Python Helper.warning方法代码示例

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
    def topGenes(self,sumDict, fileName,number=20,value=4):
        if number > len(sumDict):
            if len(sumDict)<1:
                Helper.warning("no edited genes found", self.logFile, self.textField)
                return
            Helper.warning("The number of top genes you wanted is bigger than the number of edited genes", self.logFile, self.textField)
            number=len(sumDict)
        if value > 4:
            Helper.error("sumDict only hold four values", self.logFile, self.textField)
        
        
        counts=collections.OrderedDict(sorted(sumDict.items(), key=lambda t: t[1][value],reverse=True)[:number])
        barNameTuple=()
        valueMatrix=[[]]
        for array in counts.values():
            valueMatrix[0].append(array[value])
        for gene in counts.keys():
            barNameTuple+=(gene.names[0],)

        if value==0:
            barName="3'-UTR"
        elif value==1:
            barName="5'-UTR"
        elif value==2:
            barName="Exonic"
        elif value==3:
            barName="Intronic"
        elif value==4:
            barName="Total"
        
        yLim=max(max(i) for i in valueMatrix)+1
        Helper.createBarplot(valueMatrix, fileName, barNameTuple, [barName], width=0.35, title="Highly Edited Genes",yLim=yLim,barText=False,yText="Editing Counts")

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
def parseSummaryFile(sumFile,logFile=None,textField=0):
    '''
    Parses a .summary file from an rnaEditor output directory and returns it as an ordered dict
    Note: unedited Genes will be skipped
    :param sumFile: .summary file of rnaEditor
    :param logFile:
    :param textField:
    :return: OrderedDict {GeneName1:[GeneId1,3'UTR,5'UTR,EXON,Intron,Total]}
    '''
    
    
    if type(sumFile)==str:
        try:
            sumFile=open(sumFile,"r")
        except IOError:
            Helper.warning("Could not open %s to write Variant" % sumFile ,logFile,textField)
    elif type(sumFile)==file:
        pass
    else:
        raise TypeError("Summary file hat to be path or file object", logFile, textField)
    
    dict=OrderedDict()
    totalGenes=0
    for line in sumFile:
        if line.startswith("#"): continue #skip comments
        line = line.rstrip().split()
        totalGenes+=1
        if int(line[6])<1: continue #skip unedited genes
        try:
            v=map(int,line[2:7])
        except ValueError:
            v=line[2:7]
        dict[line[0]]=[line[1]]+v
        
    return dict,totalGenes

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
def topGenes(sumDict, fileName,number=20,value=5, logFile=None,textField=0):
        if number > len(sumDict):
            if len(sumDict)<1:
                Helper.warning("no edited genes found", logFile, textField)
                return
            Helper.warning("The given gene number is bigger than the number of total edited genes", logFile, textField)
            number=len(sumDict)
        if value not in (1,2,3,4,5):
            Helper.error("sumDict hast to be between 1 an 5", logFile, textField)
        
        
        counts=OrderedDict(sorted(sumDict.items(), key=lambda t: t[1][value],reverse=True)[:number])
        barNameTuple=()
        valueMatrix=[[]]
        for array in counts.values():
            valueMatrix[0].append(array[value])
        for gene in counts.keys():
            barNameTuple+=(counts[gene][0],)

        if value==1:
            barName="3'-UTR"
        elif value  ==2:
            barName="5'-UTR"
        elif value==3:
            barName="Exonic"
        elif value==4:
            barName="Intronic"
        elif value==5:
            barName="Total"
        
        yLim=max(max(i) for i in valueMatrix)+1
        Helper.createBarplot(valueMatrix, fileName, barNameTuple, [barName], width=0.35, title="Highly Edited Genes",yLim=yLim,barText=False,yText="Editing Counts")
        
        
        file= open(fileName.replace("png","txt"),"w")
        file.write("\t".join(["Gene_Symbol","Number_of_editing_sites"])+"\n")
        htmlStr="<table class='geneTable'><tr><th>GeneName</th><th>Number of editing sites</th></tr>"
        for gene in counts:
            htmlStr+="<tr><td>%s</td><td>%s</td></tr>"%(counts[gene][0],counts[gene][value])
            geneName=counts[gene][0]
            numbers=str(counts[gene][value])
            file.write("\t".join([geneName,numbers]) +"\n")
        htmlStr+="</table>"
        return htmlStr

