decode test

sequence_control.py

@@ -2,10 +2,14 @@ import sys
 import dna_file_reader as dfr
 import hashing
 import source_encoding
-from numpy import source
+import source_decoding
+
 
 
 def check_homopolymere(sequence, max_h):
+    """
+    count the number of homopolymeres in the sequence
+    """
     h_nbr = 0 #number of homopolymere larger than h_max found
     row_size = 0 #size of the current row
     last_nucleotide = "" #previous nucleotide in the sequence
@@ -54,6 +58,9 @@ def check_GC(sequence, window_size):
 
 
 def check_loop(sequence, loop_size, window_size):
+    """
+    count the number of potential loops (reverse complement of a sub sequence in a local window)
+    """
     loop_nbr = 0
     if len(sequence) < 2*loop_size: #sequence too short for any loop
         return 0
@@ -67,7 +74,10 @@ def check_loop(sequence, loop_size, window_size):
     return loop_nbr
 
 
-def sequence_check(sequence, window_size, verbose=False):
+def sequence_check(sequence, window_size=60, verbose=False):
+    """
+    test if a the conditions for a correct sequence are met
+    """
     h_nbr = check_homopolymere(sequence, 3)
     if verbose: print("number of homopolymere larger than",3,":",h_nbr)
     min_GC_percent, max_GC_percent = check_GC(sequence, window_size)
@@ -75,7 +85,7 @@ def sequence_check(sequence, window_size, 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 > 40 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:
@@ -84,11 +94,13 @@ def sequence_check(sequence, window_size, verbose=False):
     
     
 def hash_until_correct(sequence, start_key=0):
-    
+    """
+    use a hash on the sequence until it meets the conditions, return the hash key
+    """
     hash_key = start_key
     hash_filter = hashing.hash_string_to_formated_number(str(hash_key), len(sequence), 4)
     hashed_sequence = source_encoding.apply_filter(sequence, hash_filter)
-    while not sequence_check(hashed_sequence, 60):
+    while not sequence_check(hashed_sequence):
         hash_key += 1
         hash_filter = hashing.hash_string_to_formated_number(str(hash_key), len(sequence), 4)
         hashed_sequence = source_encoding.apply_filter(sequence, hash_filter)
@@ -108,6 +120,16 @@ def find_hash_keys(sequence):
     print(tot_hash)
     sequence_check(tot_hash, 60, True)
     
+def decode_poeme(sequence):
+    hash_keys = [2137,4123,1324,833,3]
+    decoded_seq = ""
+    for i in range(5):
+        sub_seq = sequence[200*i:200*(i+1)]
+        hash_filter = hashing.hash_string_to_formated_number(str(hash_keys[i]), 200, 4)
+        decoded_sub_seq = source_decoding.remove_filter(sub_seq, hash_filter)
+        decoded_seq += decoded_sub_seq
+    print(decoded_seq)
+    
 # =================== main ======================= #
 if __name__ == '__main__':
      
@@ -119,4 +141,5 @@ if __name__ == '__main__':
 
     _, sequence = dfr.read_single_sequence_fasta(sequence_path)
     
-    
+    print(sequence_check(sequence, verbose=True))
+