comparison fast5_subset.xml @ 1:3bdd8fa109b1 draft

"planemo upload for repository https://github.com/nanoporetech/ont_fast5_api/ commit a5d038871ff0e1b133039b59183dee795449b383"

0:eb1f4aa80c72

<?xml version="1.0"?>
<tool id="ont_fast5_api_fast5_subset" name="Fast5 subset" version="@TOOL_VERSION@+galaxy0" profile="18.01">
    <description>of multi read file</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <version_command></version_command>
    <command detect_errors="exit_code"><![CDATA[
## initialize
mkdir data &&
#for $num, $current in enumerate($input):
    ln -s '$current' './data/batch${num}.fast5' &&
#end for

## run
fast5_subset
## required
--input ./data
-s ./results
--read_id_list '$read_id_list'
## optional
--batch_size $batch_size
-t \${GALAXY_SLOTS:-4}
    ]]></command>
    <inputs>
        <param argument="--input" type="data" format="fast5" multiple="true"
            label="Select multi read input file(s)"/>
        <param argument="--read_id_list" type="data" format="tabular"
            label="Select file with read_ids" help="Either containing 1 read_id per line or a tabular file with a column named read_id."/>
        <param argument="--batch_size" type="integer" value="4000" min="1"
            label="Set batch size" help="Number of single reads to include in each multi read file"/>
    </inputs>
    <outputs>
        <data name="out_results" format="fast5">
            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fast5" format="fast5" directory="results" assign_primary_output="true" visible="true"/>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input" value="batch.fast5"/>
            <param name="read_id_list" value="list.txt"/>
            <param name="batch_size" value="2"/>
            <output name="out_results">
                <assert_contents>
                    <has_size value="23304"/>
                </assert_contents>
                <!-- batch0 is represented by out_results -->
                <discovered_dataset designation="batch1" ftype="fast5">
                    <assert_contents>
                        <has_size value="17328"/>
                    </assert_contents>
                </discovered_dataset>
            </output>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

@WID@

fast5_subset extracts reads from multi_read_fast5_file(s) based on a list of read IDs.

**Input**

A multi read file in FAST5 format and a list of read IDs that should be extracted.

**Output**

A multi read file in FAST5 format containing a subset of the input file.

.. class:: infomark

**References**

1:3bdd8fa109b1

<?xml version="1.0"?>
<tool id="ont_fast5_api_fast5_subset" name="@TOOL_NAME@ Subset" version="@TOOL_VERSION@+galaxy1" profile="18.01">
    <description>of multi read file(s)</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <!-- no specific version command for subcommand fast5_subset available -->
    <version_command><![CDATA[compress_fast5 -v]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
## initialize
mkdir -p './data' &&
tar -xf '$input' -C './data' &&

## run
fast5_subset
## required
--input './data'
@SAVEPATH@
--read_id_list '$read_id_list'
## optional
@COMPRESSION@
@BATCHSIZE@
@THREADS@

## create tarball
@TARBALL@
    ]]></command>
    <inputs>
        <expand macro="input" argument="--input"/>
        <param argument="--read_id_list" type="data" format="tabular" label="Select file with read IDs" help="Either containing 1 read_id per line or a tabular file with a column named read_id."/>
        <expand macro="batch_size"/>
        <expand macro="compression">
            <option value="none" selected="true">None</option>
            <option value="vbz">VBZ</option>
        </expand>
    </inputs>
    <outputs>
        <expand macro="output"/>
    </outputs>
    <tests>
        <!-- #1 default -->
        <test expect_num_outputs="1">
            <param name="input" value="multi.fast5.tar"/>
            <param name="read_id_list" value="list.txt"/>
            <output name="out_results">
                <assert_contents>
                    <has_size value="30720"/>
                </assert_contents>
            </output>
        </test>
        <!-- #2 -->
        <test expect_num_outputs="1">
            <param name="input" value="multi.fast5.tar"/>
            <param name="read_id_list" value="list.txt"/>
            <param name="batch_size" value="2"/>
            <param name="compression" value="gzip"/>
            <output name="out_results">
                <assert_contents>
                    <has_size value="51200"/>
                </assert_contents>
            </output>
        </test>
        <!-- #3 -->
        <test expect_num_outputs="1">
            <param name="input" value="multi.fast5.tar"/>
            <param name="read_id_list" value="list.txt"/>
            <param name="compression" value="vbz"/>
            <output name="out_results">
                <assert_contents>
                    <has_size value="40960"/>
                </assert_contents>
            </output>
        </test>
        <!-- #4 -->
        <test expect_num_outputs="1">
            <param name="input" value="multi.fast5.tar"/>
            <param name="read_id_list" value="list.txt"/>
            <param name="compression" value="vbz_legacy_v0"/>
            <output name="out_results">
                <assert_contents>
                    <has_size value="40960"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

@WID@

*fast5_subset* extracts reads from multi read FAST5 file(s) based on a list of read IDs.

**Input**

Multi read file(s) in FAST5 format, that are stored in a flat TAR, and a list of read IDs that should be extracted.

**Output**

Multi read file(s) in FAST5 format containing a subset of the input file(s). The rseults are are stored in a flat TAR.

.. class:: infomark

**References**