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_mixed_entropy_values(PDB, buried_temp, surface_temp):
new_entropies = []
#Make the files
buried_file = "align_data_array_" + PDB + "_" + str(buried_temp) + ".dat"
surface_file = "align_data_array_" + PDB + "_" + str(surface_temp) + ".dat"
#Get the RSA Values
RSA = af.make_array(af.get_RSA_Values(buried_file))
buried_entropies = af.get_native_entropy(buried_file)
surface_entropies = af.get_native_entropy(surface_file)
#Get the entropy values
for i in xrange(len(RSA)):
if (float(RSA[i]) <=0.25):
new_entropies.append(buried_entropies[i])
else:
new_entropies.append(surface_entropies[i])
return RSA, new_entropies
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 = []
all_k_values = []
k_values = []
k_lists = []
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
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)]
all_k_values = [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19]
k_count = 0
for element in frequencies:
if element == 0.0:
continue
else:
frequency_data.append(np.log(element))
k_values.append(all_k_values[k_count])
k_count = k_count + 1
set_k_r(k_values, lower_RSA_boundary, upper_RSA_boundary)
return frequency_data
for PDB in PDBS:
RSA1, entropy_mix1 = get_mixed_entropy_values(PDB, 0.0, 0.1)
RSA2, entropy_mix2 = get_mixed_entropy_values(PDB, 0.03, 0.1)
[cor_entropy_RSA_mix1, pvalue1] = pearsonr(RSA1, entropy_mix1)
cor_entropy_RSA_mix1 = float(cor_entropy_RSA_mix1)
cor_values1.append(cor_entropy_RSA_mix1)
[cor_entropy_RSA_mix2, pvalue2] = pearsonr(RSA2, entropy_mix2)
cor_entropy_RSA_mix2 = float(cor_entropy_RSA_mix2)
cor_values2.append(cor_entropy_RSA_mix2)
natural_file = "align_natural_data_array_" + PDB + ".dat"
natural_RSA = af.make_array(af.get_RSA_Values(natural_file))
natural_entropy = af.get_native_entropy(natural_file)
[natural_cor_entropy_RSA, pvalue3] = pearsonr(natural_RSA, natural_entropy)
natural_cor_entropy_RSA = float(natural_cor_entropy_RSA)
natural_cor_values.append(natural_cor_entropy_RSA)
fig = plt.figure(1, dpi = 400, figsize = (16,6))
correlation_values = [cor_values1, cor_values2, natural_cor_values]
correlation_values_transpose = transpose(correlation_values)
(m,n) = correlation_values_transpose.shape
#rcParams['lines.linewidth'] = 2
ax = axes([0.066, 0.115, 0.43, 0.85])
#text(-0.37, 0.6, "A", fontweight = 'bold', ha = 'center', va = 'center', fontsize = 20)
'''
buried_all_temp_data = []
intermediate_all_temp_data = []
surface_all_temp_data = []
noah_buried_all_temp_mean_entropy_data_array = []
noah_intermediate_all_temp_mean_entropy_data_array = []
noah_surface_all_temp_mean_entropy_data_array = []
noah_buried_medians = []
noah_intermediate_medians = []
noah_surface_medians = []
for line in buried_mean_entropy_temp_data:
data = re.split("\t", line)
data.pop(0)
data_array = analysis_functions.make_array(data)
buried_all_temp_data.append(data_array)
#mean_entropy_temp_values_array = analysis_functions.make_array(data)
noah_buried_all_temp_mean_entropy_data_array = array(buried_all_temp_data)
print len(noah_buried_all_temp_mean_entropy_data_array)
noah_buried_medians = median(noah_buried_all_temp_mean_entropy_data_array, axis = 0)
print len(noah_buried_medians)
for line in intermediate_mean_entropy_temp_data:
data = re.split("\t", line)
data.pop(0)
data_array = analysis_functions.make_array(data)
intermediate_all_temp_data.append(data_array)
#mean_entropy_temp_values_array = analysis_functions.make_array(data)
noah_intermediate_all_temp_mean_entropy_data_array = array(intermediate_all_temp_data)
noah_intermediate_medians = median(noah_intermediate_all_temp_mean_entropy_data_array, axis = 0)
mean_KL_method_data = mean_KL_method_file.readlines()
mean_KL_method_file.close()
header = mean_KL_method_data.pop(0)
'''
mean_KL_method_ordered_file = open("graph_mean_KL_all_method_data_ordered.csv", "r")
