pdbLocation = noah_structure_path + searchPDB #This is the location of the pdb file
natural_sequences = af.get_natural_sequences_noah(file) #Gets a list with the natural sequences
cut_natural_sequences = af.get_cut_natural_sequences(identity, natural_sequences)
print "Length of Cut Natural Sequences: " + str(len(cut_natural_sequences[0]))
ancestor = cut_natural_sequences[0] #Gets the "ancestral sequence"
ancestor_length = len(ancestor) #Grab the length of the ancestral sequence
print "Ancestor Length: " + str(len(natural_sequences[0]))
#list of files that contain L vs RSA data
data = []
#list of sequences with missing RSA values
bad_list = []
#Get all the RSA values using DSSP
seq_data = af.get_noah_RSA_values(pdb_id, chain_id)
RSA = seq_data[1] #Get the RSA values
RSA_dict = seq_data[2] #Get the dict mapping positions to RSA
new_RSA = af.get_cut_RSA_values(pdb_id, RSA, RSA_dict)
index = 0
#Arrays full of the designed and natural sequences
natural_data_arr = cut_natural_sequences
designed_data_arr = af.get_cut_designed_sequences(designed_file)
fpW_natural = open("results_array_natural_" + pdb_id + "_" + chain_id + ".csv","w")
fpW_designed = open("results_array_" + pdb_id + "_" + chain_id + "_" + "soft" + ".csv","w")
#write the RSA values:
fpW_natural.write(af.dump_csv_line(new_RSA))
fpW_designed.write(af.dump_csv_line(new_RSA))
gap_locations.append(counter) #This is an array that tracks which residues have gaps
counter = counter + 1
#This section takes out the ancestral gaps from all the aligned sequences and then writes the files
#to the results_PDB_ID_CHAIN_ID.csv
natural_pdb_file_title = "results_natural_" + pdb_id + "_" + chain_id + ".csv"
natural_out_sequences = open(natural_pdb_file_title,"w")
#list of files that contain L vs RSA data
data = []
#list of sequences with missing RSA values
bad_list = []
#Get all the RSA values using DSSP
seq_data = af.get_noah_RSA_values(pdb_id, chain_id) #Get the RSA info from DSSP
RSAValues = []
RSA = seq_data[1]
RSA_dict = seq_data[2]
new_RSA = af.get_cut_RSA_values(pdb_id, RSA, RSA_dict) #Gets the RSA values that correspond to the sequence residues
index = 0
natural_data_arr = cut_natural_sequences
#filepointer for the partial result
fpW_natural = open("results_array_natural_" + pdb_id + "_" + chain_id + ".csv","w")
#write the RSA values:
fpW_natural.write(af.dump_csv_line(new_RSA))
[natural_sample1, natural_sample2] = af.split_natural_sequences(natural_data_arr) #Splits the sequences into two samples