comparison limma_voom.xml @ 4:a61a6e62e91f draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/limma_voom commit 6a458881c0819b75e55e64b3f494679d43bb9ee8

3:38aab66ae5cb

<tool id="limma_voom" name="limma" version="3.34.6.0">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>
        <requirement type="package" version="3.34.6">bioconductor-limma</requirement>
        <requirement type="package" version="3.20.7">bioconductor-edger</requirement>
        <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>

&&
mkdir ./output_dir

&&
cp '$outReport.files_path'/*.tsv output_dir/
    ]]></command>

    <inputs>

        <!-- DE Method Option -->

                        <valid initial="string.letters,string.digits"><add value="_" /></valid>
                    </sanitizer>
                    </param>
                    <repeat name="rep_group" title="Group" min="2" default="2">
                        <param name="groupName" type="text" label="Name"
                        help="Name of group that the counts files(s) belong to (e.g. WT or Mut). NOTE: Please only use letters, numbers or underscores (case sensitive).">
                        <sanitizer>
                            <valid initial="string.letters,string.digits"><add value="_" /></valid>
                        </sanitizer>
                        </param>
                        <param name="countsFile" type="data" format="tabular" multiple="true" label="Counts file(s)"/>
                    </repeat>
                </repeat>
            </when>

            <when value="matrix">

        <section name="out" expanded="false" title="Output Options">
            <param name="normCounts" type="boolean" truevalue="1" falsevalue="0" checked="false"
                label="Output Normalised Counts Table?"
                help="Output a file containing the normalised counts, these are in log2 counts per million (logCPM). Default: No">
            </param>
            <param name="rdaOption" type="boolean" truevalue="1" falsevalue="0" checked="false"
                label="Output RData file?"
                help="Output all the data used by R to construct the plots and tables, can be loaded into R. A link to the RData file will be provided in the HTML report. Default: No">
            </param>
        </section>

    <outputs>
        <data name="outReport" format="html" label="${tool.name} on ${on_string}: Report" />
        <collection name="outTables" type="list" label="${tool.name} on ${on_string}: Tables">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.tsv$" format="tabular" directory="output_dir" visible="false" />
        </collection>
    </outputs>

    <tests>
        <!-- Ensure report is output -->
        <test>

            <repeat name="rep_contrast">
                <param name="contrast" value="WT-Mut" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="2">
                <element name="limma-voom_Mut-WT" ftype="tabular" file="limma-voom_Mut-WT.tsv" />
                <element name="limma-voom_WT-Mut" ftype="tabular" file="limma-voom_WT-Mut.tsv" />
            </output_collection>
            <output name="outReport" >
                <assert_contents>
                    <has_text text="Limma Analysis Output" />
                    <not_has_text text="RData" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure annotation file input works -->
        <test>
            <param name="format" value="matrix" />
            <param name="annoOpt" value="yes" />
            <param name="geneanno" value="anno.txt" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="1">
                <element name="limma-voom_Mut-WT" ftype="tabular" file="limma-voom_Mut-WT_anno.tsv" />
            </output_collection>
        </test>
        <!-- Ensure RData file can be output -->
        <test>
            <param name="format" value="matrix" />
            <param name="rdaOption" value="true" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_factor">
                <param name="factorName" value="Genotype"/>
                <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT" />

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

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="1" >
                <element name="limma-voom_Mut-WT" ftype="tabular" file="limma-voom_Mut-WT_2fact.tsv" />
            </output_collection>
        </test>
        <!-- Ensure factors file input works -->
        <test>
            <param name="format" value="matrix" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="1">
                <element name="limma-voom_Mut-WT" ftype="tabular" file="limma-voom_Mut-WT_2fact.tsv" />
            </output_collection>
        </test>
        <!-- Ensure normalised counts file output works-->
        <test>
            <param name="format" value="matrix" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="2">
                <element name="limma-voom_Mut-WT" ftype="tabular" file="limma-voom_Mut-WT.tsv" />
                <element name="limma-voom_normcounts" ftype="tabular" file="limma-voom_normcounts.tsv" />
            </output_collection>
        </test>
        <!-- Ensure multiple counts files input works -->
        <test>
            <param name="format" value="files" />