mean_KL_method_ordered_data = mean_KL_method_ordered_file.readlines()
mean_KL_method_ordered_file.close()
ordered_header = mean_KL_method_ordered_data.pop(0)
'''
all_method_data = []
all_method_mean_KL_data_array = []
for line in mean_KL_method_data:
data = re.split("\t", line)
data.pop(0)
data_array = analysis_functions.make_array(data)
all_method_data.append(data_array)
mean_KL_method_values_array = analysis_functions.make_array(data)
all_method_mean_KL_data_array = array(all_method_data)
'''
all_method_ordered_data = []
all_method_ordered_mean_KL_data_array = []
for line in mean_KL_method_ordered_data:
data = re.split("\t", line)
data.pop(0)
data_array = analysis_functions.make_array(data)
all_method_ordered_data.append(data_array)
mean_KL_ordered_method_values_array = analysis_functions.make_array(data)
all_method_ordered_mean_KL_data_array = array(all_method_ordered_data)
'''
ax.get_yaxis().tick_left()
ax.set_xticks([1, 2, 3])
ax.set_xticklabels(["designed", "evolved \n from design", "natural"])
# mean KL data
mean_KL_method_file = open("graph_mean_KL_all_method_data.csv", "r")
mean_KL_method_data = mean_KL_method_file.readlines()
mean_KL_method_file.close()
header = mean_KL_method_data.pop(0)
all_method_data = []
all_method_mean_KL_data_array = []
for line in mean_KL_method_data:
data = re.split("\t", line)
data.pop(0)
data_array = af.make_array(data)
all_method_data.append(data_array)
mean_KL_method_values_array = af.make_array(data)
all_method_mean_KL_data_array = array(all_method_data)
# effective number data
all_temp_entropy_values = []
protein_file_name = "graph_mean_data_natural.csv"
[natural_mean_RSA_values, natural_mean_entropy_values, natural_cor_entropy_RSA_values, natural_mean_split_KL_values, natural_cor_entropy_icn_values, natural_cor_entropy_iwcn_values] = af.get_mean_designed_data(protein_file_name)
protein_file_name = "graph_mean_data_rosetta.csv"
[designed_mean_RSA_values_rosetta, designed_mean_entropy_values_rosetta, designed_cor_entropy_RSA_values_rosetta, designed_mean_KL_values_rosetta, designed_cor_entropy_icn_values_rosetta, designed_cor_entropy_iwcn_values_rosetta] = af.get_mean_designed_data(protein_file_name)
protein_file_name = "graph_mean_data_evolved.csv"
header = natural_protein_data.pop(0)
for line in natural_protein_data:
data = re.split("\t", line)
natural_data.append(data)
for data in natural_data:
#print data
pdb_names.append(data[0])
chain_names.append(data[1])
natural_mean_RSA_values.append(data[2])
natural_mean_entropy_values.append(data[3])
natural_cor_entropy_RSA_values.append(data[4])
natural_intercept_values.append(data[6])
natural_slope_values.append(data[7])
natural_mean_RSA_values_array = analysis_functions.make_array(natural_mean_RSA_values)
natural_mean_entropy_values_array = analysis_functions.make_array(natural_mean_entropy_values)
natural_cor_entropy_RSA_values_array = analysis_functions.make_array(natural_cor_entropy_RSA_values)
natural_intercept_values_array = analysis_functions.make_array(natural_intercept_values)
natural_slope_values_array = analysis_functions.make_array(natural_slope_values)
protein_file_name = "graph_mean_data_ordered_0.0_noah.csv"
[designed_mean_RSA_values_00, designed_mean_entropy_values_00, designed_cor_entropy_RSA_values_00, designed_mean_KL_values_00, designed_intercept_values_00, designed_slope_values_00] = analysis_functions.get_mean_ordered_designed_data(protein_file_name)
designed_mean_RSA_values_array_00 = array(designed_mean_RSA_values_00)
designed_mean_entropy_values_array_00 = array(designed_mean_entropy_values_00)
designed_cor_entropy_RSA_values_array_00 = array(designed_cor_entropy_RSA_values_00)
designed_mean_KL_values_array_00 = array(designed_mean_KL_values_00)
designed_intercept_values_array_00 = array(designed_intercept_values_00)
designed_slope_values_array_00 = array(designed_slope_values_00)
mean_KL_temp_ordered_file = open("graph_mean_KL_buried_temp_data_ordered_noah.csv", "r")
