BioPython: Extract Sequence IDs from Blast Output File

Question

I have a BLAST output file in XML format. These are 22 query sequences with 50 feedbacks from each sequence. And I want to extract all the 50x22 strokes. This is the code I have, but it only extracts 50 hits from the first request.

from Bio.Blast import NCBIXM
blast_records = NCBIXML.parse(result_handle)
blast_record = blast_records.next()

save_file = open("/Users/jonbra/Desktop/my_fasta_seq.fasta", 'w')

for alignment in blast_record.alignments:
    for hsp in alignment.hsps:
            save_file.write('>%s\n' % (alignment.title,))
save_file.close()

Anyone have suggestions for extracting all the hits? I think I need to use something other than alignments. Hope this was clear. Thank you

John

Answer 1

This should get all the entries. New compared to the original -

for blast_record in blast_records

python " " , blast_records ( CBIXML , parse() )

from Bio.Blast import NCBIXM
blast_records = NCBIXML.parse(result_handle)

save_file = open("/Users/jonbra/Desktop/my_fasta_seq.fasta", 'w')

for blast_record in blast_records:
  for alignment in blast_record.alignments:
      for hsp in alignment.hsps:
            save_file.write('>%s\n' % (alignment.title,))
  #here possibly to output something to file, between each blast_record
save_file.close()

Answer 2

from Bio.Blast import NCBIXML
for record in NCBIXML.parse(open("rpoD.xml")) :
    print "QUERY: %s" % record.query
    for align in record.alignments :
        print " MATCH: %s..." % align.title[:60]
        for hsp in align.hsps :
            print " HSP, e=%f, from position %i to %i" \
                % (hsp.expect, hsp.query_start, hsp.query_end)
            if hsp.align_length < 60 :
                 print "  Query: %s" % hsp.query
                 print "  Match: %s" % hsp.match
                 print "  Sbjct: %s" % hsp.sbjct
            else :
                 print "  Query: %s..." % hsp.query[:57]
                 print "  Match: %s..." % hsp.match[:57]
                 print "  Sbjct: %s..." % hsp.sbjct[:57]


print "Done"

from Bio.Blast import NCBIXML
for record in NCBIXML.parse(open("NC_003197.xml")) :
    #We want to ignore any queries with no search results:
    if record.alignments :
        print "QUERY: %s..." % record.query[:60]
        for align in record.alignments :
            for hsp in align.hsps :
                print " %s HSP, e=%f, from position %i to %i" \
                % (align.hit_id, hsp.expect, hsp.query_start, hsp.query_end)
print "Done"

http://www2.warwick.ac.uk/fac/sci/moac/currentstudents/peter_cock/python/rpsblast/