            <repeat name="rep_contrast">
                <param name="contrast" value="WT-Mut" />
            </repeat>
            <param name="normCounts" value="true" />
            <output_collection name="outTables" count="3">
                <element name="limma-voom_Mut-WT" ftype="tabular" file="limma-voom_Mut-WT_2fact_anno.tsv" />
                <element name="limma-voom_WT-Mut" ftype="tabular" file="limma-voom_WT-Mut_2fact_anno.tsv" />
                <element name="limma-voom_normcounts" ftype="tabular" file="limma-voom_normcounts_anno.tsv" />
            </output_collection>
        </test>
        <!-- Ensure limma-trend option works -->
        <test>
            <param name="format" value="matrix" />

                <assert_contents>
                    <has_text text="The limma-trend method was used" />
                </assert_contents>
            </output>
            <output_collection name="outTables" count="1">
                <element name="limma-trend_Mut-WT" ftype="tabular" file="limma-trend_Mut-WT.tsv" />
            </output_collection>
        </test>
    </tests>

    <help><![CDATA[

If the sequencing depth is reasonably consistent across the RNA samples, then the simplest and most
robust approach to differential expression is to use limma-trend. This approach will usually work well if the
ratio of the largest library size to the smallest is not more than about 3-fold. When the library sizes are quite variable between samples, then the voom approach is theoretically more powerful than limma-trend. For more information see the excellent `limma User's Guide`_.

**Counts Data:**

The counts data can either be input as separate counts files (one sample per file) or a single count matrix (one sample per column). The rows correspond to genes, and columns correspond to the counts for the samples. Values must be tab separated, with the first row containing the sample/column labels and the first column containing the row/gene labels. Gene identifiers can be of any type but must be unique and not repeated within a counts file.

Example - **Separate Count Files**:

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

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

**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.

Example:

    ==========  ==========  ===================================================
    **GeneID**  **Symbol**  **GeneName**
    ----------  ----------  ---------------------------------------------------
    1287        Pzp         pregnancy zone protein
    1298        Aanat       arylalkylamine N-acetyltransferase
    1302        Aatk        apoptosis-associated tyrosine kinase
    1303        Abca1       ATP-binding cassette, sub-family A (ABC1), member 1
    1304        Abca4       ATP-binding cassette, sub-family A (ABC1), member 4
    1305        Abca2       ATP-binding cassette, sub-family A (ABC1), member 2
    ==========  ==========  ===================================================

**Factor Information:**
Enter factor names and groups in the tool form, or provide a tab-separated file that has the samples in the same order as listed in the columns of the counts matrix. The second column should contain the primary factor levels (e.g. WT, Mut) with optional additional columns for any secondary factors.

*Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered and spaces must not be used. Optionally, additional factors can be included, these are variables that might influence your experiment e.g. Batch, Gender, Subject. If additional factors are entered, edgeR will fit an additive linear model.

*Groups:* The names of the groups for the factor. These must be entered in the same order as the samples (to which the groups correspond) are listed in the columns of the counts matrix. Spaces must not be used and if entered into the tool form above, the values should be separated by commas.


**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.

Example:

    ==========  ==========  ===================================================
    **GeneID**  **Symbol**  **GeneName**
    ----------  ----------  ---------------------------------------------------
    1287        Pzp         pregnancy zone protein
    1298        Aanat       arylalkylamine N-acetyltransferase
    1302        Aatk        apoptosis-associated tyrosine kinase
    1303        Abca1       ATP-binding cassette, sub-family A (ABC1), member 1
    1304        Abca4       ATP-binding cassette, sub-family A (ABC1), member 4
    1305        Abca2       ATP-binding cassette, sub-family A (ABC1), member 2
    ==========  ==========  ===================================================

**Contrasts of Interest:**
The contrasts you wish to make between levels.
A common contrast would be a simple difference between two levels: "Mut-WT"
represents the difference between the mutant and wild type genotypes.

