features[0].location.start.position
genomicEnd = features[0].location.end.position
genomicStrand = features[0].strand
laggingComplementStrand = self.strandChooser(features[0])
if "alignment" in features[0].qualifiers.keys():
aMatch = features[0].qualifiers["alignment"]
else:
aMatch = ''
targetMap[id] = (genomicStart + genomicEnd)/2
logFile.write(id+"\n")
logFile.write(aMatch+"\n")
#if self.verbose: print aMatch
s = str(r.seq)
originalString = s
#Find larget section using special targeting tag
matchTag = re.search(tagRE,s)
if matchTag == None:
tagLoc = len(s)/2
else:
targetTag = matchTag.group(0)
tagLoc = s.index(targetTag) + len(targetTag)/2
if self.verbose: print "Target [%s] location [%s]" % (targetTag,tagLoc)
start = int(tagLoc - boundary)
end = int(tagLoc + boundary)
#!May need a little touch up
if start < 0:
start = 0
end = int(boundary*2)
if end > len(s):
end = len(s)
if self.verbose: print"region %s -> %s of %s" % (start,end,len(s))
lowSearchBound = start - searchSize - 5
highSearchBound = end + searchSize + 5
if lowSearchBound < 0:
lowSearchBound = 0
if highSearchBound > len(s):
highSearchBound = len(s)
if genomicStrand == laggingComplementStrand:
s = r.seq[lowSearchBound:highSearchBound]
sx = r.seq[start:end]
else:
s = r.seq[lowSearchBound:highSearchBound].reverse_complement()
sx = r.seq[start:end].reverse_complement()
searchEnd = (end-start+searchSize+5)
searchStart = searchSize + 5
try:
testSeqs = self.optimizeSecondaryStructure(s, searchStart, searchEnd, searchSize, cutOff, ratio = 2)
testSeqs.sort()
if len(testSeqs) == 0:
(score,adjust,foldScore,bestSeq) = ("na","na","na","na")
else:
(score,adjust,foldScore,bestSeq) = testSeqs.pop(0)
except:
testSeqs = []
(score,adjust,foldScore,bestSeq) = ("na","na","na",sx)
print "failed to exicute secondary structure test"
#print "[%s]" % (s)
#bestSeq = self.addStars(bestSeq,self.stars)
if len(bestSeq) < boundary*2:
print "Short Sequence"
if self.verbose: print "%s best %s S:%s [%s] (%s)" % (len(testSeqs), adjust, score, foldScore, len(bestSeq))
if self.verbose: print "[%s]" % (bestSeq)
result.add(id,"original", originalString)
result.add(id,"hits", hits)
result.add(id,"genomic_start", genomicStart)
result.add(id,"genomic_end", genomicEnd)
result.add(id,"genomic_strand", genomicStrand)
result.add(id,"lagging_complement_strand", laggingComplementStrand)
result.add(id,"best", bestSeq)
result.add(id,"fold score", foldScore)
result.add(id,"off center", adjust)
#append to list of sequence regions
sRegion = r
sRegion.seq = sx
sRegions.append(sRegion)
index = index + 1
logFile.close()
return (targetMap,result,sRegions)
