view tools/maf/interval_maf_to_merged_fasta.xml @ 1:cdcb0ce84a1b

Uploaded

<tool id="Interval_Maf_Merged_Fasta2" name="Stitch MAF blocks" version="1.0.1">
  <description>given a set of genomic intervals</description>
  <command interpreter="python">
    #if $maf_source_type.maf_source == "user" #interval_maf_to_merged_fasta.py --dbkey=$dbkey --species=$maf_source_type.species --mafSource=$maf_source_type.maf_file --mafIndex=$maf_source_type.maf_file.metadata.maf_index --interval_file=$input1 --output_file=$out_file1 --chromCol=${input1.metadata.chromCol} --startCol=${input1.metadata.startCol} --endCol=${input1.metadata.endCol} --strandCol=${input1.metadata.strandCol} --mafSourceType=$maf_source_type.maf_source --mafIndexFileDir=${GALAXY_DATA_INDEX_DIR}
    #else                                     #interval_maf_to_merged_fasta.py --dbkey=$dbkey --species=$maf_source_type.species --mafSource=$maf_source_type.maf_identifier --interval_file=$input1 --output_file=$out_file1 --chromCol=${input1.metadata.chromCol} --startCol=${input1.metadata.startCol} --endCol=${input1.metadata.endCol} --strandCol=${input1.metadata.strandCol} --mafSourceType=$maf_source_type.maf_source --mafIndexFileDir=${GALAXY_DATA_INDEX_DIR}
    #end if# --overwrite_with_gaps=$overwrite_with_gaps
  </command>
  <inputs>
    <page>
        <param format="interval" name="input1" type="data" label="Choose intervals">
          <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 name="maf_file" type="data" format="maf" label="MAF File">
                <options>
                  <filter type="data_meta" ref="input1" key="dbkey" />
                </options>
                <validator type="dataset_ok_validator" />
              </param>
              <param name="species" type="select" display="checkboxes" multiple="true" label="Choose species" help="Select species to be included in the final alignment">
                <options>
                  <filter type="data_meta" ref="maf_file" key="species" />
                </options>
              </param>
            </when>
            <when value="cached">
              <param name="maf_identifier" 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"/>
                  <column name="species" index="3"/>
                  <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> 
              <param name="species" type="select" display="checkboxes" multiple="true" label="Choose species" help="Select species to be included in the final alignment">
                <options from_file="maf_index.loc">
                  <column name="uid" index="1"/>
                  <column name="value" index="3"/>
                  <column name="name" index="3"/>
                  <filter type="param_value" ref="maf_identifier" name="uid" column="1"/>
                  <filter type="multiple_splitter" column="3" separator=","/>
                </options>
              </param>
            </when>
        </conditional>
        <param name="overwrite_with_gaps" type="select" label="Split into Gapless MAF blocks" help="When set to Yes, blocks are divided around gaps appearing in any species. This will prevent gaps occurring in the interior of the sequence for an aligning species from overwriting a nucleotide found for the same position in a lower-scoring block.">
          <option value="True" selected="true">No</option>
          <option value="False">Yes</option>
        </param>
    </page>
   </inputs>
  <outputs>
    <data format="fasta" name="out_file1" />
  </outputs>
  <tests>
    <test>
      <param name="input1" value="13.bed" dbkey="hg18" ftype="bed"/>
      <param name="maf_source" value="cached"/>
      <param name="maf_identifier" value="17_WAY_MULTIZ_hg18"/>
      <param name="species" value="hg18,mm8"/>
      <param name="overwrite_with_gaps" value="True"/>
      <output name="out_file1" file="interval_maf_to_merged_fasta_out3.fasta" />
    </test>
    <test>
      <param name="input1" value="1.bed" dbkey="hg17" ftype="bed"/>
      <param name="maf_source" value="cached"/>
      <param name="maf_identifier" value="8_WAY_MULTIZ_hg17"/>
      <param name="species" value="canFam1,hg17,mm5,panTro1,rn3"/>
      <param name="overwrite_with_gaps" value="True"/>
      <output name="out_file1" file="interval_maf_to_merged_fasta_out.dat" />
    </test>
    <test>
      <param name="input1" value="1.bed" dbkey="hg17" ftype="bed"/>
      <param name="maf_source" value="user"/>
      <param name="maf_file" value="5.maf"/>
      <param name="species" value="canFam1,hg17,mm5,panTro1,rn3"/>
      <param name="overwrite_with_gaps" value="True"/>
      <output name="out_file1" file="interval_maf_to_merged_fasta_user_out.dat" />
    </test>
  </tests>
  <help>
**What it does**

A single genomic region can be covered by multiple alignment blocks. In many cases it is desirable to stitch these alignment blocks together. This tool accepts a list of genomic intervals. For every interval it performs the following:

  * finds all MAF blocks that overlap the interval;
  * sorts MAF blocks by alignment score;
  * stitches blocks together and resolves overlaps based on alignment score;
  * outputs alignments in FASTA format.

------

**Example**

Here three MAF blocks overlapping a single interval are stitched together. Space between blocks 2 and 3 is filled with gaps:

.. image:: ./static/images/maf_icons/stitchMaf.png

------

**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>