view dada2_plotQualityProfile.xml @ 5:863ebf0d28d5 draft

planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/topic/dada2/tools/dada2 commit 990192685955e9cda0282e348c28ef6462d88a38

<tool id="dada2_plotQualityProfile" name="dada2: plotQualityProfile" version="@DADA2_VERSION@+galaxy@WRAPPER_VERSION@">
    <description>plot a visual summary of the quality scores</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
##name files by linking
#import re
#if "batch" in str($paired_cond.paired_select)
  #set elid = re.sub('[^\w\-\.]', '_', str($paired_cond.fl.element_identifier))
  #if "single" in str($paired_cond.paired_select)
    ln -s '$paired_cond.fl' '$elid' &&
  #else
    ln -s '$paired_cond.fl.forward' '$elid'_forward &&
    ln -s '$paired_cond.fl.reverse' '$elid'_reverse &&
  #end if
#else
  #for $read in $paired_cond.fl:
    #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
    #if "single" in str($paired_cond.paired_select)
      ln -s '$read' '$elid' &&
    #else
      ln -s '$read.forward' '$elid'_forward &&
      ln -s '$read.reverse' '$elid'_reverse &&
    #end if
  #end for
#end if
	
	Rscript --slave '$dada2_script'
    ]]></command>
    <configfiles>
        <configfile name="dada2_script"><![CDATA[
#import re
files = c()
#if "batch" in str($paired_cond.paired_select)
  #set elid = re.sub('[^\w\-\.]', '_', str($paired_cond.fl.element_identifier))
  #if "single" in str($paired_cond.paired_select)
    files = c(files, '$elid')
  #else
    files = c(files, paste('$elid', 'forward', sep = "_"))
    files = c(files, paste('$elid', 'reverse', sep = "_"))
  #end if
#else
  #for $read in $paired_cond.fl:
    #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
    #if "single" in str($paired_cond.paired_select)
      files = c(files, '$elid')
    #else
      files = c(files, paste('$elid', 'forward', sep = "_"))
      files = c(files, paste('$elid', 'reverse', sep = "_"))
    #end if
  #end for
#end if

library(ggplot2, quietly=T)
library(dada2, quietly=T)

qp <- plotQualityProfile(files,
#if str($n) != ""
    n=$n,
#end if
    aggregate = $aggregate)

ggsave('output.pdf', qp, width = 20,height = 15,units = c("cm"))
    ]]></configfile>
    </configfiles>
    <inputs>
        <conditional name="paired_cond">
            <param name="paired_select" type="select" label="Input data organisation and processing mode" help="Select if data is organized in a paired collection or not (note that the pairing of the data sets is not used by the tool); batch will create a separate pdf for each input data set or data set pair; non-batch will create one pdf containing a plot for each data set">
                <option value="paired">paired - non batch</option>
                <option value="single">single - non batch</option>
                <option value="paired_batch">paired - batch</option>
                <option value="single_batch">single - batch</option>
            </param>
            <when value="paired">
                <param argument="fl" type="data_collection" collection_type="list:paired" format="fastqsanger,fastqsanger.gz" label="Short read data"/>
            </when>
            <when value="single">
                <param argument="fl" type="data" multiple="true" format="fastqsanger,fastqsanger.gz" label="Short read data"/>
            </when>
            <when value="paired_batch">
                <param argument="fl" type="data_collection" collection_type="paired" format="fastqsanger,fastqsanger.gz" label="Short read data"/>
            </when>
            <when value="single_batch">
                <param argument="fl" type="data" format="fastqsanger,fastqsanger.gz" label="Short read data"/>
            </when>
        </conditional>
        <param argument="aggregate" type="boolean" label="Aggregate data" checked="True" truevalue="TRUE" falsevalue="FALSE" help="Create a single plot for all data sets (default) or a separate plot for each data set"/>
        <param argument="n" type="integer" value="500000" label="sample number" help="number of records to sample from the fastq file"/>
    </inputs>
    <outputs>
        <data name="output" format="pdf" from_work_dir="output.pdf"/>
    </outputs>
    <tests>
        <!-- paired non-batch, aggregate -->
        <test>
            <param name="aggregate" value="TRUE"/>
            <param name="paired_cond|paired_select" value="paired"/>
            <param name="paired_cond|fl">
                <collection type="list:paired">
                    <element name="F3D0_S188_L001">
                        <collection type="paired">
                            <element name="forward" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
                            <element name="reverse" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
                         </collection>
                    </element>
                </collection>
            </param>
            <output name="output" value="qualityProfileMultiple.pdf" ftype="pdf"/>
        </test>
        <!-- paired, batch, no aggregate-->
        <test>
            <param name="aggregate" value="FALSE"/>
            <param name="paired_cond|paired_select" value="paired_batch"/>
            <param name="paired_cond|fl">
                <collection type="paired">
                    <element name="forward" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
                    <element name="reverse" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
                </collection>
            </param>
            <output name="output" value="qualityProfile.pdf" ftype="pdf"/>
        </test>
        <!-- single, non-batch, aggregate -->
        <test>
            <param name="aggregate" value="TRUE"/>
            <param name="paired_cond|paired_select" value="single"/>
            <param name="paired_cond|fl" value="F3D0_S188_L001_R1_001.fastq.gz,F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="n" value="10000"/>
            <output name="output" value="qualityProfileSmallSample.pdf" ftype="pdf"/>
        </test>
        <!-- single, batch, no aggregate -->
        <test>
            <param name="aggregate" value="FALSE"/>
            <param name="paired_cond|paired_select" value="single_batch"/>
            <param name="paired_cond|fl" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="n" value="10000"/>
            <output name="output" value="qualityProfileSmallSample.pdf" ftype="pdf" compare="sim_size"/>
        </test>    </tests>
    <help><![CDATA[
Summary
.......

This function plots a visual summary of the distribution of quality scores as a function of sequence position for the input fastq datasets.

Details
.......

The distribution of quality scores at each position is shown as a grey-scale heat map, with dark colors corresponding to higher frequency. The plotted lines show positional summary statistics: green is the mean, orange is the median, and the dashed orange lines are the 25th and 75th quantiles. If the sequences vary in length, a red line will be plotted showing the percentage of reads that extend
to at least that position.

Note this tool ignores the pairing of the reads, but the data is just processed as list.
    ]]></help>
    <expand macro="citations"/>
</tool>