annotate find_intervals.xml @ 33:5064f618ec1c

remove munkres dependency

<tool id="gd_find_intervals" name="Remarkable Intervals" version="1.1.0">
  <description>: Find high-scoring runs of SNPs</description>

  <command interpreter="python">
    find_intervals.py "$input" "$input.metadata.dbkey" "$output" "$output.files_path"

    #if $override_metadata.choice == "0"
      "$input.metadata.ref" "$input.metadata.rPos"
    #else
      "$override_metadata.ref_col" "$override_metadata.rpos_col"
    #end if

    "$score_col" "$shuffles"

    #if $cutoff.type == 'percentage'
      "$cutoff.cutoff_pct"
    #else
      "=$cutoff.cutoff_val"
    #end if

    "$out_format"
  </command>

  <inputs>
    <param name="input" type="data" format="tabular" label="Dataset">
      <validator type="unspecified_build" message="This dataset does not have a reference species and cannot be used with this tool" />
    </param>

    <param name="score_col" type="data_column" data_ref="input" numerical="true" label="Column with score"/>

    <conditional name="cutoff">
      <param name="type" type="select" label="Score-shift type">
        <option value="percentage">percentage</option>
        <option value="value">value</option>
      </param>
      <when value="percentage">
        <param name="cutoff_pct" type="float" value="95" min="0" max="100" label="Percentage score-shift"/>
      </when>
      <when value="value">
        <param name="cutoff_val" type="float" value="0.0" label="Value score-shift"/>
      </when>
    </conditional>

    <param name="shuffles" type="integer" min="0" value="0" label="Number of randomizations"/>

    <param name="out_format" type="select" format="integer" label="Report individual positions">
      <option value="0" selected="true">no</option>
      <option value="1">yes</option>
    </param>

    <conditional name="override_metadata">
      <param name="choice" type="select" format="integer" label="Choose columns" help="Note: you must choose the columns if the input dataset is neither gd_snp nor gd_genotype.">
        <option value="0" selected="true">no, get columns from metadata</option>
        <option value="1" >yes, choose columns here</option>
      </param>
      <when value="0" />
      <when value="1">
        <param name="ref_col" type="data_column" data_ref="input" numerical="false" label="Column with reference chromosome" help="Note: be sure this corresponds to the build recorded in the metadata."/>
        <param name="rpos_col" type="data_column" data_ref="input" numerical="true" label="Column with reference position" help="Note: either zero-based or one-based positions will work."/>
      </when>
    </conditional>
  </inputs>

  <outputs>
    <data name="output" format="interval">
        <change_format>
            <when input="out_format" value="1" format="bigwigpos" />
        </change_format>
    </data>
  </outputs>

  <requirements>
    <requirement type="package" version="0.1">gd_c_tools</requirement>
  </requirements>

  <tests>
    <test>
      <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" />
      <param name="score_col" value="5" />
      <param name="type" value="value" />
      <param name="cutoff_val" value="700.0" />
      <param name="shuffles" value="10" />
      <param name="out_format" value="0" />
      <param name="choice" value="0" />

      <output name="output" file="test_out/find_intervals/find_intervals.interval" />
    </test>
  </tests>

  <help>
**Dataset formats**

The input dataset is tabular_ (which includes gd_snp_ and gd_genotype_),
with required columns of chromosome, position, and score (in any column).
The output dataset is interval_. (`Dataset missing?`_)

.. _tabular: ./static/formatHelp.html#tab
.. _gd_snp: ./static/formatHelp.html#gd_snp
.. _gd_genotype: ./static/formatHelp.html#gd_genotype
.. _interval: ./static/formatHelp.html#interval
.. _Dataset missing?: ./static/formatHelp.html

-----

**What it does**

The user selects a tabular dataset (such as the SNV formats gd_snp and
gd_genotype) and if the dataset is not in an SNV format, specifies the
columns containing chromosome, position, and scores (such as an FST-value
for the SNP).  With SNV formats, the metadata tells which columns hold the
chromosome and position.  Other inputs include a percentage or raw score
for the "score-shift" which should be greater than the average value
for the scores column.  A higher value will give smaller intervals in
the output.  If a percentage (e.g. 95%) is specified then that percentile
of the scores is used as the shift; percentile may not work well if many
rows or SNPs have the same score (in that case use a raw score).

The program subtracts the shift from every score, then finds genomic
intervals (i.e., consecutive runs of SNPs) whose total score cannot be
increased by adding or subtracting one or more adjusted scores at the
ends of the interval.  Another input is the number of times the data
should be randomized (only intervals with score exceeding the maximum
for the randomized data are reported).  If 100 shuffles are requested,
then any interval reported by the tool has a score with probability
less than 0.01 of being equaled or exceeded by chance, assuming that
the scores vary independently by position.

-----

**Example**

- Input (showing only the chromosome, position, and score columns)::

    chr2      39      0.40
    chr2     103      0.97
    chr2     188      0.72
    chr2     203      0.68
    chr2     321      0.92
    ...
    chr2    1132      0.85
    chr2    1321      0.34
    ...

- Suppose the user-specified score-shift is 0.75.  This value is subtracted from each score, giving::

    chr2      39     -0.35
    chr2     103      0.22
    chr2     188     -0.03
    chr2     203     -0.07
    chr2     321      0.17
    ...
    chr2    1132      0.10
    chr2    1321     -0.41
    ...

- The output, not reporting individual positions, might be (depending on the values not shown above)::

    chr2    103    1132    1.42
  </help>
</tool>