annotate snpeff_get_chr_names.xml @ 19:36dc3690a82c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpeff commit 530737ce6054364b394db08d42e3777355fa5c05

<tool id="snpEff_get_chr_names" name="SnpEff chromosome-info:" version="@WRAPPER_VERSION@.galaxy1">
    <description>list chromosome names/lengths</description>
    <macros>
        <import>snpEff_macros.xml</import>
    </macros>
    <requirements>
        <expand macro="requirement" />
    </requirements>
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
      snpEff dump
      #if $snpDb.genomeSrc == 'cached':
        -dataDir ${snpDb.genomeVersion.fields.path}
        $snpDb.genomeVersion
      #elif $snpDb.genomeSrc == 'history':
        -dataDir '${snpDb.snpeff_db.extra_files_path}'
        '${snpDb.snpeff_db.metadata.genome_version}'
      #elif $snpDb.genomeSrc == 'custom':
          -dataDir '${snpDb.snpeff_db.extra_files_path}'
          -configOption '${snpDb.snpeff_db.metadata.genome_version}'.genome='${snpDb.snpeff_db.metadata.genome_version}'
          '${snpDb.snpeff_db.metadata.genome_version}'
      #else
        -download
        '$snpDb.genome_version'
      #end if
      | awk '/# Chromosomes/{y=1;next}y' | grep "#" | grep -E "[0-9]" | awk 'BEGIN {err=1;} {c=$0;sub(/^[^a-zA-Z0-9_]+/, "", c) && err=0; sub(/[^a-zA-Z0-9_]+/, "\t", c) && err=0; sub(/[^0-9]*$/, "", c) && err=0; print c } END {exit err}' > '$chr_names'
    ]]></command>
    <inputs>
        <conditional name="snpDb">
            <param name="genomeSrc" type="select" label="Genome source">
                <!-- These options are referenced in the help section of SnpEff download tool. If you change them, change help of SnpEff download as well -->
                <option value="cached">Locally installed snpEff database</option>
                <option value="history">Downloaded snpEff database in your history</option>
                <option value="named">Download on demand</option>
                <option value="custom">Custom snpEff database in your history</option>
            </param>
            <when value="cached">
                <param name="genomeVersion" type="select" label="Genome">
                    <help>This can only be used on built-in databases manually configured by your galaxy admin.</help>
                    <options from_data_table="snpeffv_genomedb">
                            <filter type="static_value" name="SNPEFF_VERSION" value="@SNPEFF_VERSION@" column="1"/>
                            <filter type="unique_value" column="2" />
                    </options>
                </param>
            </when>
            <when value="history">
                <param name="snpeff_db" type="data" format="snpeffdb" label="@SNPEFF_VERSION@ Genome Data">
                    <help>This can only be used on databases in your history that were downloaded using the snpEff download tool.</help>
                    <options options_filter_attribute="metadata.SNPEFF_VERSION" >
                        <filter type="add_value" value="@SNPEFF_VERSION@" />
                    </options>
                    <validator type="expression" message="This version of SnpEff will only work with @SNPEFF_VERSION@ genome databases">value is not None and value.metadata.SNPEFF_VERSION == "@SNPEFF_VERSION@"</validator>
                </param>
            </when>
            <when value="named">
                <param name="genome_version" type="text" value="" label="Snpff Genome Version Name (e.g. GRCh38.76)">
                    <help>The list of available databases can be obtained with 'SnpEff databases' tool. If the database name is not found, locate a database here and download it in your history.</help>
                    <validator type="regex" message="A genome version name is required">\S+</validator>
                </param>
            </when>
            <when value="custom">
                <param name="snpeff_db" type="data" format="snpeffdb" label="@SNPEFF_VERSION@ Genome Data">
                    <help>This can only be used on databases in your history that were created using the snpEff build tool.</help>
                    <options options_filter_attribute="metadata.SNPEFF_VERSION" >
                        <filter type="add_value" value="@SNPEFF_VERSION@" />
                    </options>
                    <validator type="expression" message="This version of SnpEff will only work with @SNPEFF_VERSION@ genome databases">value is not None and value.metadata.SNPEFF_VERSION == "@SNPEFF_VERSION@"</validator>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="tabular" name="chr_names" label="Chromosome names and sizes"/>
    </outputs>
    <tests>
        <test>
            <param name="genomeSrc" value="named"/>
            <param name="genome_version" value="Bacillus_subtilis_subsp_subtilis_str_168"/>
            <output name="chr_names">
                <assert_contents>
                    <has_text text="Chromosome" />
                    <has_text text="4215606" />
                </assert_contents>
            </output>
        </test>
        <test expect_failure="True">
            <param name="genomeSrc" value="named"/>
            <param name="genome_version" value="should_not_match"/>
        </test>
    </tests>
    <help><![CDATA[

**What it does**

This tool outputs a tab-delimited file of chromosome names and their lengths, as they are in the selected genome/SnpEff database.  The output can be used to validate and rename chromosomes in VCF files in order to annotate its records.

Note, make sure that the genome you select from the snpEff database precisely matches the one used in your analysis.  As a cursory check, you can use the chromosome lengths in this output to match those in your reference, however the lengths can match, but the version may still differ.

Known issue: this strategy will not work if more than 1 chromosome in the same genome has the same length.

-------

.. class:: infomark

**The usage scenario**

Suppose you want to use snpEff to annotate a VCF file that was generated using an mouse reference with a different chromosome naming convention than in the snpEff database. To do this you can:

    #. Use `SnpEff databases` to find the precise genome name for mouse data (e.g. "mm10") as it appears in the snpEff database.
    #. List the chromosome names using this tool.  Either select a built-in genome, one in your history, or select "Download on demand" and enter the genome version obtained in the previous step (which only actually downloads if snpEff doesn't already have it).
    #. Check that the chromosomes in the SnpEff database are the same as the reference you used (e.g. as a cursory check, ensure the chromosome lengths reported from the SnpEff database match those of your reference).
    #. Edit your vcf file to replace the chromosome names with the ones the SnpEff database uses.
    #. Use **SnpEff eff** and supply the edited VCF file.

    ]]></help>
    <expand macro="citations" />
</tool>