def sequenceFilter(seqDict,minSize,minAbundance):
nameList=seqDict.keys()
for name in nameList:
size=int(getAttriValueFromSeqName(name,"sampleSize"))
abundance=int(getAttriValueFromSeqName(name,"abundance"))
if size<minSize or abundance<minAbundance:
del seqDict[name]
return seqDict
def sequenceFilter(seqDict, minSize, minAbundance):
nameList = seqDict.keys()
for name in nameList:
size = int(getAttriValueFromSeqName(name, "sampleSize"))
abundance = int(getAttriValueFromSeqName(name, "abundance"))
if size < minSize or abundance < minAbundance:
del seqDict[name]
return seqDict
def listbySampleSize(fastafile):
reDict = {}
for line in open(fastafile, "r"):
if line.startswith(">"):
size = getAttriValueFromSeqName(line, "sampleSize")
if reDict.get(size, False):
reDict[size].append(line.lstrip(">").rstrip())
else:
reDict[size] = [line.lstrip(">").rstrip()]
return reDict
def listbySampleSize(fastafile):
reDict={}
for line in open(fastafile,"r"):
if line.startswith(">"):
size=getAttriValueFromSeqName(line,"sampleSize")
if reDict.get(size,False):
reDict[size].append(line.lstrip(">").rstrip())
else:
reDict[size]=[line.lstrip(">").rstrip()]
return reDict
def assignedSingleton2Annotated(seedDict, distanceFile, threshold,
singletonfile):
singletonList = [] #return
reDict = {}
usesingleton = []
for line in open(distanceFile, 'r'):
lineList = line.strip().split()
candidateDict = reDict.get(lineList[1], None)
if candidateDict:
if candidateDict.get(lineList[2], None):
reDict[lineList[1]][lineList[2]].append(lineList[0])
else:
reDict[lineList[1]][lineList[2]] = [lineList[0]]
else:
reDict[lineList[1]] = {}
reDict[lineList[1]][lineList[2]] = [lineList[0]]
for Candi in reDict:
candidateName = Candi
candiDict = reDict[Candi]
distanceList = candiDict.keys()
minDistance = min(distanceList)
if float(minDistance) <= float(threshold):
usesingleton.append(Candi)
seedList = candiDict[minDistance]
if len(seedList) > 1:
maxSize = 0
selectSeedSequenceName = ""
for seqName in seedList:
sampleSize = getAttriValueFromSeqName(
seqName, "sampleSize")
if int(sampleSize) > int(maxSize):
maxSize = sampleSize
selectSeedSequenceName = seqName
else:
pass
else:
selectSeedSequenceName = seedList[0]
reDict[Candi] = selectSeedSequenceName
else:
reDict[Candi] = 'None'
for line in open(singletonfile, 'r'):
if line.startswith('>'):
name = line[1:].strip()
if name in usesingleton:
continue
else:
singletonList.append(name)
#
for candiName in reDict:
ParentsSeq = reDict[candiName]
if ParentsSeq == 'None':
pass
else:
seedDict[ParentsSeq].append(candiName)
return seedDict, singletonList
def assignedSingleton2Annotated(seedDict,distanceFile,threshold,singletonfile):
singletonList=[] #return
reDict={}
usesingleton=[]
for line in open(distanceFile,'r'):
lineList=line.strip().split()
candidateDict=reDict.get(lineList[1],None)
if candidateDict:
if candidateDict.get(lineList[2],None):
reDict[lineList[1]][lineList[2]].append(lineList[0])
else:
reDict[lineList[1]][lineList[2]]=[lineList[0]]
else:
reDict[lineList[1]]={}
reDict[lineList[1]][lineList[2]]=[lineList[0]]
for Candi in reDict:
candidateName=Candi
candiDict=reDict[Candi]
distanceList=candiDict.keys()
minDistance=min(distanceList)
if float(minDistance)<=float(threshold):
usesingleton.append(Candi)
seedList=candiDict[minDistance]
if len(seedList)>1:
maxSize=0
selectSeedSequenceName=""
for seqName in seedList:
sampleSize=getAttriValueFromSeqName(seqName,"sampleSize")
if int(sampleSize)>int(maxSize):
maxSize=sampleSize
selectSeedSequenceName=seqName
else:
pass
else:
selectSeedSequenceName=seedList[0]
reDict[Candi]=selectSeedSequenceName
else:
reDict[Candi]='None'
for line in open(singletonfile,'r'):
if line.startswith('>'):
name=line[1:].strip()
if name in usesingleton:
continue
else:
singletonList.append(name)
#
for candiName in reDict:
ParentsSeq=reDict[candiName]
if ParentsSeq=='None':
pass
else:
seedDict[ParentsSeq].append(candiName)
return seedDict,singletonList
def selectRefBySampeSize(minsampleSize,tempDir,copysequence,reference):
totalRef=os.path.splitext(copysequence)[0]+".ref"
print totalRef
fref=open(totalRef,'w') #used as reference for chimera detection
requry=os.path.splitext(copysequence)[0]+".requry"
fqury=open(requry,'w') #used as requery for chimera detecthion
nonchimera=os.path.splitext(copysequence)[0]+".nonchimera"
fnonch=open(nonchimera,'w') #a part of sequence for output that nonchimera.
