--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/gemini_burden.xml	Thu Feb 18 08:51:59 2016 -0500
@@ -0,0 +1,152 @@
+<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.0">
+    <description>perform sample-wise gene-level burden calculations</description>
+    <macros>
+        <import>gemini_macros.xml</import>
+        <token name="@BINARY@">burden</token>
+    </macros>
+    <expand macro="requirements" />
+    <expand macro="stdio" />
+    <expand macro="version_command" />
+    <command>
+<![CDATA[
+        gemini @BINARY@
+          --cases $cases
+          --controls $controls
+            $save_tscores
+            $nonsynonymous
+            $calpha
+            --permutations $permutations
+            #if float( str($min_aaf) ) >= 0.0:
+                --min-aaf $min_aaf
+            #end if
+            #if float( str($max_aaf) ) >= 0.0:
+                --max-aaf $max_aaf
+            #end if
+            "${ infile }"
+            > "${ outfile }"
+]]>
+
+    </command>
+    <inputs>
+        <expand macro="infile" />
+
+        <param name="cases" type="text" value="" label="Space separated list of cases for association testing" help="(--cases)"/>
+        <param name="controls" type="text" value="" label="Space separated list of controls for association testing" help="(--controls)"/>
+
+        <param name="save_tscores" type="boolean" truevalue="--save_tscores" falsevalue="" checked="False"
+            label="Save the permuted T-scores in the output file" help="(--save_tscores)"/>
+
+        <param name="nonsynonymous" type="boolean" truevalue="--nonsynonymous" falsevalue="" checked="False"
+            label="Count all nonsynonymous variants as contributing burden" help="(--nonsynonymous)"/>
+        <param name="calpha" type="boolean" truevalue="--calpha" falsevalue="" checked="False"
+            label="Run the C-alpha association test" help="(--calpha)"/>
+        <param name="min_aaf" type="float" value="-1" label="The min. alt. allele frequency for a variant to be included"
+            help="(--min-aaf)">
+            <!--validator type="in_range" min="0.0"/-->
+        </param>
+        <param name="max_aaf" type="float" value="-1" label="The max. alt. allele frequency for a variant to be included"
+            help="(--max-aaf)">
+            <!--validator type="in_range" min="0.0"/-->
+        </param>
+
+        <param name="permutations" type="integer" value="1000" label="Number of permutations to run for the C-alpha test"
+            help="(--permutations)">
+            <validator type="in_range" min="0"/>
+        </param>
+
+    </inputs>
+    <outputs>
+        <data name="outfile" format="tabular" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="infile" value="gemini_burden_input.db" ftype="gemini.sqlite" />
+            <param name="controls" value="M10475 M10478" />
+            <param name="cases" value="M10500 M128215" />
+            <param name="calpha" value="True" />
+            <output name="outfile" file="gemini_burden_result.tabular" />
+        </test>
+    </tests>
+    <help><![CDATA[
+**What it does**
+
+Burden performs sample-wise gene-level burden calculations.
+
+The burden tool provides a set of utilities to perform burden summaries on a per-gene, per sample basis. By default, it outputs a table of gene-wise counts of all high impact variants in coding regions for each sample:
+
+GEMINI burden example::
+
+ gene    M10475  M10478  M10500  M128215
+ WDR37   2       2       2       2
+ CTBP2   0       0       0       1
+ DHODH   1       0       0       0
+
+**Setting examples**
+
+**--nonsynonymous**
+
+If you want to be a little bit less restrictive, you can include all non-synonymous variants instead.
+
+GEMINI output with setting --nonsynonymous::
+
+ gene    M10475  M10478  M10500  M128215
+ SYCE1   0       1       1       0
+ WDR37   2       2       2       2
+ CTBP2   0       0       0       1
+ ASAH2C  2       1       1       0
+ DHODH   1       0       0       0
+
+**--calpha**
+
+If your database has been loaded with a PED file describing case and control samples, you can calculate the c-alpha statistic for cases vs. control.
+
+GEMINI output with setting --calpha::
+
+ gene    T       c       Z       p_value
+ SYCE1   -0.5    0.25    -1.0    0.841344746069
+ WDR37   -1.0    1.5     -0.816496580928 0.792891910879
+ CTBP2   0.0     0.0     nan     nan
+ ASAH2C  -0.5    0.75    -0.57735026919  0.718148569175
+ DHODH   0.0     0.0     nan     nan
+
+To calculate the **P-value** using a permutation test, use the --permutations option, specifying the number of permutations of the case/control labels you want to use.
+
+**--min-aaf and --max-aaf for --calpha**
+
+By default, all variants affecting a given gene will be included in the C-alpha computation. However, one may establish alternate allele frequency boundaries for the variants included using the --min-aaf and --max-aaf options.
+
+Used settings:
+
+  - -calpha test.burden.db 
+  - -min-aaf 0.0 
+  - -max-aaf 0.01
+  - -cases 
+  - -controls for --calpha
+
+If you do not have a PED file loaded, or your PED file does not follow the standard PED phenotype encoding format you can still perform the c-alpha test, but you have to specify which samples are the control samples and which are the case samples.
+
+Used settings:
+
+ - -controls M10475 M10478 
+ - -cases M10500 M128215 
+ - -calpha
+
+Output::
+
+ gene    T       c       Z       p_value
+ SYCE1   -0.5    0.25    -1.0    0.841344746069
+ WDR37   -1.0    1.5     -0.816496580928 0.792891910879
+ CTBP2   0.0     0.0     nan     nan
+ ASAH2C  -0.5    0.75    -0.57735026919  0.718148569175
+ DHODH   0.0     0.0     nan     nan
+
+**--nonsynonymous --calpha**
+
+If you would rather consider all nonsynonymous variants for the C-alpha test rather than just the medium and high impact variants, add the --nonsynonymous flag.
+
+
+    ]]></help>
+    <expand macro="citations">
+        <citation type="doi">10.1371/journal.pgen.1001322</citation><!-- c-alpha citation -->
+    </expand>
+</tool>