view ngs-tools_split_by_barcode.xml @ 3:5cb5f350b053 draft

Uploaded

<tool id="ngs-tools_split_by_barcode" name="Barcode Splitter (ngs-tools)" force_history_refresh="True">
	<description></description>
    <requirements>
        <requirement type="package" version="0.1.4">ngs-tools</requirement>
    </requirements>
    <command>
        ngs-tools split-by-barcode
            $keep_barcode $input_format.format
            --barcode-size $barcode_length --max-distance $max_distance
            #for $i in $barcodes
              --barcode ${i.barcode}
            #end for
            --report $output1 --galaxy $output1.id --output $__new_file_path__
            $barcode_index
            #for $i in $input_format.inputs
              ${i.input}
            #end for
    </command>

	<inputs>
        <conditional name="input_format">
            <param name="format" type="select" label="Input format">
                <option value="--fastq" selected="true">Fastq</option>
                <option value="">Fasta</option>
            </param>
            <when value="--fastq">
                <repeat name="inputs" title="Dataset" help="Datasets to split.">
                    <param name="input" type="data" label="Dataset to split" format="fastq,fastqsanger,fastqsolexa,fastqillumina" />
                </repeat>
            </when>
            <when value="">
                <repeat name="inputs" title="Dataset" help="Datasets to split.">
                    <param name="input" type="data" label="Dataset to split" format="fasta" />
                </repeat>
            </when>
        </conditional>
        <param format="tabular" name="barcode_index" type="data" label="Barcodes index" help="See below for description." />
        <param name="barcode_length" type="integer" size="3" value="11" label="Barcode length" help="Please specify the barcode length." />
        <repeat name="barcodes" title="Barcode" help="Barcodes to use. By default all barcodes with the correct length in the index are used. By using this option you can limit which ones to use.">
            <param name="barcode" type="text" label="Barcode to use" />
        </repeat>
        <param name="keep_barcode" type="select" label="Do not trim the barcode" help="By default barcodes are trimmed from the resulting splitted datasets">
            <option value="" selected="true">No</option>
            <option value="--keep-barcode">Yes</option>
        </param>
        <param name="max_distance" type="integer" size="3" value="2" label="Number of allowed polymorphisms" help="Max Levenshtein's distance when looking for mutated barcodes." />
	</inputs>
	
	<outputs>
		<data format="interval" name="output1" />
	</outputs>
<help>

**What it does**

This tool splits FASTQ or FASTA datasets into several datasets, using barcodes as the split criteria.

--------

**Barcode index format**

Barcode index datasets are simple tab separated files.
Each line should contain an identifier (descriptive name for the barcode), and the barcode itself (A/C/G/T), separated by a TAB character.
Example::

    RL001   ACACGACGACT
    RL002   ACACGTAGTAT
    RL003   ACACTACTCGT
    RL004   ACGACACGTAT
    RL005   ACGAGTAGACT
    
For each barcode, a new FASTQ or FASTA dataset will be created (with the barcode's identifier as part of the dataset name).
Sequences matching the barcode will be stored in the appropriate dataset.

One additional FASTQ or FASTA dataset will be created (the 'Unassigned' dataset), where sequences not matching any barcode will be stored.

The output of this tool is one history dataset per each barcode provided plus a report with the split counts.

------

This tool is based on `ngs-tools`__ by Carlos Borroto &lt;[e-mail]&gt;.

 .. __: https://github.com/cjav/ngs-tools/
 
</help>
</tool>