/tools/picard/picard_ReorderSam.xml

<tool name="Reorder SAM/BAM" id="picard_ReorderSam" version="0.3.0">
  <requirements><requirement type="package">picard</requirement></requirements>
  <command interpreter="python">
    picard_wrapper.py
      --input=$inputFile
      #if $source.indexSource == "built-in"
        --ref="${ filter( lambda x: str( x[0] ) == str( $source.ref ), $__app__.tool_data_tables[ 'picard_indexes' ].get_fields() )[0][-1] }"
      #else
        --ref-file=$refFile
        --species-name=$source.speciesName
        --build-name=$source.buildName
        --trunc-names=$source.truncateSeqNames
      #end if
      --allow-inc-dict-concord=$allowIncDictConcord
      --allow-contig-len-discord=$allowContigLenDiscord
      --output-format=$outputFormat
      --output=$outFile
      -j "${GALAXY_DATA_INDEX_DIR}/shared/jars/ReorderSam.jar"
  </command>
  <inputs>
    <param format="bam,sam" name="inputFile" type="data" label="SAM/BAM dataset to be reordered"
           help="If empty, upload or import a SAM/BAM dataset." />
    <conditional name="source">
      <param name="indexSource" type="select" label="Select Reference Genome" help="This tool will re-order SAM/BAM in the same order as reference selected below.">
        <option value="built-in">Locally cached</option>
        <option value="history">History</option>
      </param>
      <when value="built-in">
        <param name="ref" type="select" label="Select a reference genome">
          <options from_data_table="picard_indexes" />
        </param>
      </when>
      <when value="history">
        <param name="refFile" type="data" format="fasta" metadata_name="dbkey" label="Using reference file" />
        <param name="speciesName" type="text" value="" label="Species name" />
        <param name="buildName" type="text" value="" label="Build name" />
        <param name="truncateSeqNames" type="boolean" checked="False" truevalue="true" falsevalue="false" label="Truncate sequence names after first whitespace" />
      </when>
    </conditional>
    <param name="allowIncDictConcord" type="boolean" checked="False" truevalue="true" falsevalue="false" label="Allow incomplete dict concordance?" help="Allows a partial overlap of the BAM contigs with the new reference sequence contigs." />
    <param name="allowContigLenDiscord" type="boolean" checked="False" truevalue="true" falsevalue="false" label="Allow contig length discordance?" help="This is dangerous--don't check it unless you know exactly what you're doing!" />
    <param name="outputFormat" type="boolean" checked="True" truevalue="bam" falsevalue="sam" label="Output BAM instead of SAM" help="Uncheck for SAM output" />
  </inputs>
  <outputs>
    <data name="outFile" format="bam" label="${tool.name} on ${on_string}: reordered ${outputFormat}">
      <change_format>
        <when input="outputFormat" value="sam" format="sam" />
      </change_format>
    </data>
  </outputs>
  <tests>
    <test>
      <!-- Commands:
      cp test-data/phiX.fasta .
      samtools faidx phiX.fasta
      java -jar CreateSequenceDictionary.jar R=phiX.fasta O=phiX.dict URI=phiX.fasta TRUNCATE_NAMES_AT_WHITESPACE=false SPECIES=phiX174
      java -jar ReorderSam.jar VALIDATION_STRINGENCY=LENIENT I=test-data/picard_RS_input1.bam O=picard_RS_output1.bam REFERENCE=phiX.fasta ALLOW_INCOMPLETE_DICT_CONCORDANCE=false ALLOW_CONTIG_LENGTH_DISCORDANCE=false
    -->
      <param name="inputFile" value="picard_RS_input1.bam" />
      <param name="indexSource" value="history" />
      <param name="refFile" value="phiX.fasta" />
      <param name="speciesName" value="phiX174" />
      <param name="buildName" value="" />
      <param name="truncateSeqNames" value="false" />
      <param name="allowIncDictConcord" value="false" />
      <param name="allowContigLenDiscord" value="false" />
      <param name="outputFormat" value="True" />
      <output name="outFile" file="picard_RS_output1.bam" ftype="bam" lines_diff="4" compare="contains" />
    </test>
    <test>
      <!-- Command:
      java -jar ReorderSam.jar VALIDATION_STRINGENCY=LENIENT I=test-data/picard_RS_input2.sam O=picard_RS_output2.sam REFERENCE=/path/to/phiX/picard_index/phiX.fa ALLOW_INCOMPLETE_DICT_CONCORDANCE=false ALLOW_CONTIG_LENGTH_DISCORDANCE=false
      /path/to/phiX/srma_index/phiX.fa is path to phiX.fa, phiX.fa.fai, and phiX.dict
      -->
      <param name="inputFile" value="picard_RS_input2.sam" />
      <param name="indexSource" value="built-in" />
      <param name="ref" value="phiX" />
      <param name="allowIncDictConcord" value="false" />
      <param name="allowContigLenDiscord" value="false" />
      <param name="outputFormat" value="False" />
      <output name="outFile" file="picard_RS_output2.sam" ftype="sam" lines_diff="4" sort="True" />
    </test>
    <test>
      <!-- Commands:
      cp test-data/picard_RS_input4.fasta .
      samtools faidx picard_RS_input4.fasta
      java -jar CreateSequenceDictionary.jar R=picard_RS_input4.fasta O=picard_RS_input4.dict URI=picard_RS_input4.fasta TRUNCATE_NAMES_AT_WHITESPACE=true SPECIES=phiX174 GENOME_ASSEMBLY=phiX_buildBlah1.1
      java -jar ReorderSam.jar VALIDATION_STRINGENCY=LENIENT I=test-data/picard_RS_input3.bam O=picard_RS_output3.sam REFERENCE=picard_RS_input4.fasta ALLOW_INCOMPLETE_DICT_CONCORDANCE=true ALLOW_CONTIG_LENGTH_DISCORDANCE=false
      picard_RS_input3.bam can be made from picard_RS_input3.sam
      -->
      <param name="inputFile" value="picard_RS_input3.bam" />
      <param name="indexSource" value="history" />
      <param name="refFile" value="picard_RS_input4.fasta" />
      <param name="speciesName" value="phiX174" />
      <param name="buildName" value="phiX_buildBlah1.1" />
      <param name="truncateSeqNames" value="true" />
      <param name="allowIncDictConcord" value="true" />
      <param name="allowContigLenDiscord" value="false" />
      <param name="outputFormat" value="False" />
      <output name="outFile" file="picard_RS_output3.sam" ftype="sam" lines_diff="12" sort="True" />
    </test>
  </tests>
  <help>

