diff picard_EstimLibComplexity.xml @ 95:6ad4014eddd7 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/picard_EstimLibComplexity.xml	Mon Feb 24 16:51:27 2014 -0500
@@ -0,0 +1,124 @@
+<tool name="Estimate Library Complexity" id="rgEstLibComp" version="1.106.0">
+  <description>estimates library complexity from sequence of read pairs alone</description>
+  <requirements><requirement type="package" version="1.106.0">picard</requirement></requirements>
+  <command interpreter="python">
+   picard_wrapper.py -i "${input_file}" -n "${out_prefix}" --tmpdir "${__new_file_path__}" --minid "${minIDbases}"
+   --maxdiff "${maxDiff}" --minmeanq "${minMeanQ}" --readregex "${readRegex}" --optdupdist "${optDupeDist}"
+   -j "\$JAVA_JAR_PATH/EstimateLibraryComplexity.jar" -d "${html_file.files_path}" -t "${html_file}"
+  </command>
+  <inputs>
+    <param format="bam,sam" name="input_file" type="data" label="SAM/BAM dataset"
+      help="If empty, upload or import a SAM/BAM dataset."/>
+    <param name="out_prefix" value="Library Complexity" type="text"
+      label="Title for the output file" help="Use this remind you what the job was for." size="80" />
+    <param name="minIDbases" value="5" type="integer"  label="Minimum identical bases at starts of reads for grouping" size="5" 
+      help="Total_reads / 4^max_id_bases reads will be compared at a time. Lower numbers = more accurate results and exponentially more time/memory." />
+     <param name="maxDiff" value="0.03" type="float"
+      label="Maximum difference rate for identical reads" size="5" 
+      help="The maximum rate of differences between two reads to call them identical" />
+     <param name="minMeanQ" value="20" type="integer"
+      label="Minimum percentage" size="5" 
+      help="The minimum mean quality of bases in a read pair. Lower average quality reads filtered out from all calculations" />
+     <param name="readRegex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*" type="text" size="120"
+      label="Regular expression that can be used to parse read names in the incoming SAM file" 
+      help="Names are parsed to extract: tile/region, x coordinate and y coordinate, to estimate optical duplication rate" >
+      <sanitizer>
+        <valid initial="string.printable">
+         <remove value="&apos;"/>
+        </valid>
+        <mapping initial="none">
+          <add source="&apos;" target="__sq__"/>
+        </mapping>
+      </sanitizer>
+     </param>
+     <param name="optDupeDist" value="100" type="text"
+      label="The maximum offset between two duplicte clusters in order to consider them optical duplicates." size="5" 
+      help="e.g. 5-10 pixels. Later Illumina software versions multiply pixel values by 10, in which case 50-100" />
+
+  </inputs>
+  <outputs>
+    <data format="html" name="html_file" label="${out_prefix}_lib_complexity.html"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input_file" value="picard_input_tiny.sam" />
+      <param name="out_prefix" value="Library Complexity" />
+      <param name="minIDbases" value="5" />
+      <param name="maxDiff" value="0.03" />
+      <param name="minMeanQ" value="20" />
+      <param name="readRegex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*" />
+      <param name="optDupeDist" value="100" />      
+      <output name="html_file" file="picard_output_estlibcomplexity_tinysam.html" ftype="html" lines_diff="30" />
+    </test>
+  </tests>
+  <help>
+
+.. class:: infomark
+
+**Purpose**
+
+Attempts to estimate library complexity from sequence alone. 
+Does so by sorting all reads by the first N bases (5 by default) of each read and then 
+comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be 
+duplicates if they match each other with no gaps and an overall mismatch rate less than or equal to MAX_DIFF_RATE (0.03 by default).
+
+Reads of poor quality are filtered out so as to provide a more accurate estimate. 
+The filtering removes reads with any no-calls in the first N bases or with a mean base quality lower than 
+MIN_MEAN_QUALITY across either the first or second read.
+
+The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the 
+calculation of library size. Also, since there is no alignment to screen out technical reads one 
+further filter is applied on the data. After examining all reads a histogram is built of 
+[#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are
+then removed from the histogram as outliers before library size is estimated.
+
+**Picard documentation**
+
+This is a Galaxy wrapper for EstimateLibraryComplexity, a part of the external package Picard-tools_.
+
+ .. _Picard-tools: http://www.google.com/search?q=picard+samtools
+
+-----
+
+.. class:: infomark
+
+**Inputs, outputs, and parameters**
+
+Picard documentation says (reformatted for Galaxy):
+
+.. csv-table::
+   :header-rows: 1
+
+    Option	Description
+    "INPUT=File","One or more files to combine and estimate library complexity from. Reads can be mapped or unmapped. This option may be specified 0 or more times."
+    "OUTPUT=File","Output file to writes per-library metrics to. Required."
+    "MIN_IDENTICAL_BASES=Integer","The minimum number of bases at the starts of reads that must be identical for reads to be grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads will be compared at a time, so lower numbers will produce more accurate results but consume exponentially more memory and CPU. Default value: 5."
+    "MAX_DIFF_RATE=Double","The maximum rate of differences between two reads to call them identical. Default value: 0.03. "
+    "MIN_MEAN_QUALITY=Integer","The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads with lower average quality are filtered out and not considered in any calculations. Default value: 20."
+    "READ_NAME_REGEX=String","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. The regular expression should contain three capture groups for the three variables, in order. Default value: [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. This option can be set to 'null' to clear the default value."
+    "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"
+    "CREATE_MD5_FILE=Boolean","Whether to create an MD5 digest for any BAM files created. Default value: false. This option can be set to 'null' to clear the default value. "
+
+.. class:: warningmark
+
+**Warning on SAM/BAM quality**
+
+Many SAM/BAM files produced externally and uploaded to Galaxy do not fully conform to SAM/BAM specifications. Galaxy deals with this by using the **LENIENT**
+flag when it runs Picard, which allows reads to be discarded if they're empty or don't map. This appears
+to be the only way to deal with SAM/BAM that cannot be parsed.
+
+.. class:: infomark
+
+**Note on the Regular Expression**
+
+(from the Picard docs)
+This tool requires a valid regular expression to parse out the read names in the incoming SAM or BAM file. 
+These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size. 
+The regular expression should contain three capture groups for the three variables, in order. 
+Default value: [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
+
+
+  </help>
+</tool>
+
+