mean_KL_temp_ordered_data = mean_KL_temp_ordered_file.readlines()
mean_KL_temp_ordered_file.close()
ordered_header = mean_KL_temp_ordered_data.pop(0)
mean_entropy_temp_file = open("graph_mean_entropy_buried_temp_data_noah.csv", "r")
mean_entropy_temp_data = mean_entropy_temp_file.readlines()
mean_entropy_temp_file.close()
header = mean_entropy_temp_data.pop(0)
all_temp_data = []
all_temp_mean_KL_data_array = []
for line in mean_KL_temp_data:
data = re.split("\t", line)
data.pop(0)
data_array = af.make_array(data)
all_temp_data.append(data_array)
mean_KL_temp_values_array = af.make_array(data)
all_temp_mean_KL_data_array = array(all_temp_data)
all_temp_ordered_data = []
all_temp_ordered_mean_KL_data_array = []
for line in mean_KL_temp_ordered_data:
data = re.split("\t", line)
data.pop(0)
data_array = af.make_array(data)
all_temp_ordered_data.append(data_array)
mean_KL_ordered_temp_values_array = af.make_array(data)
all_temp_ordered_mean_KL_data_array = array(all_temp_ordered_data)
all_temp_data = []
modified_method_array = array(modified_methods)
protein_file = open("graph_mean_data_natural.csv", "r")
natural_protein_data = protein_file.readlines()
protein_file.close()
header = natural_protein_data.pop(0)
for line in natural_protein_data:
data = re.split("\t", line)
natural_data.append(data)
for data in natural_data:
pdb_names.append(data[0])
natural_cor_entropy_RSA_values.append(data[4])
natural_cor_entropy_RSA_values_array = af.make_array(natural_cor_entropy_RSA_values)
protein_file_name = "graph_mean_data_rosetta.csv"
[designed_mean_RSA_values_rosetta, designed_mean_entropy_values_rosetta, designed_cor_entropy_RSA_values_rosetta, designed_mean_KL_values_rosetta, designed_cor_entropy_iwcn_values_rosetta] = af.get_mean_designed_data(protein_file_name)
designed_cor_entropy_RSA_values_array_rosetta = array(designed_cor_entropy_RSA_values_rosetta)
protein_file_name = "graph_mean_data_evolved.csv"
[designed_mean_RSA_values_evolved, designed_mean_entropy_values_evolved, designed_cor_entropy_RSA_values_evolved, designed_mean_KL_values_evolved, designed_cor_entropy_iwcn_values_evolved] = af.get_mean_designed_data(protein_file_name)
designed_cor_entropy_RSA_values_array_evolved = array(designed_cor_entropy_RSA_values_evolved)
all_method_cor_entropy_RSA_values.append(designed_cor_entropy_RSA_values_rosetta)
all_method_cor_entropy_RSA_values.append(designed_cor_entropy_RSA_values_evolved)
all_method_cor_entropy_RSA_values.append(natural_cor_entropy_RSA_values)
natural_proteins = file #Open the files with results
designed_proteins_rosetta = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(
"rosetta") + ".dat"
designed_proteins_evolved = "align_data_array_" + pdb_id + "_" + chain_id + "_" + str(
"evolved") + ".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_KL(
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))
#Calculates cn & wcn
# cn13_data = analysis_functions.get_cn13_values(pdb_id, chain_id)
# iCN13 = cn13_data[0]
# iCN13_array = analysis_functions.make_array(cn13_data)
# mean_iCN13_values.append(mean(iCN13_array))
iwcn_data = calc_wcn.get_iwcn_values(pdb_id, chain_id)
iWCN_array = analysis_functions.make_array(iwcn_data)
mean_iWCN_values.append(mean(iWCN_array))
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
protein_file.close()
header = natural_protein_data.pop(0)
for line in natural_protein_data:
data = re.split("\t", line)
natural_data.append(data)
for data in natural_data:
pdb_names.append(data[0])
chain_names.append(data[1])
natural_mean_RSA_values.append(data[2])
natural_mean_entropy_values.append(data[3])
natural_cor_entropy_RSA_values.append(data[4])
natural_mean_split_KL_values.append(data[5])
natural_mean_RSA_values_array = analysis_functions.make_array(natural_mean_RSA_values)
natural_mean_entropy_values_array = analysis_functions.make_array(natural_mean_entropy_values)
