comparison snpSift_caseControl.xml @ 2:bf8c1526871b draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f

1:98708b88af9f

<tool id="snpSift_caseControl" name="SnpSift CaseControl" version="@WRAPPER_VERSION@.0">
    <description>Count samples are in 'case' and 'control' groups.</description>
    <!-- 
        You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory)
    -->
    <macros>
        <import>snpSift_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
    java -Xmx1G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" caseControl -q 
    #if str($name).strip() != '':
      -name "$name"
    #end if
    #if $ctrl.ctrl_src == 'caseString':
      '$ctrl.caseControlStr' 
    #else
      -tfam "$ctrl.tfam"
    #end if
    "$input" > "$output"
]]>
    </command>
    <inputs>
        <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
        <conditional name="ctrl">

        </when>
        <when value="tfam">
            <param format="tabular" name="tfam" type="data" label="PLINK TFAM file" help="Read more about TFAM at http://pngu.mgh.harvard.edu/~purcell/plink/data.shtml#tr"/>
        </when>
        </conditional>
        <param name="name" type="text" optional="true" label="name" help="name to append to the 'Cases' or 'Controls' tags">
            <validator type="regex" message="Use only valid ID characters">[_a-zA-Z0-9]+</validator>
        </param>
    </inputs>
    <outputs>
        <data format="vcf" name="output" />
    </outputs>

    </tests>
    <help><![CDATA[

**SnpSift CaseControl**

Allows you to count how many samples are in 'case' group and a 'control' group. You can count 'homozygous', 'heterozygous' or 'any' variants. 

Case and control are defined by a string containing plus and minus symbols {'+', '-', '0'} where '+' is case, '-' is control and '0' is neutral. 

This command adds two annotations to the VCF file:

 - **CaseControl**: Two comma separated numbers numbers representing the number of samples that have the variant in the case and the control group. Example: 

  "CaseControl=3,4" *the variant is present in 3 cases and 4 controls.*


 - **CaseControlP**: A p-value (Fisher exact test) that the number of cases is N or more. Example:

For example, if we have ten samples (which means ten genotype columns in the VCF file), the first four are 'case' and the last six are 'control', so the description string would be "++++------".  Let's say we want to distinguish genotypes that are homozygous in 'case' and either homozygous or heterozygous in 'control'.  We would set:

  - Hom/Het case = "hom"

  - Hom/Het control = "any"  

  - Case / Control column designation = ""++++------"


@EXTERNAL_DOCUMENTATION@

2:bf8c1526871b

<tool id="snpSift_caseControl" name="SnpSift CaseControl" version="@WRAPPER_VERSION@.1">
    <description>Count samples are in 'case' and 'control' groups.</description>
    <!--
        You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory)
    -->
    <macros>
        <import>snpSift_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
        @CONDA_SNPSIFT_JAR_PATH@ &&
        java -Xmx1G -jar "\$SNPSIFT_JAR_PATH/SnpSift.jar" caseControl -q
        #if str($name).strip() != '':
            -name "$name"
        #end if
        #if $ctrl.ctrl_src == 'caseString':
            '$ctrl.caseControlStr'
        #else
            -tfam "$ctrl.tfam"
        #end if
        "$input" > "$output"
]]>
    </command>
    <inputs>
        <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
        <conditional name="ctrl">

        </when>
        <when value="tfam">
            <param format="tabular" name="tfam" type="data" label="PLINK TFAM file" help="Read more about TFAM at http://pngu.mgh.harvard.edu/~purcell/plink/data.shtml#tr"/>
        </when>
        </conditional>
        <param name="name" type="text" label="name" help="name to append to the 'Cases' or 'Controls' tags">
            <validator type="regex" message="Use only valid ID characters">[_a-zA-Z0-9]*</validator>
        </param>
    </inputs>
    <outputs>
        <data format="vcf" name="output" />
    </outputs>

    </tests>
    <help><![CDATA[

**SnpSift CaseControl**

Allows you to count how many samples are in 'case' group and a 'control' group. You can count 'homozygous', 'heterozygous' or 'any' variants.

Case and control are defined by a string containing plus and minus symbols {'+', '-', '0'} where '+' is case, '-' is control and '0' is neutral.

This command adds two annotations to the VCF file:

 - **CaseControl**: Two comma separated numbers numbers representing the number of samples that have the variant in the case and the control group. Example:

  "CaseControl=3,4" *the variant is present in 3 cases and 4 controls.*


 - **CaseControlP**: A p-value (Fisher exact test) that the number of cases is N or more. Example:

For example, if we have ten samples (which means ten genotype columns in the VCF file), the first four are 'case' and the last six are 'control', so the description string would be "++++------".  Let's say we want to distinguish genotypes that are homozygous in 'case' and either homozygous or heterozygous in 'control'.  We would set:

  - Hom/Het case = "hom"

  - Hom/Het control = "any"

  - Case / Control column designation = ""++++------"


@EXTERNAL_DOCUMENTATION@