comparison gemini_annotate.xml @ 7:567837ca5f33 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 251c6024b4ff643a63e17fbfe2590998c2bae3a7"

6:0c8f7322f8fc

<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@+galaxy1">
    <description>the variants in an existing GEMINI database with additional information</description>
    <macros>
        <import>gemini_macros.xml</import>
        <token name="@BINARY@">annotate</token>
        <xml name="add_as">

    <expand macro="version_command" />
    <command>
<![CDATA[

    ## For GEMINI to work correctly, tabixed file must have form [name].[bed|vcf].gz
    #set $tabixed_file = "tabixed.%s.gz" % $annotate_source.ext
    bgzip -c '$annotate_source' > '$tabixed_file' &&
    tabix -p '$annotate_source.ext' '$tabixed_file' &&
    cp '$infile' '$outfile' &&

    gemini @BINARY@
        -f '$tabixed_file'
        -a $a.a_selector

            -o #echo ",".join($operations)
            -c '#echo ",".join($column_names)#'
        #else:
            -c '${a.column_name}'
        #end if
        #if str($annotate_source.ext) == "vcf":
            $region_only
        #end if
        '$outfile'
]]>
    </command>
    <inputs>
        <expand macro="infile" />
        <param argument="-f" name="annotate_source" type="data" format="vcf,bed"
        label="Dataset to use as the annotation source"
        help="The tool can use the information from a BED or VCF dataset to annotate the database variants."/>
        <param argument="--region-only" name="region_only" type="boolean" checked="true" truevalue="" falsevalue="--region-only"
        label="Strict variant-identity matching of database and annotation records (VCF format only)"
        help="The default is to consider VCF-formatted annotations only if a variant in the GEMINI database and a record in the annotation source describe the exact same nucleotide change at the same position in the genome. You can disable this option to make use of any annotation that overlaps with the position of a database variant. This setting is ignored for annotation sources in BED format, for which matching is always based on overlapping positions only." />

    <outputs>
        <data name="outfile" format="gemini.sqlite" />
    </outputs>
    <tests>
        <test>
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <param name="annotate_source" value="anno.bed" />
            <param name="region_only" value="false" />
            <conditional name="a">
                <param name="a_selector" value="count" />
                <param name="column_name" value="anno5" />
            </conditional>
            <assert_command>
                <not_has_text text="--region-only" />
            </assert_command>
            <output name="outfile" file="gemini_annotate_result.db" ftype="gemini.sqlite" compare="sim_size" delta="1000"/>
        </test>
        <test>
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <param name="annotate_source" value="anno.bed" />

                    <param name="operation" value="first" />
                </repeat>
            </conditional>
            <assert_command>
                <has_text_matching expression="-a +extract" />
                <has_text_matching expression="-e +1" />
                <has_text_matching expression="-c +anno5" />
                <has_text_matching expression="-t +text" />
                <has_text_matching expression="-o +first" />
            </assert_command>
        </test>
        <test>

                    <param name="operation" value="first" />
                </repeat>
            </conditional>
            <assert_command>
                <has_text_matching expression="-a +extract" />
                <has_text_matching expression="-e +1,2" />
                <has_text_matching expression="-c +anno5,anno6" />
                <has_text_matching expression="-t +text,integer" />
                <has_text_matching expression="-o +first,first" />
            </assert_command>
        </test>
    </tests>

7:567837ca5f33

<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@+galaxy2">
    <description>the variants in an existing GEMINI database with additional information</description>
    <macros>
        <import>gemini_macros.xml</import>
        <token name="@BINARY@">annotate</token>
        <xml name="add_as">

