[Biopython] problem to find a accesion number in tab delimited file

[Fernando]

Hello everybody,

I'm trying to perform a GOs annotation using the SIMAP database which is
Blast2GO annotated. Everything is fine, but I have problems when I try
to find the accession number in the file where entry numbers are
associated with their GOs. The problem is that the script does not find
the number in the input file when really there is. I tried several things
without good results (re.match, insert in a list and then extract the element, etc)
File where the GOs are associated with entry numbers has this structure (accession number, GO term, blats2go score):
1f0ba1d119f52ff28e907d2b5ea450db	GO:0007154	79
1f0ba1d119f52ff28e907d2b5ea450db	GO:0005605	99

The python code:
#!/usr/bin/env python
import re
from Bio.Blast import NCBIXML
from Bio import SeqIO

input_file = open('/home/fpiston/Desktop/test_go/test2.fasta', 'rU')
result_handle = open('/home/fpiston/Desktop/test_go/test2.xml', 'rU')
save_file = open('/home/fpiston/Desktop/test_go/test2.out', 'w')

fh = open('/home/fpiston/Desktop/test_go/Os_Bd_Ta_blat2go_fake', 'rU')
q_dict =  SeqIO.to_dict(SeqIO.parse(input_file, "fasta"))
blast_records = NCBIXML.parse(result_handle)

hits = []

for blast_record in blast_records:
    if blast_record.alignments:
        list = (blast_record.query).split()
        if re.match('ENA|\w*|\w*', list[0]) != None:
            list2 = list[0].split("|")
            save_file.write('%s\t' % list2[1])
        else:
            save_file.write('%s\t' % list[0])
        for alignment in blast_record.alignments:
            for hsp in alignment.hsps:
                h = alignment.hit_def    #at this point all right
                for l in fh:             #here, 'l' in not found in 'fh'
                    ls = l.split()
                    if h in ls:
                        print h
                        print 'ok'
                        save_file.write('%s\t' % ls[1])
                save_file.write('\n')
        hits.append(blast_record.query.split()[0])
misses =set(q_dict.keys()) - set(hits)
  
for i in misses:
    list = i.split("|")
    if len(list) > 1:
        save_file.write('%s\t' % list[1])
    else:
        save_file.write('%s\t' % list)
    save_file.write('%s\n' % 'no_match')

save_file.close() 



 Fernando
 --