2018 Hakyung July Lab note
From Crop Genomics Lab.
HT-seq, edgeR 처리 후 한 파일에 리스트 형태로 저장
file = open ("/data2/haggui/RNA/edgeR/raw_edgeR/control.counts.edgeR","r") lines = file.readlines() list = [] for line in lines : gene_name = line.split('"')[1] #"gene name" 으로 되어 있는 것 가져오기 dic = [0,0,0,0,0] dic[0] = (gene_name) #dic = [genename,0,0,0,0] Cfile = open("/data2/haggui/RNA/edgeR/DEG_edgeR/DEG_control.txt","r") Template:색 Clines = Cfile.readlines() for Cline in Clines : Cgene_name = Cline.split('"')[1] ClogFC = float(Cline.split(' ')[1]) #logFC value if Cgene_name == gene_name : if ClogFC < -1 : dic[1] = dic[1]+1 # SS2-2 > TG 이면 1 elif ClogFC > 1 : dic[1] = dic[1]+2 # TG < SS2-2 이면 2, dic = [genename,2,0,0,0] else : pass else : pass Cfile.close() Sfile = open("/data2/haggui/RNA/edgeR/DEG_edgeR/DEG_SS2-2.txt","r") #SS2-2가 drought 때 어떻게 변하는지 Slines = Sfile.readlines() for Sline in Slines : Sgene_name = Sline.split('"')[1] SlogFC = float(Sline.split(' ')[1]) if Sgene_name == gene_name : if SlogFC > 1 : dic[2] = dic[2]+1 # up-regulation이면 1 elif SlogFC < -1 : dic[2] = dic[2]+2 # down-regulation이면 2 else : pass else : pass Sfile.close() Tfile = open("/data2/haggui/RNA/edgeR/DEG_edgeR/DEG_TG.txt","r") Tlines = Tfile.readlines() for Tline in Tlines : Tgene_name = Tline.split('"')[1] TlogFC = float(Tline.split(' ')[1]) if Tgene_name == gene_name : if TlogFC > 1 : dic[3] = dic[3]+1 elif TlogFC < -1 : dic[3] = dic[3]+2 else : pass else : pass Tfile.close() Dfile = open("/data2/haggui/RNA/edgeR/DEG_edgeR/DEG_drought.txt","r") Dlines = Dfile.readlines() for Dline in Dlines : Dgene_name = Dline.split('"')[1] DlogFC = float(Dline.split(' ')[1]) if Dgene_name == gene_name : if DlogFC < -1 : dic[4] = dic[4]+1 elif DlogFC > 1: dic[4] = dic[4]+2 else : pass else : pass Dfile.close() list.append(dic)
f = open('exp_list.txt','w') import pickle pickle.dump(list,f) f.close()