annotate tools/extract/phastOdds/phastOdds_tool.xml @ 0:9071e359b9a3

Uploaded

<tool id="phastOdds_for_intervals" name="Compute phastOdds score" version="1.0.0">
  <description>for each interval</description>
  <command interpreter="python">get_scores_galaxy.py $per_col ${score_file}.h5 ${score_file}.mapping.bed $input $output ${input.metadata.chromCol} ${input.metadata.startCol} ${input.metadata.endCol}</command>
  <inputs>
    <param format="interval" name="input" type="data" label="Interval file">
      <validator type="unspecified_build" message="Unspecified build, this tool works with data from genome builds hg17. Click the pencil icon in your history item to set the genome build."/>
      <validator type="dataset_metadata_in_file" filename="phastOdds.loc" metadata_name="dbkey" metadata_column="0" message="Sequences are currently unavailable for the specified build." />
    </param>
    <param name="score_file" type="select" label="Available datasets">
      <options from_file="phastOdds.loc">
        <column name="name" index="1"/>
        <column name="value" index="2"/>
        <column name="dbkey" index="0"/>
        <filter type="data_meta" ref="input" key="dbkey" column="0" />
      </options>
    </param>
	<param name="per_col" type="boolean" label="Standardize" help="Standardizes the score to be per alignment column" checked="yes" truevalue="-p" falsevalue=""/>
  </inputs>
  <outputs>
    <data format="interval" name="output" metadata_source="input"/>
  </outputs>
  <requirements>
    <requirement type="python-module">numpy</requirement>
    <requirement type="python-module">tables</requirement>
  </requirements>
  <tests>
    <test>
      <param name="input" value="4.bed" dbkey="hg17" ftype="bed"/>
      <param name="score_file" value="/galaxy/data/phastOdds_precomputed/encode_SEP-2005_tba.v2_phastOdds" />
      <param name="per_col" value="true" />
      <output name="output" file="phastOdds_tool_out.interval" />
    </test>
  </tests>
  <help>
    
.. class:: warningmark

This tool currently only works with interval data from genome build hg17.

.. class:: warningmark

This tool assumes that the input dataset is in interval format and contains at least a chrom column, a start column and an end column.  These 3 columns can be dispersed throughout any number of other data columns. 

-----

**Syntax**

Append a column to each line of an interval file containing the phastOdds score for that interval.

-----

**Example**

If your original data has the following format:

+-----+-----+---+
|chrom|start|end|
+-----+-----+---+

and you choose to compute phastOdds scores, your output will look like this:

+-----+-----+---+-----+
|chrom|start|end|score|
+-----+-----+---+-----+

  </help>
</tool>