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
 def printClusters(self, outFile):
     
     if type(outFile) == str:
         try:
             outFile=open(outFile,"w")
             
         except IOError:
             Helper.warning("Could not open %s to write Variant" % outFile ,self.logFile,self.textField)
     if type(outFile) != file:   
         raise AttributeError("Invalid outfile type in 'printVariantDict' (need string or file, %s found)" % type(outFile))
     
     startTime=Helper.getTime()
     Helper.info("[%s] Print Clusters to %s" %  (startTime.strftime("%c"),outFile.name),self.logFile,self.textField)
     
     
     outFile.write("\t".join(["#Chr","Start","Stop","IslandID","GeneID","Gene Symbol","Cluster Length","Number of Editing_sites","Editing_rate","\n"]))
     
     for cluster in self.clusterDict.keys():
         end = max(v.position for v in self.clusterDict[cluster])
         start = min(v.position for v in self.clusterDict[cluster])
         
         length = end - start
         editingRate=float(len(self.clusterDict[cluster]))/float(length)
         geneIdSet=set()
         geneNameSet=set()
         for v in self.clusterDict[cluster]:
             try: 
                 gene = v.attributes['GI'][0][0]
                 if type(gene) == Gene:
                     geneIdSet.add(gene.geneId)
                     geneNameSet |= set(gene.names)
                     #geneList.append(v.attributes['GI'][0][0])
                 else:
                     geneIdSet.add("Intergenic")
                     geneNameSet.add("Intergenic")
             except KeyError:
                 geneIdSet.add("N/A") #when variant has no attribute GI
         
         outFile.write("\t".join([v.chromosome,str(start),str(end),"Island"+str(cluster), #Chr","Start","Stop","Cluster Name",
                                  ",".join(map(str,geneIdSet)),",".join(map(str,geneNameSet)), #"GeneID","Gene Symbol"
                                  str(length),str(len(self.clusterDict[cluster])),'%1.2f'%float(editingRate),"\n"]))

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
 def printVariantDict(self,outfile):
     '''
     print the variants from the dictionary to the outfile if defined
     '''
     if type(outfile) == str:
         try:
             outfile=open(outfile,"w")
         except IOError:
             Helper.warning("Could not open %s to write Variant" % outfile ,self.logFile,self.textField)
     if type(outfile) != file:   
         raise AttributeError("Invalid outfile type in 'printVariantDict' (need string or file, %s found)" % type(outfile))
     
     startTime=Helper.getTime()
     Helper.info("[%s] Print Variants to %s" %  (startTime.strftime("%c"),outfile.name),self.logFile,self.textField)
         
     outfile.write("\t".join(["#CHROM", "POS", "ID", "REF", "ALT", "QUAL", "FILTER", "INFO", "\n"]))
     for v in self.variantDict.values():
         attributeString=""
         for key in v.attributes.keys():
             if key=="BaseCounts":
                 attributeString+= "BaseCounts=" + ",".join(v.attributes["BaseCounts"]) + ";"
                 continue                
             elif key =="GI":
                 a=""
                 for anno in v.attributes["GI"]:
                     gene,segment = anno
                     if gene == "-":
                         a += gene+":"+"|".join(segment)  
                     else:
                         if type(gene)==str: #when variantDict was not annotated yet
                             a+=gene +":"+"|".join(segment)+","
                         else:     
                             a+=gene.names[0]+":"+"|".join(segment)+","
                         
                 attributeString+=key+"="+a[:-1]+";"
                 continue
             attributeString+= key+"="+str(v.attributes[key])+";"
         outfile.write("\t".join([v.chromosome,str(v.position),v.id,v.ref,v.alt,str(v.qual),v.filter, attributeString+"\n"]))    

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
    def printGeneList(self,genome,outfile,printSummary=True):
        '''
        print List of genes with all the variants
        Gene-Variation-File
        "Gene_ID","gene_Name","SEGMENT","#CHROM","GENE_START","GENE_STOP","VAR_POS","REF","ALT","QUAL","BaseCount(A,C,T,G)"
        
        Gene Summary File
        "Gene_ID",Gene_Name,#3'UTR,#5'UTR,#EXON,'INTRON,#TOTAL
        :param genome:  object of class Genome
        :param outfile: 
        :param printSummary: boolean wether to print summary-file
        '''

        sumDict={}
        
        if type(genome) != Genome:
            raise AttributeError("Type of genome is %s, but has to be an object of Genome" % type(genome))
        
        if type(outfile) == str:
            try:
                outfile=open(outfile,"w")
                
            except IOError:
                Helper.warning("Could not open %s to write Variant" % outfile ,self.logFile,self.textField)
        if type(outfile) != file:   
            raise AttributeError("Invalid outfile type in 'printVariantDict' (need string or file, %s found)" % type(outfile))
        
        startTime=Helper.getTime()
        Helper.info("[%s] Print Genes and Variants to %s" %  (startTime.strftime("%c"),outfile.name),self.logFile,self.textField)
        
        sumFile=open(outfile.name[:outfile.name.rfind(".")]+".summary","w")        
        
        outfile.write("\t".join(["#Gene_ID","Name","SEGMENT","#CHROM","GENE_START","GENE_STOP","VAR_ID","VAR_POS",
                                 "REF","ALT","QUAL","#A","#C","#G","#T","Reads_Total","Edited_Reads","Editing_Ratio","\n"]))
        
