comparison limma_voom.xml @ 16:5d903d528193 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/limma_voom commit 349e35a66009449851b21e2810bc5aaa58225fca

15:41573afd6871

<tool id="limma_voom" name="limma" version="3.36.5">
    <description>
        Perform differential expression with limma-voom or limma-trend
    </description>

    <requirements>
        <requirement type="package" version="3.36.5">bioconductor-limma</requirement>
        <requirement type="package" version="3.22.5">bioconductor-edger</requirement>
        <requirement type="package" version="1.4.30">r-statmod</requirement>
        <requirement type="package" version="1.0.0">r-scales</requirement>
        <requirement type="package" version="0.2.20">r-rjson</requirement>
        <requirement type="package" version="1.20.2">r-getopt</requirement>
        <requirement type="package" version="3.0.1">r-gplots</requirement>
        <requirement type="package" version="1.8.2">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>

                <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.">
                        <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]+$</validator>
                            </param>
                            <param name="groupNames" type="text" label="Groups"
                                help="Enter the group names for the samples separated with commas e.g. WT,WT,WT,Mut,Mut,Mut. The order of the names must match the order of the samples in the columns of the count matrix. NOTE: Please only use letters, numbers or underscores (case sensitive).">
                                <validator type="empty_field" />
                                <validator type="regex" message="Please only use letters, numbers or underscores, and separate levels by commas">^[\w,]+$</validator>
                            </param>
                        </repeat>
                    </when>

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**:

    ========== =======
    **GeneID** **WT1**

    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. 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.

16:5d903d528193

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

    <requirements>
        <requirement type="package" version="3.38.3">bioconductor-limma</requirement>
        <requirement type="package" version="3.24.1">bioconductor-edger</requirement>
        <requirement type="package" version="1.4.30">r-statmod</requirement>
        <requirement type="package" version="1.0.0">r-scales</requirement>
        <requirement type="package" version="0.2.20">r-rjson</requirement>
        <requirement type="package" version="1.20.2">r-getopt</requirement>
        <requirement type="package" version="3.0.1">r-gplots</requirement>
        <requirement type="package" version="1.10.0">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>

                <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>

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. The sample labels must start with a letter. Gene identifiers can be of any type but must be unique and not repeated within a counts file.

Example - **Separate Count Files**:

    ========== =======
    **GeneID** **WT1**

    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.