Changeset 64 for liacs/dbdm/dbdm_4/parse_fasta.py

Timestamp:

Dec 27, 2009, 7:57:56 PM (15 years ago)

Author:

Rick van der Zwet

Message:

Sample GHMM, needs statistics and verifing still

File:

• liacs/dbdm/dbdm_4/parse_fasta.py (modified) (2 diffs)

liacs/dbdm/dbdm_4/parse_fasta.py

@@ -11 +11 @@
 from reading_frames import reading_frames
 
-# The mapping is kind of odd, as 'r' could mean either 'g' or 'a'
+# The mapping is kind of odd, as 'r' could mean either 'g' or 'a', but in our
+# case we map them  all to unknown
+
 fasta_translate = { 
-    'r' : 'ga', # purine
-    'y' : 'tc', # pyrimide
-    'k' : 'gt', # keto
-    'm' : 'ac', # amino 
-    's' : 'gc', # strong
-    'w' : 'at', # weak
-    'b' : 'gtc',
-    'd' : 'gat',
-    'h' : 'act',
-    'v' : 'gca',
+    'r' : 'n', # purine
+    'y' : 'n', # pyrimide
+    'k' : 'n', # keto
+    'm' : 'n', # amino 
+    's' : 'n', # strong
+    'w' : 'n', # weak
+    'b' : 'n',
+    'd' : 'n',
+    'h' : 'n',
+    'v' : 'n',
     }
     
@@ -83 +85 @@
 seq2 = parse_file(file2)
 
-# Wrong assumption, replace is not possible as the real value is not know yet
-# seq1 = fasta.replace(seq1)
-# seq2 = fasta.replace(seq2)
+# Simplify answers
+seq1 = fasta.replace(seq1)
+seq2 = fasta.replace(seq2)
 
 # Find overlap