comparison tools/fastq/fastq_filter_by_id.py @ 2:d570cc324779

Migrated tool version 0.0.4 from old tool shed archive to new tool shed repository

1:b79caa511ba2

#!/usr/bin/env python
"""Filter a FASTQ 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).

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.
Here sensible values for the column numbers would therefore be "1" or "2".

This script is copyright 2010 by Peter Cock, SCRI, UK. All rights reserved.
See accompanying text file for licence details (MIT/BSD style).

This is version 0.0.2 of the script.
"""
import sys
from galaxy_utils.sequence.fastq import fastqReader, fastqWriter

def stop_err( msg ):

    negative_writer = fastqWriter(open(out_negative_file, "w"))
    for record in reader:
        #The [1:] is because the fastaReader leaves the @ on the identifer.
        if not record.identifier or record.identifier.split()[0][1:] not in ids:
            negative_writer.write(record)
    positive_writer.close()
    negative_writer.close()
else:
    stop_err("Neither output file requested")
reader.close()

2:d570cc324779

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

NOTE - This script is now OBSOLETE, having been replaced by a new verion
which handles FASTA, FASTQ and SFF all in one.

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).

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.
Here sensible values for the column numbers would therefore be "1" or "2".

This script is copyright 2010-2011 by Peter Cock, SCRI, UK. All rights reserved.
See accompanying text file for licence details (MIT/BSD style).

This is version 0.0.4 of the script.
"""
import sys
from galaxy_utils.sequence.fastq import fastqReader, fastqWriter

def stop_err( msg ):

    negative_writer = fastqWriter(open(out_negative_file, "w"))
    for record in reader:
        #The [1:] is because the fastaReader leaves the @ on the identifer.
        if not record.identifier or record.identifier.split()[0][1:] not in ids:
            negative_writer.write(record)
    negative_writer.close()
else:
    stop_err("Neither output file requested")
reader.close()