diff bamCorrelate.xml @ 28:f7712a057440 draft

new bugfix release
author bgruening
date Wed, 02 Apr 2014 09:15:44 -0400
parents bf1b1dcdd67b
children 3a2aab18a217
line wrap: on
line diff
--- a/bamCorrelate.xml	Mon Mar 17 16:23:58 2014 -0400
+++ b/bamCorrelate.xml	Wed Apr 02 09:15:44 2014 -0400
@@ -1,4 +1,4 @@
-<tool id="deeptools_bamCorrelate" name="bamCorrelate" version="1.0.5">
+<tool id="deeptools_bamCorrelate" name="bamCorrelate" version="@WRAPPER_VERSION@.0">
     <description>correlates pairs of BAM files</description>
     <expand macro="requirements" />
     <expand macro="stdio" />
@@ -35,7 +35,9 @@
 
         #if $mode.modeOpt == "bins":
             --binSize '$mode.binSize'
-            --numberOfSamples '$mode.numberOfSamples'
+            --distanceBetweenBins '$mode.distanceBetweenBins'
+            $mode.doNotRemoveOutliers
+
         #else:
             --BED $mode.region_file
         #end if
@@ -74,8 +76,8 @@
             help ="Reads will be extended to match this length unless they are paired-end, in which case they will be extended to match the fragment length. *NOTE*: If the BAM files contain mated and unmated paired-end reads, unmated reads will be extended to match the fragment length."/>
 
         <param name="corMethod" type="select" label="Correlation method">
+            <option value="spearman" selected="True">Spearman</option>
             <option value="pearson">Pearson</option>
-            <option value="spearman">Spearman</option>
         </param>
 
         <conditional name="mode">
@@ -89,9 +91,28 @@
                     label="Bin size in bp"
                     help="Length in base pairs for a window used to sample the genome."/>
 
-                <param name="numberOfSamples" type="integer" value="100000" min="1" 
-                    label="Number of samples"
-                    help="Number of samples taken from the genome to compute the scaling factors"/>
+                <param name="distanceBetweenBins" type="integer" value="0" min="0"
+                    label="Distance between bins"
+                    help="By default, bamCorrelate considers consecutive bins of
+                        the specified 'Bin size'. However, to reduce the
+                        computation time, a larger distance between bins can
+                        by given. Larger distances result in less bins being
+                        considered"/>
+
+                <param name="doNotRemoveOutliers" type="boolean"
+                    truevalue="--doNotRemoveOutliers" falsevalue="" label="Do not filter outliers"
+                    help="By default, bins with very large counts are removed.
+                        By setting this option, outliers will not be
+                        removed. Bins with unusually large counts normally
+                        correspond to regions in the genome that accumulate
+                        lot of reads like satellite regions. If outliers are not
+                        removed the pearson correlation will wrongly report a
+                        very high correlation; that's why, by default,
+                        bamCorrelate tries to remove outliers using
+                        the median absolute deviation (MAD) method applying a
+                        threshold of 200 to only consider extremely large
+                        deviations from the median."/>
+
                 <expand macro="bamCorrelate_mode_actions" />
             </when>
             <when value="BED-file">