Support more options for MarkDuplicates

Author: bbimber

SequenceAnalysis/api-src/org/labkey/api/sequenceanalysis/run/PicardWrapper.java

@@ -96,7 +96,6 @@ protected List<String> getBaseArgs()
 
         //note: having issues, probably due to OS versions
         params.add("USE_JDK_DEFLATER=true");
-        params.add("USE_JDK_INFLATER=true");
 
         return params;
     }

SequenceAnalysis/src/org/labkey/sequenceanalysis/run/bampostprocessing/MarkDuplicatesStep.java

@@ -1,5 +1,6 @@
 package org.labkey.sequenceanalysis.run.bampostprocessing;
 
+import org.json.JSONObject;
 import org.labkey.api.pipeline.PipelineJobException;
 import org.labkey.api.sequenceanalysis.model.Readset;
 import org.labkey.api.sequenceanalysis.pipeline.BamProcessingOutputImpl;
@@ -35,7 +36,15 @@ public static class Provider extends AbstractPipelineStepProvider<MarkDuplicates
         public Provider()
         {
             super("MarkDuplicates", "Mark Duplicates", "Picard", "This runs Picard tools MarkDuplicates command in order to mark and/or remove duplicate reads.  Please note this can have implications for downstream analysis, because reads marked as duplicates are frequently omitted.  This is often desired, but can be a problem for sequencing of PCR products.", Arrays.asList(
-                    ToolParameterDescriptor.createCommandLineParam(CommandLineParam.create("REMOVE_DUPLICATES"), "removeDuplicates", "Remove Duplicates", "If selected, duplicate reads will be removed, as opposed to flagged as duplicates.", "checkbox", null, null)
+                    ToolParameterDescriptor.createCommandLineParam(CommandLineParam.create("REMOVE_DUPLICATES"), "removeDuplicates", "Remove Duplicates", "If selected, duplicate reads will be removed, as opposed to flagged as duplicates.", "checkbox", null, null),
+                    ToolParameterDescriptor.createCommandLineParam(CommandLineParam.create("MAX_RECORDS_IN_RAM"), "maxRecordsInRam", "Max Records in RAM", "When writing files that need to be sorted, this will specify the number of records stored in RAM before spilling to disk. Increasing this number reduces the number of file handles needed to sort the file, and increases the amount of RAM needed.", "ldk-integerfield", new JSONObject(){{
+                        put("minValue", 0);
+                    }}, null),
+                    ToolParameterDescriptor.createCommandLineParam(CommandLineParam.create("SORTING_COLLECTION_SIZE_RATIO "), "sortingCollectionSizeRatio", "Sorting Collection Size Ratio", "This number, plus the maximum RAM available to the JVM, determine the memory footprint used by some of the sorting collections. If you are running out of memory, try reducing this number. Default is 0.25", "ldk-numberfield", new JSONObject(){{
+                        put("minValue", 0);
+                        put("maxValue", 1);
+                        put("decimalPrecision", 2);
+                    }}, null)
             ), null, "http://picard.sourceforge.net/command-line-overview.shtml");
         }