import sys fp1=open(sys.argv[1],'r') # Experimental_mol/bio/cel fp2=open(sys.argv[2], 'r') #MASK_BLAST_RESULT FILE (UNI tab UNI, UNI, UNI) fp3=open(sys.argv[2]+"_gores1", 'w') # OUTPUT is (UNI tab GO, GO, GO) #fp1=open(r'C:\Users\ASUS\Desktop\SCFBIO2\MASK\exp_mol') #fp2=open(r'C:\Users\ASUS\Desktop\SCFBIO2\MASK\P28','r+') #fp3=open(r'C:\Users\ASUS\Desktop\SCFBIO2\MASK\final','w+') dic={} gos=[] for line in fp1: row=line.rstrip('\n').split('\t') uni=row[0].rstrip() #print(uni) dic.setdefault(row[0],[]) for go in row[1].rstrip().split(','): #print(go) dic[uni].append(go) #print(dic) list1=[] for line in fp2: list1=[] row=line.rstrip('\n').split("\t") for i in row[1].split(","): if i in dic: list1.append(dic[i]) #print(list1) list2=[] for i in list1: for j in i: list2.append(j) #set(list2) #print(list2) list3=[] k=0 for i in list2: for j in list3: if(j==i): k=1 break else: k=0 if(k==0): list3.append(i) dic_mask={} #print(list3) #fp3.write(str(list2)+"\n") #print(str(list3)) fp3.write(row[0]+ "\t" + ",".join(list3)+"\n")