comparison repex_full_clustering.xml @ 7:65d1a27e9339 draft default tip

planemo upload commit ccbd120278facd9aa39c1c46665ee994ebd3cff2-dirty

6:335d138b654b

<tool id="repeatexplorer2" name="RepeatExplorer2 clustering: " version="2.3.8.1" >
    <stdio>
      <regex match="lastdb: can't open file: NEAR" source="stderr" level="fatal" description="Version of last is too old, use ver 956 or higher\n" />
      <regex match="Traceback" source="stderr" level="fatal" description="Unknown error" />
      <regex match="error" source="stderr" level="fatal" description="Unknown error" />
      <regex match="Warning" source="stderr" level="warning" description="Unknown error" />
      <exit_code range="1:" level="fatal" description="Error" />
    </stdio>
    <description>Improved version or repeat discovery and characterization using graph-based sequence clustering</description>
   <requirements>
     <requirement type="package">last</requirement>
     <requirement type="package">imagemagick</requirement>
     <requirement type="package">mafft</requirement>
     <requirement type="package">blast</requirement>
     <requirement type="package" version="0.9.29" >diamond</requirement>
     <requirement type="package">blast-legacy</requirement>
     <requirement type="package">r-igraph</requirement>
     <requirement type="package">r-data.tree</requirement>
     <requirement type="package">r-stringr</requirement>
     <requirement type="package">r-r2html</requirement>
     <requirement type="package">r-hwriter</requirement>
     <requirement type="package">r-dt</requirement>
     <requirement type="package">r-scales</requirement>
     <requirement type="package">r-plotrix</requirement>
     <requirement type="package">r-png</requirement>
     <requirement type="package">r-plyr</requirement>
     <requirement type="package">r-dplyr</requirement>
     <requirement type="package">r-optparse</requirement>
     <requirement type="package">r-dbi</requirement>
     <requirement type="package">r-rsqlite</requirement>
     <requirement type="package">r-rserve</requirement>
     <requirement type="package">bioconductor-biostrings</requirement>
     <requirement type="package" version="2.3.8.1">repex_tarean</requirement>
     <requirement type="set_environment">REPEX</requirement>
     <requirement type="set_environment">REPEX_VERSION</requirement>
     <requirement type="package" version="0.9.1" >pyrserve</requirement>
   </requirements>
    <command >
      export PYTHONHASHSEED=0;
      \${REPEX}/seqclust --sample ${read_sampling.sample} --output_dir=tarean_output --logfile=${log} --cleanup $paired --taxon $taxon

      #if $advanced_options.advanced:
      --mincl $advanced_options.size_threshold $advanced_options.keep_names $advanced_options.automatic_filtering  -D $advanced_options.blastx.options_blastx
      --assembly_min $advanced_options.assembly_min_cluster_size

      ${FastaFile}  >stdout.log 2> stderr.log ;
      echo "STDOUT CONTENT:" >> ${log} ;
      cat stdout.log >> ${log} ;
      echo "STDERR CONTENT:" >> ${log};
      cat stderr.log >> ${log} &&
      \${REPEX}/stderr_filter.py stderr.log &&
      cd tarean_output &&
      zip -r  ${ReportArchive}.zip * &&
      mv ${ReportArchive}.zip ${ReportArchive} &&
      cp index.html ${ReportFile} &&
      mkdir ${ReportFile.files_path} &&
      cp -r --parents libdir ${ReportFile.files_path} &&
      cp -r --parents seqclust/clustering/superclusters ${ReportFile.files_path} &&
      cp -r --parents seqclust/clustering/clusters ${ReportFile.files_path} &&
      cp seqclust/clustering/hitsort.cls ${ReportFile.files_path}/seqclust/clustering/hitsort.cls &&
      cp *.png ${ReportFile.files_path}/ &&
      cp *.csv ${ReportFile.files_path}/ &&
      cp *.html ${ReportFile.files_path}/  &&
      cp *.css ${ReportFile.files_path}/  &&
      cp *.fasta ${ReportFile.files_path}/ 2>>$log  && rm -r ../tarean_output || :

    </command>
 <inputs>
	<param name="FastaFile" label="NGS reads" type="data" format="fasta"
	       help="Input file must contain FASTA-formatted NGS reads. Illumina paired-end reads are recommended."/>

      <param name="automatic_filtering" label="Perform automatic filtering of abundant satellite repeats" help="Automatic filtering identifies the most abundant tandem repeats and partially removes their reads from the analysis. This enables to analyze higher proportions of other less abundant repeats." type="boolean" truevalue="--automatic_filtering" falsevalue="" checked="false"/>
      <param name="keep_names" label="Keep original read names" type="boolean" truevalue="--keep_names" falsevalue="" checked="false" help="By default, reads are renamed using integers. Use this option to keep original names."/>
      <param name="assembly_min_cluster_size" type="integer" label="Minimal cluster size for assembly" value="5" min="2" max="100"/>
    </when>
  </conditional>

