def get_RSA_frequencies(natural_proteins, lower_RSA_boundary, upper_RSA_boundary):
natural_distribution = af.get_AA_distribution(natural_proteins)
natural_RSA = af.get_RSA_Values(natural_proteins)
natural_RSA_array = af.make_array(natural_RSA)
seq_length = len(natural_RSA)
bin_1 = []
bin_2 = []
bin_3 = []
bin_4 = []
bin_5 = []
i = 0
count = 0
for site in natural_distribution:
if (lower_RSA_boundary<=natural_RSA_array[i] and natural_RSA_array[i]<= upper_RSA_boundary):
#print natural_RSA_array[i]
#print site[0:4]
bin_1.append(site[0])
bin_2.append(site[1])
bin_3.append(site[2])
bin_4.append(site[3])
bin_5.append(site[4])
i = i + 1
count = count + 1
else:
i = i + 1
if count == 0:
frequency_data = [0.0, 0.0, 0.0, 0.0, 0.0]
else:
frequency_data = [mean(bin_1)/mean(bin_1), mean(bin_2)/mean(bin_1), mean(bin_3)/mean(bin_1), mean(bin_4)/mean(bin_1), mean(bin_5)/mean(bin_1)]
if (mean(bin_1)) == 0.0:
print "MEAN OF BIN 1 is ZERO!!!!"
print frequency_data
#frequency_data = [mean(bin_1), mean(bin_2), mean(bin_3), mean(bin_4), mean(bin_5)]
print "Number of residues in bin: " + str(count)
return frequency_data
def get_RSA_frequencies(natural_proteins, lower_RSA_boundary, upper_RSA_boundary):
natural_distribution = af.get_AA_distribution(natural_proteins)
#natural_distribution = get_AA_distribution_mod(natural_proteins)
#natural_dis_array = array(natural_distribution)
#m,n = natural_dis_array.shape
#print "num_residues, length of alignment: " + str(n),m
#print natural_distribution
natural_RSA = af.get_RSA_Values(natural_proteins)
natural_RSA_array = af.make_array(natural_RSA)
seq_length = len(natural_RSA)
frequency_data = []
bin_1 = []
bin_2 = []
bin_3 = []
bin_4 = []
bin_5 = []
bin_6 = []
bin_7 = []
bin_8 = []
bin_9 = []
bin_10 = []
bin_11 = []
bin_12 = []
bin_13 = []
bin_14 = []
bin_15 = []
bin_16 = []
bin_17 = []
bin_18 = []
bin_19 = []
bin_20 = []
i = 0
count = 0
for site in natural_distribution:
if (lower_RSA_boundary<=natural_RSA_array[i] and natural_RSA_array[i]<= upper_RSA_boundary):
#print natural_RSA_array[i]
#print site[0:4]
bin_1.append(site[0])
bin_2.append(site[1])
bin_3.append(site[2])
bin_4.append(site[3])
bin_5.append(site[4])
bin_6.append(site[5])
bin_7.append(site[6])
bin_8.append(site[7])
bin_9.append(site[8])
bin_10.append(site[9])
bin_11.append(site[10])
bin_12.append(site[11])
bin_13.append(site[12])
bin_14.append(site[13])
bin_15.append(site[14])
bin_16.append(site[15])
bin_17.append(site[16])
bin_18.append(site[17])
bin_19.append(site[18])
bin_20.append(site[19])
i = i + 1
count = count + 1
else:
i = i + 1
if count == 0: #Need to find a way to exclude the point
frequency_data = [-1] # [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
#return frequency_data
else:
frequencies = [np.mean(bin_1)/np.mean(bin_1), np.mean(bin_2)/np.mean(bin_1), np.mean(bin_3)/np.mean(bin_1), np.mean(bin_4)/np.mean(bin_1), np.mean(bin_5)/np.mean(bin_1), np.mean(bin_6)/np.mean(bin_1), np.mean(bin_7)/np.mean(bin_1), np.mean(bin_8)/np.mean(bin_1), np.mean(bin_9)/np.mean(bin_1), np.mean(bin_10)/np.mean(bin_1), np.mean(bin_11)/np.mean(bin_1), np.mean(bin_12)/np.mean(bin_1), np.mean(bin_13)/np.mean(bin_1), np.mean(bin_14)/np.mean(bin_1), np.mean(bin_15)/np.mean(bin_1), np.mean(bin_16)/np.mean(bin_1), np.mean(bin_17)/np.mean(bin_1), np.mean(bin_18)/np.mean(bin_1), np.mean(bin_19)/np.mean(bin_1), np.mean(bin_20)/np.mean(bin_1)]
for element in frequencies:
if element == 0.0:
frequency_data.append(0.0)
else:
frequency_data.append(np.log(element))
#print np.log(element)
#if (mean(bin_1)) == 0.0:
# print "MEAN OF BIN 1 is ZERO!!!!"
#print frequency_data
#frequency_data = [mean(bin_1), mean(bin_2), mean(bin_3), mean(bin_4), mean(bin_5)]
#print "Number of residues in bin: " + str(count)
return frequency_data
chain_names.append(chain_id) natural_proteins = file #Open the files with results designed_proteins_00 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(0.0) + ".dat" designed_proteins_01 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(0.1) + ".dat" designed_proteins_03 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(0.3) + ".dat" designed_proteins_06 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(0.6) + ".dat" designed_proteins_09 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(0.9) + ".dat" designed_proteins_12 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(1.2) + ".dat" designed_proteins_003 = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(0.03) + ".dat" split_natural_1 = "align_natural_sample1_data_array_" + pdb_id + "_" + chain_id + ".dat" split_natural_2 = "align_natural_sample2_data_array_" + pdb_id + "_" + chain_id + ".dat" #Calculates all of the data for comparison (ex. entropy) natural_distribution = analysis_functions.get_AA_distribution(natural_proteins) natural_entropy = analysis_functions.get_native_entropy(natural_proteins) natural_entropy_array = analysis_functions.make_array(natural_entropy) natural_RSA = analysis_functions.get_RSA_Values(natural_proteins) natural_RSA_array = analysis_functions.make_array(natural_RSA) natural_mean_RSA_values.append(mean(natural_RSA_array)) natural_mean_entropy_values.append(mean(natural_entropy_array)) designed_distribution_00 = analysis_functions.get_AA_distribution(designed_proteins_00) designed_entropy_00 = analysis_functions.get_native_entropy(designed_proteins_00) designed_entropy_array_00 = analysis_functions.make_array(designed_entropy_00) designed_RSA_00 = analysis_functions.get_RSA_Values(designed_proteins_00) designed_RSA_array_00 = analysis_functions.make_array(designed_RSA_00) designed_mean_RSA_values_00.append(mean(designed_RSA_array_00)) designed_mean_entropy_values_00.append(mean(designed_entropy_array_00))