annotate vsnp_get_snps.xml @ 1:9ac0b1d5560d draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/vsnp commit 2a94c64d6c7236550bf483d2ffc4e86248c63aab"

<tool id="vsnp_get_snps" name="vSNP: get SNPs" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description></description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <expand macro="openpyxl_requirement"/>
        <expand macro="pandas_requirement"/>
        <expand macro="pyvcf_requirement"/>
        <expand macro="xlrd_requirement"/>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
#import re

#set input_vcf_dir = 'input_vcf_dir'
#set output_json_avg_mq_dir = 'output_json_avg_mq_dir'
#set output_json_snps_dir = 'output_json_snps_dir'
#set output_snps_dir = 'output_snps_dir'

mkdir -p $input_vcf_dir &&
mkdir -p $output_json_avg_mq_dir &&
mkdir -p $output_json_snps_dir &&
mkdir -p $output_snps_dir &&

#if str($input_additional_zc_vcf_collection_cond.input_additional_zc_vcf_collection) =='yes':
    #set dbkey = '?'
    #for $i in $input_additional_zc_vcf_collection_cond.input_vcf_collection:
        #if str($dbkey) == '?':
            #set dbkey = $i.metadata.dbkey
        #else if str($dbkey) != $i.metadata.dbkey:
            >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique, check ${i.name}" && exit 1
        #end if
        #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier))
        ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' &&
    #end for
    #if str($dbkey) == '?':
        >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1
    #end if
#end if
#if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single":
    #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier))
    ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' &&
#else
    #for $i in $input_zc_vcf_type_cond.input_zc_vcf_collection:
        #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier))
        ln -s '${i}' '$input_vcf_dir/${zc_vcf_identifier}' &&
    #end for
#end if
#if str($input_excel_cond.input_excel_param) == 'yes':
    #if str($input_excel_cond.excel_source_cond.excel_source) == 'cached':
        #set excel_file = 'No genome specified for input VCF (database) file(s)'
        #set excel_fields = $__app__.tool_data_tables['vsnp_excel'].get_fields()
        ## The value of excel_fields is a nested list that looks like this.
        ## [['AF2122', 'Mbovis_define_filter.xlsx', '~/tool-data/vsnp/AF2122/excel/Mbovis_define_filter.xlsx', 'Excel file for AF2122'],...]
        #for $i in $excel_fields:
            #if str($i[0]) == $dbkey:
                #set excel_file = $i[2]
                #break
            #end if
        #end for
    #else:
        #set excel_file = $input_excel_cond.excel_source_cond.input_excel
    #end if
#end if
python '$__tool_directory__/vsnp_get_snps.py'
--ac $ac
#if str($input_excel_cond.input_excel_param) == 'yes':
    --input_excel '$excel_file'
#end if
$all_isolates
--input_vcf_dir '$input_vcf_dir'
--min_mq $min_mq
--min_quality_score $min_quality_score
--output_json_avg_mq_dir '$output_json_avg_mq_dir'
--output_json_snps_dir '$output_json_snps_dir'
--output_snps_dir '$output_snps_dir'
--output_summary '$output_summary'
--processes \${GALAXY_SLOTS:-8}
--quality_score_n_threshold $quality_score_n_threshold
--dbkey '$dbkey'
]]></command>
    <inputs>
        <conditional name="input_zc_vcf_type_cond">
            <param name="input_zc_vcf_type" type="select" label="Choose the category of the files to be analyzed">
                <option value="collection" selected="true">A collection of zero coverage VCF files</option>
                <option value="single">A single zero coverage VCF file</option>
            </param>
            <when value="single">
                <param name="input_zc_vcf" type="data" format="vcf" label="Zero coverage VCF file"/>
            </when>
            <when value="collection">
                <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/>
            </when>
        </conditional>
        <conditional name="input_additional_zc_vcf_collection_cond">
            <param name="input_additional_zc_vcf_collection" type="select" label="Include an additional collection of curated zero-coverage VCF files?">
                <option value="no" selected="true">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="no"/>
            <when value="yes">
                <param name="input_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files with SNPs found in closely related isolate groups"/>
            </when>
        </conditional>
        <param name="ac" type="integer" min="0" value="2" label="Allele count threshold" help="At least 1 position must have this value for a SNP to be added to a group"/>
        <param name="min_mq" type="integer" min="0" value="56" label="Map quality threshold" help="At least 1 position must have a higher MQ value for a SNP to be added to a group"/>
        <param name="min_quality_score" type="integer" min="0" value="150" label="Quality score threshold" help="At least 1 position must have a higher quality score for a SNP to be added to a group"/>
        <param name="quality_score_n_threshold" type="integer" min="0" value="150" label="Minimum quality score N value for alleles" help="Alleles are marked as N for quality scores between this value and the minimum quality score value above"/>
        <conditional name="input_excel_cond">
            <param name="input_excel_param" type="select" label="Use Excel file for grouping and filtering?">
                <option value="yes" selected="true">Yes</option>
                <option value="no">No</option>
            </param>
            <when value="yes">
                <conditional name="excel_source_cond">
                    <param name="excel_source" type="select" label="Choose the source for the Excel file">
                        <option value="cached">locally cached</option>
                        <option value="history">from history</option>
                    </param>
                    <when value="cached">
                        <param name="input_excel" type="select" label="Excel file">
                            <options from_data_table="vsnp_excel">
                                <validator type="no_options" message="No built-in Excel grouping and filtering datasets are available"/>
                            </options>
                        </param>
                    </when>
                    <when value="history">
                        <param name="input_excel" type="data" format="xlsx" label="Excel file"/>
                    </when>
                </conditional>
            </when>
            <when value="no"/>
        </conditional>
        <param name="all_isolates" type="boolean" truevalue="--all_isolates" falsevalue="" checked="true" label="Create a group containing all isolates?"/>
    </inputs>
    <outputs>
        <collection name="snps" type="list" label="${tool.name} on ${on_string} (SNPs)">
            <discover_datasets pattern="__name_and_ext__" directory="output_snps_dir"/>
        </collection>
        <collection name="json_avg_mq" type="list" label="${tool.name} on ${on_string} (average mq)">
            <discover_datasets pattern="__name_and_ext__" directory="output_json_avg_mq_dir"/>
        </collection>
        <collection name="json_snps" type="list" label="${tool.name} on ${on_string} (SNPs as json)">
            <discover_datasets pattern="__name_and_ext__" directory="output_json_snps_dir"/>
        </collection>
        <data name="output_summary" format="html" label="${tool.name} on ${on_string} (summary)"/>
    </outputs>
    <tests>
        <!--
            Unfortunately the test files cannot be gzipped since Galaxy changes the file names
