comparison filter_genes.xml @ 0:f689c4ea8c43 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/gsc_filter_genes commit 09dcd74dbc01f448518cf3db3e646afb0675a6fe

0:f689c4ea8c43

<tool id="filter_genes" name="Filter genes in single cell data" version="0.9.0">
    <description>which are detected in less that a given fraction of the libraries</description>
    <requirements>
        <requirement type="package" version="1.3.2=r3.3.2_0">r-optparse</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[ 
        Rscript $__tool_directory__/filter_genes.R 
            --input $input 
            --sep 
            #if $sep == 'tab':
              'tab'
            #elif $sep == 'comma':
              'comma'
            #end if
            --colnames '$colnames'
            --percentile_detection '$percentile_detection'
            --absolute_detection '$absolute_detection'
            --output $output
]]></command>
    <inputs>
        <param name="input" type="data" format="txt,tabular" label="Expression data" help="a csv or tsv table file" />
        <param name="sep" type="select" label="Indicate column separator">
            <option value="tab" selected="true">Tabs</option>
            <option value="comma">Comma</option>
        </param>
        <param name="colnames" type="select" label="Firt row contains column names">
            <option value="TRUE" selected="true">True</option>
            <option value="FALSE">False</option>
        </param>
        <param name="percentile_detection" value="0.0" type="float" label="remove genes that are expressed in less than this fraction of cells"
               help="Fraction is expressed as a floatting number &lt; 1" />
        <param name="absolute_detection" value="0" type="integer" label="remove genes that are expressed in less than this number of cells"
               help="an absolute number of cells/libraries" />
    </inputs>
    <outputs>
        <data name="output" format="tabular" label="Cell data filtered from ${on_string}" />
    </outputs>
    <tests>
        <test> <!-- null case -->
            <param name="input" value="input.tsv" ftype="txt"/>
            <param name="sep" value='tab' />
            <param name="colnames" value="TRUE"/>
            <output name="output" file="filtered-null.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="input.csv" ftype="txt"/>
            <param name="sep" value='comma' />
            <param name="colnames" value="TRUE"/>
            <param name="percentile_detection" value="0.05"/>
            <output name="output" file="filtered-0.05.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="input.csv" ftype="txt"/>
            <param name="sep" value='comma' />
            <param name="colnames" value="TRUE"/>
            <param name="percentile_detection" value="0.0"/>
            <param name="absolute_detection" value="5"/>
            <output name="output" file="filtered-5.tab" ftype="tabular"/>
        </test>
    </tests>
    <help>

**What it does**

The tools takes a table of *normalized* gene expression values
(i.e. log2(CPM+1), TPM, RPK, etc...) from single cell RNAseq sequencing libraries (columns)
and filters out genes (rows) that are detected in less than the specified fraction of libraries,
or than an absolute number of libraries.

The criteria ("less than this fraction of cells" or "less than this number of cells") left at 0 is not used.
If none criteria is set, no gene will be filtered out. If both criteria are set (which is logically impossible),
the criteria "less than this fraction of cells" will be used by default.

A TSV gene expression table for genes that passed the filter is returned.

**Input**

A table of comma (csv) or tabulation (tsv) separated values of _normalized_ gene expressions,
i.e. log2(CPM+1), TPM, RPK, etc...
Gene names should be in the first column and cell names should be in the first row.
Note that in a number of a csv files, header of the gene column is omitted, resulting in
a first row with one item less than in other rows. Although this is not recommended, the tool
handles this type of table and will return a filtered table with the same structure.

    </help>
    <citations>
        <citation type="bibtex">
        @Manual{,
             title = {R: A Language and Environment for Statistical Computing},
             author = {{R Core Team}},
             organization = {R Foundation for Statistical Computing},
             address = {Vienna, Austria},
             year = {2014},
             url = {http://www.R-project.org/},
        }
        </citation>
    </citations>
</tool>