comparison limma_voom.xml @ 17:86b3df7db58b draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/limma_voom commit 42b1160a549a85c87ed5226a83b55c4e44648597

16:5d903d528193

<tool id="limma_voom" name="limma" version="3.38.3">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>

                <option value="matrix">Single Count Matrix</option>
            </param>

            <when value="files">
                <repeat name="rep_factor" title="Factor" min="1">
                    <param name="factorName" type="text" label="Name" help="Name of experiment factor of interest (e.g. Genotype). One factor must be entered and there must be two or more groups per factor. Optional additional factors (e.g. Batch) can be entered using the Insert Factor button below, see Help section for more information. NOTE: Please only use letters, numbers or underscores, and the first character of each factor must be a letter">
                    <sanitizer>
                        <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), and the first character of each group must be a letter">
                        <sanitizer>
                            <valid initial="string.letters,string.digits"><add value="_" /></valid>
                        </sanitizer>
                        </param>
                        <param name="countsFile" type="data" format="tabular" multiple="true" label="Counts files"/>

            <when value="matrix">
                <param name="counts" type="data" format="tabular" label="Count Matrix"/>

                <conditional name="fact">
                    <param name="ffile" type="select" label="Input factor information from file?"
                        help="You can choose to input the factor and group information for the samples from a file or manually enter below. NOTE: Please only use letters, numbers or underscores (case sensitive), and the first character of each sample, factor and group must be a letter">
                        <option value="no">No</option>
                        <option value="yes">Yes</option>
                    </param>
                    <when value="yes">
                        <param name="finfo" type="data" format="tabular" label="Factor File"/>
                    </when>
                    <when value="no" >
                        <repeat name="rep_factor" title="Factor" min="1">
                            <param name="factorName" type="text" label="Factor Name"
                                help="Name of experiment factor of interest (e.g. Genotype). One factor must be entered and there must be two or more groups per factor. Additional factors (e.g. Batch) can be entered using the Insert Factor button below, see Help section below. NOTE: Please only use letters, numbers or underscores, and the first character of each factor must be a letter">
                                <validator type="empty_field" />
                                <validator type="regex" message="Please only use letters, numbers or underscores">^[\w]+$</validator>
                            </param>
                            <param name="groupNames" type="text" label="Groups"
                                help="Enter the group names for the samples separated with commas e.g. WT,WT,WT,Mut,Mut,Mut. The order of the names must match the order of the samples in the columns of the count matrix. NOTE: Please only use letters, numbers or underscores (case sensitive), and the first character of each group must be a letter">
                                <validator type="empty_field" />
                                <validator type="regex" message="Please only use letters, numbers or underscores, and separate levels by commas">^[\w,]+$</validator>
                            </param>
                        </repeat>
                    </when>

        </data>
    </outputs>

    <tests>
        <!-- Ensure report is output -->
        <test>
            <param name="format" value="matrix" />
            <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" />

                    <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" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_factor">

                    </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">

                    <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" />
            <repeat name="rep_factor">
                <param name="factorName" value="Genotype"/>
                <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT" />

                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure factors file with unordered samples works -->
        <test>
            <param name="format" value="matrix" />
            <param name="ffile" value="yes" />
            <param name="finfo" value="factorinfo.txt" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_contrast">

                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure filtered and normalised count outputs works-->
        <test>
            <param name="format" value="matrix" />
            <param name="filtCounts" value="true" />
            <param name="normCounts" value="true" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_factor">

                    <not_has_text text="11302"/>
                </assert_contents>
            </output>
        </test>
        <!-- Ensure multiple counts files input works -->
        <test>
            <param name="format" value="files" />
            <repeat name="rep_factor">
                <param name="factorName" value="Genotype"/>
                <repeat name="rep_group">
                    <param name="groupName" value="WT"/>

                    <has_text_matching expression="11304.*Abca4.*15.7545" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure limma-trend option works -->
        <test>
            <param name="format" value="matrix" />
            <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" />

                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <param name="topgenes" value="6" />
            <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>

                    </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="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <param name="topgenes" value="6" />
            <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>

                        <has_text_matching expression="11304.*0.4540" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>

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

    Mut1       Mut          b1
    Mut2       Mut          b2
    Mut3       Mut          b3
    ========== ============ =========

*Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered, the name should start with a letter 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, an additive linear model will be used.

