annotate tools/maf/maf_stats.xml @ 0:9071e359b9a3

Uploaded

<tool id="maf_stats1" name="MAF Coverage Stats" version="1.0.1">
  <description>Alignment coverage information</description>
  <command interpreter="python">
    maf_stats.py
    #if $maf_source_type.maf_source == "user":
      $maf_source_type.maf_source $input2 $input1 $out_file1 $dbkey ${input1.metadata.chromCol} ${input1.metadata.startCol} ${input1.metadata.endCol} $summary
    #else:
      $maf_source_type.maf_source $maf_source_type.mafType $input1 $out_file1 $dbkey ${input1.metadata.chromCol} ${input1.metadata.startCol} ${input1.metadata.endCol} $summary
    #end if
    ${GALAXY_DATA_INDEX_DIR}
    #if $maf_source_type.maf_source == "user":
    $input2.metadata.maf_index
    #end if
  </command>
  <inputs>
    <param format="interval" name="input1" label="Interval File" type="data">
      <validator type="unspecified_build" />
    </param>
    <conditional name="maf_source_type">
      <param name="maf_source" type="select" label="MAF Source">
        <option value="cached" selected="true">Locally Cached Alignments</option>
        <option value="user">Alignments in Your History</option>
      </param>
      <when value="user">
        <param format="maf" name="input2" label="MAF File" type="data">
          <options>
            <filter type="data_meta" ref="input1" key="dbkey" />
          </options>
          <validator type="dataset_ok_validator" />
        </param>
      </when>
      <when value="cached">
        <param name="mafType" type="select" label="MAF Type">
          <options from_file="maf_index.loc">
            <column name="name" index="0"/>
            <column name="value" index="1"/>
            <column name="dbkey" index="2"/>
            <filter type="data_meta" ref="input1" key="dbkey" column="2" multiple="True" separator=","/>
            <validator type="no_options" message="No alignments are available for the build associated with the selected interval file"/>
          </options>
        </param> 
      </when>
    </conditional>
    <param name="summary" type="select" label="Type of Output">
      <option value="false" selected="true">Coverage by Region</option>
      <option value="true">Summarize Coverage</option>
    </param>
  </inputs>
  <outputs>
    <data format="interval" name="out_file1" metadata_source="input1">
      <change_format>
        <when input="summary" value="true" format="tabular" />
      </change_format>
    </data>
  </outputs>
  <requirements>
    <requirement type="python-module">numpy</requirement>
  </requirements>
  <tests>
    <test>
      <param name="input1" value="1.bed" dbkey="hg17" format="bed"/>
      <param name="maf_source" value="cached"/>
      <param name="mafType" value="8_WAY_MULTIZ_hg17"/>
      <output name="out_file1" file="maf_stats_interval_out.dat"/>
      <param name="summary" value="false"/>
    </test>
    <test>
      <param name="input1" value="1.bed" dbkey="hg17" format="bed"/>
      <param name="maf_source" value="cached"/>
      <param name="mafType" value="8_WAY_MULTIZ_hg17"/>
      <output name="out_file1" file="maf_stats_summary_out.dat"/>
      <param name="summary" value="true"/>
    </test>
  </tests>
  <help>

**What it does**

This tool takes a MAF file and an interval file and relates coverage information by interval for each species.
If a column does not exist in the reference genome, it is not included in the output.

Consider the interval: "chrX 1000 1100 myInterval"
  Let's suppose we want to do stats on three way alignments for H, M, and R. The result look like this:

    chrX 1000 1100 myInterval H XXX YYY 
    
    chrX 1000 1100 myInterval M XXX YYY 
    
    chrX 1000 1100 myInterval R XXX YYY 
    

  where XXX and YYY are:

    XXX = number of nucleotides
    
    YYY = number of gaps

----

Alternatively, you can request only summary information for a set of intervals:
  
  ========  ===========  ========
  #species  nucleotides  coverage
  ========  ===========  ========
  hg18         30639      0.2372
  rheMac2      7524       0.0582
  panTro2      30390      0.2353
  ========  ===========  ========

  where **coverage** is the number of nucleotides divided by the total length of the provided intervals.

------

**Citation**

If you use this tool, please cite `Blankenberg D, Taylor J, Nekrutenko A; The Galaxy Team. Making whole genome multiple alignments usable for biologists. Bioinformatics. 2011 Sep 1;27(17):2426-2428. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21775304&gt;`_


  </help>
</tool>