annotate nanocomp.xml @ 1:d4f671d70a65 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/nanocomp/ commit 9a1b66804467677804637fc471c7aa794ebc7a9b

<tool id="nanocomp" name="NanoComp" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.2">
	<description>Compare multiple runs of long read sequencing data and alignments.</description>
	<macros>
		<token name="@TOOL_VERSION@">1.25.3</token>
		<token name="@VERSION_SUFFIX@">0</token>
	</macros>
	<xrefs>
		<xref type="bio.tools">nanocomp</xref>
	</xrefs>
		<requirements>
			<requirement type="package" version="@TOOL_VERSION@">nanocomp</requirement>
		</requirements>
	<version_command>NanoComp -v</version_command>
	<command detect_errors="exit_code"><![CDATA[
 #import re
 ##link input file with names
  #for $file in $inputs.input_type.input_data
   #if '.' in str($file.name)
    #set $in_name = re.sub('[\-\:\s]', '_', str($file.name))
   #else
    #set $in_name = re.sub('[\-\:\s]', '_', str($file.name))  + "." + $file.ext
   #end if
   ln -sf $file $in_name &&
  #end for

 ##run nanocomp
  NanoComp

  ##no need for the static images (becomes deprecated)
  --make_no_static

 ## Compute options
  --threads \${GALAXY_SLOTS:-4}

 ##add input files
  #if $inputs.input_type.input_type_selector == "fastq"
   --fastq
  #else if $inputs.input_type.input_type_selector == "fastq_r" 
   --fastq_rich
  #else if $inputs.input_type.input_type_selector == "fasta"
   --fasta
  #else if $inputs.input_type.input_type_selector == "bam"
   --bam
  #else if $inputs.input_type.input_type_selector == "ubam"
   --ubam
  #else if $inputs.input_type.input_type_selector == "cram"
   --cram
  #else if $inputs.input_type.input_type_selector == "pickle"
   --pickle
  #else if $inputs.input_type.input_type_selector == "arrow"
   --arrow
  #end if

  #for $file in $inputs.input_type.input_data
   #if '.' in str($file.name)
    #set $in_name = re.sub('[\-\:\s]', '_', str($file.name))
   #else
    #set $in_name = re.sub('[\-\:\s]', '_', str($file.name))  + "." + $file.ext
   #end if
   $in_name
  #end for

 ##Filter options
  #if $filters.maxlength
    --maxlength $filters.maxlength
  #end if
  #if $filters.minlength
    --minlength $filters.minlength
  #end if

 ##Plot options
  #if $plot_options.plot
    --plot $plot_options.plot 
  #end if

  #if $plot_options.title
    --title "$plot_options.title"
  #end if

  #if $plot_options.names
    --names $plot_options.names
  #end if

  #if $plot_options.colors
    --colors $plot_options.colors
  #end if

 ##Output options
  #if $output_options.tsv_stats
    $output_options.tsv_stats
  #end if

  --verbose 
  >& $out_log

]]></command>
	<inputs>
		<section name="inputs" title="Input data" expanded="True"> 
			<conditional name="input_type">
				<param name="input_type_selector" type="select" label="Choose Input Format and Files">
					<option value="fastq" selected="true">FASTQ files</option>
					<option value="fastq_r">FASTQ-rich files</option>
					<option value="fasta">FASTA files</option>
					<option value="bam">BAM files</option>
					<option value="ubam">uBAM files</option>
					<option value="cram">CRAM files</option>
					<option value="pickle">PICKLE files</option>
					<option value="arrow">ARROW files</option>
				</param>
				<when value="fastq">
					<param name="input_data" type="data" format="fastq,fastq.gz" multiple="true" label="FASTQ input files" help="Data is in (compressed) fastq format" />
				</when>
				<when value="fastq_r">
					<param name="input_data" type="data" format="fastq,fastq.gz" multiple="true" label="FASTQ input files" help="Data is in one or more fastq file(s) generated by MinKNOW or guppy with additional information concerning channel and time" />
				</when>
				<when value="fasta">
					<param name="input_data" type="data" format="fasta,fasta.gz" multiple="true" label="FASTA input files" help="Data is in (compressed) fasta format" />
				</when>
				<when value="bam">
					<param name="input_data" type="data" format="bam" multiple="true" label="BAM input files" help="Data is in sorted bam files." />
				</when>
				<when value="ubam">
					<param name="input_data" type="data" format="bam" multiple="true" label="Unmapped BAM input files" help="Data is in one or more unmapped bam files." />
				</when>
				<when value="cram">
					<param name="input_data" type="data" format="cram" multiple="true" label="CRAM input files" help="Data is in sorted cram files." />
				</when>
				<when value="pickle">
					<param name="input_data" type="data" format="binary" multiple="true" label="PICKLE input files" help="Data is in one or more pickle file(s) from using NanoComp/NanoPlot." />
				</when>
				<when value="arrow">
					<param name="input_data" type="data" format="binary" multiple="true" label="ARROW input files" help="Data is in one or more feather/arrow file(s)." />
				</when>
			</conditional>
		</section>	

