view vsnp_statistics.xml @ 19:ae006e01b0fa draft

"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 858ccc1b3f72e286f34819d84de52d2e158d6d78"
author greg
date Wed, 04 Aug 2021 13:36:36 +0000
parents 076069733de7
children d4ef7003c539
line wrap: on
line source

<tool id="vsnp_statistics" name="vSNP: statistics" version="@WRAPPER_VERSION@.2+galaxy0" profile="@PROFILE@">
    <description></description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <expand macro="biopython_requirement"/>
        <expand macro="numpy_requirement"/>
        <expand macro="openpyxl_requirement"/>
        <expand macro="pandas_requirement"/>
        <expand macro="xlrd_requirement"/>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
#import re

#if $input_type_cond.input_type in ["single", "pair"]:
    #set read1 = $input_type_cond.read1
    #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.element_identifier))
    ln -s '${read1}' '${read1_identifier}' &&
    #if $input_type_cond.input_type == "pair":
        #set read2 = $input_type_cond.read2
        #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.element_identifier))
        ln -s '${read2}' '${read2_identifier}' &&
    #end if
#else:
    #set identifier = re.sub('[^\s\w\-]', '_', str($input_type_cond.reads_collection.element_identifier))
    #set read1 = $input_type_cond.reads_collection.forward
    #set read1_identifier = $identifier + '_R1'
    ln -s '${read1}' '${read1_identifier}' &&
    #set read2 = $input_type_cond.reads_collection.reverse
    #set read2_identifier = $identifier + '_R2'
    ln -s '${read2}' '${read2_identifier}' &&
#end if

python '$__tool_directory__/vsnp_statistics.py'
--read1 '${read1_identifier}'
#if $input_type_cond.input_type in ["pair", "paired"]:
  --read2 '${read2_identifier}'
#end if
#if $read1.is_of_type('fastqsanger.gz'):
    --gzipped
#end if
--dbkey '$samtools_idxstats.metadata.dbkey'
--samtools_idxstats '$samtools_idxstats'
--vsnp_azc_metrics '$vsnp_azc_metrics'
--output '$output'
]]></command>
    <inputs>
        <conditional name="input_type_cond">
            <param name="input_type" type="select" label="Choose the category of the files to be analyzed">
                <option value="single" selected="true">Single files</option>
                <option value="paired">Paired reads</option>
                <option value="pair">Paired reads in separate data sets</option>
            </param>
            <when value="single">
                <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/>
            </when>
            <when value="paired">
                <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of fastqsanger paired read files"/>
            </when>
            <when value="pair">
                <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/>
                <param name="read2" type="data" format="fastqsanger.gz,fastqsanger" label="Read2 fastq file"/>
            </when>
        </conditional>
        <param name="samtools_idxstats" type="data" format="tabular" label="Samtools idxstats file"/>
        <param name="vsnp_azc_metrics" type="data" format="tabular" label="vSNP: add zero coverage metrics file"/>
    </inputs>
    <outputs>
        <data name="output" format="tabular"/>
    </outputs>
    <tests>
        <!-- A single fastq file -->
        <test expect_num_outputs="1">
            <param name="input_type" value="single"/>
            <param name="read1" value="Mcap_Deer_DE_SRR650221.fastq.gz" ftype="fastqsanger.gz" dbkey="89"/>
            <param name="samtools_idxstats" value="samtools_idxstats1.tabular" ftype="tabular" dbkey="89"/>
            <param name="vsnp_azc_metrics" value="add_zc_metrics1.tabular" ftype="tabular" dbkey="89"/>
            <output name="output" file="vsnp_statistics1.tabular" ftype="tabular"/>
        </test>
        <!-- A set of paired fastq files -->
        <test expect_num_outputs="1">
            <param name="input_type" value="pair"/>
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz" dbkey="89"/>
            <param name="read2" value="13-1941-6_S4_L001_R2_600000.fastq.gz" ftype="fastqsanger.gz" dbkey="89"/>
            <param name="samtools_idxstats" value="samtools_idxstats2.tabular" ftype="tabular" dbkey="89"/>
            <param name="vsnp_azc_metrics" value="add_zc_metrics2.tabular" ftype="tabular" dbkey="89"/>
            <output name="output" file="vsnp_statistics2.tabular" ftype="tabular"/>
        </test>
        <!-- A collection of paired fastq files -->
        <test expect_num_outputs="1">
            <param name="input_type" value="paired"/>
            <param name="reads_collection">
                <collection type="paired">
                    <element name="forward" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz"/>
                    <element name="reverse" value="13-1941-6_S4_L001_R2_600000.fastq.gz" ftype="fastqsanger.gz"/>
                </collection>
            </param>
            <param name="samtools_idxstats" value="samtools_idxstats5.tabular" ftype="tabular" dbkey="89"/>
            <param name="vsnp_azc_metrics" value="add_zc_metrics5.tabular" ftype="tabular" dbkey="89"/>
            <output name="output" file="vsnp_statistics4.tabular" ftype="tabular"/>
        </test>
    </tests>
    <help>
**What it does**

Accepts associated fastq files, SAMtools idxstats files and **vSNP: add zero coverage** metrics files and extracts information from them
to produce an Excel spreadsheet containing statistics for each sample.  The samples can be a single read, a single set of paired reads in
separate datasets or  collection of paired reads.  The output statistics include reference, file size, mean read length, mean read quality,
reads passing Q30, total reads, all mapped reads, unmapped reads, unmapped reads percentage of total, reference with coverage, average depth
of coverage and good SNP count.
    </help>
    <expand macro="citations"/>
</tool>