Example #1
0
def annotatePos(insList, refGenome, outfileName, annotDir, printout):
    """loop through available annotations in annotDir/refgenome"""
    namefile = open(annotDir + "/" + refGenome + "/names.txt", 'r')
    outfile = open(outfileName, 'w')

    # set up each annotator (name, tabix file) present
    annDict = {}
    for nameline in namefile:
        (tname, tfile) = nameline.rstrip().split("\t")
        tfile = annotDir + "/" + refGenome + "/" + tfile
        annotator = annotate.annotator(tfile, tname, refGenome)
        annDict[tname] = annotator
    namefile.close()

    for ins in insList:
        outstring = str(ins)
        for annName, ann in annDict.iteritems():
            bedline = "\t".join((ins.chr, ins.start, ins.end))
            if ins.start > ins.end:
                bedline = "\t".join((ins.chr, ins.end, ins.start))
            annList = ann.annotate(bedline, refGenome)
            annJoin = ",".join(annList)
            ins.annot.append(annJoin)
        if printout and ins.pseudo == 'False':  # exclude overlaps with known pseudogenes
            print ins
        if ins.pseudo == 'False':
            outfile.write(str(ins) + "\n")
    outfile.close()
Example #2
0
def annotatePos(insList,refGenome,annotDir,outfileName,printout):
    namefile = open(annotDir + "/" + refGenome + "/names.txt", 'r')
    outfile  = open(outfileName, 'w')
 
    # set up each annotator (name, tabix file) present
    annDict = {}
    for nameline in namefile:
        (tname,tfile) = nameline.rstrip().split("\t")
        tfile = annotDir + "/" + refGenome + "/" + tfile
        annotator = annotate.annotator(tfile, tname, refGenome)
        annDict[tname] = annotator
    namefile.close()

    for ins in insList:
        outstring = str(ins)
        for annName,ann in annDict.iteritems():
            bedline = "\t".join((ins.chr,ins.start,ins.end))
            if ins.start > ins.end:
                bedline = "\t".join((ins.chr,ins.end,ins.start))
            annList = ann.annotate(bedline,refGenome)
            annJoin = ",".join(annList)
            ins.annot.append(annJoin)
        if printout:
            print ins
        outfile.write(str(ins) + "\n")
    outfile.close()
def annotatePos(insList,refGenome,outfileName,annotDir,printout):
    """loop through available annotations in annotDir/refgenome"""
    namefile = open(annotDir + "/" + refGenome + "/names.txt", 'r')
    outfile  = open(outfileName, 'w')
 
    # set up each annotator (name, tabix file) present
    annDict = {}
    for nameline in namefile:
        (tname,tfile) = nameline.rstrip().split("\t")
        tfile = annotDir + "/" + refGenome + "/" + tfile
        annotator = annotate.annotator(tfile, tname, refGenome)
        annDict[tname] = annotator
    namefile.close()

    for ins in insList:
        outstring = str(ins)
        for annName,ann in annDict.iteritems():
            bedline = "\t".join((ins.chr,ins.start,ins.end))
            if ins.start > ins.end:
                bedline = "\t".join((ins.chr,ins.end,ins.start))
            annList = ann.annotate(bedline,refGenome)
            annJoin = ",".join(annList)
            ins.annot.append(annJoin)
        if printout and ins.pseudo == 'False': # exclude overlaps with known pseudogenes
            print ins
	if ins.pseudo == 'False':
            outfile.write(str(ins) + "\n")
    outfile.close()