def get_mean_AA_freqs(file):
freqs = []
aa_counts = []
input = open(file, "r")
protein_data = input.readlines()
input.close()
site_data = af.get_transformed_data(protein_data)
for site in site_data:
new_site = []
for element in site:
new_site.append(float(element))
freqs.append(new_site)
freq_array = np.array(freqs)
m,n = freq_array.shape
total_aa = sum(freq_array)
m,n = freq_array.shape
j = 0
while (j < n):
aa_freq_sum = sum(freq_array[:, j])
aa_counts.append(float(aa_freq_sum)/float(total_aa))
j = j + 1
return aa_counts
def get_mean_AA_freqs(file):
freqs = []
aa_counts = []
input = open(file, "r")
protein_data = input.readlines()
input.close()
site_data = af.get_transformed_data(protein_data)
for site in site_data:
new_site = []
for element in site:
new_site.append(float(element))
freqs.append(new_site)
freq_array = np.array(freqs)
m, n = freq_array.shape
total_aa = sum(freq_array)
m, n = freq_array.shape
j = 0
while (j < n):
aa_freq_sum = sum(freq_array[:, j])
aa_counts.append(float(aa_freq_sum) / float(total_aa))
j = j + 1
return aa_counts
def get_position_count_data(file):
buried_counts = []
surface_counts = []
buried_sites = []
surface_sites= []
input = open(file, "r")
protein_data = input.readlines()
input.close()
RSA = af.get_RSA_Values(file)
alignment_length = len(RSA)
site_data = af.get_transformed_data(protein_data)
#print RSA
#print site_data
i = 0
for site in site_data:
if(float(RSA[i]) < 0.05):
buried_sites.append(site)
else:
surface_sites.append(site)
i = i + 1
buried_array = np.array(buried_sites)
surface_array = np.array(surface_sites)
#print buried_array
#print buried_array
buried_m, buried_n = buried_array.shape
buried_total_sum = sum(sum(buried_array))
#print buried_m
#print buried_n
surface_m, surface_n = surface_array.shape
surface_total_sum = sum(sum(surface_array))
#print surface_total_sum
j = 0
while (j < buried_n):
buried_site_sum = sum(buried_array[:, j])
buried_counts.append(float(buried_site_sum)/float(buried_total_sum))
j = j + 1
j = 0
while (j < surface_n):
surface_site_sum = sum(surface_array[:, j])
surface_counts.append(float(surface_site_sum)/float(surface_total_sum))
j = j + 1
return buried_counts, surface_counts
def get_position_count_data(file):
buried_counts = []
surface_counts = []
buried_sites = []
surface_sites = []
input = open(file, "r")
protein_data = input.readlines()
input.close()
RSA = af.get_RSA_Values(file)
alignment_length = len(RSA)
site_data = af.get_transformed_data(protein_data)
i = 0
for site in site_data:
if (float(RSA[i]) <= 0.05):
buried_sites.append(site)
else:
surface_sites.append(site)
i = i + 1
buried_array = np.array(buried_sites)
surface_array = np.array(surface_sites)
buried_m, buried_n = buried_array.shape
buried_total_sum = sum(sum(buried_array))
surface_m, surface_n = surface_array.shape
surface_total_sum = sum(sum(surface_array))
#print surface_total_sum
j = 0
while (j < buried_n):
buried_site_sum = sum(buried_array[:, j])
buried_counts.append(float(buried_site_sum) / float(buried_total_sum))
j = j + 1
j = 0
while (j < surface_n):
surface_site_sum = sum(surface_array[:, j])
surface_counts.append(
float(surface_site_sum) / float(surface_total_sum))
j = j + 1
return buried_counts, surface_counts