requrySeqDict=fasta2dict(copysequence)
for name in requrySeqDict:
if int(getAttriValueFromSeqName(name,"sampleSize"))>=minsampleSize:
fref.write(">%s\n%s\n"%(name,requrySeqDict[name]))
fnonch.write(">%s\n%s\n"%(name,requrySeqDict[name]))
else:
fqury.write(">%s\n%s\n"%(name,requrySeqDict[name]))
refdict=fasta2dict(reference)
for name in refdict:
fref.write(">%s\n%s\n"%(name,refdict[name]))
return totalRef,requry,nonchimera
def selectRefBySampeSize(minsampleSize, tempDir, copysequence, reference):
totalRef = os.path.splitext(copysequence)[0] + ".ref"
print totalRef
fref = open(totalRef, 'w') #used as reference for chimera detection
requry = os.path.splitext(copysequence)[0] + ".requry"
fqury = open(requry, 'w') #used as requery for chimera detecthion
nonchimera = os.path.splitext(copysequence)[0] + ".nonchimera"
fnonch = open(nonchimera,
'w') #a part of sequence for output that nonchimera.
requrySeqDict = fasta2dict(copysequence)
for name in requrySeqDict:
if int(getAttriValueFromSeqName(name, "sampleSize")) >= minsampleSize:
fref.write(">%s\n%s\n" % (name, requrySeqDict[name]))
fnonch.write(">%s\n%s\n" % (name, requrySeqDict[name]))
else:
fqury.write(">%s\n%s\n" % (name, requrySeqDict[name]))
refdict = fasta2dict(reference)
for name in refdict:
fref.write(">%s\n%s\n" % (name, refdict[name]))
return totalRef, requry, nonchimera
ftable=open(outtable,'w')
fmulti=open(outmultiple,'w')
fsingle=open(outsingleton,'w')
flist=open(unique_list,'w')
lenDict,tagList=readFasta(fastaList)
ftable.write("sequenceName\tsampleSize\ttotalAbundance\taverageAbundance\t%s\n"%'\t'.join(tagList))
n=0
for lens in lenDict:
for seq in lenDict[lens]:
if len(lenDict[lens])==0:
continue
n+=1
nameList=[]
for seqname in lenDict[lens][seq]:
sample=getAttriValueFromSeqName(seqname,'SampleTag')
nameList.append(sample)
distriList=[]
for tag in tagList:
count=nameList.count(tag)
distriList.append(count)
samplesize=len(tagList)-distriList.count(0)
abundance=sum(distriList)
average=float(sum(distriList))/len(distriList)
flist.write(">unique%d;sampleSize=%d;abundance=%d;\t%s\n"%(n,samplesize,abundance,','.join(lenDict[lens][seq])))
fout.write(">unique%d;sampleSize=%d;abundance=%d;\n%s\n"%(n,samplesize,abundance,seq))
if character=="sampleSize":
char=samplesize
elif character=="abundance":
char=abundance
if char>1:
