/tools/maf/maf_stats.xml

  1<tool id="maf_stats1" name="MAF Coverage Stats" version="1.0.1">
  2  <description>Alignment coverage information</description>
  3  <command interpreter="python">
  4    maf_stats.py
  5    #if $maf_source_type.maf_source == "user":
  6      $maf_source_type.maf_source $input2 $input1 $out_file1 $dbkey ${input1.metadata.chromCol} ${input1.metadata.startCol} ${input1.metadata.endCol} $summary
  7    #else:
  8      $maf_source_type.maf_source $maf_source_type.mafType $input1 $out_file1 $dbkey ${input1.metadata.chromCol} ${input1.metadata.startCol} ${input1.metadata.endCol} $summary
  9    #end if
 10    ${GALAXY_DATA_INDEX_DIR}
 11    #if $maf_source_type.maf_source == "user":
 12    $input2.metadata.maf_index
 13    #end if
 14  </command>
 15  <inputs>
 16    <param format="interval" name="input1" label="Interval File" type="data">
 17      <validator type="unspecified_build" />
 18    </param>
 19    <conditional name="maf_source_type">
 20      <param name="maf_source" type="select" label="MAF Source">
 21        <option value="cached" selected="true">Locally Cached Alignments</option>
 22        <option value="user">Alignments in Your History</option>
 23      </param>
 24      <when value="user">
 25        <param format="maf" name="input2" label="MAF File" type="data">
 26          <options>
 27            <filter type="data_meta" ref="input1" key="dbkey" />
 28          </options>
 29          <validator type="dataset_ok_validator" />
 30        </param>
 31      </when>
 32      <when value="cached">
 33        <param name="mafType" type="select" label="MAF Type">
 34          <options from_file="maf_index.loc">
 35            <column name="name" index="0"/>
 36            <column name="value" index="1"/>
 37            <column name="dbkey" index="2"/>
 38            <filter type="data_meta" ref="input1" key="dbkey" column="2" multiple="True" separator=","/>
 39            <validator type="no_options" message="No alignments are available for the build associated with the selected interval file"/>
 40          </options>
 41        </param> 
 42      </when>
 43    </conditional>
 44    <param name="summary" type="select" label="Type of Output">
 45      <option value="false" selected="true">Coverage by Region</option>
 46      <option value="true">Summarize Coverage</option>
 47    </param>
 48  </inputs>
 49  <outputs>
 50    <data format="interval" name="out_file1" metadata_source="input1">
 51      <change_format>
 52        <when input="summary" value="true" format="tabular" />
 53      </change_format>
 54    </data>
 55  </outputs>
 56  <requirements>
 57    <requirement type="python-module">numpy</requirement>
 58  </requirements>
 59  <tests>
 60    <test>
 61      <param name="input1" value="1.bed" dbkey="hg17" format="bed"/>
 62      <param name="maf_source" value="cached"/>
 63      <param name="mafType" value="8_WAY_MULTIZ_hg17"/>
 64      <output name="out_file1" file="maf_stats_interval_out.dat"/>
 65      <param name="summary" value="false"/>
 66    </test>
 67    <test>
 68      <param name="input1" value="1.bed" dbkey="hg17" format="bed"/>
 69      <param name="maf_source" value="cached"/>
 70      <param name="mafType" value="8_WAY_MULTIZ_hg17"/>
 71      <output name="out_file1" file="maf_stats_summary_out.dat"/>
 72      <param name="summary" value="true"/>
 73    </test>
 74  </tests>
 75  <help>
 76
 77**What it does**
 78
 79This tool takes a MAF file and an interval file and relates coverage information by interval for each species.
 80If a column does not exist in the reference genome, it is not included in the output.
 81
 82Consider the interval: "chrX 1000 1100 myInterval"
 83  Let's suppose we want to do stats on three way alignments for H, M, and R. The result look like this:
 84
 85    chrX 1000 1100 myInterval H XXX YYY 
 86    
 87    chrX 1000 1100 myInterval M XXX YYY 
 88    
 89    chrX 1000 1100 myInterval R XXX YYY 
 90    
 91
 92  where XXX and YYY are:
 93
 94    XXX = number of nucleotides
 95    
 96    YYY = number of gaps
 97
 98----
 99
100Alternatively, you can request only summary information for a set of intervals:
101  
102  ========  ===========  ========
103  #species  nucleotides  coverage
104  ========  ===========  ========
105  hg18         30639      0.2372
106  rheMac2      7524       0.0582
107  panTro2      30390      0.2353
108  ========  ===========  ========
109
110  where **coverage** is the number of nucleotides divided by the total length of the provided intervals.
111
112------
113
114**Citation**
115
116If 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;`_
117
118
119  </help>
120</tool>