comparison goseq.xml @ 3:783e8b70b047 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/goseq commit 46c4278d292ab4d76dc5f3f74c3109c3179be7ef

2:ab492df30cdf

<tool id="goseq" name="goseq" version="1.26.0">
    <description>tests for overrepresented gene categories</description>
    <requirements>
        <requirement type="package" version="1.3.2">r-optparse</requirement>
        <requirement type="package" version="1.26.0">bioconductor-goseq</requirement>
        <requirement type="package" version="3.3.0">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.4.0">bioconductor-org.dm.eg.db</requirement>
        <requirement type="package" version="3.4.1">bioconductor-org.dr.eg.db</requirement>
        <requirement type="package" version="3.4.0">bioconductor-org.mm.eg.db</requirement>
    </requirements>
    <stdio>
        <regex match="Execution halted"
               source="both"
               level="fatal"

               source="both"
               level="fatal"
               description="An undefined error occured, please check your input carefully and contact your administrator." />
    </stdio>
    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", goseq version" $(R --vanilla --slave -e "library(goseq); cat(sessionInfo()\$otherPkgs\$goseq\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", optparse version" $(R --vanilla --slave -e "library(optparse); cat(sessionInfo()\$otherPkgs\$optparse\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Hs.eg.db version" $(R --vanilla --slave -e "library(org.Hs.eg.db); cat(sessionInfo()\$otherPkgs\$org.Hs.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Dr.eg.db version" $(R --vanilla --slave -e "library(org.Dr.eg.db); cat(sessionInfo()\$otherPkgs\$org.Dr.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Dm.eg.db version" $(R --vanilla --slave -e "library(org.Dm.eg.db); cat(sessionInfo()\$otherPkgs\$org.Dm.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Mm.eg.db version" $(R --vanilla --slave -e "library(org.Mm.eg.db); cat(sessionInfo()\$otherPkgs\$org.Mm.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>
    <command><![CDATA[
Rscript '$__tool_directory__/goseq.r'

--dge_file '$dge_file'

--sampling_tab '$sampling_tab'

--make_plots '$out.make_plots'
--length_bias_plot '$length_bias_plot'
--sample_vs_wallenius_plot '$sample_vs_wallenius_plot'
--rdata '$out.rdata_out'

--p_adj_method '$adv.p_adj_method'
--use_genes_without_cat '$adv.use_genes_without_cat'

    ]]></command>

    <!-- Input Files-->
    <inputs>

            <param name="repcnt" type="integer" size="3" min="0" max="10000" value="0" label="Sampling number" help="Number of random samples to be calculated when sampling is used. Set to 0 to not do sampling. Larger values take a long time. Default: 0" />
        </section>

        <!-- Output Options -->
        <section name="out" title="Output Options">
            <param name="make_plots" type="boolean" checked="false" label="Produce diagnostic plots?" help="This will produce the length bias (PWF) plot. If both sampling and wallenius methods are selected, it will also produce a plot comparing their p-values. These plots may help you compare the different p-value estimation methods that goseq can use. Default: No" />
            <param name="rdata_out" type="boolean" checked="false" label="Output RData file?" help="Output all the data used by R to construct the tables and plots, can be loaded into R. Default: No" />
        </section>

        <!-- Advanced Options -->

        </section>
    </inputs>

    <outputs>
        <data name="wallenius_tab" format="tabular" label="${tool.name} on ${on_string}: Ranked category list - Wallenius method">
            <filter>methods['wallenius]'</filter>
        </data>
        <data name="sampling_tab" format="tabular" label="${tool.name} on ${on_string}: Ranked category list - Sampling method">
            <filter>methods['repcnt'] != 0</filter>
        </data>
        <data name="nobias_tab" format="tabular" label="${tool.name} on ${on_string}: Ranked category list - Hypergeometric method">

            <filter>out['make_plots']</filter>
        </data>
        <data name="rdata" format="rdata" from_work_dir="goseq_analysis.RData" label="${tool.name} on ${on_string}: RData file">
            <filter>out['rdata_out']</filter>
        </data>
    </outputs>