  

 </inputs>
    <outputs>
	<data name="log" format="txt" label="RepeatExplorer2 - log file"/> 
	<data name="ReportArchive" format="zip" label="RepeatExplorer2 - Archive with HTML report from data ${FastaFile.hid}"/> 

7:65d1a27e9339

<tool id="repeatexplorer2" name="RepeatExplorer2 clustering: " version="2.3.8.2" >
    <stdio>
      <regex match="lastdb: can't open file: NEAR" source="stderr" level="fatal" description="Version of last is too old, use ver 956 or higher\n" />
      <regex match="Traceback" source="stderr" level="fatal" description="Unknown error" />
      <regex match="error" source="stderr" level="fatal" description="Unknown error" />
      <regex match="Warning" source="stderr" level="warning" description="Unknown error" />
      <exit_code range="1:" level="fatal" description="Error" />
    </stdio>
    <description>Improved version or repeat discovery and characterization using graph-based sequence clustering</description>
   <requirements>
     <container type="singularity">library://repeatexplorer/default/repex_tarean:0.3.8-dbaa07f</container>
   </requirements>
<command>
      export PYTHONHASHSEED=0;
      export TAREAN_CPU=\$GALAXY_SLOTS;
      export TAREAN_MAX_MEM=\$GALAXY_MEMORY_MB;
      seqclust --sample ${read_sampling.sample} --output_dir=tarean_output --logfile=${log} --cleanup $paired --taxon $taxon

      #if $advanced_options.advanced:
      --mincl $advanced_options.size_threshold $advanced_options.keep_names $advanced_options.automatic_filtering  -D $advanced_options.blastx.options_blastx
      --assembly_min $advanced_options.assembly_min_cluster_size

      ${FastaFile}  >stdout.log 2> stderr.log ;
      echo "STDOUT CONTENT:" >> ${log} ;
      cat stdout.log >> ${log} ;
      echo "STDERR CONTENT:" >> ${log};
      cat stderr.log >> ${log} &&
      /opt/repex_tarean/stderr_filter.py stderr.log &&
      cd tarean_output &&
      zip -r  ${ReportArchive}.zip * &&
      mv  ${ReportArchive}.zip ${ReportArchive} &&
      cp index.html ${ReportFile} &&
      mkdir -p ${ReportFile.extra_files_path} &&
      cp -r --parents libdir ${ReportFile.extra_files_path} &&
      cp -r --parents seqclust/clustering/superclusters ${ReportFile.extra_files_path} &&
      cp -r --parents seqclust/clustering/clusters ${ReportFile.extra_files_path} &&
      cp seqclust/clustering/hitsort.cls ${ReportFile.extra_files_path}/seqclust/clustering/hitsort.cls &&
      cp *.png ${ReportFile.extra_files_path}/ &&
      cp *.csv ${ReportFile.extra_files_path}/ &&
      cp *.html ${ReportFile.extra_files_path}/  &&
      cp *.css ${ReportFile.extra_files_path}/  &&
      cp *.fasta ${ReportFile.extra_files_path}/ 2>>$log  && rm -r ../tarean_output || :

    </command>
 <inputs>
	<param name="FastaFile" label="NGS reads" type="data" format="fasta"
	       help="Input file must contain FASTA-formatted NGS reads. Illumina paired-end reads are recommended."/>

      <param name="automatic_filtering" label="Perform automatic filtering of abundant satellite repeats" help="Automatic filtering identifies the most abundant tandem repeats and partially removes their reads from the analysis. This enables to analyze higher proportions of other less abundant repeats." type="boolean" truevalue="--automatic_filtering" falsevalue="" checked="false"/>
      <param name="keep_names" label="Keep original read names" type="boolean" truevalue="--keep_names" falsevalue="" checked="false" help="By default, reads are renamed using integers. Use this option to keep original names."/>
      <param name="assembly_min_cluster_size" type="integer" label="Minimal cluster size for assembly" value="5" min="2" max="100"/>
    </when>
  </conditional>
  <param name="queue_select" type="select" label="Select queue">
      <option value="basic_fast_queue">basic (max runtime 2 days, 4 GB RAM)</option>
      <option value="long_slow_queue">long (max runtime 2 weeks, 64 GB RAM)</option>
      <option value="extra_long_slow_queue">extra long (max runtime 4 weeks, 64 GB RAM)</option>
  </param>

 </inputs>
    <outputs>
	<data name="log" format="txt" label="RepeatExplorer2 - log file"/> 
	<data name="ReportArchive" format="zip" label="RepeatExplorer2 - Archive with HTML report from data ${FastaFile.hid}"/>