comparison annotateMyIDs.xml @ 2:9ab35a2245ce draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/annotatemyids commit 348750c48bc5e4f9ecad408519cdd2c68ac749ab

1:2e1b256f732f

<tool id="annotatemyids" name="annotateMyIDs" version="3.5.0.0">
    <description>annotate a generic set of identifiers</description>
    <requirements>
        <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.mm.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>
    </requirements>
    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", 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: ")", optparse version" $(R --vanilla --slave -e "library(optparse); cat(sessionInfo()\$otherPkgs\$optparse\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
        #if $rscriptOpt:
            cp '${annotatemyids_script}' '${out_rscript}' &&
        #end if

id_type <- "${id_type}"
organism <- "${organism}"
output_cols <- "${output_cols}"
file_has_header <- ${file_has_header}

ids <- as.character(read.table('$id_file', header=file_has_header)[,1])

if(organism == "Hs"){
    suppressPackageStartupMessages(library(org.Hs.eg.db))

    cat(paste("Organism type not supported", organism))
}

cols <- unlist(strsplit(output_cols, ","))
result <- select(db, keys=ids, keytype=id_type, columns=cols)
write.table(result, file='$out_tab', sep="\t", row.names=FALSE, quote=FALSE)

    ]]></configfile>
    </configfiles>
    <inputs>

            <option value="REFSEQ">REFSEQ</option>
            <option value="GO">GO</option>
            <option value="ONTOLOGY">ONTOLOGY</option>
            <option value="PATH">KEGG</option>
        </param>
        <param name="rscriptOpt" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Output Rscript?" help="If this option is set to Yes, the Rscript used to annotate the IDs will be provided as a text file in the output. Default: No" />
    </inputs>
    <outputs>
        <data name="out_tab" format="tabular" from_work_dir="*.tab" label="${tool.name} on ${on_string}: Annotated IDs" />
        <data name="out_rscript" format="txt" from_work_dir="*.txt" label="${tool.name} on ${on_string}: Rscript">

        <test expect_num_outputs="1">
            <param name="id_file" value="ensembl_ids.tab" ftype="tabular"/>
            <param name="id_type" value="ENSEMBL"/>
            <param name="organism" value="Hs"/>
            <param name="output_cols" value="ENSEMBL,GO,ONTOLOGY,EVIDENCE" />
            <output name="out_tab" file="out_gokegg.tab" compare="contains" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

2:9ab35a2245ce

<tool id="annotatemyids" name="annotateMyIDs" version="3.5.0.1">
    <description>annotate a generic set of identifiers</description>
    <requirements>
        <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.mm.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>
    </requirements>
    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", 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 detect_errors="exit_code"><![CDATA[
        #if $rscriptOpt:
            cp '${annotatemyids_script}' '${out_rscript}' &&
        #end if

id_type <- "${id_type}"
organism <- "${organism}"
output_cols <- "${output_cols}"
file_has_header <- ${file_has_header}
remove_dups <- ${remove_dups}

ids <- as.character(read.table('$id_file', header=file_has_header)[,1])

if(organism == "Hs"){
    suppressPackageStartupMessages(library(org.Hs.eg.db))

    cat(paste("Organism type not supported", organism))
}

cols <- unlist(strsplit(output_cols, ","))
result <- select(db, keys=ids, keytype=id_type, columns=cols)

if(remove_dups) {
    result <- result[!duplicated(result$${id_type}),]
}

write.table(result, file='$out_tab', sep="\t", row.names=FALSE, quote=FALSE)

    ]]></configfile>
    </configfiles>
    <inputs>

            <option value="REFSEQ">REFSEQ</option>
            <option value="GO">GO</option>
            <option value="ONTOLOGY">ONTOLOGY</option>
            <option value="PATH">KEGG</option>
        </param>
        <param name="remove_dups" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Remove duplicates?" help="If this option is set to Yes, only the first occurrence of each input Gene ID will be kept. Default: No" />
        <param name="rscriptOpt" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Output Rscript?" help="If this option is set to Yes, the Rscript used to annotate the IDs will be provided as a text file in the output. Default: No" />
    </inputs>
    <outputs>
        <data name="out_tab" format="tabular" from_work_dir="*.tab" label="${tool.name} on ${on_string}: Annotated IDs" />
        <data name="out_rscript" format="txt" from_work_dir="*.txt" label="${tool.name} on ${on_string}: Rscript">

        <test expect_num_outputs="1">
            <param name="id_file" value="ensembl_ids.tab" ftype="tabular"/>
            <param name="id_type" value="ENSEMBL"/>
            <param name="organism" value="Hs"/>
            <param name="output_cols" value="ENSEMBL,GO,ONTOLOGY,EVIDENCE" />
            <output name="out_tab" file="out_gokegg.tab" />
        </test>
        <!-- Ensure duplicate Gene ID removal works -->
        <test expect_num_outputs="1">
            <param name="id_file" value="ensembl_ids.tab" ftype="tabular"/>
            <param name="id_type" value="ENSEMBL"/>
            <param name="organism" value="Hs"/>
            <param name="output_cols" value="ENSEMBL,GO,ONTOLOGY,EVIDENCE" />
            <param name="remove_dups" value="True" />
            <output name="out_tab" file="out_gokegg_dupsrem.tab" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark