Changed code style

Author: alevchuk

README

@@ -1,4 +1,4 @@
-Pairwise alignment in Python.
+Pairwise string alignment in Python.
 
 My contribution will be:
  * Code cleanup

water

@@ -8,34 +8,33 @@ import sys, string
 
 # zeros() was origianlly from NumPy. Implemented by alevchuk 2011-04-10
 def zeros(shape):
-  retval = []
-  for x in range(shape[0]):
-    retval.append([])
-    for y in range(shape[1]):
-      retval[-1].append(0)
-  return retval
+    retval = []
+    for x in range(shape[0]):
+        retval.append([])
+        for y in range(shape[1]):
+            retval[-1].append(0)
+    return retval
 
-#read the first sequence
-f1=open(sys.argv[1], 'r')
-seq1=f1.readline()
-seq1=string.strip(seq1)
+# Command-line arguments
+f1 = open(sys.argv[1], 'r')
+seq1 = f1.readline()
+seq1 = string.strip(seq1)
 
-#read the second sequence
-f2=open(sys.argv[2], 'r')
-seq2=f2.readline()
-seq2=string.strip(seq2)
+f2 = open(sys.argv[2], 'r')
+seq2 = f2.readline()
+seq2 = string.strip(seq2)
 
-m,n =  len(seq1),len(seq2)  #length of two sequences
+m, n = len(seq1), len(seq2)  # length of two sequences
 
 match_award      = 10
 mismatch_penalty = -5
 gap_penalty      = -5 # both for opening and extanding
 
-#generate DP table and traceback path pointer matrix
-score=zeros((m+1,n+1))      #the DP table
-pointer=zeros((m+1,n+1))    #to store the traceback path
+# Generate DP table and traceback path pointer matrix
+score = zeros((m+1, n+1))      # the DP table
+pointer = zeros((m+1, n+1))    # to store the traceback path
 
-P=0;
+P = 0
 
 def match_score(alpha, beta):
     if alpha == beta:
@@ -45,85 +44,87 @@ def match_score(alpha, beta):
     else:
         return mismatch_penalty
 
-max_score=P;        #initial maximum score in DP table
-
-#calculate DP table and mark pointers
-for i in range(1,m+1):
-    for j in range(1,n+1):
-        score_up=score[i-1][j] + gap_penalty
-        score_down=score[i][j-1] + gap_penalty
-        score_diagonal=score[i-1][j-1]+match_score(seq1[i-1],seq2[j-1]);
-        score[i][j]=max(0,score_up,score_down,score_diagonal);
-        if score[i][j]==0:
-            pointer[i][j]=0; #0 means end of the path
-        if score[i][j]==score_up:
-            pointer[i][j]=1; #1 means trace up
-        if score[i][j]==score_down:
-            pointer[i][j]=2; #2 means trace left
-        if score[i][j]==score_diagonal:
-            pointer[i][j]=3; #3 means trace diagonal
-        if score[i][j]>=max_score:
-            max_i=i;
-            max_j=j;
-            max_score=score[i][j];
-#END of DP table
-
-
-align1,align2='','';    #initial sequences
-
-i,j=max_i,max_j;    #indices of path starting point
+max_score = P        # initial maximum score in DP table
+
+# Calculate DP table and mark pointers
+for i in range(1, m + 1):
+    for j in range(1, n + 1):
+        score_up = score[i-1][j] + gap_penalty
+        score_down = score[i][j-1] + gap_penalty
+        score_diagonal = score[i-1][j-1] + match_score(seq1[i-1], seq2[j-1])
+        score[i][j] = max(0,score_up, score_down, score_diagonal)
+        if score[i][j] == 0:
+            pointer[i][j] = 0 # 0 means end of the path
+        if score[i][j] == score_up:
+            pointer[i][j] = 1 # 1 means trace up
+        if score[i][j] == score_down:
+            pointer[i][j] = 2 # 2 means trace left
+        if score[i][j] == score_diagonal:
+            pointer[i][j] = 3 # 3 means trace diagonal
+        if score[i][j] >= max_score:
+            max_i = i
+            max_j = j
+            max_score = score[i][j];
+
+
+align1, align2 = '', ''    # initial sequences
+
+i,j = max_i,max_j    # indices of path starting point
 