        for v in self.variantDict.values():
            anno = v.attributes["GI"]
            for a in anno:
                gene,segments = a
                totalReads=str(int(sum(map(int,v.attributes["BaseCounts"]))))
                if v.ref =="A" and v.alt == "G":
                    editedReads=str(v.attributes["BaseCounts"][2])
                    ratio=str(round(float(editedReads)/float(totalReads),2))
                elif (v.ref=="T" and v.alt=="C"):
                    editedReads=str(v.attributes["BaseCounts"][1])
                    ratio=str(round(float(editedReads)/float(totalReads),2))
                else:
                    editedReads="0"
                    ratio="0"
                    
                
                if gene == "-":
                    out=["-", "-",",".join(segments),v.chromosome,"-","-",v.id,str(v.position),
                                             v.ref,v.alt,str(v.qual),"\t".join(v.attributes["BaseCounts"]),totalReads,editedReads,ratio,"\n"]
                    outfile.write("\t".join(out))
                else:
                    out=[gene.geneId, gene.names[0],",".join(segments),v.chromosome,str(gene.start),str(gene.end),v.id,str(v.position),
                                             v.ref,v.alt,str(v.qual),"\t".join(v.attributes["BaseCounts"]),totalReads,editedReads,ratio,"\n"]
                    outfile.write("\t".join(out))
                
                #count variations per gene
                if gene not in sumDict:
                    sumDict[gene]= [0,0,0,0,0]
                
                for seg in segments:
                    if seg == "3'UTR":
                        sumDict[gene][0]+=1
                    elif seg == "5'UTR":
                        sumDict[gene][1]+=1
                    elif seg in ("coding-exon","noncoding-exon"):
                        sumDict[gene][2]+=1
                    elif seg == "intron":
                        sumDict[gene][3]+=1
                    sumDict[gene][4]+=1
        
        

                     
        #print number of variants per gene
        if printSummary:

            
            sumDictGeneIds=set()
            sumFile.write("\t".join(["#Gene_ID","Name","#3'UTR","#5'UTR","#EXON","INTRON","#TOTAL","\n"]))
            for gene in sumDict.keys():
                numbers=map(str,sumDict[gene])
                if gene=="-":
                    sumFile.write("\t".join(["intergenic","-"]+["-","-","-","-",numbers[4]]+["\n"]))
                else:
                    sumFile.write("\t".join([gene.geneId,gene.names[0]]+numbers+["\n"]))
                    sumDictGeneIds.add(gene.geneId)        
            #print non effected Genes
            #this was added to have the whole set og genes in the summary file
            #so that it is easier to compare results in Excel
            genesByGeneId=genome.getGenesByGeneID()
            a=set(genesByGeneId.keys())
            b=sumDictGeneIds
            nonEffectedGenes = a-b
            for geneId in nonEffectedGenes:
                gene=genesByGeneId[geneId]
#.........这里部分代码省略.........

# 需要导入模块: from Helper import Helper [as 别名]
# 或者: from Helper.Helper import warning [as 别名]
    def checkDependencies(self):
        """checks if all files are there
        if all programs are installed properly and if the output directory is writable"""
        try:
            self.logFile=open(self.params.output + ".log","w+")
        except IOError:
            Helper.error("Cannot open Log File", textField=self.textField)

        if type(self.fastqFiles) == list:
            self.fastqFiles=self.fastqFiles
        elif type(self.fastqFile) == str:
            self.fastqFiles=[self.fastqFiles]
        else:
            Helper.error("FastQ File has wrong variable type",self.logFile,self.textField)
        
        for file in self.fastqFiles:
            if not os.path.isfile(file):
                Helper.error("Could not find: %s" %file,self.logFile,self.textField)
            
        '''
        Checks the existence of the necessary packages and tools
        :param sourceDir: folder which contains all the software
        '''
        Helper.newline(1)
        Helper.info("CHECK DEPENDENCIES",self.logFile,self.textField)
        
        #check if all tools are there
        if not os.path.isfile(self.params.sourceDir+"bwa"):
            Helper.error("BWA not found in %s" % self.params.sourceDir,self.logFile,self.textField)
        if not os.path.isfile(self.params.sourceDir+"picard-tools/SortSam.jar"):
            Helper.error("SortSam.jar not found in %s" % self.params.sourceDir+"picard-tools",self.logFile,self.textField)
        if not os.path.isfile(self.params.sourceDir+"picard-tools/MarkDuplicates.jar"):
            Helper.error("MarkDuplicates.jar not found in %s" % self.params.sourceDir+"picard-tools",self.logFile,self.textField)
        if not os.path.isfile(self.params.sourceDir+"GATK/GenomeAnalysisTK.jar"):
            Helper.error("GenomeAnalysisTK.jar not found in %s" % self.params.sourceDir+"GATK/",self.logFile,self.textField)
        if not os.path.isfile(self.params.sourceDir+"blat"):
            Helper.error("blat not found in %s" % self.params.sourceDir,self.logFile,self.textField)
        if not os.path.isfile(self.params.sourceDir+"samtools"):
            Helper.error("samtools not found in %s" % self.params.sourceDir,self.logFile,self.textField)
        if not os.system("java -version")==0:
            Helper.error("Java could not be found, Please install java",self.logFile,self.textField)
        
