comparison dada2_plotQualityProfile.xml @ 9:d908015e5889 draft

planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/topic/dada2/tools/dada2 commit a54770771e567c7ad8a9dd75cc4689c3935ef11c

8:7970dfbedde3

    <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 '$dada2_script'
    ]]></command>
    <configfiles>
        <configfile name="dada2_script"><![CDATA[
#import re
fwd_files = c()
rev_files = c()
#if "batch" in str($paired_cond.paired_select)
  #set elid = re.sub('[^\w\-\.]', '_', str($paired_cond.fl.element_identifier))
  #if "single" in str($paired_cond.paired_select)
    fwd_files = c(fwd_files, '$elid')
  #else
    fwd_files = c(fwd_files, paste('$elid', 'forward', sep = "_"))
    rev_files = c(rev_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($paired_cond.paired_select)
      fwd_files = c(fwd_files, '$elid')
    #else
      fwd_files = c(fwd_files, paste('$elid', 'forward', sep = "_"))
      rev_files = c(rev_files, paste('$elid', 'reverse', sep = "_"))
    #end if
  #end for
#end if

#if not "batch" in str($paired_cond.paired_select)
agg = $paired_cond.aggregate
#else
agg = FALSE
#end if

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

qp <- plotQualityProfile(fwd_files,
#if str($n) != ""
    n=$n,
#end if
    aggregate = agg)
ggsave('output.pdf', qp, width = 20,height = 15,units = c("cm"))

#if "paired" in str($paired_cond.paired_select)
qp <- plotQualityProfile(rev_files,
#if str($n) != ""
    n=$n,
#end if
    aggregate = agg)
ggsave('output_rev.pdf', qp, width = 20,height = 15,units = c("cm"))
#end if
    ]]></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="fastq,fastq.gz" label="Short read data"/>
                <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"/>
            </when>
            <when value="single">
                <param argument="fl" type="data" multiple="true" format="fastq,fastq.gz" label="Short read data"/>
                <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"/>
            </when>
            <when value="paired_batch">
                <param argument="fl" type="data_collection" collection_type="paired" format="fastq,fastq.gz" label="Short read data"/>
            </when>
            <when value="single_batch">
                <param argument="fl" type="data" format="fastq,fastq.gz" label="Short read data"/>
            </when>
        </conditional>
        <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">
            <filter>"single" in paired_cond['paired_select']</filter>
		</data>
		<data name="output_fwd" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: forward reads">
            <filter>"paired" in paired_cond['paired_select']</filter>
        </data>
		<data name="output_rev" format="pdf" from_work_dir="output_rev.pdf" label="${tool.name} on ${on_string}: reverse reads">
            <filter>"paired" in paired_cond['paired_select']</filter>
        </data>
    </outputs>
    <tests>
        <!-- paired non-batch, aggregate -->
        <test>
            <param name="paired_cond|paired_select" value="paired"/>
            <param name="paired_cond|aggregate" value="TRUE"/>
            <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_fwd" value="qualityProfileMultiple.pdf" ftype="pdf"/>
            <output name="output_rev" value="qualityProfileMultiple_rev.pdf" ftype="pdf"/>
        </test>
        <!-- paired, batch, no aggregate-->
        <test>
            <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_fwd" value="qualityProfile.pdf" ftype="pdf"/>
            <output name="output_rev" value="qualityProfile_rev.pdf" ftype="pdf"/>
        </test>
        <!-- single, non-batch, aggregate -->
        <test>
            <param name="paired_cond|paired_select" value="single"/>
            <param name="paired_cond|aggregate" value="TRUE"/>
            <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>

9:d908015e5889

    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
##name files by linking
#import re
mkdir forward &&
#if $batch_cond.paired_cond.paired_select != "single"
    mkdir reverse &&
#end if

#if $batch_cond.batch_select == "batch":
    #set elid = re.sub('[^\w\-\.]', '_', str($batch_cond.paired_cond.reads.element_identifier))
    #if $batch_cond.paired_cond.paired_select != "paired"
        ln -s '$batch_cond.paired_cond.reads' forward/'$elid' &&
    #else
        ln -s '$batch_cond.paired_cond.reads.forward' forward/'$elid' &&
        ln -s '$batch_cond.paired_cond.reads.reverse' reverse/'$elid' &&
    #end if
    #if $batch_cond.paired_cond.paired_select == "separate"
        ln -s '$batch_cond.paired_cond.sdaer' reverse/'$elid' &&
    #end if
#else
    #for $read in $batch_cond.paired_cond.reads:
        #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
        #if $batch_cond.paired_cond.paired_select != "paired"
            ln -s '$read' forward/'$elid' &&
        #else
            ln -s '$read.forward' forward/'$elid' &&
            ln -s '$read.reverse' reverse/'$elid' &&
        #end if
    #end for
    #if $batch_cond.paired_cond.paired_select == "separate"
        #for $read in $batch_cond.paired_cond.sdaer:
            #set elid = re.sub('[^\w\-\.]', '_', str($read.element_identifier))
            ln -s '$read' reverse/'$elid' &&
        #end for
    #end if
#end if