    * a HTML report with plots and additional information

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

    * a normalised counts table
    * an RData file

-----

**Citations:**

4:a61a6e62e91f

<tool id="limma_voom" name="limma" version="3.34.9.0">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>
        <requirement type="package" version="3.34.9">bioconductor-limma</requirement>
        <requirement type="package" version="3.20.7">bioconductor-edger</requirement>
        <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>

&&
mkdir ./output_dir

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

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

    <inputs>

        <!-- DE Method Option -->

                        <valid initial="string.letters,string.digits"><add value="_" /></valid>
                    </sanitizer>
                    </param>
                    <repeat name="rep_group" title="Group" min="2" default="2">
                        <param name="groupName" type="text" label="Name"
                        help="Name of group that the counts files belong to (e.g. WT or Mut). NOTE: Please only use letters, numbers or underscores (case sensitive).">
                        <sanitizer>
                            <valid initial="string.letters,string.digits"><add value="_" /></valid>
                        </sanitizer>
                        </param>
                        <param name="countsFile" type="data" format="tabular" multiple="true" label="Counts files"/>
                    </repeat>
                </repeat>
            </when>

            <when value="matrix">

        <section name="out" expanded="false" title="Output Options">
            <param name="normCounts" type="boolean" truevalue="1" falsevalue="0" checked="false"
                label="Output Normalised Counts Table?"
                help="Output a file containing the normalised counts, these are in log2 counts per million (logCPM). Default: No">
            </param>
            <param name="rscript" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Output Rscript?" help="If this option is set to Yes, the Rscript used will be provided as a text file in the output. Default: No"/>
            <param name="rdaOption" type="boolean" truevalue="1" falsevalue="0" checked="false"
                label="Output RData file?"
                help="Output all the data used by R to construct the plots and tables, can be loaded into R. A link to the RData file will be provided in the HTML report. Default: No">
            </param>
        </section>

    <outputs>
        <data name="outReport" format="html" label="${tool.name} on ${on_string}: Report" />
        <collection name="outTables" type="list" label="${tool.name} on ${on_string}: Tables">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.tsv$" format="tabular" directory="output_dir" visible="false" />
        </collection>
        <data name="rscript" format="txt" label="${tool.name} on ${on_string}: Rscript">
            <filter>out['rscript']</filter>
        </data>
    </outputs>

    <tests>
        <!-- Ensure report is output -->
        <test>

            <repeat name="rep_contrast">
                <param name="contrast" value="WT-Mut" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="2">
                <element name="limma-voom_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="GeneID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.4573" />
                    </assert_contents>
                </element>
                <element name="limma-voom_WT-Mut" ftype="tabular" >
                     <assert_contents>
                        <has_text_matching expression="GeneID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*-0.4573" />
                    </assert_contents>
                </element>
            </output_collection>
            <output name="outReport" >
                <assert_contents>
                    <has_text text="Limma Analysis Output" />
                    <not_has_text text="RData" />
                </assert_contents>
            </output>
       </test>
        <!-- Ensure annotation file input works -->
        <test>
            <param name="format" value="matrix" />
            <param name="annoOpt" value="yes" />
            <param name="geneanno" value="anno.txt" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="1">
                <element name="limma-voom_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="EntrezID.*Symbol.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*Abca4.*0.4573" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure Rscript and RData file can be output -->
        <test>
            <param name="format" value="matrix" />
            <param name="rscript" value="True"/>
            <param name="rdaOption" value="true" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_factor">
                <param name="factorName" value="Genotype"/>
                <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT" />

            <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" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="1" >
                <element name="limma-voom_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="GeneID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.4590" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure factors file input works -->
        <test>
            <param name="format" value="matrix" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="1">
                <element name="limma-voom_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="GeneID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.4590" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure normalised counts file output works-->
        <test>
            <param name="format" value="matrix" />

            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <output_collection name="outTables" count="2">
                <element name="limma-voom_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="GeneID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.4573" />
                    </assert_contents>
                </element>
                <element name="limma-voom_normcounts" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="GeneID.*Mut1.*Mut2.*Mut3.*WT1.*WT2.*WT3" />
                        <has_text_matching expression="11304.*15.7545" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure multiple counts files input works -->
        <test>
            <param name="format" value="files" />

