for items in split_contents: fst+=letters[items["res_name"]] return fst #pdbfilename="/data/farhan/SoftwareTools/HomopolymerProject/data/pdb/5wvc.pdb" pdbfile_A=sys.argv[1] pdbfile_B=sys.argv[2] #chain_1=sys.argv[2] #chain_2=sys.argv[3] dist=sys.argv[3] outfile=sys.argv[4] #fasta=sys.argv[6] split_contents_A=contents2Info(readPDB(pdbfile_A)) split_contents_B=contents2Info(readPDB(pdbfile_B)) chain_1=getChain(pdbfile_A) chain_2=getChain(pdbfile_B) cb_list_A=getCB(split_contents_A) cb_list_B=getCB(split_contents_B) fasta_A=pdb2FastaFromSplitContents(cb_list_A) L_A=len(fasta_A) fasta_B=pdb2FastaFromSplitContents(cb_list_B) L_B=len(fasta_B) print (fasta_A) if (fasta_A != fasta_B): print ("Fasta sequences of both files are not same...chosing the one with highest length") if (L_A > L_B):
#pdbfilename="/data/farhan/SoftwareTools/HomopolymerProject/data/pdb/5wvc.pdb" pdbfilename = sys.argv[1] #chain_1=sys.argv[2] #chain_2=sys.argv[3] #dist=sys.argv[4] fasta_file = sys.argv[2] dist = int(sys.argv[3]) outfile = sys.argv[4] #pdbfilename="/data/farhan/SoftwareTools/HomopolymerProject/data/Actin/monomer/1j6z.pdb" #chain_1="A" #chain_2="A" #dist=8 #outfile="Actin_out/Actin_monomer" chain_dict = readPDB(pdbfilename) split_contents_A = contents2Info(readPDB(pdbfilename)) split_contents_B = contents2Info(readPDB(pdbfilename)) chain_1 = getChain(pdbfilename) chain_2 = getChain(pdbfilename) cb_list = getCB(split_contents_A) #Read fasta from fasta_dictionary.txt fasta = pdb2FastaFromSplitContents(cb_list) #fasta_dict_file="fasta_dictionary.txt" #fasta_dict=readFastaDict(fasta_dict_file) #fasta=getFastaFromDictionary(pdbfilename,fasta_dict) f_fasta = "" with open(fasta_file, "r") as f: for line in f: if line.startswith(">"): continue
def getMaxResNum(pdb_file): split_contents=contents2Info(readPDB(pdb_file)) res_num_first=split_contents[0]["res_num"] res_num_last=split_contents[len(split_contents)-1]["res_num"] print (res_num_first,res_num_last) return (res_num_first,res_num_last)