comparison find_intervals.xml @ 21:d6b961721037

Miller Lab Devshed version 4c04e35b18f6

20:8a4b8efbc82c

    "$out_format"
  </command>

  <inputs>
    <param name="input" type="data" format="tabular" label="Input">
      <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="Cutoff 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 cutoff"/>
      </when>
      <when value="value">
        <param name="cutoff_val" type="float" value="0.0" label="Value cutoff"/>
      </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 need to choose the columns if the input dataset is not gd_snp">
        <option value="0" selected="true">No, get columns from metadata</option>
        <option value="1" >Yes, choose columns</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 the build in the metadata is the same as using here."/>
        <param name="rpos_col" type="data_column" data_ref="input" numerical="true" label="Column with reference position" help="Note: either zero or one based positions will work"/>
      </when>
    </conditional>
  </inputs>

  <outputs>

if the dataset is not also gd_snp format, specifies 
the columns containing chromosome, position, and scores (such as an Fst-value for the SNP). 
For gd_snp format the metadata can be used to specify the chromosome and 
position.
Other inputs include
a percentage or raw score for the "cutoff" 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 cutoff; 
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
cutoff 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).  

21:d6b961721037

    "$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 not gd_snp.">
        <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>

if the dataset is not also gd_snp format, specifies 
the columns containing chromosome, position, and scores (such as an Fst-value for the SNP). 
For gd_snp format the metadata can be used to specify 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).