diff picard_MarkDuplicates.xml @ 18:7615ac66c6e5 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 3ce5dea3af8f4816b4a83914b53402aa84e08fca
author iuc
date Sat, 20 Jan 2018 08:28:24 -0500
parents fc288950c3b7
children 5053a18d9bc8
line wrap: on
line diff
--- a/picard_MarkDuplicates.xml	Thu Apr 13 19:09:24 2017 -0400
+++ b/picard_MarkDuplicates.xml	Sat Jan 20 08:28:24 2018 -0500
@@ -1,4 +1,4 @@
-<tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.1">
+<tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.2">
   <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
   <macros>
     <import>picard_macros.xml</import>
@@ -24,12 +24,14 @@
     DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}'
 
     #import pipes
-    READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
+    #if $read_name_regex:
+      READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) }
+    #end if
     OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}'
 
     # Optional arguments
     #if $barcode_tag:
-    BARCODE_TAG='${barcode_tag}'
+      BARCODE_TAG='${barcode_tag}'
     #end if
 
     VALIDATION_STRINGENCY='${validation_stringency}'
@@ -50,8 +52,8 @@
       <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
     </param>
 
-
-    <param name="read_name_regex" type="text" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*." label="Regular expression that can be used to parse read names in the incoming SAM/BAM dataset" help="READ_NAME_REGEX; Read names are parsed to extract three variables: tile/region, x coordinate and y coordinate. These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size. See help below for more info; default=[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.">
+    <param name="read_name_regex" type="text" value="" label="Regular expression that can be used in unusual situations to parse non-standard read names in the incoming SAM/BAM dataset" help="READ_NAME_REGEX; Read names are parsed to extract three variables: tile/region, x coordinate and y coordinate. These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size. See help below for more info; default='' (uses : separation)">
+ 
       <sanitizer>
         <valid initial="string.printable">
         </valid>
@@ -76,12 +78,23 @@
       <param name="comment" value="test-run"/>
       <param name="assume_sorted" value="True"/>
       <param name="remove_duplicates" value="True"/>
-      <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
+      <param name="read_name_regex" value=".*[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*"/>
       <param name="optical_duplicate_pixel_distance" value="100"/>
       <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
       <param name="validation_stringency" value="LENIENT"/>
       <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/>
     </test>
+    <test>
+      <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
+      <param name="comment" value="test-run"/>
+      <param name="assume_sorted" value="True"/>
+      <param name="remove_duplicates" value="False"/>
+      <param name="read_name_regex" value=""/>
+      <param name="optical_duplicate_pixel_distance" value="100"/>
+      <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
+      <param name="validation_stringency" value="LENIENT"/>
+      <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/>
+    </test>
   </tests>
 
 
@@ -102,7 +115,9 @@
   REMOVE_DUPLICATES=Boolean     If true do not write duplicates to the output file instead of writing them with
                                 appropriate flags set.  Default value: false.
 
-  READ_NAME_REGEX=String        Regular expression that can be used to parse read names in the incoming SAM file. Read
+  READ_NAME_REGEX=String        This option is only needed if your read names do not follow a standard illumina convention
+                                of colon separation but do contain tile, x, and y coordinates (unusual).
+                                A regular expression that can be used to parse read names in the incoming SAM file. Read
                                 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
                                 These values are used to estimate the rate of optical duplication in order to give a more
                                 accurate estimated library size. Set this option to null to disable optical duplicate
@@ -111,18 +126,19 @@
                                 is specified, a regex match is not actually done, but instead the read name  is split on
                                 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
                                 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
-                                are assumed to be tile, x and y values.  Default value:
-                                [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
+                                are assumed to be tile, x and y values.  Default value: ''
+                                
 
   DUPLICATE_SCORING_STRATEGY=ScoringStrategy
   DS=ScoringStrategy            The scoring strategy for choosing the non-duplicate among candidates.  Default value:
                                 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
 
   OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
-                                The maximum offset between two duplicte clusters in order to consider them optical
-                                duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
-                                unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
-                                which case 50-100 is more normal.  Default value: 100.
+                                The maximum offset between two duplicate clusters in order to consider them optical
+                                duplicates. This should be set to 100 for (circa 2011+) read names and typical flowcells.
+                                Structured flow cells (NovaSeq, HiSeq 4000, X) should use ~2500. 
+                                For older conventions, distances could be to some fairly small number (e.g. 5-10 pixels)
+                                Default value: 100.
 
   BARCODE_TAG=String            Barcode SAM tag (ex. BC for 10X Genomics)  Default value: null.