comparison tools/fasta_tools/fasta_filter_by_id.py @ 1:5cd569750e85

Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository

0:2e5f8ad1a096

#!/usr/bin/env python
"""Filter a FASTA file with IDs from a tabular file, e.g. from BLAST.

Takes five command line options, tabular filename, ID column numbers
(comma separated list using one based counting), input FASTA filename, and
two output FASTA filenames (for records with and without any BLAST hits).
If the either output filename is just a minus sign, that file is not created.
This is intended to allow output for just the matched (or just the non-matched)
records.

Note in the default NCBI BLAST+ tabular output, the query sequence ID is
in column one, and the ID of the match from the database is in column two.

        if not line.startswith("#"):
            ids.add(line.rstrip("\n").split("\t")[col])
    print "Using %i IDs from tabular file" % (len(ids))
handle.close()

#Write filtered FASTA file based on IDs from BLAST file
reader = fastaReader(open(in_file, "rU"))
if out_positive_file != "-" and out_negative_file != "-":
    print "Generating two FASTA files"
    positive_writer = fastaWriter(open(out_positive_file, "w"))
    negative_writer = fastaWriter(open(out_negative_file, "w"))

1:5cd569750e85

#!/usr/bin/env python
"""Filter a FASTA file with IDs from a tabular file, e.g. from BLAST.

Takes five command line options, tabular filename, ID column numbers
(comma separated list using one based counting), input FASTA filename, and
two output FASTA filenames (for records with and without the given IDs).

If either output filename is just a minus sign, that file is not created.
This is intended to allow output for just the matched (or just the non-matched)
records.

Note in the default NCBI BLAST+ tabular output, the query sequence ID is
in column one, and the ID of the match from the database is in column two.

        if not line.startswith("#"):
            ids.add(line.rstrip("\n").split("\t")[col])
    print "Using %i IDs from tabular file" % (len(ids))
handle.close()

#Write filtered FASTA file based on IDs from tabular file
reader = fastaReader(open(in_file, "rU"))
if out_positive_file != "-" and out_negative_file != "-":
    print "Generating two FASTA files"
    positive_writer = fastaWriter(open(out_positive_file, "w"))
    negative_writer = fastaWriter(open(out_negative_file, "w"))