source: liacs/dbdm/dbdm_4/fasta-hmm.py@ 52

#!/usr/bin/env python
from Bio import SeqIO,Seq
from Bio import Alphabet
from Bio.Alphabet.IUPAC import ambiguous_dna,unambiguous_dna
import Bio.Data.CodonTable


handle = open("data/AE005174v2-1.fas", "rU")
for seq_record in SeqIO.parse(handle, "fasta",ambiguous_dna):
    print seq_record.id
    print repr(seq_record.seq)
    print seq_record.seq.alphabet
    print seq_record.letter_annotations

    # How to translate damm thing into plain nucleic acid codes
    # http://en.wikipedia.org/wiki/FASTA_format
    stupid = seq_record.seq.to_str().translate({'W' : 'G'})

    pdict = {}
    for n in range(1, len(stupid)):
        protein = stupid[n]
        if not pdict.has_key(protein):
            pdict[protein] = 1
        else:
            pdict[protein] += 1

    print pdict