natural_cor_entropy_RSA_values_array = analysis_functions.make_array(natural_cor_entropy_RSA_values)
natural_mean_split_KL_values_array = analysis_functions.make_array(natural_mean_split_KL_values)
protein_file_name = "graph_mean_data_0.0_noah.csv"
[designed_mean_RSA_values_00, designed_mean_entropy_values_00, designed_cor_entropy_RSA_values_00, designed_mean_KL_values_00] = analysis_functions.get_mean_designed_data(protein_file_name)
designed_mean_RSA_values_array_00 = array(designed_mean_RSA_values_00)
designed_mean_entropy_values_array_00 = array(designed_mean_entropy_values_00)
designed_cor_entropy_RSA_values_array_00 = array(designed_cor_entropy_RSA_values_00)
designed_mean_KL_values_array_00 = array(designed_mean_KL_values_00)
protein_file_name = "graph_mean_data_0.3_noah.csv"
[designed_mean_RSA_values_03, designed_mean_entropy_values_03, designed_cor_entropy_RSA_values_03, designed_mean_KL_values_03] = analysis_functions.get_mean_designed_data(protein_file_name)
mean_KL_temp_ordered_file = open("graph_mean_KL_buried_temp_data_ordered.csv", "r")
mean_KL_temp_ordered_data = mean_KL_temp_ordered_file.readlines()
mean_KL_temp_ordered_file.close()
ordered_header = mean_KL_temp_ordered_data.pop(0)
mean_entropy_temp_file = open("graph_mean_entropy_buried_temp_data.csv", "r")
mean_entropy_temp_data = mean_entropy_temp_file.readlines()
mean_entropy_temp_file.close()
header = mean_entropy_temp_data.pop(0)
all_temp_data = []
all_temp_mean_KL_data_array = []
for line in mean_KL_temp_data:
data = re.split("\t", line)
data.pop(0)
data_array = analysis_functions.make_array(data)
all_temp_data.append(data_array)
mean_KL_temp_values_array = analysis_functions.make_array(data)
all_temp_mean_KL_data_array = array(all_temp_data)
all_temp_ordered_data = []
all_temp_ordered_mean_KL_data_array = []
for line in mean_KL_temp_ordered_data:
data = re.split("\t", line)
data.pop(0)
data_array = analysis_functions.make_array(data)
all_temp_ordered_data.append(data_array)
mean_KL_ordered_temp_values_array = analysis_functions.make_array(data)
all_temp_ordered_mean_KL_data_array = array(all_temp_ordered_data)
all_temp_data = []
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))
protein_file = open("graph_mean_data_natural.csv", "r")
natural_protein_data = protein_file.readlines()
protein_file.close()
#print natural_protein_data
header = natural_protein_data.pop(0)
for line in natural_protein_data:
data = re.split("\t", line)
natural_data.append(data)
for data in natural_data:
pdb_names.append(data[0])
chain_names.append(data[1])
natural_mean_entropy_values.append(data[3])
#natural_mean_RSA_values_array = analysis_functions.make_array(natural_mean_RSA_values)
natural_mean_entropy_values_array = analysis_functions.make_array(natural_mean_entropy_values)
#natural_cor_entropy_RSA_values_array = analysis_functions.make_array(natural_cor_entropy_RSA_values)
#natural_mean_split_KL_values_array = analysis_functions.make_array(natural_mean_split_KL_values)
protein_file_name = "graph_mean_data_0.0.csv"
[designed_mean_RSA_values_00, designed_mean_entropy_values_00, designed_cor_entropy_RSA_values_00, designed_mean_KL_values_00] = analysis_functions.get_mean_designed_data(protein_file_name)
#designed_mean_RSA_values_array_00 = array(designed_mean_RSA_values_00)
designed_mean_entropy_values_array_00 = array(designed_mean_entropy_values_00)
#designed_cor_entropy_RSA_values_array_00 = array(designed_cor_entropy_RSA_values_00)
#designed_mean_KL_values_array_00 = array(designed_mean_KL_values_00)
protein_file_name = "graph_mean_data_0.03.csv"
[designed_mean_RSA_values_003, designed_mean_entropy_values_003, designed_cor_entropy_RSA_values_003, designed_mean_KL_values_003] = analysis_functions.get_mean_designed_data(protein_file_name)
#print natural_mean_entropy_values
#designed_mean_RSA_values_array_003 = array(designed_mean_RSA_values_003)
