comparison deseq2.xml @ 6:4939397c4706 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/deseq2 commit 3bc8d91ee546682ef8e9303bd1044bb14cf21b07

5:d38fd393402e

<tool id="deseq2" name="DESeq2" version="2.1.8.4">
    <description>Determines differentially expressed features from count tables</description>
    <requirements>
        <!-- odering is crucial, otherwise R will override the ENV variables from deseq2 -->
        <requirement type="package" version="1.20.0">r-getopt</requirement>
        <requirement type="package" version="2.17.0">r-gplots</requirement>
        <requirement type="package" version="0.2.15">r-rjson</requirement>
        <requirement type="package" version="1.10.1">bioconductor-deseq2</requirement>
    </requirements>
    <stdio>
        <regex match="Execution halted"
           source="both"
           level="fatal"

        echo $(R --version | grep version | grep -v GNU)", DESeq2 version" $(R --vanilla --slave -e "library(DESeq2); cat(sessionInfo()\$otherPkgs\$DESeq2\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]>
    </version_command>
    <command>
    <![CDATA[
        R -e 'library(DESeq2); sink("DESEQ2_ROOT_PATH"); cat(file.path(find.package("DESeq2"),"script","deseq2.R"))' &&

        #import json
        Rscript \$(cat DESEQ2_ROOT_PATH)
            -o "$deseq_out"
            #if $pdf:
                -p "$plots"
            #end if
            #set $temp_factor_names = list()
            #for $factor in $rep_factorName:
                #set $temp_factor = list()
                #for $level in $factor.rep_factorLevel:

                #end for
                $temp_factor.reverse()
                $temp_factor_names.append([str($factor.factorName), $temp_factor])
            #end for
            -f '#echo json.dumps(temp_factor_names)#'
            -t "$fit_type"
            #if $outlier_replace_off:
                -a
            #end if
            #if $outlier_filter_off:
                -b

            #if $auto_mean_filter_off:
                -c
            #end if
            #if $many_contrasts:
                -m
            #end if
    ]]>
    </command>
    <inputs>
        <repeat name="rep_factorName" title="Factor" min="1">
            <param name="factorName" type="text" value="FactorName" label="Specify a factor name"
                help="Only letters, numbers and underscores will be retained in this field">
                <sanitizer>
                    <valid initial="string.letters,string.digits"><add value="_" /></valid>
                </sanitizer>
            </param>
            <repeat name="rep_factorLevel" title="Factor level" min="2" default="2">
                <param name="factorLevel" type="text" value="FactorLevel" label="Specify a factor level"
                    help="Only letters, numbers and underscores will be retained in this field">
                    <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>
        <param name="pdf" type="boolean" truevalue="1" falsevalue="0" checked="true"
            label="Visualising the analysis results"
            help="output an additional PDF files" />
        <param name="many_contrasts" type="boolean" truevalue="1" falsevalue="0" checked="false"
            label="Output all levels vs all levels of primary factor (use when you have >2 levels for primary factor)"
            help=" DESeq2 performs independent filtering by default using the mean of normalized counts as a filter statistic" />
        <param name="fit_type" type="select" label="Fit type">
            <option value="1" selected="true">parametric</option>

            help=" DESeq2 performs independent filtering by default using the mean of normalized counts as a filter statistic" />
    </inputs>
    <outputs>
        <data format="tabular" name="deseq_out" label="DESeq2 result file on ${on_string}">
            <filter>many_contrasts is False</filter>
        </data>
        <collection name="split_output" type="list" label="DESeq2 result files on ${on_string}">
            <filter>many_contrasts is True</filter>
            <discover_datasets pattern="None.(?P&lt;designation&gt;.+_vs_.+)" format="tabular" directory="." visible="false"/>
        </collection>
        <data format="pdf" name="plots" label="DESeq2 plots on ${on_string}">
            <filter>pdf == True</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <repeat name="rep_factorName">
                <param name="factorName" value="Treatment"/>

                <repeat name="rep_factorLevel">
                    <param name="factorLevel" value="Untreated"/>
                    <param name="countsFile" value="GSM461176_untreat_single.counts,GSM461177_untreat_paired.counts,GSM461178_untreat_paired.counts,GSM461182_untreat_single.counts"/>
                </repeat>
            </repeat>
            <param name="pdf" value="no"/>
            <output name="deseq_out" file="deseq2_out.tab" compare="sim_size" delta="1000"/>
            <output name="deseq_out_filtered" file="deseq2_out_filtered.tab" compare="sim_size" delta="1000"/>
        </test>
    </tests>
    <help>
<![CDATA[
.. class:: infomark

6:4939397c4706

<tool id="deseq2" name="DESeq2" version="2.11.38">
    <description>Determines differentially expressed features from count tables</description>
    <requirements>
        <requirement type="package" version="1.12.4">bioconductor-deseq2</requirement> 
    </requirements>
    <stdio>
        <regex match="Execution halted"
           source="both"
           level="fatal"

        echo $(R --version | grep version | grep -v GNU)", DESeq2 version" $(R --vanilla --slave -e "library(DESeq2); cat(sessionInfo()\$otherPkgs\$DESeq2\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]>
    </version_command>
    <command>
    <![CDATA[

        #if $tximport.tximport_selector == 'tximport':
            #if $tximport.mapping_format.mapping_format_selector == 'gtf':
                ln -s '$tximport.mapping_format.gtf_file' mapping.gtf &&
            #else:
                ln -s '$tximport.mapping_format.tabular_file' mapping.txt &&
            #end if
        #end if

        #import json
        Rscript '${__tool_directory__}/deseq2.R'
            -o '$deseq_out'
            #if $pdf:
                -p '$plots'
            #end if
            #if $normCounts:
                -n '$counts_out'
            #end if
            #set $temp_factor_names = list()
            #for $factor in $rep_factorName:
                #set $temp_factor = list()
                #for $level in $factor.rep_factorLevel:

