comparison tools/fastq/fastq_filter_by_id.xml @ 3:e0041942a12d draft default tip

v0.0.5 - galaxy_sequence_utils dependency and other cleanups inc using MIT license

2:d570cc324779

<tool id="fastq_filter_by_id" name="Filter FASTQ by ID" version="0.0.4" hidden="true">
	<description>from a tabular file</description>
	<command interpreter="python">
fastq_filter_by_id.py $input_tabular $columns $input_fastq
#if $output_choice_cond.output_choice=="both"
 $output_pos $output_neg
#elif $output_choice_cond.output_choice=="pos"
 $output_pos -
#elif $output_choice_cond.output_choice=="neg"
 - $output_neg
#end if
	</command>
	<inputs>
		<param name="input_fastq" type="data" format="fastq" label="FASTQ file to filter on the identifiers"/>
		<param name="input_tabular" type="data" format="tabular" label="Tabular file containing FASTQ identifiers"/>
		<param name="columns" type="data_column" data_ref="input_tabular" multiple="True" numerical="False" label="Column(s) containing FASTA identifiers" help="Multi-select list - hold the appropriate key while clicking to select multiple columns">
			<validator type="no_options" message="Pick at least one column"/>
		</param>
		<conditional name="output_choice_cond">
			<param name="output_choice" type="select" label="Output positive matches, negative matches, or both?">
				<option value="both">Both positive matches (ID on list) and negative matches (ID not on list), as two FASTA files</option>
				<option value="pos">Just positive matches (ID on list), as a single FASTA file</option>
				<option value="neg">Just negative matches (ID not on list), as a single FASTA file</option>
			</param>
			<!-- Seems need these dummy entries here, compare this to indels/indel_sam2interval.xml -->
			<when value="both" />
			<when value="pos" />
			<when value="neg" />
		</conditional>
	</inputs>
	<outputs>
		<data name="output_pos" format="fastq" label="With matched ID">
            <!-- TODO - Replace this with format="input:input_fastq" if/when that works -->
            <change_format>
                <when input_dataset="input_fastq" attribute="extension" value="fastqsanger" format="fastqsanger" />
                <when input_dataset="input_fastq" attribute="extension" value="fastqsolexa" format="fastqsolexa" />
                <when input_dataset="input_fastq" attribute="extension" value="fastqillumina" format="fastqillumina" />
                <when input_dataset="input_fastq" attribute="extension" value="fastqcssanger" format="fastqcssanger" />
            </change_format>
			<filter>output_choice_cond["output_choice"] != "neg"</filter>
		</data>
		<data name="output_neg" format="fastq" label="Without matched ID">
            <!-- TODO - Replace this with format="input:input_fastq" if/when that works -->
            <change_format>
                <when input_dataset="input_fastq" attribute="extension" value="fastqsanger" format="fastqsanger" />
                <when input_dataset="input_fastq" attribute="extension" value="fastqsolexa" format="fastqsolexa" />
                <when input_dataset="input_fastq" attribute="extension" value="fastqillumina" format="fastqillumina" />
                <when input_dataset="input_fastq" attribute="extension" value="fastqcssanger" format="fastqcssanger" />
            </change_format>
			<filter>output_choice_cond["output_choice"] != "pos"</filter>
		</data>
	</outputs>
	<tests>
	</tests>
	<help>

**Deprecated**

This tool is now obsolete, and should not be used in future. It has been
replaced by a more general version covering FASTA, FASTQ and SFF in one
single tool.

**What it does**

By default it divides a FASTQ file in two, those sequences with or without an
ID present in the tabular file column(s) specified. You can opt to have a
single output file of just the matching records, or just the non-matching ones.

Note that the order of sequences in the original FASTA file is preserved.
Also, if any sequences share an identifier, duplicates are not removed.

**Example Usage**

You may have performed some kind of contamination search, for example running
BLASTN against a database of cloning vectors or bacteria, giving you a tabular
file containing read identifiers. You could use this tool to extract only the
reads without BLAST matches (i.e. those which do not match your contaminant
database).

	</help>
</tool>