comments and refactors

sequence_control.py

@@ -6,13 +6,12 @@ import source_encoding
 import source_decoding
 
 
-
 def check_homopolymere(sequence, max_h):
     """
-    count the number of homopolymeres in the sequence
+    count the number of homopolymeres larger than h_max in the sequence
     """
     h_nbr = 0 #number of homopolymere larger than h_max found
-    row_size = 0 #size of the current row
+    row_size = 0 #size of the current row of consecutive nucleotides
     last_nucleotide = "" #previous nucleotide in the sequence
     for nucleotide in sequence:
         if nucleotide == last_nucleotide:
@@ -30,7 +29,7 @@ def check_homopolymere(sequence, max_h):
 
 def check_GC(sequence, window_size):
     """
-    returns the min and max GC percentage in all windows of the sequence
+    returns the minimum and maximum GC percentage for all the windows of the sequence
     """
     
     def check_GC_Window(window):
@@ -44,7 +43,7 @@ def check_GC(sequence, window_size):
     
     if len(sequence) <= window_size:
         GC_percent = check_GC_Window(sequence)
-        return GC_percent,GC_percent
+        return GC_percent, GC_percent
         
     max_GC_percent = 0
     min_GC_percent = 100
@@ -77,7 +76,7 @@ def check_loop(sequence, loop_size, window_size):
 
 def sequence_check(sequence, window_size=60, verbose=False):
     """
-    test if a the conditions for a correct sequence are met
+    test if a the conditions for a correct sequence are met, return True if all 3 constraints are valid
     """
     h_nbr = check_homopolymere(sequence, 3)
     if verbose: print("number of homopolymere larger than",3,":",h_nbr)
@@ -86,7 +85,7 @@ def sequence_check(sequence, window_size=60, verbose=False):
     loop_nbr = check_loop(sequence, 6, window_size)
     if verbose: print("number of potential loop :",loop_nbr)
     
-    if h_nbr == 0 and min_GC_percent >= 45 and max_GC_percent <= 55 and loop_nbr == 0:
+    if h_nbr == 0 and min_GC_percent >= 40 and max_GC_percent <= 55 and loop_nbr == 0:
         if verbose: print("sequence is correct")
         return True
     else:
@@ -112,14 +111,15 @@ def hash_until_correct(sequence, start_key=0):
 def find_hash_keys(sequence):
     """
     find the keys to hash the sequence to pass the conditions
-    the sequence is divided in sub sequences and each one is hashed to pass the conditions
+    the sequence is divided in sub sequences and each one is hashed until it passes the conditions
     
     """
     tot_hash = ""
     hash_keys = []
-    sub_seq_size = 200
+    sub_seq_size = 250 #higher -> less keys, but more time consuming 
     sub_seq_nbr = int(math.ceil(len(sequence)/sub_seq_size))
     for i in range(sub_seq_nbr):
+        #display progress bar
         k=int(20*len(hash_keys)/sub_seq_nbr)
         sys.stdout.write('\r')
         sys.stdout.write("[%-20s] %d%%" % ('='*k, 5*k))
@@ -139,7 +139,7 @@ def find_hash_keys(sequence):
     
     print("\n"+tot_hash)
     print(hash_keys)
-    sequence_check(tot_hash, 60, True)
+    sequence_check(tot_hash, 60, True) #will be valid
     
 def decode_poeme(sequence):
     hash_keys = [2137,4123,1324,833,3]
@@ -150,7 +150,8 @@ def decode_poeme(sequence):
         decoded_sub_seq = source_decoding.remove_filter(sub_seq, hash_filter)
         decoded_seq += decoded_sub_seq
     print(decoded_seq)
-    
+   
+
 # =================== main ======================= #
 if __name__ == '__main__':