        
        
        #check if all files are there
        if not os.path.isfile(self.params.refGenome):
            Helper.error("Could not find Reference Genome in %s: " % self.params.refGenome,self.logFile,self.textField)
        
        # Files for BWA
        if not os.path.isfile(self.params.refGenome+".amb"):
            Helper.warning("Could not find %s.amb" % self.params.refGenome,self.logFile,self.textField)
            Helper.error("run: 'bwa index %s' to create it" % self.params.refGenome,self.logFile,self.textField)
        if not os.path.isfile(self.params.refGenome+".ann"):
            Helper.warning("Could not find %s.ann" % self.params.refGenome,self.logFile,self.textField)
            Helper.error("run: 'bwa index %s' to create it" % self.params.refGenome,self.logFile,self.textField)
        if not os.path.isfile(self.params.refGenome+".bwt"):
            Helper.warning("Could not find %s.bwt" % self.params.refGenome,self.logFile,self.textField)
            Helper.error("run: 'bwa index %s' to create it" % self.params.refGenome,self.logFile,self.textField)
        if not os.path.isfile(self.params.refGenome+".pac"):
            Helper.warning("Could not find %s.pac" % self.params.refGenome,self.logFile,self.textField)
            Helper.error("run: 'bwa index %s' to create it" % self.params.refGenome,self.logFile,self.textField)
        if not os.path.isfile(self.params.refGenome+".sa"):
            Helper.warning("Could not find %s.sa" % self.params.refGenome,self.logFile,self.textField)
            Helper.error("run: 'bwa index %s' to create it" % self.params.refGenome,self.logFile,self.textField)

        
        #Files for GATK
        
        
        if self.params.refGenome.endswith("fasta"):
            if not os.path.isfile(self.params.refGenome.replace(".fasta",".dict")):
                Helper.warning("Could not find %s" % self.params.refGenome.replace(".fasta",".dict"),self.logFile,self.textField)
                Helper.error("run: 'java -jar %spicard-tools/CreateSequenceDictionary.jar R=%s  O= %s' to create it" % (self.params.sourceDir,self.params.refGenome,self.params.refGenome.replace(".fastq",".dict")),self.logFile,self.textField)
        elif self.params.refGenome.endswith("fa"):
            if not os.path.isfile(self.params.refGenome.replace(".fa",".dict")):
                Helper.warning("Could not find %s" % self.params.refGenome.replace(".fa",".dict"),self.logFile,self.textField)
                Helper.error("run: 'java -jar %spicard-tools/CreateSequenceDictionary.jar R=%s  O= %s' to create it" % (self.params.sourceDir,self.params.refGenome,self.params.refGenome.replace(".fa",".dict")),self.logFile,self.textField)
        else:
            Helper.error("RefGenome has wrong suffix. Either '.fa' or '.fasta'")
        if not os.path.isfile(self.params.refGenome+".fai"):
            Helper.warning("Could not find %s.sai" % self.params.refGenome,self.logFile,self.textField)
            Helper.error("run: 'samtools faidx %s' to create it" % self.params.refGenome,self.logFile,self.textField)
    
        #SNP databases
        if not os.path.isfile(self.params.dbsnp):
            Helper.error("Could not find dbSNP database %s: " % self.params.dbsnp,self.logFile,self.textField)
        if not os.path.isfile(self.params.hapmap) and self.params.hapmap != "None":
            Helper.error("Could not find Hapmap database %s: " % self.params.hapmap,self.logFile,self.textField)
        if not os.path.isfile(self.params.omni) and self.params.omni != "None":
            Helper.error("Could not find Omni database %s: " % self.params.omni,self.logFile,self.textField)
        if not os.path.isfile(self.params.esp) and self.params.esp != "None":
            Helper.error("Could not find 1000G database %s: " % self.params.esp,self.logFile,self.textField)
            
        #region Files
        if not os.path.isfile(self.params.aluRegions):
            Helper.error("Could not find %s: " % self.params.aluRegions,self.logFile,self.textField)
            
        if not os.path.isfile(self.params.gtfFile):
            Helper.error("Could not find %s: " % self.params.gtfFile,self.logFile,self.textField)

#.........这里部分代码省略.........