    <tests>
        <!-- Ensure Wallenius table is output -->
        <test expect_num_outputs="1">
            <param name="dge_file" value="dge_list.tab" ftype="tabular" />
            <param name="length_file" value="gene_length.tab" ftype="tabular" />
            <param name="catSource" value="history" />
            <param name="category_file" value="category.tab" ftype="tabular" />
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab" file="wal.tab" compare="contains" />
        </test>
        <!-- Ensure getting GO categories works -->
        <test expect_num_outputs="1">
            <param name="dge_file" value="dge_list.tab" ftype="tabular"/>
            <param name="length_file" value="gene_length.tab" ftype="tabular"/>
            <param name="catSource" value="getgo" />
            <param name="genome" value="hg38" />
            <param name="gene_id" value="ensGene" />
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab" ftype="tabular" file="getgo.hg38.tab" compare="contains"/>
        </test>
        <!-- Ensure getting GO categories for another genome (zebrafish) works -->
        <test expect_num_outputs="1">
            <param name="dge_file" value="dge_list_zf.tab" ftype="tabular"/>
            <param name="length_file" value="gene_length_zf.tab" ftype="tabular"/>
            <param name="catSource" value="getgo" />
            <param name="genome" value="danRer10"/>
            <param name="gene_id" value="ensGene" />
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab" ftype="tabular" file="getgo.danRer10.tab" compare="contains"/>
        </test>
        <!-- Ensure length bias plot works -->
        <test expect_num_outputs="2">
            <param name="dge_file" value="dge_list.tab" ftype="tabular" />
            <param name="length_file" value="gene_length.tab" ftype="tabular" />

-----

**Outputs**

* This tool outputs a tabular file containing a ranked list of gene categories, similar to below. The default output is the Wallenius method table. If the Sampling and/or Hypergeometric methods are also selected, additional tables are produced.
* Optionally, this tool can also output some diagnostic plots and an RData file, see **Output Options** above.

Example:

=========== =============== ================ ============ ========== ======================================== ========== =================== ====================
*category*  *over_rep_pval* *under_rep_pval* *numDEInCat* *numInCat* *term*                                   *ontology* *p.adjust.over_rep* *p.adjust.under_rep*

3:783e8b70b047

<tool id="goseq" name="goseq" version="1.30.0">
    <description>tests for overrepresented gene categories</description>
    <requirements>
        <requirement type="package" version="1.6.0">r-optparse</requirement>
        <requirement type="package" version="1.30.0">bioconductor-goseq</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.dm.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.dr.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement>
        <requirement type="package" version="0.7.6">r-dplyr</requirement>
        <requirement type="package" version="3.0.0">r-ggplot2</requirement>
    </requirements>
    <stdio>
        <regex match="Execution halted"
               source="both"
               level="fatal"

               source="both"
               level="fatal"
               description="An undefined error occured, please check your input carefully and contact your administrator." />
    </stdio>
    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", goseq version" $(R --vanilla --slave -e "library(goseq); cat(sessionInfo()\$otherPkgs\$goseq\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", optparse version" $(R --vanilla --slave -e "library(optparse); cat(sessionInfo()\$otherPkgs\$optparse\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Hs.eg.db version" $(R --vanilla --slave -e "library(org.Hs.eg.db); cat(sessionInfo()\$otherPkgs\$org.Hs.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Dr.eg.db version" $(R --vanilla --slave -e "library(org.Dr.eg.db); cat(sessionInfo()\$otherPkgs\$org.Dr.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Dm.eg.db version" $(R --vanilla --slave -e "library(org.Dm.eg.db); cat(sessionInfo()\$otherPkgs\$org.Dm.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Mm.eg.db version" $(R --vanilla --slave -e "library(org.Mm.eg.db); cat(sessionInfo()\$otherPkgs\$org.Mm.eg.db\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", dplyr version" $(R --vanilla --slave -e "library(dplyr); cat(sessionInfo()\$otherPkgs\$dplyr\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", ggplot2 version" $(R --vanilla --slave -e "library(ggplot2); cat(sessionInfo()\$otherPkgs\$ggplot2\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>
    <command><![CDATA[
Rscript '$__tool_directory__/goseq.r'

--dge_file '$dge_file'

--sampling_tab '$sampling_tab'

--make_plots '$out.make_plots'
--length_bias_plot '$length_bias_plot'
--sample_vs_wallenius_plot '$sample_vs_wallenius_plot'

--rdata '$out.rdata_out'
--p_adj_method '$adv.p_adj_method'
--use_genes_without_cat '$adv.use_genes_without_cat'

#if $out.topgo_plot:
    --top_plot '$out.topgo_plot'
#end if

    ]]></command>

    <!-- Input Files-->
    <inputs>

            <param name="repcnt" type="integer" size="3" min="0" max="10000" value="0" label="Sampling number" help="Number of random samples to be calculated when sampling is used. Set to 0 to not do sampling. Larger values take a long time. Default: 0" />
        </section>

        <!-- Output Options -->
        <section name="out" title="Output Options">
            <param name="topgo_plot" type="boolean" checked="false" label="Output Top GO terms plot?" help="Output a PDF plot of the Top 10 over-represented GO terms. Default: No" />
            <param name="make_plots" type="boolean" checked="false" label="Produce diagnostic plots?" help="This will produce the length bias (PWF) plot. If both sampling and wallenius methods are selected, it will also produce a plot comparing their p-values. These plots may help you compare the different p-value estimation methods that goseq can use. Default: No" />
            <param name="rdata_out" type="boolean" checked="false" label="Output RData file?" help="Output all the data used by R to construct the tables and plots, can be loaded into R. Default: No" />
        </section>