            <repeat name="rep_contrast">
                <param name="contrast" value="WT-Mut" />
            </repeat>
            <param name="normCounts" value="true" />
            <output_collection name="outTables" count="3">
                <element name="limma-voom_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*Abca4.*0.4590" />
                    </assert_contents>
                </element>
                <element name="limma-voom_WT-Mut" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="EntrezID.*Symbol.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*Abca4.*-0.4590" />
                    </assert_contents>
                </element>
                <element name="limma-voom_normcounts" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="EntrezID.*Symbol.*Mut1.*Mut2.*Mut3.*WT1.*WT2.*WT3" />
                        <has_text_matching expression="11304.*Abca4.*15.7545" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure limma-trend option works -->
        <test>
            <param name="format" value="matrix" />

                <assert_contents>
                    <has_text text="The limma-trend method was used" />
                </assert_contents>
            </output>
            <output_collection name="outTables" count="1">
                <element name="limma-trend_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="GeneID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.4540" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure limma-trend option with annotation works -->
        <test>
            <param name="format" value="matrix" />
            <param name="counts" value="matrix.txt" />
            <param name="annoOpt" value="yes" />
            <param name="geneanno" value="anno.txt" />
            <repeat name="rep_factor">
                <param name="factorName" value="Genotype"/>
                <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT" />
            </repeat>
            <repeat name="rep_contrast">
                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <param name="de_select" value="trend" />
            <param name="rdaOption" value="true" />
            <output name="outReport" >
                <assert_contents>
                    <has_text text="The limma-trend method was used" />
                </assert_contents>
            </output>
            <output_collection name="outTables" count="1">
                <element name="limma-trend_Mut-WT" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="EntrezID.*Symbol.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.4540" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>

    <help><![CDATA[

If the sequencing depth is reasonably consistent across the RNA samples, then the simplest and most
robust approach to differential expression is to use limma-trend. This approach will usually work well if the
ratio of the largest library size to the smallest is not more than about 3-fold. When the library sizes are quite variable between samples, then the voom approach is theoretically more powerful than limma-trend. For more information see the excellent `limma User's Guide`_.

**Counts Data:**
The counts data can either be input as separate counts files (one sample per file) or a single count matrix (one sample per column). The rows correspond to genes, and columns correspond to the counts for the samples. Values must be tab separated, with the first row containing the sample/column labels and the first column containing the row/gene labels. Gene identifiers can be of any type but must be unique and not repeated within a counts file.

Example - **Separate Count Files**:

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

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

**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 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**
    ----------  ----------  ---------------------------------------------------
    11287       Pzp         pregnancy zone protein
    11298       Aanat       arylalkylamine N-acetyltransferase
    11302       Aatk        apoptosis-associated tyrosine kinase
    11303       Abca1       ATP-binding cassette, sub-family A (ABC1), member 1
    11304       Abca4       ATP-binding cassette, sub-family A (ABC1), member 4
    11305       Abca2       ATP-binding cassette, sub-family A (ABC1), member 2
    ==========  ==========  ===================================================

**Factor Information:**
Enter factor names and groups in the tool form, or provide a tab-separated file that has the samples in the same order as listed in the columns of the counts matrix. The second column should contain the primary factor levels (e.g. WT, Mut) with optional additional columns for any secondary factors.

*Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered and spaces must not be used. Optionally, additional factors can be included, these are variables that might influence your experiment e.g. Batch, Gender, Subject. If additional factors are entered, edgeR will fit an additive linear model.

*Groups:* The names of the groups for the factor. These must be entered in the same order as the samples (to which the groups correspond) are listed in the columns of the counts matrix. Spaces must not be used and if entered into the tool form above, the values should be separated by commas.


**Contrasts of Interest:**
The contrasts you wish to make between levels.
A common contrast would be a simple difference between two levels: "Mut-WT"
represents the difference between the mutant and wild type genotypes.

    * 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
    * an RData file

-----

**Citations:**