    Rscript --slave '$dada2_script'
    ]]></command>
    <configfiles>
        <configfile name="dada2_script"><![CDATA[
#import re
library(ggplot2, quietly=T)
library(dada2, quietly=T)

#if $batch_cond.batch_select != "batch"
agg = $batch_cond.aggregate
#else
agg = FALSE
#end if

fwd_files = list.files("forward", full.names=T)
qp <- plotQualityProfile(fwd_files, n=$n, aggregate = agg)
ggsave('output.pdf', qp, width = 20,height = 15,units = c("cm"))

#if $batch_cond.paired_cond.paired_select != "single"
rev_files = list.files("reverse", full.names=T)
qp <- plotQualityProfile(rev_files, n=$n, aggregate = agg)
ggsave('output_rev.pdf', qp, width = 20,height = 15,units = c("cm"))
#end if
    ]]></configfile>
    </configfiles>
    <inputs>
        <conditional name="batch_cond">
            <param name="batch_select" type="select" label="Processing mode" help="Joint processing processes all reads at once in a single job creating a single output (two in the case of paired data). Batch processes the samples in separate jobs and creates separate output for each">
                <option value="joint">Joint</option>
                <option value="batch">Batch</option>
            </param>
            <when value="joint">
                <expand macro="fastq_input" multiple="True" collection_type="list:paired" argument_fwd="fl" argument_rev="fl"/>
                <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"/>
            </when>
            <when value="batch">
                <expand macro="fastq_input" multiple="False" collection_type="paired" argument_fwd="fl" argument_rev="fl"/>
            </when>
        </conditional>
        <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">
            <filter>batch_cond['paired_cond']['paired_select'] == "single"</filter>
        </data>
        <data name="output_fwd" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: forward reads">
            <filter>batch_cond['paired_cond']['paired_select'] != "single"</filter>
        </data>
        <data name="output_rev" format="pdf" from_work_dir="output_rev.pdf" label="${tool.name} on ${on_string}: reverse reads">
            <filter>batch_cond['paired_cond']['paired_select'] != "single"</filter>
        </data>
    </outputs>
    <tests>
        <!-- paired joint, no-aggregate -->
        <test expect_num_outputs="2">
            <param name="batch_cond|batch_select" value="joint"/>
            <param name="batch_cond|paired_cond|paired_select" value="paired"/>
            <param name="batch_cond|paired_cond|reads">
                <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>
            <param name="batch_cond|aggregate" value="FALSE"/>
            <output name="output_fwd" value="qualityProfileMultiple.pdf" ftype="pdf"/>
            <output name="output_rev" value="qualityProfileMultiple_rev.pdf" ftype="pdf"/>
        </test>
        <!-- paired-separate joint, no-aggregate (sim_size because element ids differ) -->
        <test expect_num_outputs="2">
            <param name="batch_cond|batch_select" value="joint"/>
            <param name="batch_cond|paired_cond|paired_select" value="separate"/>
            <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="batch_cond|paired_cond|sdaer" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="batch_cond|aggregate" value="FALSE"/>
            <output name="output_fwd" value="qualityProfileMultiple.pdf" ftype="pdf" compare="sim_size"/>
            <output name="output_rev" value="qualityProfileMultiple_rev.pdf" ftype="pdf" compare="sim_size"/>
        </test>
        <!-- single, non-batch, aggregate, small sample -->
        <test expect_num_outputs="1">
            <param name="batch_cond|batch_select" value="joint"/>
            <param name="batch_cond|paired_cond|paired_select" value="single"/>
            <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz,F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="n" value="10000"/>
            <param name="batch_cond|aggregate" value="TRUE"/>
            <output name="output" value="qualityProfileSmallSample.pdf" ftype="pdf"/>
        </test>

        <!-- paired, batch -->
        <test expect_num_outputs="2">
            <param name="batch_cond|batch_select" value="batch"/>
            <param name="batch_cond|paired_cond|paired_select" value="paired"/>
            <param name="batch_cond|paired_cond|reads">
                <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_fwd" value="qualityProfile.pdf" ftype="pdf"/>
            <output name="output_rev" value="qualityProfile_rev.pdf" ftype="pdf"/>
        </test>
        <!-- paired-separate batch  (sim_size because element ids differ)-->
        <test expect_num_outputs="2">
            <param name="batch_cond|batch_select" value="batch"/>
            <param name="batch_cond|paired_cond|paired_select" value="separate"/>
            <param name="batch_cond|paired_cond|reads" value="F3D0_S188_L001_R1_001.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="batch_cond|paired_cond|sdaer" value="F3D0_S188_L001_R2_001.fastq.gz" ftype="fastqsanger.gz"/>
            <output name="output_fwd" value="qualityProfile.pdf" ftype="pdf" compare="sim_size"/>
            <output name="output_rev" value="qualityProfile_rev.pdf" ftype="pdf" compare="sim_size"/>
        </test>
        <!-- single, batch -->
        <test expect_num_outputs="1">
            <param name="batch_cond|batch_select" value="batch"/>
            <param name="batch_cond|paired_cond|paired_select" value="single"/>
            <param name="batch_cond|paired_cond|reads" 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.
    ]]></help>
    <expand macro="citations"/>
</tool>