                #end for
                $temp_factor.reverse()
                $temp_factor_names.append([str($factor.factorName), $temp_factor])
            #end for
            -f '#echo json.dumps(temp_factor_names)#'
            -t '$fit_type'
            #if $outlier_replace_off:
                -a
            #end if
            #if $outlier_filter_off:
                -b

            #if $auto_mean_filter_off:
                -c
            #end if
            #if $many_contrasts:
                -m
            #end if
            #if $tximport.tximport_selector == 'tximport':
                -i
                #if $tximport.mapping_format.mapping_format_selector == 'gtf':
                    -x mapping.gtf
                #else:
                    -x mapping.txt
                #end if

            #end if
    ]]>
    </command>
    <inputs>
        <repeat name="rep_factorName" title="Factor" min="1">
            <param name="factorName" type="text" value="FactorName" label="Specify a factor name, e.g. effects_drug_x or cancer_markers"
                help="Only letters, numbers and underscores will be retained in this field">
                <sanitizer>
                    <valid initial="string.letters,string.digits"><add value="_" /></valid>
                </sanitizer>
            </param>
            <repeat name="rep_factorLevel" title="Factor level" min="2" default="2">
                <param name="factorLevel" type="text" value="FactorLevel" label="Specify a factor level, typical values could be 'tumor', 'normal', 'treated' or 'control'"
                    help="Only letters, numbers and underscores will be retained in this field">
                    <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>

        <conditional name="tximport">
            <param name="tximport_selector" type="select" label="Choice of Input data">
                <option value="count" selected="True">Count data (e.g. from htseq-count or feature-count)</option>
                <option value="tximport">TPM values (e.g. from sailfish or salmon)</option>
            </param>
            <when value="tximport">
                <conditional name="mapping_format">
                    <param name="mapping_format_selector" type="select" label="Gene mapping format">
                        <option value="gtf" selected="True">GTF</option>
                        <option value="tabular">Transcript-ID and Gene-ID mapping file</option>
                    </param>
                    <when value="gtf">
                        <param name="gtf_file" type="data" format="gtf" label="GTF file with Transcript - Gene mapping"/>
                    </when>
                    <when value="tabular">
                        <param name="tabular_file" type="data" format="tabular" label="Tabular file with Transcript - Gene mapping"/>
                    </when>
                </conditional>
            </when>
            <when value="count" />
        </conditional>
        <param name="pdf" type="boolean" truevalue="1" falsevalue="0" checked="true"
            label="Visualising the analysis results"
            help="output an additional PDF files" />
        <param name="normCounts" type="boolean" truevalue="1" falsevalue="0" checked="false"
            label="Output normalized counts table" />
        <param name="many_contrasts" type="boolean" truevalue="1" falsevalue="0" checked="false"
            label="Output all levels vs all levels of primary factor (use when you have >2 levels for primary factor)"
            help=" DESeq2 performs independent filtering by default using the mean of normalized counts as a filter statistic" />
        <param name="fit_type" type="select" label="Fit type">
            <option value="1" selected="true">parametric</option>

            help=" DESeq2 performs independent filtering by default using the mean of normalized counts as a filter statistic" />
    </inputs>
    <outputs>
        <data format="tabular" name="deseq_out" label="DESeq2 result file on ${on_string}">
            <filter>many_contrasts is False</filter>
            <actions>
                <action name="column_names" type="metadata" default="GeneID,Base mean,log2(FC),StdErr,Wald-Stats,P-value,P-adj" />
            </actions>
        </data>
        <collection name="split_output" type="list" label="DESeq2 result files on ${on_string}">
            <filter>many_contrasts is True</filter>
            <discover_datasets pattern="None.(?P&lt;designation&gt;.+_vs_.+)" format="tabular" directory="." visible="false"/>
        </collection>
        <data format="pdf" name="plots" label="DESeq2 plots on ${on_string}">
            <filter>pdf == True</filter>
        </data>
        <data format="tabular" name="counts_out" label="Normalized counts file on ${on_string}">
            <filter>normCounts == True</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <repeat name="rep_factorName">
                <param name="factorName" value="Treatment"/>

                <repeat name="rep_factorLevel">
                    <param name="factorLevel" value="Untreated"/>
                    <param name="countsFile" value="GSM461176_untreat_single.counts,GSM461177_untreat_paired.counts,GSM461178_untreat_paired.counts,GSM461182_untreat_single.counts"/>
                </repeat>
            </repeat>
            <param name="pdf" value="False"/>
            <param name="normCounts" value="True"/>
            <output name="counts_out" file="normalized_readcounts.tab"/>
            <output name="deseq_out" file="deseq2_out.tab"/>
        </test>
        <test>
            <repeat name="rep_factorName">
                <param name="factorName" value="Treatment"/>
                <repeat name="rep_factorLevel">
                    <param name="factorLevel" value="Treated"/>
                    <param name="countsFile" value="sailfish_quant_result1.tab,sailfish_quant_result2.tab"/>
                </repeat>
                <repeat name="rep_factorLevel">
                    <param name="factorLevel" value="Untreated"/>
                    <param name="countsFile" value="sailfish_quant_result3.tab,sailfish_quant_result4.tab"/>
                </repeat>
            </repeat>
            <param name="pdf" value="False"/>
            <param name="tximport_selector" value="tximport"/>
            <param name="mapping_format_selector" value="gtf"/>
            <param name="gtf_file" value="genes_sub.gtf"/>
            <output name="deseq_out" file="deseq2_tximport_out.tab"/>
        </test>
    </tests>
    <help>
<![CDATA[
.. class:: infomark