		<section name="filters" title="Filtering Input Prior To Plotting" expanded="false">
			<param argument="--maxlength" type="integer" optional="true" label="Max read length filtering" help="Drop reads longer than length specified." />
			<param argument="--minlength" type="integer" optional="true" label="Min read length filtering" help="Drop reads shorter than length specified." />
		</section>

		<section name="plot_options" title="Plot Customization Options" expanded="false">
			<param argument="--plot" type="select" label="Plot Type" help="Specify the type of plot to be used.">
				<option value="box">Box plot</option>
				<option value="violin" selected="true">Violin plot</option>
				<option value="ridge">Ridge (joyplot) plot</option>
				<option value="not">No plot</option>
			</param>
			<param argument="--title" type="text" label="Custom plot titles" help="Add a title to all plots." />
			<param argument="--names" type="text" label="Custom names" help="Specify the names (space seperated, respective to input) to be used for the datasets." />
			<param argument="--colors" type="text" label="Custom colors" help="Specify the colors (space seperated, respective to input) to be used for each the datasets. Can be any valid Matplotlib color: Named, HEX-string, RGB, ... " />
		</section>	

		<section name="output_options" title="Output Options" expanded="false">
			<param argument="--tsv_stats" type="boolean" truevalue="--tsv_stats" falsevalue="" optional="true" checked="false" label="TSV Output Format" help="Output the statistics file as properly formatted TSV."/>
		</section>

	</inputs>


	<outputs>
		<data name="out_log" format="txt" label="${tool.name} on ${on_string}: Log file"/>
		<data name="stats_file" format="txt" from_work_dir="NanoStats.txt" label="${tool.name} on ${on_string}: Statistics file"/>	
		<data name="html_report" format="html" from_work_dir="NanoComp-report.html" label="${tool.name} on ${on_string}: Html Report"/>	
	</outputs>
	<tests>
		<test expect_num_outputs="3">
			<section name="inputs">
				<conditional name="input_type">	
					<param name="input_type_selector" value="fastq" />
					<param name="input_data" value="in1.fastq.gz,in2.fastq.gz,in3.fastq.gz" />
				</conditional>
			</section>
			<output name="stats_file" > 
				<assert_contents>
					<has_text text="General summary" />
				</assert_contents>
			</output>
			<output name="html_report"> 
				<assert_contents>
					<has_text text="html"/>
					<has_text text="Summary statistics"/>
				</assert_contents>
			</output>
		</test>
		<test expect_num_outputs="3">
			<section name="inputs">
				<conditional name="input_type">
					<param name="input_type_selector" value="bam" />
					<param name="input_data" value="in4.bam,in5.bam" />
				</conditional>
			</section>
			<section name="filters" >
				<param name="maxlength" value="15000"/>
				<param name="minlength" value="500"/>
			</section>
			<output name="html_report">
				<assert_contents>
					<has_text text="html"/>
					<has_text text="Summary statistics"/>
				</assert_contents>
			</output>
		</test>
		<test expect_num_outputs="3">
			<section name="inputs">
				<conditional name="input_type">	
					<param name="input_type_selector" value="fastq" />
					<param name="input_data" value="in1.fastq.gz,in3.fastq.gz" />
				</conditional>
			</section>
			<section name="output_options">
				<param name="tsv_stats" value="true"/>
			</section>
			<output name="stats_file" > 
			<assert_contents>
				<has_text text="Metrics" />
			</assert_contents>
			</output>
		</test>
		<test expect_num_outputs="3">
			<section name="inputs">
				<conditional name="input_type">
					<param name="input_type_selector" value="bam" />
					<param name="input_data" value="in4.bam,in5.bam" />
				</conditional>
			</section>
			<section name="plot_options" >
		<param name="plot" value="box"/>
			</section>
			<output name="html_report">
				<assert_contents>
					<has_text text="html"/>
					<has_text text="Plots"/>
				</assert_contents>
			</output>
		</test>
	</tests>
	<help><![CDATA[
**NanoComp** 

Compare multiple runs of long read sequencing data and alignments. Creates violin plots or box plots of length, quality and percent identity and creates dynamic, overlaying read length histograms and a cumulative yield plot.

**Usage Instructions**  

Multiple input files (of the same type) are allowed

**Output Files**  

HTML file with the stats report and associated plots

**More Information**  

- **Official Repository**: [GitHub - wdecoster/nanocomp](https://github.com/wdecoster/nanocomp)  
]]></help>
	<citations>
		<citation type="doi">10.1093/bioinformatics/btad311</citation>
	</citations>
</tool>