annotate wgmlst_add.xml @ 0:a3cc35af3635 draft

planemo upload for repository https://github.com/bvalot/pyMLST commit 13edfab02a5da9e374c38ecbd0e229ec0f8d53bb

<tool id="wgmlst_add_wrapper" name="Add strain to cg/wgMLST database" version="2.1.3">
  <description></description>
  <requirements>
	<requirement type="package" version="2.1.3">pymlst</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" level="fatal" />
  </stdio>
  <version_command>wgMLST -v</version_command>
  <command><![CDATA[
	cp '${database}' '${databaseout}' &&
    wgMLST 
	#if $data.input == "fasta"
	  add
	#else
	  add2
	#end if
	#if str($coverage)
	  -c $coverage
	#end if
	#if str($identity)
	  -i $identity
	#end if
	#if $data.input == "fasta"
	  #if $strain
	    -s '$strain'
	  #else
	    -s '$data.fastain.name.replace(" ", "_").replace("-", "_")'
	  #end if
      '${databaseout}' '${data.fastain}'
    #end if
	#if $data.input == "fastqsingle"
	  #if str($data.reads)
	    -r $data.reads
	  #end if
	  #if $strain
	    -s '$strain'
	  #else
	    -s '$data.single.name.replace(" ", "_").replace("-", "_")'
	  #end if
	  '${databaseout}' '${data.single}'
    #end if
	#if $data.input == "fastqpaired"
	  #if str($data.reads)
	    -r $data.reads
	  #end if
	  #if $strain
	    -s '$strain'
	  #else
	    -s '$data.forward.name.replace(" ", "_").replace("-", "_")'
	  #end if
      '${databaseout}' '${data.forward}' '${data.reverse}'
    #end if
	#if $data.input == "fastqpaired2"
	  #if str($data.reads)
	    -r $data.reads
	  #end if 
	  #if $strain
	    -s '$strain'
	  #else
	    -s '$data.pairedfile.name.replace(" ", "_").replace("-", "_")'
	  #end if
      '${databaseout}' '${data.pairedfile.forward}'
	  '${data.pairedfile.reverse}'
    #end if
	#if $log
	  2> '${logfile}'
	#end if
	]]>
  </command>
  <inputs>
	<param name="database" type="data"
           format="sqlite"
           label="cg/wgMLST database"
           help="Sqlite format from cg/wgMLST database" />
	<conditional name="data">
	  <param name="input" type="select" label="Select type of data">
        <option value="fasta" selected="true">Assembly (fasta)</option>
        <option value="fastqsingle">Raw data (single)</option>
        <option value="fastqpaired">Raw data (paired separated)</option>
        <option value="fastqpaired2">Raw data (paired)</option>
	  </param>
	  <when value="fasta">
        <param name="fastain" type="data" format="fasta"
               label="Assembly Genome" help="Fasta format" />
      </when>	  
	  <when value="fastqsingle">
        <param name="single" type="data" format="fastq,fastq.gz"
               label="Single read file" help="Fastq(gz) format" />
		<param name="reads" type="integer" value="10" optional="true"
               label="Minimum reads coverage to search gene" />
      </when>
	  <when value="fastqpaired">
        <param name="forward" type="data" format="fastq,fastq.gz"
               label="Forward read file" help="Fastq(gz) format" />
        <param name="reverse" type="data" format="fastq,fastq.gz"
               label="Reverse read file" help="Fastq(gz) format" />
		<param name="reads" type="integer" value="10" optional="true"
			   label="Minimum reads coverage to search gene" />
      </when>
	  <when value="fastqpaired2">
        <param name="pairedfile" type="data_collection" format="fastq,fastq.gz"
               label="Paired of read files" help="Fastq(gz) format"
               collection_type="paired" />
		<param name="reads" type="integer" value="10" optional="true"
			   label="Minimum reads coverage to search gene" />
	  </when>	
	</conditional>
	<param name="strain" type="text" value="" size="50"
		   optional="false"
		   label="Strain"
		   help="Name of the strain">
	  <sanitizer invalid_char="_" >
        <valid initial="string.ascii_letters,string.digits">
          <add value="_" />
		  <add value="." />
        </valid>
    </sanitizer>
	</param> 
	<param name="identity" type="float" value="0.9" optional="false"
		   label="Identity"
		   help="Minimum identity to search gene" />
	<param name="coverage" type="float" value="0.9" optional="false"
		   label="Coverage"
		   help="Minimum coverage to search gene" />
	<param name="log" type="boolean" checked="true"
           label="Write log file" />	
  </inputs>
  <outputs>
    <data name="databaseout" format="sqlite" label="${database.name}">
	</data>
    <data name="logfile" format="txt" label="${tool.name} on ${on_string}: log">
	  <filter>log</filter>
	</data>	
  </outputs>
  <tests>
	<test expect_num_outputs="2">
	  <param name="database" value="wgmlst_ecoli.db" />
	  <conditional name="data">
		<param name="input" value="fasta" />
		<param name="fastain" ftype="fasta" value="EHSB-021.fasta" />
	  </conditional>
	  <param name="identity" value="0.8" />
	  <output name="logfile" ftype="txt">
	  <assert_contents>
		<has_text text="Added 2497 new MLST genes to the database" />
		<has_text text="Found 32 partial genes, filled 30" />
		<has_text text="Removed 4 genes" />
	  </assert_contents>
	  </output>
	</test>
	<!-- <test expect_num_outputs="2"> -->
	<!--   <param name="database" value="wgmlst_ecoli.db" /> -->
	<!--   <param name="strain" value="EHSB-021" /> -->
	<!--   <conditional name="data"> -->
	<!-- 	<param name="input" value="fastqpaired" /> -->
	<!-- 	<param name="forward" ftype="fastq.gz" value="EHSB-021_R1.fastq.gz" /> -->
	<!-- 	<param name="reverse" ftype="fastq.gz" value="EHSB-021_R2.fastq.gz" /> -->
	<!-- 	<param name="reads" value="5" /> -->
	<!--   </conditional> -->
	<!--   <output name="logfile" ftype="txt"> -->
	<!--   <assert_contents> -->
	<!-- 	<has_text_matching expression="Add 24\d\d new MLST genes to database" /> -->
	<!-- 	<has_text_matching expression="Remove \d genes with uncertain bases" /> -->
	<!-- 	<has_text_matching expression="Remove \d\d genes with bad CDS" /> -->
	<!--   </assert_contents> -->
	<!--   </output> -->
	<!-- </test> -->
  </tests>
  <help>
**What it does**

Add a Strain to the cg/wgMLST database

You can use
- Genome assembly (blat search)
- Raw data (kma search)

**Options:**
  -s, --strain TEXT     Name of the strain (default:genome name).
  -i, --identity FLOAT   Minimum identity to search gene (default=0.9).
  -c, --coverage FLOAT   Minimum coverage to search gene (default=0.95).
  -r, --reads INTEGER    Minimum reads coverage to search gene (default=10).
  -f, --fasta FILENAME   Write fasta file with gene allele.

**License and citation**

This Galaxy tool is Copyright © 2022 `B. Valot` and is released under the `GPL3 license`.
  </help>
  <citations>
  </citations>
</tool>