        <!-- Advanced Options -->

        </section>
    </inputs>

    <outputs>
        <data name="wallenius_tab" format="tabular" label="${tool.name} on ${on_string}: Ranked category list - Wallenius method">
            <filter>methods['wallenius']</filter>
        </data>
        <data name="sampling_tab" format="tabular" label="${tool.name} on ${on_string}: Ranked category list - Sampling method">
            <filter>methods['repcnt'] != 0</filter>
        </data>
        <data name="nobias_tab" format="tabular" label="${tool.name} on ${on_string}: Ranked category list - Hypergeometric method">

            <filter>out['make_plots']</filter>
        </data>
        <data name="rdata" format="rdata" from_work_dir="goseq_analysis.RData" label="${tool.name} on ${on_string}: RData file">
            <filter>out['rdata_out']</filter>
        </data>
        <data name="top_plot" format="pdf" from_work_dir="top10.pdf" label="${tool.name} on ${on_string}: Top over-represented GO terms plot">
            <filter>methods['wallenius']</filter>
            <filter>out['topgo_plot']</filter>
        </data>
    </outputs>

    <tests>
        <!-- Ensure top plot is output -->
        <test expect_num_outputs="2">
            <param name="dge_file" value="dge_list.tab" ftype="tabular" />
            <param name="length_file" value="gene_length.tab" ftype="tabular" />
            <param name="catSource" value="history" />
            <param name="category_file" value="category.tab" ftype="tabular" />
            <param name="use_genes_without_cat" value="true" />
            <param name="topgo_plot" value="true" />
            <output name="top_plot" ftype="pdf" file="topgo.pdf" compare="sim_size"/>
        </test>
        <!-- Ensure Wallenius table is output -->
        <test expect_num_outputs="1">
            <param name="dge_file" value="dge_list.tab" ftype="tabular" />
            <param name="length_file" value="gene_length.tab" ftype="tabular" />
            <param name="catSource" value="history" />
            <param name="category_file" value="category.tab" ftype="tabular" />
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab">
                <assert_contents>
                    <has_text_matching expression="category.*over_represented_pvalue.*under_represented_pvalue.*numDEInCat.*numInCat.*term.*ontology.*p.adjust.over_represented.*p.adjust.under_represented" />
                    <has_text_matching expression="GO:0000278.*0.01" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure getting GO categories works -->
        <test expect_num_outputs="1">
            <param name="dge_file" value="dge_list.tab" ftype="tabular"/>
            <param name="length_file" value="gene_length.tab" ftype="tabular"/>
            <param name="catSource" value="getgo" />
            <param name="genome" value="hg38" />
            <param name="gene_id" value="ensGene" />
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab">
                <assert_contents>
                    <has_text_matching expression="category.*over_represented_pvalue.*under_represented_pvalue.*numDEInCat.*numInCat.*term.*ontology.*p.adjust.over_represented.*p.adjust.under_represented" />
                    <has_text_matching expression="GO:0005576.*5.2" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure getting GO categories for another genome (zebrafish) works -->
        <test expect_num_outputs="1">
            <param name="dge_file" value="dge_list_zf.tab" ftype="tabular"/>
            <param name="length_file" value="gene_length_zf.tab" ftype="tabular"/>
            <param name="catSource" value="getgo" />
            <param name="genome" value="danRer10"/>
            <param name="gene_id" value="ensGene" />
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab">
                <assert_contents>
                    <has_text_matching expression="category.*over_represented_pvalue.*under_represented_pvalue.*numDEInCat.*numInCat.*term.*ontology.*p.adjust.over_represented.*p.adjust.under_represented" />
                    <has_text_matching expression="GO:0031324.*0.08" />
                </assert_contents>
            </output>
        </test>
        <!-- Ensure length bias plot works -->
        <test expect_num_outputs="2">
            <param name="dge_file" value="dge_list.tab" ftype="tabular" />
            <param name="length_file" value="gene_length.tab" ftype="tabular" />

-----

**Outputs**

* This tool outputs a tabular file containing a ranked list of gene categories, similar to below. The default output is the Wallenius method table. If the Sampling and/or Hypergeometric methods are also selected, additional tables are produced.
* Optionally, this tool can also output a plot of the top 10 over-represented categories, some diagnostic plots and an RData file, see **Output Options** above.

Example:

=========== =============== ================ ============ ========== ======================================== ========== =================== ====================
*category*  *over_rep_pval* *under_rep_pval* *numDEInCat* *numInCat* *term*                                   *ontology* *p.adjust.over_rep* *p.adjust.under_rep*