 #traceback, follow pointers
-while pointer[i][j]!=0:
-    if pointer[i][j]==3:
-        align1=align1+seq1[i-1];
-        align2=align2+seq2[j-1];
-        i=i-1;
-        j=j-1;
-    elif pointer[i][j]==2:
-        align1=align1+'-';
-        align2=align2+seq2[j-1];
-        j=j-1;
-    elif pointer[i][j]==1:
-        align1=align1+seq1[i-1];
-        align2=align2+'-';
-        i=i-1;
-#END of traceback
-
-align1=align1[::-1];    #reverse sequence 1
-align2=align2[::-1];    #reverse sequence 2
-
-i,j=0,0;
+while pointer[i][j] != 0:
+    if pointer[i][j] == 3:
+        align1 = align1 + seq1[i-1]
+        align2 = align2 + seq2[j-1]
+        i = i - 1
+        j = j - 1
+    elif pointer[i][j] == 2:
+        align1 = align1 + '-'
+        align2 = align2 + seq2[j-1]
+        j = j - 1
+    elif pointer[i][j] == 1:
+        align1 = align1 + seq1[i-1]
+        align2 = align2 + '-'
+        i = i - 1
+
+align1 = align1[::-1]    #reverse sequence 1
+align2 = align2[::-1]    #reverse sequence 2
+
+i,j = 0,0
 
 #calcuate identity, similarity, score and aligned sequeces
-def result(align1,align2):
-    symbol='';
-    found=0;
-    score=0;
-    identity,similarity=0,0;
+def result(align1, align2):
+    symbol = ''
+    found = 0
+    score = 0
+    identity, similarity = 0, 0
     for i in range(0,len(align1)):
-        if align1[i]==align2[i]:                #if two AAs are the same, then output the letter
-            symbol=symbol+align1[i];
-            identity=identity+1;
-            similarity=similarity+1;
-            score=score+match_score(align1[i],align2[i]);
-        elif align1[i]!=align2[i] and align1[i]!='-' and align2[i]!='-': #if they are not identical and none of them is gap
-            score=score+match_score(align1[i],align2[i]);
+        # if two AAs are the same, then output the letter
+        if align1[i] == align2[i]:                
+            symbol = symbol + align1[i]
+            identity = identity + 1
+            similarity = similarity + 1
+            score += match_score(align1[i], align2[i])
+
+        # if they are not identical and none of them is gap
+        elif align1[i] != align2[i] and align1[i] != '-' and align2[i] != '-': 
+            score += match_score(align1[i], align2[i])
             symbol += ' '
-            found=0;
-        elif align1[i]=='-' or align2[i]=='-':          #if one of them is a gap, output a space
-            symbol=symbol+' ';
-            score = score + gap_penalty
+            found = 0
 
-    identity=float(identity)/len(align1)*100;
-    similarity=float(similarity)/len(align2)*100;
+        #if one of them is a gap, output a space
+        elif align1[i] == '-' or align2[i] == '-':          
+            symbol += ' '
+            score += gap_penalty
+
+    identity = float(identity) / len(align1) * 100
+    similarity = float(similarity) / len(align2) * 100
 
-    print 'Identity =', "%3.3f" % identity, 'percent';
-    print 'Similarity =', "%3.3f" % similarity, 'percent';
-    print 'Score =', score;
+    print 'Identity =', "%3.3f" % identity, 'percent'
+    print 'Similarity =', "%3.3f" % similarity, 'percent'
+    print 'Score =', score
     print align1
     print symbol
     print align2
-#END of function result
 
-result(align1,align2)
+result(align1, align2)