#snag the RSA values
RSA = natural_data[0]
#get a list of char amino acid codes
AA = resdict.values()
#print "Dimensions of array {}".format(natural_data.ndim)
n,m = natural_data.shape
n_d, m_d = designed_data.shape
#print "Natural Protein Length", m
#print "Designed Protein Length", m_d
designed_protein_lengths.append(m_d)
#Open .dat files that you will write the results to.
natural_fpW = open("align_natural_data_array_" + pdb_id + "_" + chain_id + ".dat","w")
natural_fpW.write(af.dump_csv_line2(rows))
designed_fpW = open("align_data_array_" + pdb_id + "_" + chain_id + "_" + method + ".dat","w")
designed_fpW.write(af.dump_csv_line2(rows))
counter = 0
natural_aaSum = 0
designed_aaSum = 0
aaCutOff = 0 #This is cut-off. If a site has less than this percent of amino acids left after taking out the gaps do not use that site in the analysis.
for i in range(0,m): #This blocks calculates the site frequency data
natural_aaCount = []
designed_aaCount = []
#covert back to list so we can use the "count" method
try:
natural_aaList = list(natural_data[1:,i])
designed_aaList = list(designed_data[1:,i])
except IndexError:
natural_sample2_data = np.array(natural_sample2_data, dtype=object)
#snag the RSA values
RSA = natural_data[0]
#get a list of char amino acid codes
AA = resdict.values()
#print "Dimensions of array {}".format(natural_data.ndim)
n, m = natural_data.shape
n_sample1, m_sample = natural_sample1_data.shape
#Open .dat files that you will write the results to.
natural_sample1_fpW = open(
"align_natural_sample1_data_array_" + pdb_id + "_" + chain_id + ".dat",
"w")
natural_sample1_fpW.write(af.dump_csv_line2(rows))
natural_sample2_fpW = open(
"align_natural_sample2_data_array_" + pdb_id + "_" + chain_id + ".dat",
"w")
natural_sample2_fpW.write(af.dump_csv_line2(rows))
counter = 0
natural_sample1_aaSum = 0
natural_sample2_aaSum = 0
for i in range(0, m): #Calculates the site frequency data
natural_aaCount = []
designed_aaCount = []
natural_sample1_aaCount = []
natural_sample2_aaCount = []
#covert back to list so we can use the "count" method
if(debug):
print len(natural_sample2_data[i])
natural_sample2_data = np.array(natural_sample2_data, dtype = object)
#snag the RSA values
RSA = natural_data[0]
#get a list of char amino acid codes
AA = resdict.values()
#print "Dimensions of array {}".format(natural_data.ndim)
n,m = natural_data.shape
n_sample1, m_sample = natural_sample1_data.shape
#Open .dat files that you will write the results to.
natural_sample1_fpW = open("align_natural_sample1_data_array_ordered_" + pdb_id + "_" + chain_id + ".dat","w")
natural_sample1_fpW.write(af.dump_csv_line2(rows))
natural_sample2_fpW = open("align_natural_sample2_data_array_ordered_" + pdb_id + "_" + chain_id + ".dat","w")
natural_sample2_fpW.write(af.dump_csv_line2(rows))
counter = 0
natural_aaSum = 0
designed_aaSum = 0
natural_sample1_aaSum = 0
natural_sample2_aaSum = 0
for i in range(0,m):
natural_aaCount = []
designed_aaCount = []
natural_sample1_aaCount = []
natural_sample2_aaCount = []
#covert back to list so we can use the "count" method
#if(debug):
# print len(designed_data[i])
designed_data = np.array(designed_data, dtype = object)
#snag the RSA values
RSA = natural_data[0]
#get a list of char amino acid codes
AA = resdict.values()
#print "Dimensions of array {}".format(natural_data.ndim)
n,m = natural_data.shape
#Open .dat files that you will write the results to.
natural_fpW = open("align_natural_data_array_ordered_" + pdb_id + "_" + chain_id + ".dat","w")
natural_fpW.write(af.dump_csv_line2(rows))
designed_fpW = open("align_data_array_ordered_" + pdb_id + "_" + chain_id + "_" + "soft" + ".dat","w")
designed_fpW.write(af.dump_csv_line2(rows))
counter = 0
natural_aaSum = 0
designed_aaSum = 0
aaCutOff = 0 #This is cut-off. If a site has less than this percent of amino acids left after taking out the gaps do not use that site in the analysis.
for i in range(0,m): #This blocks calculates the site frequency data
natural_aaCount = []
designed_aaCount = []
#covert back to list so we can use the "count" method
try:
natural_aaList = list(natural_data[1:,i])
designed_aaList = list(designed_data[1:,i])
except IndexError:
RSA = natural_data[0]
#get a list of char amino acid codes
AA = resdict.values()
#print "Dimensions of array {}".format(natural_data.ndim)
n, m = natural_data.shape
n_d, m_d = designed_data.shape
#print "Natural Protein Length", m
#print "Designed Protein Length", m_d
designed_protein_lengths.append(m_d)
#Open .dat files that you will write the results to.
natural_fpW = open(
"align_natural_data_array_" + pdb_id + "_" + chain_id + ".dat",
"w")
natural_fpW.write(af.dump_csv_line2(rows))
designed_fpW = open(
"align_data_array_" + pdb_id + "_" + chain_id + "_" + method +
".dat", "w")
designed_fpW.write(af.dump_csv_line2(rows))
counter = 0
natural_aaSum = 0
designed_aaSum = 0
aaCutOff = 0 #This is cut-off. If a site has less than this percent of amino acids left after taking out the gaps do not use that site in the analysis.
for i in range(0, m): #This blocks calculates the site frequency data
natural_aaCount = []
designed_aaCount = []
#covert back to list so we can use the "count" method
try:
natural_aaList = list(natural_data[1:, i])
