def find_distance(sequence_dictionary):
## Takes dictionary generated by readfasta and calculates distance matrix###
popped_list = []
p_distance = 0
evol_distance = 0
distance_matrix = {}
copied_dict = sequence_dictionary.copy(
) ###Making a copy of sequence_dictionary##
for key in copied_dict:
if key not in popped_list:
seq1 = copied_dict[key]
popped_list.append(key)
for i in sequence_dictionary:
seq2 = sequence_dictionary[i]
s = alignment_util.readScoringMatrix(
"/home/kumara3/CSE620K/proj6/Blosum62.txt")
output_key_i = alignment.SmithWatermanAffine(
seq1, seq2, s, 7, 1
) ###SmithWatermanAffine for calculating the alignment between pair of sequences###
output = [it
for it in output_key_i] ## alignment stored in a list##
count_m = 0 ## count for number of matches in sequences##
count_mis = 0 ## count for number of mismatches in sequence##
X = [x for x in output[1:2]] ## sequence 1 from alignment
Y = [y for y in output[2:3]] ## sequence 2 from alignment
X_string = ''.join(X)
Y_string = ''.join(Y)
size = max(len(X_string), len(Y_string))
for k in range(0, size):
if X_string[k] == Y_string[k]:
count_m += 1
elif X_string[k] != Y_string[k]:
count_mis += 1
else:
if X_string[k] == '-' or Y_string[k] == '-':
print "IGNORE"
p_distance = count_mis / float(
count_m + count_mis) ## calculating the p distance
evol_distance = -0.75 * log(
float(1 - 4 * p_distance /
3)) ## calculating distance for evolutionary matrix
distance_matrix.setdefault(key, {}).setdefault(
i, evol_distance) ## creating and filing the distance matrix
if key == i:
distance_matrix[key][i] = 0
return distance_matrix
def find_distance(sequence_dictionary):
## Takes dictionary generated by readfasta and calculates distance matrix###
popped_list = []
p_distance = 0
evol_distance = 0
distance_matrix= {}
copied_dict = sequence_dictionary.copy() ###Making a copy of sequence_dictionary##
for key in copied_dict:
if key not in popped_list:
seq1 = copied_dict[key]
popped_list.append(key)
for i in sequence_dictionary:
seq2 = sequence_dictionary[i]
s = alignment_util.readScoringMatrix("/home/kumara3/CSE620K/proj6/Blosum62.txt")
output_key_i = alignment.SmithWatermanAffine(seq1,seq2,s,7,1) ###SmithWatermanAffine for calculating the alignment between pair of sequences###
output = [it for it in output_key_i] ## alignment stored in a list##
count_m = 0 ## count for number of matches in sequences##
count_mis= 0 ## count for number of mismatches in sequence##
X = [x for x in output[1:2]] ## sequence 1 from alignment
Y = [y for y in output[2:3]] ## sequence 2 from alignment
X_string = ''.join(X)
Y_string = ''.join(Y)
size = max(len(X_string), len(Y_string))
for k in range(0,size):
if X_string[k] == Y_string[k]:
count_m += 1
elif X_string[k] != Y_string[k]:
count_mis += 1
else:
if X_string[k] == '-' or Y_string[k] == '-':
print "IGNORE"
p_distance = count_mis/float(count_m+count_mis) ## calculating the p distance
evol_distance = -0.75*log(float(1-4*p_distance/3)) ## calculating distance for evolutionary matrix
distance_matrix.setdefault(key,{}).setdefault(i,evol_distance) ## creating and filing the distance matrix
if key == i:
distance_matrix[key][i] = 0
return distance_matrix
import argparse
import alignment
import alignment_sol
import alignment_util
import random
import sys
labels = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
D1 = alignment_util.readScoringMatrix("DNA1.txt")
D2 = alignment_util.readScoringMatrix("DNA2.txt")
D3 = alignment_util.genScoringMatrix(10, -5)
D4 = alignment_util.genScoringMatrix(5,0)
B = alignment_util.readScoringMatrix("Blosum62.txt")
#############################
def test_SW(seq1, seq2, S, g):
s, a1, a2 = alignment.SmithWaterman(seq1, seq2, S, g)
s_sol, a1_sol, a2_sol = alignment_sol.SmithWaterman(seq1, seq2, S, g)
score = 0
# First: test that the function has returned has an optimal alignment
if alignment_util.scoreAlignment(a1, a2, S, g) == s_sol:
score += 70
# Second: test that the function has returned an optimal score
if s == s_sol:
score += 20
# Third: Test that the function has returned the correct score for the alignment
def setUp(self):
self.S1 = alignment_util.readScoringMatrix("DNA1.txt")
self.S2 = alignment_util.readScoringMatrix("DNA2.txt")
self.S3 = alignment_util.genScoringMatrix(10,-10)
self.S4 = alignment_util.readScoringMatrix("Blosum62.txt")
def setUp(self):
self.S1 = alignment_util.readScoringMatrix("DNA1.txt")
self.S2 = alignment_util.readScoringMatrix("DNA2.txt")
self.S3 = alignment_util.genScoringMatrix(10, -10)
self.S4 = alignment_util.readScoringMatrix("Blosum62.txt")
import argparse
import alignment
import alignment_sol
import alignment_util
import random
import sys
labels = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
D1 = alignment_util.readScoringMatrix("DNA1.txt")
D2 = alignment_util.readScoringMatrix("DNA2.txt")
D3 = alignment_util.genScoringMatrix(10, -5)
D4 = alignment_util.genScoringMatrix(5, 0)
B = alignment_util.readScoringMatrix("Blosum62.txt")
#############################
def test_SW(seq1, seq2, S, g):
s, a1, a2 = alignment.SmithWaterman(seq1, seq2, S, g)
s_sol, a1_sol, a2_sol = alignment_sol.SmithWaterman(seq1, seq2, S, g)
score = 0
# First: test that the function has returned has an optimal alignment
if alignment_util.scoreAlignment(a1, a2, S, g) == s_sol:
score += 70
# Second: test that the function has returned an optimal score
if s == s_sol:
score += 20
# Third: Test that the function has returned the correct score for the alignment