    <expand macro="version_command" />
    <command>
<![CDATA[

    ## For GEMINI to work correctly, tabixed file must have form [name].[bed|vcf].gz
    #if $annotate_source.ext == 'vcf_bgzip':
        ## File is bgzipped and tabixed already -> just symlink data and index
        #set $tabixed_file = 'tabixed.vcf.gz'
        ln -s '$annotate_source' $tabixed_file &&
        ln -s '$annotate_source.metadata.tabix_index' ${tabixed_file}.tbi &&
    #else:
        ## bgzip and index vcf or bed
        #set $tabixed_file = "tabixed.%s.gz" % $annotate_source.ext
        bgzip -c '$annotate_source' > '$tabixed_file' &&
        tabix -p '$annotate_source.ext' '$tabixed_file' &&
    #end if
    ## gemini annotate modifies its input database in-place so, in Galaxy,
    ## we need to create a copy first!
    cp '$infile' '$outfile' &&

    gemini @BINARY@
        -f '$tabixed_file'
        -a $a.a_selector

            -o #echo ",".join($operations)
            -c '#echo ",".join($column_names)#'
        #else:
            -c '${a.column_name}'
        #end if
        #if str($annotate_source.ext) != "bed":
            $region_only
        #end if
        '$outfile'
]]>
    </command>
    <inputs>
        <expand macro="infile" />
        <param argument="-f" name="annotate_source" type="data" format="vcf,vcf_bgzip,bed"
        label="Dataset to use as the annotation source"
        help="The tool can use the information from a BED or VCF dataset to annotate the database variants."/>
        <param argument="--region-only" name="region_only" type="boolean" checked="true" truevalue="" falsevalue="--region-only"
        label="Strict variant-identity matching of database and annotation records (VCF format only)"
        help="The default is to consider VCF-formatted annotations only if a variant in the GEMINI database and a record in the annotation source describe the exact same nucleotide change at the same position in the genome. You can disable this option to make use of any annotation that overlaps with the position of a database variant. This setting is ignored for annotation sources in BED format, for which matching is always based on overlapping positions only." />

    <outputs>
        <data name="outfile" format="gemini.sqlite" />
    </outputs>
    <tests>
        <test>
            <!-- test with annotation source in bed format -->
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <param name="annotate_source" value="anno.bed" ftype="bed" />
            <param name="region_only" value="false" />
            <conditional name="a">
                <param name="a_selector" value="count" />
                <param name="column_name" value="anno5" />
            </conditional>
            <assert_command>
                <!-- confirm region_only gets ignored for bed input -->
                <not_has_text text="--region-only" />
            </assert_command>
            <output name="outfile" file="gemini_annotate_result.db" ftype="gemini.sqlite" compare="sim_size" delta="1000"/>
        </test>
        <test>
            <!-- test with annotation source in vcf format -->
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <param name="annotate_source" value="gemini_amend.vcf" ftype="vcf" />
            <param name="region_only" value="false" />
            <conditional name="a">
                <param name="a_selector" value="count" />
                <param name="column_name" value="anno5" />
            </conditional>
            <output name="outfile" file="gemini_annotate_result.db" ftype="gemini.sqlite" compare="sim_size" delta="1000"/>
        </test>
        <test>
            <!-- test with annotation source in vcf_bgzip format -->
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <param name="annotate_source" value="gemini_amend.vcf.gz" ftype="vcf_bgzip" />
            <param name="region_only" value="false" />
            <conditional name="a">
                <param name="a_selector" value="count" />
                <param name="column_name" value="anno5" />
            </conditional>
            <output name="outfile" file="gemini_annotate_result.db" ftype="gemini.sqlite" compare="sim_size" delta="1000"/>
        </test>
        <test>
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <param name="annotate_source" value="anno.bed" />

                    <param name="operation" value="first" />
                </repeat>
            </conditional>
            <assert_command>
                <has_text_matching expression="-a +extract" />
                <has_text_matching expression="-e +&apos;1&apos;" />
                <has_text_matching expression="-c +&apos;anno5&apos;" />
                <has_text_matching expression="-t +text" />
                <has_text_matching expression="-o +first" />
            </assert_command>
        </test>
        <test>

                    <param name="operation" value="first" />
                </repeat>
            </conditional>
            <assert_command>
                <has_text_matching expression="-a +extract" />
                <has_text_matching expression="-e +&apos;1,2&apos;" />
                <has_text_matching expression="-c +&apos;anno5,anno6&apos;" />
                <has_text_matching expression="-t +text,integer" />
                <has_text_matching expression="-o +first,first" />
            </assert_command>
        </test>
    </tests>