comparison limma_voom.xml @ 9:4255881bebb1 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/limma_voom commit 5f8052ab47b789da5ea47feb48e1b8e08b5fc1e0

8:00a42b66e522

<tool id="limma_voom" name="limma" version="3.34.9.4">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>

        <requirement type="package" version="1.4.30">r-statmod</requirement>
        <requirement type="package" version="0.5.0">r-scales</requirement>
        <requirement type="package" version="0.2.15">r-rjson</requirement>
        <requirement type="package" version="1.20.0">r-getopt</requirement>
        <requirement type="package" version="3.0.1">r-gplots</requirement>
    </requirements>

    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", limma version" $(R --vanilla --slave -e "library(limma); cat(sessionInfo()\$otherPkgs\$limma\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", edgeR version" $(R --vanilla --slave -e "library(edgeR); cat(sessionInfo()\$otherPkgs\$edgeR\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", statmod version" $(R --vanilla --slave -e "library(statmod); cat(sessionInfo()\$otherPkgs\$statmod\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", scales version" $(R --vanilla --slave -e "library(scales); cat(sessionInfo()\$otherPkgs\$scales\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", rjson version" $(R --vanilla --slave -e "library(rjson); cat(sessionInfo()\$otherPkgs\$rjson\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", getopt version" $(R --vanilla --slave -e "library(getopt); cat(sessionInfo()\$otherPkgs\$getopt\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", gplots version" $(R --vanilla --slave -e "library(gplots); cat(sessionInfo()\$otherPkgs\$gplots\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>

    <command detect_errors="exit_code"><![CDATA[
#import json
Rscript '$__tool_directory__/limma_voom.R'

&&
mkdir ./output_dir

&&
cp '$outReport.files_path'/*.tsv output_dir/

#if $out.rscript:
    && cp '$__tool_directory__/limma_voom.R' '$rscript'
#end if
    ]]></command>

        </conditional>

        <!-- Gene Annotations -->
        <conditional name="anno">
            <param name="annoOpt" type="select" label="Use Gene Annotations?"
                    help="If you provide an annotation file, annotations will be added to the table(s) of differential expression results to provide descriptions for each gene, and used to label the top genes in the Volcano plot. See Help section below.">
                <option value="no">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="yes">
                <param name="geneanno" type="data" format="tabular" label="Gene Annotations"/>

            <output name="outReport" >
                <assert_contents>
                    <has_text text="RData" />
                </assert_contents>
            </output>
            <output name="rscript" value="out_rscript.txt"/>
        </test>
        <!-- Ensure secondary factors work -->
        <test>
            <param name="format" value="matrix" />
            <param name="counts" value="matrix.txt" />

    <help><![CDATA[
.. class:: infomark

**What it does**

Given a matrix of counts (e.g. from featureCounts) and optional information about the genes, performs differential expression (DE) using the limma_ Bioconductor package and produces plots and tables useful in DE analysis.

In the `limma approach`_ to RNA-seq, read counts are converted to log2-counts-per-million (logCPM) and the mean-variance relationship is modelled either with precision weights or with an empirical Bayes prior trend. The precision weights approach is called “voom” and the prior trend approach is called “limma-trend”. For more information, see the Help section below.

-----

    ========== ======= ======= ======= ======== ======== ========

**Gene Annotations:**
Optional input for gene annotations, this can contain more
information about the genes than just an ID number. The annotations will
be available in the differential expression results table and the optional normalised counts table. The file must contain a header row and have the gene IDs in the first column. The second column will be used to label the genes in the Volcano plot instead of the default Gene IDs. The number of rows should match that of the counts files, add NA for any gene IDs with no annotation. The Galaxy tool **annotateMyIDs** can be used to obtain annotations for human, mouse, fly and zebrafish.

Example:

    ==========  ==========  ===================================================
    **GeneID**  **Symbol**  **GeneName**

This tool outputs

    * a table of differentially expressed genes for each contrast of interest
    * a HTML report with plots and additional information

Optionally, under **Output Options** you can choose to output

    * a normalised counts table
    * the R script used by this tool

      Nucleic Acids Research 40, 4288-4297

Please report problems or suggestions to: [e-mail]

.. _limma: http://www.bioconductor.org/packages/release/bioc/html/limma.html
.. _limma approach: https://www.ncbi.nlm.nih.gov/pubmed/25605792
.. _limma User's Guide: http://bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf
.. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
.. _edgeR User's Guide: https://bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
.. _McCarthy and Smyth, 2009: https://www.ncbi.nlm.nih.gov/pubmed/19176553

9:4255881bebb1

<tool id="limma_voom" name="limma" version="3.34.9.5">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>

        <requirement type="package" version="1.4.30">r-statmod</requirement>
        <requirement type="package" version="0.5.0">r-scales</requirement>
        <requirement type="package" version="0.2.15">r-rjson</requirement>
        <requirement type="package" version="1.20.0">r-getopt</requirement>
        <requirement type="package" version="3.0.1">r-gplots</requirement>
        <requirement type="package" version="1.6.0">bioconductor-glimma</requirement>
    </requirements>

    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", limma version" $(R --vanilla --slave -e "library(limma); cat(sessionInfo()\$otherPkgs\$limma\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", edgeR version" $(R --vanilla --slave -e "library(edgeR); cat(sessionInfo()\$otherPkgs\$edgeR\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", statmod version" $(R --vanilla --slave -e "library(statmod); cat(sessionInfo()\$otherPkgs\$statmod\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", scales version" $(R --vanilla --slave -e "library(scales); cat(sessionInfo()\$otherPkgs\$scales\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", rjson version" $(R --vanilla --slave -e "library(rjson); cat(sessionInfo()\$otherPkgs\$rjson\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", getopt version" $(R --vanilla --slave -e "library(getopt); cat(sessionInfo()\$otherPkgs\$getopt\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", gplots version" $(R --vanilla --slave -e "library(gplots); cat(sessionInfo()\$otherPkgs\$gplots\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", Glimma version" $(R --vanilla --slave -e "library(Glimma); cat(sessionInfo()\$otherPkgs\$Glimma\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>

    <command detect_errors="exit_code"><![CDATA[
#import json
Rscript '$__tool_directory__/limma_voom.R'

&&
mkdir ./output_dir

&&
#if $anno.annoOpt=='yes':
    cp -r ./glimma* '$outReport.files_path' &&
#end if
cp '$outReport.files_path'/*tsv output_dir/

#if $out.rscript:
    && cp '$__tool_directory__/limma_voom.R' '$rscript'
#end if
    ]]></command>

        </conditional>

        <!-- Gene Annotations -->
        <conditional name="anno">
            <param name="annoOpt" type="select" label="Use Gene Annotations?"
                    help="If you provide an annotation file, annotations will be added to the table(s) of differential expression results to provide descriptions for each gene, and used to label the top genes in the Volcano plot. An interactive Glimma MD plot and table will also be generated. See Help section below.">
                <option value="no">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="yes">
                <param name="geneanno" type="data" format="tabular" label="Gene Annotations"/>

            <output name="outReport" >
                <assert_contents>
                    <has_text text="RData" />
                </assert_contents>
            </output>
            <output name="rscript">
                <assert_contents>
                    <has_text_matching expression="Task run time" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure secondary factors work -->
        <test>
            <param name="format" value="matrix" />
            <param name="counts" value="matrix.txt" />

    <help><![CDATA[
.. class:: infomark

**What it does**

Given a matrix of counts (e.g. from featureCounts) and optional information about the genes, performs differential expression (DE) using the limma_ Bioconductor package and produces plots and tables useful in DE analysis. If an annotation file is provided, interactive Glimma_ plots and a table of differentially expressed genes will also be generated. See an example workflow here_.

In the `limma approach`_ to RNA-seq, read counts are converted to log2-counts-per-million (logCPM) and the mean-variance relationship is modelled either with precision weights or with an empirical Bayes prior trend. The precision weights approach is called “voom” and the prior trend approach is called “limma-trend”. For more information, see the Help section below.

-----

    ========== ======= ======= ======= ======== ======== ========

**Gene Annotations:**
Optional input for gene annotations, this can contain more
information about the genes than just an ID number. The annotations will
be available in the differential expression results table and the optional normalised counts table. They will also be used to generate interactive Glimma_ MD plots and table of differential expression, a link to the Glimma plots will be provided in the report. The input annotation file must contain a header row and have the gene IDs in the first column. The second column will be used to label the genes in the Volcano plot and interactive Glimma plots, additional columns will be available in the Glimma interactive table. The number of rows should match that of the counts files, add NA for any gene IDs with no annotation. The Galaxy tool **annotateMyIDs** can be used to obtain annotations for human, mouse, fly and zebrafish.

Example:

    ==========  ==========  ===================================================
    **GeneID**  **Symbol**  **GeneName**

This tool outputs

    * a table of differentially expressed genes for each contrast of interest
    * a HTML report with plots and additional information
    * an interactive Glimma MD plot and table (if annotation file provided)

Optionally, under **Output Options** you can choose to output

    * a normalised counts table
    * the R script used by this tool

      Nucleic Acids Research 40, 4288-4297

Please report problems or suggestions to: [e-mail]

.. _limma: http://www.bioconductor.org/packages/release/bioc/html/limma.html
.. _Glimma: https://bioconductor.org/packages/release/bioc/html/Glimma.html
.. _here: https://f1000research.com/articles/5-1408/v2
.. _limma approach: https://www.ncbi.nlm.nih.gov/pubmed/25605792
.. _limma User's Guide: http://bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf
.. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
.. _edgeR User's Guide: https://bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
.. _McCarthy and Smyth, 2009: https://www.ncbi.nlm.nih.gov/pubmed/19176553