            to be something like 00-0121_WI_Cervid_99-A_vcf_gz, and the VCF Reader requires
            gzipped files to have a .gz extension.  The exception is
            UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte
        -->
        <!-- A single vcf input, no excel file, all_isolates is False -->
        <test expect_num_outputs="4">
            <param name="input_zc_vcf_type" value="single"/>
            <param name="input_zc_vcf" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/>
            <param name="input_additional_zc_vcf_collection" value="yes"/>
            <param name="input_vcf_collection">
                <collection type="list">
                    <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/>
                    <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_excel_param" value="no"/>
            <param name="all_isolates" value=""/>
            <output_collection name="snps" type="list" count="1">
                <element name="all_vcf" ftype="fasta">
                    <assert_contents>
                        <has_size value="150"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_avg_mq" type="list" count="1">
                <element name="all_vcf" ftype="json">
                    <assert_contents>
                        <has_size value="551"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_snps" type="list" count="1">
                <element name="all_vcf" ftype="json">
                    <assert_contents>
                        <has_size value="876"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="output_summary" ftype="html">
                <assert_contents>
                    <has_size value="303"/>
                </assert_contents>
            </output>
        </test>
        <!-- An input collection, no excel file, all_isolates is False -->
        <test expect_num_outputs="4">
            <param name="input_zc_vcf_type" value="collection"/>
            <param name="input_zc_vcf_collection">
                <collection type="list">
                    <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/>
                    <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_additional_zc_vcf_collection" value="yes"/>
            <param name="input_vcf_collection">
                <collection type="list">
                    <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/>
                    <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/>
                    <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_excel_param" value="no"/>
            <param name="all_isolates" value=""/>
            <output_collection name="snps" type="list" count="1">
                <element name="all_vcf" ftype="fasta">
                    <assert_contents>
                        <has_size value="5226"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_avg_mq" type="list" count="1">
                <element name="all_vcf" ftype="json">
                    <assert_contents>
                        <has_size value="24332"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_snps" type="list" count="1">
                <element name="all_vcf" ftype="json">
                    <assert_contents>
                        <has_size value="38798"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="output_summary" ftype="html">
                <assert_contents>
                    <has_size value="303"/>
                </assert_contents>
            </output>
        </test>
        <!-- An input collection, an excel file, all_isolates is False -->
        <test expect_num_outputs="4">
            <param name="input_zc_vcf_type" value="collection"/>
            <param name="input_zc_vcf_collection">
                <collection type="list">
                    <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/>
                    <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_additional_zc_vcf_collection" value="yes"/>
            <param name="input_vcf_collection">
                <collection type="list">
                    <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/>
                    <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/>
                    <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_excel_param" value="yes"/>
            <param name="input_excel" value="89"/>
            <param name="all_isolates" value=""/>
            <output_collection name="snps" type="list" count="1">
                <element name="Mbovis-17" ftype="fasta">
                    <assert_contents>
                        <has_size value="749"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_avg_mq" type="list" count="1">
                <element name="Mbovis-17" ftype="json">
                    <assert_contents>
                        <has_size value="10884"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_snps" type="list" count="1">
                <element name="Mbovis-17" ftype="json">
                    <assert_contents>
                        <has_size value="6396"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="output_summary" ftype="html">
                <assert_contents>
                    <has_size value="1057"/>
                </assert_contents>
            </output>
        </test>
        <!-- An input collection, an excel file, all_isolates is True -->
        <test expect_num_outputs="4">
            <param name="input_zc_vcf_type" value="collection"/>
            <param name="input_zc_vcf_collection">
                <collection type="list">
                    <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/>
                    <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_additional_zc_vcf_collection" value="yes"/>
            <param name="input_vcf_collection">
                <collection type="list">
                    <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/>
                    <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/>
                    <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_excel_param" value="yes"/>
            <param name="input_excel" value="89"/>
            <param name="all_isolates" value="--all_isolates"/>
            <output_collection name="snps" type="list" count="2">
                <element name="Mbovis-17" ftype="fasta">
                    <assert_contents>
                        <has_size value="749"/>
                    </assert_contents>
                </element>
                <element name="all_vcf" ftype="fasta">
                    <assert_contents>
                        <has_size value="4920"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_avg_mq" type="list" count="2">
                <element name="Mbovis-17" ftype="json">
                    <assert_contents>
                        <has_size value="10884"/>
                    </assert_contents>
                </element>
                <element name="all_vcf" ftype="json">
                    <assert_contents>
                        <has_size value="24332"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="json_snps" type="list" count="2">
                <element name="Mbovis-17" ftype="json">
                    <assert_contents>
                        <has_size value="6396"/>
                    </assert_contents>
                </element>
                <element name="all_vcf" ftype="json">
                    <assert_contents>
                        <has_size value="36466"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="output_summary" ftype="html">
                <assert_contents>
                    <has_size value="1056"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
**What it does**

