comparison rank_terms.xml @ 27:8997f2ca8c7a

Update to Miller Lab devshed revision bae0d3306d3b

26:91e835060ad2

<tool id="gd_rank_terms" name="Rank Terms" version="1.0.0">
  <description>: Assess the enrichment/depletion of a gene set for GO terms</description>

  <command interpreter="python">
    #set $t_col1_0 = int(str($t_col1)) - 1
    #set $t_col2_0 = int(str($t_col2)) - 1
    #set $g_col2_0 = int(str($g_col2)) - 1
    rank_terms.py --input "$input1" --columnENSEMBLT $t_col1_0 --inExtnddfile "$input2" --columnENSEMBLTExtndd $t_col2_0 --columnGOExtndd $g_col2_0 --output "$output"
  </command>

  <inputs>
    <param name="input1" type="data" format="tabular" label="Query dataset" />
    <param name="t_col1" type="data_column" data_ref="input1" label="Column with ENSEMBL transcript codes" />

    <param name="input2" type="data" format="tabular" label="Background dataset" />
    <param name="t_col2" type="data_column" data_ref="input2" label="Column with ENSEMBL transcript codes" />
    <param name="g_col2" type="data_column" data_ref="input2" label="Column with GO terms" />
  </inputs>

  <outputs>
    <data name="output" format="tabular" />
  </outputs>

-----

**What it does**

Given a query set of genes from a larger background dataset, this tool
evaluates the statistical over- or under-representation of Gene Ontology
terms in the query set, using a two-tailed Fisher's exact test.

The output contains a row for each GO term, with the following columns:

1. count: the number of genes in the query set that are in this GO category
2. representation: the percentage of this category's genes (from the background dataset) that appear in the query set
3. ranking of this term, based on its representation ("1" is highest)
4. Fisher probability of enrichment/depletion of this GO category in the query dataset
5. GO term

  </help>
</tool>

27:8997f2ca8c7a

<tool id="gd_rank_terms" name="Rank Terms" version="1.1.0">
  <description>: Assess the enrichment/depletion of a gene set for GO terms</description>

  <command interpreter="python">
    #set $t_col1_0 = int(str($t_col1)) - 1
    #set $t_col2_0 = int(str($t_col2)) - 1
    #set $g_col2_0 = int(str($g_col2)) - 1
    rank_terms.py --input "$input1" --columnENSEMBLT $t_col1_0 --inExtnddfile "$input2" --columnENSEMBLTExtndd $t_col2_0 --columnGOExtndd $g_col2_0 --statsTest "$stat" --output "$output"
  </command>

  <inputs>
    <param name="input1" type="data" format="tabular" label="Query dataset" />
    <param name="t_col1" type="data_column" data_ref="input1" label="Column with ENSEMBL transcript codes" />
    <param name="input2" type="data" format="tabular" label="Background dataset" />
    <param name="t_col2" type="data_column" data_ref="input2" label="Column with ENSEMBL transcript codes" />
    <param name="g_col2" type="data_column" data_ref="input2" label="Column with GO terms" />
    <param name="stat" type="select" label="Statistic for determining enrichment/depletion">
      <option value="fisher" selected="true">two-tailed Fisher's exact test</option>
      <option value="hypergeometric">hypergeometric test</option>
      <option value="binomial">binomial probability</option>
    </param>
  </inputs>

  <outputs>
    <data name="output" format="tabular" />
  </outputs>

-----

**What it does**

Given a query set of genes from a larger background dataset, this tool
evaluates the over- or under-representation of Gene Ontology terms in the
query set, using the specified statistical test.

The output contains a row for each GO term, with the following columns:

1. count: the number of genes in the query set that are in this GO category
2. representation: the percentage of this category's genes (from the background dataset) that appear in the query set
3. ranking of this term, based on its representation ("1" is highest)
4. probability of depletion of this GO category in the query dataset
5. probability of enrichment of this GO category in the query dataset
6. GO term

  </help>
</tool>