Ignore:
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:
1 edited

Legend:

Unmodified
Added
Removed
  • liacs/dbdm/dbdm_4/parse_fasta.py

    r63 r64  
    1111from reading_frames import reading_frames
    1212
    13 # The mapping is kind of odd, as 'r' could mean either 'g' or 'a'
     13# The mapping is kind of odd, as 'r' could mean either 'g' or 'a', but in our
     14# case we map them  all to unknown
     15
    1416fasta_translate = {
    15     'r' : 'ga', # purine
    16     'y' : 'tc', # pyrimide
    17     'k' : 'gt', # keto
    18     'm' : 'ac', # amino
    19     's' : 'gc', # strong
    20     'w' : 'at', # weak
    21     'b' : 'gtc',
    22     'd' : 'gat',
    23     'h' : 'act',
    24     'v' : 'gca',
     17    'r' : 'n', # purine
     18    'y' : 'n', # pyrimide
     19    'k' : 'n', # keto
     20    'm' : 'n', # amino
     21    's' : 'n', # strong
     22    'w' : 'n', # weak
     23    'b' : 'n',
     24    'd' : 'n',
     25    'h' : 'n',
     26    'v' : 'n',
    2527    }
    2628   
     
    8385seq2 = parse_file(file2)
    8486
    85 # Wrong assumption, replace is not possible as the real value is not know yet
    86 # seq1 = fasta.replace(seq1)
    87 # seq2 = fasta.replace(seq2)
     87# Simplify answers
     88seq1 = fasta.replace(seq1)
     89seq2 = fasta.replace(seq2)
    8890
    8991# Find overlap
Note: See TracChangeset for help on using the changeset viewer.