*Groups:* The names of the groups for the factor. The names should start with a letter, and only contain letters, numbers and underscores, other characters such as spaces and hyphens must not be used. If entered into the tool form above, the order must be the same as the samples (to which the groups correspond) are listed in the columns of the counts matrix, with the values 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.

17:86b3df7db58b

<tool id="limma_voom" name="limma" version="3.38.3+galaxy1">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>

                <option value="matrix">Single Count Matrix</option>
            </param>

            <when value="files">
                <repeat name="rep_factor" title="Factor" min="1">
                    <param name="factorName" type="text" label="Name" help="Name of experiment factor of interest (e.g. Genotype). One factor must be entered and there must be two or more groups per factor. Optional additional factors (e.g. Batch) can be entered using the Insert Factor button below, see Help section for more information. NOTE: Please only use letters, numbers or underscores.">
                    <sanitizer>
                        <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"/>

            <when value="matrix">
                <param name="counts" type="data" format="tabular" label="Count Matrix"/>

                <conditional name="fact">
                    <param name="ffile" type="select" label="Input factor information from file?"
                        help="You can choose to input the factor and group information for the samples from a file or manually enter below. NOTE: Please only use letters, numbers or underscores (case sensitive), the group names MUST not contain hyphens.">
                        <option value="no">No</option>
                        <option value="yes">Yes</option>
                    </param>
                    <when value="yes">
                        <param name="finfo" type="data" format="tabular" label="Factor File"/>
                    </when>
                    <when value="no" >
                        <repeat name="rep_factor" title="Factor" min="1">
                            <param name="factorName" type="text" label="Factor Name"
                                help="Name of experiment factor of interest (e.g. Genotype). One factor must be entered and there must be two or more groups per factor. Additional factors (e.g. Batch) can be entered using the Insert Factor button below, see Help section below. NOTE: Please only use letters, numbers or underscores.">
                                <validator type="empty_field" />
                                <validator type="regex" message="Please only use letters, numbers or underscores">^[\w]+$</validator>
                            </param>
                            <param name="groupNames" type="text" label="Groups"
                                help="Enter the group names for the samples separated with commas e.g. WT,WT,WT,Mut,Mut,Mut. The order of the names must match the order of the samples in the columns of the count matrix. NOTE: Please only use letters, numbers or underscores (case sensitive), the group names MUST not contain hyphens.">
                                <validator type="empty_field" />
                                <validator type="regex" message="Please only use letters, numbers or underscores, and separate levels by commas">^[\w,]+$</validator>
                            </param>
                        </repeat>
                    </when>

        </data>
    </outputs>

    <tests>
        <!-- Ensure report is output -->
        <test expect_num_outputs="2">
            <param name="format" value="matrix" />
            <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" />

                    <not_has_text text="RData" />
                </assert_contents>
            </output>
       </test>
        <!-- Ensure annotation file input works -->
        <test expect_num_outputs="2">
            <param name="format" value="matrix" />
            <param name="annoOpt" value="yes" />
            <param name="geneanno" value="anno.txt" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_factor">

                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure Rscript and RData file can be output -->
        <test expect_num_outputs="3">
            <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">

                    <has_text_matching expression="Task run time" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure secondary factors work -->
        <test expect_num_outputs="2">
            <param name="format" value="matrix" />
            <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" />

                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure factors file with unordered samples works -->
        <test expect_num_outputs="2">
            <param name="format" value="matrix" />
            <param name="ffile" value="yes" />
            <param name="finfo" value="factorinfo.txt" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_contrast">

