lnnum = subprocess.check_output("wc -l < atom_list.lst", shell=True)
lnnum = lnnum.rstrip()
lnnum = str(lnnum)
lnnum = int(lnnum.strip("b").strip("'")) - 1
if (lnnum == 0): continue
updated_pdb_list.append(pdb + "\n") #the proper .atom files selected
atom_file_list = []
with open("atom_list.lst", "r") as f:
for line in f:
atom_file = line.strip()
atom_file_name = getName(atom_file)
chain = atom_file_name.replace(pdb_name, "")
contents = readAtom(atom_file)
split_contents = contents2Info(contents)
split_contents = addColumn(split_contents, "chain",
getChain(line.strip()))
#writedf2File("/data/farhan/SoftwareTools/HomopolymerProject/working_scripts/pdb_folder_test/work_dir/atom/6BZEA.txt",df2)
write2File(outfolder + "pdb/" + atom_file_name + ".pdb",
reassembleLines(split_contents))
atom_file_list.append(outfolder + "pdb/" + atom_file_name + ".pdb")
#writedf2File(outfolder+pdb_name+"_chain_"+chain+".pdb",df2)
#print(chain)
if (len(atom_file_list) == 0):
print("#############Zero!!!!!")
print(atom_file_list)
continue #print ("#############Zero!!!!!")
super_list = []
for atm_file in atom_file_list:
with open(atm_file, "r") as f:
for line in f:
if not line.endswith("\n"): line += "\n"
#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
f_fasta += line.strip()
print("PDB Fasta Length=", len(fasta), "\n", fasta,
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):
fasta=fasta_A
else: