diff analyze_covariates.xml @ 0:332a7de8f98a draft

Imported from capsule None

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/analyze_covariates.xml	Tue Apr 01 09:11:43 2014 -0400
@@ -0,0 +1,101 @@
+<tool id="gatk_analyze_covariates" name="Analyze Covariates" version="0.0.5">
+  <description>- draw plots</description>
+  <requirements>
+      <requirement type="package" version="1.4">gatk</requirement>
+  </requirements>
+  <macros>
+    <import>gatk_macros.xml</import>
+  </macros>
+  <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "1"
+   --stdout "${output_log}"
+   --html_report_from_directory "${output_html}" "${output_html.files_path}"
+   -p 'java 
+    -jar "${JAVA_JAR_PATH}/AnalyzeCovariates.jar"
+    -recalFile "${input_recal}"
+    -outputDir "${output_html.files_path}"
+    ##--num_threads 4 ##hard coded, for now
+    ##-log "${output_log}"
+    ##-Rscript,--path_to_Rscript path_to_Rscript; on path is good enough         
+    #if $analysis_param_type.analysis_param_type_selector == "advanced":
+        --ignoreQ "${analysis_param_type.ignore_q}"
+        --numRG "${analysis_param_type.num_read_groups}"
+        --max_quality_score "${analysis_param_type.max_quality_score}"
+        --max_histogram_value "${analysis_param_type.max_histogram_value}"
+         ${analysis_param_type.do_indel_quality}
+    #end if
+   '
+  </command>
+  <inputs>
+    <param name="input_recal" type="data" format="csv" label="Covariates table recalibration file" help="-recalFile,--recal_file &amp;lt;recal_file&amp;gt;" />
+    <conditional name="analysis_param_type">
+      <param name="analysis_param_type_selector" type="select" label="Basic or Advanced options">
+        <option value="basic" selected="True">Basic</option>
+        <option value="advanced">Advanced</option>
+      </param>
+      <when value="basic">
+        <!-- Do nothing here -->
+      </when>
+      <when value="advanced">
+        <param name="ignore_q" type="integer" value="5" label="Ignore bases with reported quality less than this number." help="-ignoreQ,--ignoreQ &amp;lt;ignoreQ&amp;gt; "/>
+        <param name="num_read_groups" type="integer" value="-1" label="Only process N read groups." help="-numRG,--numRG &amp;lt;numRG&amp;gt;"/>
+        <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &amp;lt;max_quality_score&amp;gt;"/>
+        <param name="max_histogram_value" type="integer" value="0" label="Max histogram value" help="-maxHist,--max_histogram_value &amp;lt;max_histogram_value&amp;gt;"/>
+        <param name="do_indel_quality" type="boolean" truevalue="--do_indel_quality" falsevalue="" label="Do indel quality" help="--do_indel_quality"/>
+      </when>
+    </conditional>
+  </inputs>
+  <outputs>
+    <data format="html" name="output_html" label="${tool.name} on ${on_string} (HTML)" />
+    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
+  </outputs>
+  <tests>
+      <test>
+          <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> 
+          <param name="analysis_param_type_selector" value="basic" />
+          <output name="output_html" file="gatk/gatk_analyze_covariates/gatk_analyze_covariates_out_1.html" />
+          <output name="output_log" file="gatk/gatk_analyze_covariates/gatk_analyze_covariates_out_1.log.contains" compare="contains" />
+      </test>
+  </tests>
+  <help>
+**What it does**
+
+Create collapsed versions of the recal csv file and call R scripts to plot residual error versus the various covariates.
+
+For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Base_quality_score_recalibration&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
+
+------
+
+**Inputs**
+
+GenomeAnalysisTK: AnalyzeCovariates accepts an recal CSV file.
+
+
+**Outputs**
+
+The output is in CSV and HTML files with links to PDF graphs and a data files.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
+
+-------
+
+**Settings**::
+
+ recal_file             The input recal csv file to analyze
+ output_dir             The directory in which to output all the plots and intermediate data files
+ path_to_Rscript        The path to your implementation of Rscript. For Broad users this is maybe /broad/tools/apps/R-2.6.0/bin/Rscript
+ path_to_resources      Path to resources folder holding the Sting R scripts.
+ ignoreQ                Ignore bases with reported quality less than this number.
+ numRG                  Only process N read groups. Default value: -1 (process all read groups)
+ max_quality_score      The integer value at which to cap the quality scores, default is 50
+ max_histogram_value    If supplied, this value will be the max value of the histogram plots
+ do_indel_quality       If supplied, this value will be the max value of the histogram plots
+
+@CITATION_SECTION@
+  </help>
+</tool>