view phyloseq_filter.xml @ 2:54897b7e0551 draft default tip

Updated tool

<tool id="biom_filter" name="Phyloseq Biom Filtering" version="1.22.3.2" hidden="false">
    <description>biom file filter</description>
    <requirements>
        <requirement type="package" version="1.22.3">bioconductor-phyloseq</requirement>
        <requirement type="package" version="1.20.0">r-getopt</requirement>
        <requirement type="package" version="1.0.11">r-doparallel</requirement>
        <requirement type="package" version="1.20.0">bioconductor-metagenomeseq</requirement>
        <requirement type="package" version="9.18">ghostscript</requirement>
    </requirements>
    <version_command><![CDATA[
        echo $(R --version | grep version | grep -v GNU)", phyloseq version" $(R --vanilla --slave -e "library(phyloseq); cat(sessionInfo()\$otherPkgs\$phyloseq\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
        Rscript '${__tool_directory__}/phyloseq_filter.R'
        #if str($file_source.file_source_selector) == "set_biom":
            --biom='$file_source.input'
        #else:
            --otu_table='$OTU_TABLE'
            --tax_table='$TAX_TABLE'
            --meta_table='$META_TABLE'
        #end if
        --cutoff='$cutoff'
        --kingdom='$kingdom_field'
        --keep='$keep'
        --filter='$nsample'
        --outbiom='$outputbiom'
        --outdir="$htmlfile.files_path"
        --htmlfile='$htmlfile'
        ]]>
    </command>

    <inputs>
        <conditional name="file_source">
            <param name="file_source_selector" type="select" label="Choose an input file type">
                <option value="set_biom" selected="True">BIOM File</option>
                <option value="set_table">TABULAR File</option>
            </param>
            <when value="set_biom">
                <param format="biom1" name="input" type="data" label="Input File"/>
            </when>
            <when value="set_table">
                <param format="tabular" name="OTU_TABLE" type="data" label="OTU table"/>
                <param format="tabular" name="TAX_TABLE" type="data" label="Taxonomy table"/>
                <param format="tabular" name="META_TABLE" type="data" label="Metadata table"/>
            </when>
        </conditional>
        <param name="kingdom_field" type="select" display="radio" label="Select a taxonomic rank for the analysis">
            <option value="Kingdom">Kingdom</option>
            <option value="Phylum" selected="true">Phylum</option>
            <option value="Class">Class</option>
            <option value="Order">Order</option>
            <option value="Family">Family</option>
            <option value="Genus">Genus</option>
            <option value="Species">Species</option>
        </param>
        <param name="keep" size="10" type="integer" value="5" label="Number of the most abundant taxonomic rank units to keep in the filtered BIOM file" help="e.g. Phyla, Class and etc. as specified above. Select a value > 1."/>
        <param name="cutoff" size="10" type="integer" value="1" label="Filter out OTUs. Remove OTUs from the analysis that do not appear more than X times in more than Y% of the samples. Specify value of X" help="Remove OTUs that do not appear more than X times (e.g., 5 times)"/>
        <param name="nsample" size="10" type="float" value="0.0" label="Specify value of Y (where 1.0 = 100%)"/>
    </inputs>

    <outputs>
        <data format="biom1" name="outputbiom" label="${tool.name} on ${on_string}.biom"/>
        <data format="html" name="htmlfile" label="${tool.name} on ${on_string} Sample Abundance plot.html"/>
    </outputs>

    <tests>
        <test>  <!-- Test #1: Test BIOM format input -->
            <conditional name="file_source">
                <param name="file_source_selector" value="set_biom"/>
                <param name="input" value="GP.biom" ftype="biom1"/>
            </conditional>
            <output name="htmlfile" ftype="html" file="biom_out.html" />
            <output name="outputbiom" >
                <assert_contents>
                    <has_text text="Biological Observation Matrix"/>
                </assert_contents>
            </output>
        </test>
        <test>  <!-- Test #2: Test TABULAR format inputs -->
            <conditional name="file_source">
                <param name="file_source_selector" value="set_table" />
                <param name="OTU_TABLE" value="GP_OTU_TABLE.txt" />
                <param name="TAX_TABLE" value="GP_TAX_TABLE.txt" />
                <param name="META_TABLE" value="GP_SAMPLE_TABLE.txt" />
            </conditional>
            <output name="htmlfile" ftype="html" file="matrix_out.html" />
            <output name="outputbiom" >
                <assert_contents>
                    <has_text text="Biological Observation Matrix"/>
                </assert_contents>
            </output>
        </test>
    </tests>

    <help>
**What it does**
Filter out low abundance OTUs and/or data corresponding to the least represented taxonomic grouping using R package called R_package_called_phyloseq_, and specifically according to the pre-processing step outlined in the Phyloseq_Ordination_Plot_Tutorial_.

.. _R_package_called_phyloseq: https://joey711.github.io/phyloseq/index.html
.. _Phyloseq_Ordination_Plot_Tutorial: https://joey711.github.io/phyloseq/plot_ordination-examples.html

-----

**Input**

- **Choose an input file type** - either 1 BIOM file or 3 TABULAR files (i.e. OTU, Taxonomy and Metadata tables)
- **Select a taxonomic rank for the analysis** - if filtering out low abundance taxa, this is the level of the taxonomy that you want to filter on (e.g. phyla, species)
- **Number of the most abundant taxonomic rank units to keep in the filtered BIOM file** - the number of the most abundant taxonomic rank units specified above to keep (e.g. remove all the most abundant 5 phyla or species)
- **Specify value of X** - if filtering out low abundance OTUs, use this to specify a value of X (where OTUs are removed that do not appear more than X times in more than Y% of the samples)
- **Specify value of Y (where 1.0=100%)** - if filtering out low abundance OTUs use this to specify a value of Y (where OTUs are removed that do not appear more than X times in more than Y% of the samples)

-----

=========
Resources
=========

**Wrapper Authors**

QFAB Bioinformatics ([e-mail])
Melbourne Bioinformatics
    </help>
    <citations>
        <citation type="doi">10.18129/B9.bioc.phyloseq</citation>
    </citations>
</tool>