                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure filtered and normalised count outputs works-->
        <test expect_num_outputs="4">
            <param name="format" value="matrix" />
            <param name="filtCounts" value="true" />
            <param name="normCounts" value="true" />
            <param name="counts" value="matrix.txt" />
            <repeat name="rep_factor">

                    <not_has_text text="11302"/>
                </assert_contents>
            </output>
        </test>
        <!-- Ensure multiple counts files input works -->
        <test expect_num_outputs="3">
            <param name="format" value="files" />
            <repeat name="rep_factor">
                <param name="factorName" value="Genotype"/>
                <repeat name="rep_group">
                    <param name="groupName" value="WT"/>

                    <has_text_matching expression="11304.*Abca4.*15.7545" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure limma-trend option works -->
        <test expect_num_outputs="2">
            <param name="format" value="matrix" />
            <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" />

                <param name="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <param name="topgenes" value="6" />
            <param name="de_select" value="trend" />
            <output name="outReport" >
                <assert_contents>
                    <has_text text="The limma-trend method was used" />
                </assert_contents>
            </output>

                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure limma-trend option with annotation works -->
        <test expect_num_outputs="2">
            <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="contrast" value="Mut-WT" />
            </repeat>
            <param name="normalisationOption" value="TMM" />
            <param name="topgenes" value="6" />
            <param name="de_select" value="trend" />
            <output name="outReport" >
                <assert_contents>
                    <has_text text="The limma-trend method was used" />
                </assert_contents>
            </output>

                        <has_text_matching expression="11304.*0.4540" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- Ensure samples and groups beginning with numbers can be handled -->
        <test expect_num_outputs="3">
            <param name="format" value="matrix" />
            <param name="counts" value="matrix_num.txt" />
            <param name="annoOpt" value="yes" />
            <param name="geneanno" value="anno.txt" />
            <repeat name="rep_factor">
                <param name="factorName" value="Group"/>
                <param name="groupNames" value="2,2,2,1,1,1" />
            </repeat>
            <repeat name="rep_contrast">
                <param name="contrast" value="2-1" />
            </repeat>
            <param name="filt_select" value="yes" />
            <param name="format_select" value="counts"/>
            <param name="cntReq" value="10"/>
            <param name="count_select" value="sample"/>
            <param name="cntSampleReq" value="3"/>
            <param name="normalisationOption" value="TMM" />
            <param name="normCounts" value="true" />
            <param name="topgenes" value="6" />
            <param name="de_select" value="voom" />
            <output_collection name="outTables" count="1">
                <element name="limma-voom_X2-X1" ftype="tabular" >
                    <assert_contents>
                        <has_text_matching expression="EntrezID.*logFC.*AveExpr.*t.*P.Value.*adj.P.Val.*B" />
                        <has_text_matching expression="11304.*0.45.*15.52.*4.94.*7.74.*0.0001.*5.27" />
                    </assert_contents>
                </element>
            </output_collection>
            <output name="outNorm" ftype="tabular" >
                <assert_contents>
                    <has_text_matching expression="EntrezID.*2-1.*2-2.*2-3.*1-1.*1-2.*1-3" />
                    <has_text_matching expression="11304.*15.7.*15.8.*15.6.*15.3.*15.2.*15.2" />
                </assert_contents>
            </output>
        </test>
    </tests>

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

    Mut1       Mut          b1
    Mut2       Mut          b2
    Mut3       Mut          b3
    ========== ============ =========

*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, an additive linear model will be used.

*Groups:* The names of the groups for the factor. The names should only contain letters, numbers and underscores, other characters such as spaces and hyphens MUST not be used. If entered into the tool form above, the order must be the same as the samples (to which the groups correspond) are listed in the columns of the counts matrix, with the values separated by commas. If the group names begin with a number an X will be added as a prefix.

**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.