.. class:: infomark

**Purpose**

Reorder SAM/BAM to match contig ordering in a particular reference file. Note that this is
not the same as sorting as done by the SortSam tool, which sorts by either coordinate
values or query name. The ordering in ReorderSam is based on exact name matching of
contigs/chromosomes. Reads that are mapped to a contig that is not in the new reference file are
not included in the output.

**Picard documentation**

This is a Galaxy wrapper for ReorderSam, a part of the external package Picard-tools_.

 .. _Picard-tools: http://www.google.com/search?q=picard+samtools

------

.. class:: infomark 

**Inputs, outputs, and parameters**

For the file that needs to be reordered, either a sam file or a bam file must be supplied.
If a bam file is used, it must be coordinate-sorted. A reference file is also required,
so either a fasta file should be supplied or a built-in reference can be selected.

The output contains the same reads as the input file but the reads have been rearranged so
they appear in the same order as the provided reference file. The tool will output either
bam (the default) or sam, according to user selection. Bam is recommended since it is smaller.

The only extra parameters that can be set are flags for allowing incomplete dict concordance
and allowing contig length discordance. If incomplete dict concordance is allowed, only a
partial overlap of the bam contigs with the new reference sequence contigs is required. By
default it is off, requiring a corresponding contig in the new reference for each read contig.
If contig length discordance is allowed, contig names that are the same between a read and the
new reference contig are allowed even if they have different lengths. This is usually not a
good idea, unless you know exactly what you're doing. It's off by default.

.. class:: warningmark

**Warning on SAM/BAM quality**

Many SAM/BAM files produced externally and uploaded to Galaxy do not fully conform to SAM/BAM specifications. Galaxy deals with this by using the **LENIENT**
flag when it runs Picard, which allows reads to be discarded if they're empty or don't map. This appears
to be the only way to deal with SAM/BAM that cannot be parsed.


  </help>
</tool>