annotate rgPicardLibComplexity.xml @ 3:bf1c3f9f8282

Fix for FastqToSam MAX_Q usage detection.
author Daniel Blankenberg <dan@bx.psu.edu>
date Fri, 03 May 2013 17:13:01 -0400
parents 9227b8c3093b
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
1 <tool name="Estimate Library Complexity" id="rgEstLibComp" version="1.56.0">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
2 <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
3 <command interpreter="python">
2
9227b8c3093b Updated command line format per dev team standards.
devteam <devteam@galaxyproject.org>
parents: 0
diff changeset
4 picard_wrapper.py -i "${input_file}" -n "${out_prefix}" --tmpdir "${__new_file_path__}" --minid "${minIDbases}"
9227b8c3093b Updated command line format per dev team standards.
devteam <devteam@galaxyproject.org>
parents: 0
diff changeset
5 --maxdiff "${maxDiff}" --minmeanq "${minMeanQ}" --readregex "${readRegex}" --optdupdist "${optDupeDist}"
9227b8c3093b Updated command line format per dev team standards.
devteam <devteam@galaxyproject.org>
parents: 0
diff changeset
6 -j "\$JAVA_JAR_PATH/EstimateLibraryComplexity.jar" -d "${html_file.files_path}" -t "${html_file}"
0
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
7 </command>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
8 <inputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
9 <param format="bam,sam" name="input_file" type="data" label="SAM/BAM dataset"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
10 help="If empty, upload or import a SAM/BAM dataset."/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
11 <param name="out_prefix" value="Library Complexity" type="text"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
12 label="Title for the output file" help="Use this remind you what the job was for." size="80" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
13 <param name="minIDbases" value="5" type="integer" label="Minimum identical bases at starts of reads for grouping" size="5"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
14 help="Total_reads / 4^max_id_bases reads will be compared at a time. Lower numbers = more accurate results and exponentially more time/memory." />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
15 <param name="maxDiff" value="0.03" type="float"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
16 label="Maximum difference rate for identical reads" size="5"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
17 help="The maximum rate of differences between two reads to call them identical" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
18 <param name="minMeanQ" value="20" type="integer"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
19 label="Minimum percentage" size="5"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
20 help="The minimum mean quality of bases in a read pair. Lower average quality reads filtered out from all calculations" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
21 <param name="readRegex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*" type="text" size="120"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
22 label="Regular expression that can be used to parse read names in the incoming SAM file"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
23 help="Names are parsed to extract: tile/region, x coordinate and y coordinate, to estimate optical duplication rate" >
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
24 <sanitizer>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
25 <valid initial="string.printable">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
26 <remove value="&apos;"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
27 </valid>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
28 <mapping initial="none">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
29 <add source="&apos;" target="__sq__"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
30 </mapping>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
31 </sanitizer>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
32 </param>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
33 <param name="optDupeDist" value="100" type="text"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
34 label="The maximum offset between two duplicte clusters in order to consider them optical duplicates." size="5"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
35 help="e.g. 5-10 pixels. Later Illumina software versions multiply pixel values by 10, in which case 50-100" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
36
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
37 </inputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
38 <outputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
39 <data format="html" name="html_file" label="${out_prefix}_lib_complexity.html"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
40 </outputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
41 <tests>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
42 <test>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
43 <param name="input_file" value="picard_input_tiny.sam" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
44 <param name="out_prefix" value="Library Complexity" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
45 <param name="minIDbases" value="5" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
46 <param name="maxDiff" value="0.03" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
47 <param name="minMeanQ" value="20" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
48 <param name="readRegex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
49 <param name="optDupeDist" value="100" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
50 <output name="html_file" file="picard_output_estlibcomplexity_tinysam.html" ftype="html" lines_diff="30" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
51 </test>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
52 </tests>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
53 <help>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
54
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
55 .. class:: infomark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
56
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
57 **Purpose**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
58
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
59 Attempts to estimate library complexity from sequence alone.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
60 Does so by sorting all reads by the first N bases (5 by default) of each read and then
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
61 comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
62 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).
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
63
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
64 Reads of poor quality are filtered out so as to provide a more accurate estimate.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
65 The filtering removes reads with any no-calls in the first N bases or with a mean base quality lower than
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
66 MIN_MEAN_QUALITY across either the first or second read.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
67
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
68 The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
69 calculation of library size. Also, since there is no alignment to screen out technical reads one
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
70 further filter is applied on the data. After examining all reads a histogram is built of
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
71 [#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
72 then removed from the histogram as outliers before library size is estimated.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
73
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
74 **Picard documentation**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
75
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
76 This is a Galaxy wrapper for EstimateLibraryComplexity, a part of the external package Picard-tools_.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
77
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
78 .. _Picard-tools: http://www.google.com/search?q=picard+samtools
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
79
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
80 -----
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
81
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
82 .. class:: infomark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
83
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
84 **Inputs, outputs, and parameters**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
85
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
86 Picard documentation says (reformatted for Galaxy):
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
87
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
88 .. csv-table::
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
89 :header-rows: 1
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
90
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
91 Option Description
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
92 "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."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
93 "OUTPUT=File","Output file to writes per-library metrics to. Required."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
94 "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."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
95 "MAX_DIFF_RATE=Double","The maximum rate of differences between two reads to call them identical. Default value: 0.03. "
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
96 "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."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
97 "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."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
98 "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"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
99 "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. "
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
100
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
101 .. class:: warningmark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
102
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
103 **Warning on SAM/BAM quality**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
104
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
105 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**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
106 flag when it runs Picard, which allows reads to be discarded if they're empty or don't map. This appears
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
107 to be the only way to deal with SAM/BAM that cannot be parsed.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
108
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
109 .. class:: infomark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
110
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
111 **Note on the Regular Expression**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
112
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
113 (from the Picard docs)
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
114 This tool requires a valid regular expression to parse out the read names in the incoming SAM or BAM file.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
115 These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
116 The regular expression should contain three capture groups for the three variables, in order.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
117 Default value: [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
118
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
119
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
120 </help>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
121 </tool>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
122
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
123