Accepts a zero coverage VCF file produced by the **vSNP: add zero coverage** tool (or a collection of them) along with a collection
of zero coverage VCF files that have been aligned with the same reference and contain SNPs called between closely related isolate groups.
The tool produces fasta files containing SNP alignments, json files containing the SNP positions and additional json files containing
the average map quality values.

The SNP alignments produced by this tool are used to create phylogenetic trees, so larger input collections result in more populated
phylogenetic trees.  Both of the json outputs are used by the **vSNP: build tables** tool to produce annotated SNP tables in the form
of Excel spreadsheets.

An Excel spreadsheet containing specified SNPs can optiomally be used to filter desired SNP positions by group.  Users can choose a
locally cached Excel spreadsheet or one from their current history.

A SNP is added to a group if it has at least one position with a specified allele count value, a quality score greater than a specified
value, and a map quality greater than a specified value.

If the allele count equals the specified value (2) and the quality score for a SNP position is greater than the minimum quality score
value (150), the alternate allele is called.

However, if the allele count is 1, the position is called ambiguous.  Deletions are called when the alternate allele is a gap.  If the
quality score is less than or equal to the minimum quality score N value for alleles (150), the allele is marked "N".

**Required Options**

 * **Zero coverage VCF file(s)** - Select a single or collection of zero coverage VCF files, typically produced by the **vSNP: add zero coverage** tool, from the current history.
 * **Collection of zero coverage VCF files with SNPs found in closely related isolate groups** - Select a dataset collection of zero coverage vcf files from the current history.

**Additional Options**

 * **Allele count threshold** - At least 1 position must have an allele count greater than this value for a SNP to be added to a group (2 is optimal).
 * **Map quality threshold** - At least 1 position must have a higher MQ value for a SNP to be added to a group (56 is optimal).
 * **Quality score threshold** -At least 1 position must have a higher quality score for a SNP to be added to a group (150 is optimal).
 * **Minimum quality score N value for alleles** - If none of the avove 3 requirements is met and the quality score is less than or equal to the minimum quality score N value for alleles, the allele is marked "N" (150 is optimal).
 * **Use Excel file for grouping and filtering?** - select Yes to filter desired SNP positions by group.  A cached Excel spreadsheet provides the most widely used SNP positions for grouping, but a custom spreadhseet can be selected from the current history.
 * **Create a group containing all isolates?** - select Yes to output an additional group containing of all isolates.
</help>
    <expand macro="citations"/>
</tool>