BASE="/home/bmajoros/1000G/assembly/combined" FILES=glob.glob(BASE+"/*/*.ice9") for file in FILES: print(file) parser=EssexParser(file) while(True): root=parser.nextElem() if(not root): break alts=root.pathQuery("report/status/alternate-structures") if(not alts): continue transcripts=alts.findChildren("transcript") scores={} numCryptic=0 for transcript in transcripts: change=transcript.getAttribute("structure-change") score=transcript.getAttribute("score") if(change not in scores): scores[change]=0.0 scores[change]+=float(score) numCryptic+=1 if(len(scores)!=2): continue skippingScore=scores["exon-skipping"] crypticScore=scores["cryptic-site"] print(root.getAttribute("substrate"), root.getAttribute("transcript-ID"), skippingScore,crypticScore,numCryptic,flush=True) parser.close()