Mercurial > repos > devteam > picard
annotate picard_EstimateLibraryComplexity.xml @ 15:a5a13ea16d17 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 5ebd6c8453b49dd6a36e372eb1eb6e323bb7ad8a
author | iuc |
---|---|
date | Tue, 19 Jun 2018 11:28:30 -0400 |
parents | 486d7500da69 |
children | d837223d4ad2 |
rev | line source |
---|---|
14
486d7500da69
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 7036343b9ac0a0ffc2ce4f6db465b9298ef05e73
iuc
parents:
9
diff
changeset
|
1 <tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="@TOOL_VERSION@.@WRAPPER_VERSION@"> |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
2 <description>assess sequence library complexity from read sequences</description> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
3 <macros> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
4 <import>picard_macros.xml</import> |
15
a5a13ea16d17
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 5ebd6c8453b49dd6a36e372eb1eb6e323bb7ad8a
iuc
parents:
14
diff
changeset
|
5 <token name="@WRAPPER_VERSION@">1</token> |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
6 </macros> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
7 <expand macro="requirements" /> |
7
08f69add4d06
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
4
diff
changeset
|
8 <command detect_errors="exit_code"><![CDATA[ |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
9 @java_options@ |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
10 @symlink_element_identifier@ |
7
08f69add4d06
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
4
diff
changeset
|
11 picard |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
12 EstimateLibraryComplexity |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
13 |
9
41b8d087a2d2
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f
devteam
parents:
8
diff
changeset
|
14 INPUT='$escaped_element_identifier' |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
15 OUTPUT="${outFile}" |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
16 |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
17 MIN_IDENTICAL_BASES="${min_identical_bases}" |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
18 MAX_DIFF_RATE="${max_diff_rate}" |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
19 MIN_MEAN_QUALITY="${min_mean_quality}" |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
20 MAX_GROUP_RATIO="${max_group_ratio}" |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
21 #import pipes |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
22 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
23 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
24 |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
25 VALIDATION_STRINGENCY="${validation_stringency}" |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
26 QUIET=true |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
27 VERBOSITY=ERROR |
15
a5a13ea16d17
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 5ebd6c8453b49dd6a36e372eb1eb6e323bb7ad8a
iuc
parents:
14
diff
changeset
|
28 @TMPDIR_OPTION@ |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
29 |
7
08f69add4d06
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
4
diff
changeset
|
30 ]]></command> |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
31 <inputs> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
32 <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" /> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
33 <param name="min_identical_bases" type="integer" value="5" label="The minimum number of bases at the starts of reads that must be identical for reads to be grouped together for duplicate detection" help="MIN_IDENTICAL_BASES; 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=5"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
34 <param name="max_diff_rate" type="float" value="0.03" label="The maximum rate of differences between two reads to call them identical" help="MAX_DIFF_RATE; default=0.03"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
35 <param name="min_mean_quality" type="integer" min="0" max="93" value="20" label="The minimum mean quality of the bases in a read pair for the read to be analyzed" help="MIN_MEAN_QUALITY; Reads with lower average quality are filtered out and not considered in any calculations; default=20"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
36 <param name="max_group_ratio" type="integer" value="500" label="Do not process self-similar groups that are this many times over the mean expected group size" help="MAX_GROUP_RATIO; I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then the mean expected group size would be approximately 10 reads; default-500"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
37 |
4
2589e6207cb4
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 33927a87ba2eee9bf0ecdd376a66241b17b3d734
devteam
parents:
3
diff
changeset
|
38 <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]+).*."> |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
39 <sanitizer> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
40 <valid initial="string.printable"> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
41 </valid> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
42 </sanitizer> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
43 </param> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
44 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
45 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
46 <expand macro="VS" /> |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
47 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
48 </inputs> |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
49 |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
50 <outputs> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
51 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
52 </outputs> |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
53 |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
54 <tests> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
55 <test> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
56 <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
57 <param name="min_identical_bases" value="5"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
58 <param name="max_diff_rate" value="0.03"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
59 <param name="min_mean_quality" value="20"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
60 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
61 <param name="optical_duplicate_pixel_distance" value="100"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
62 <param name="max_group_ratio" value="500"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
63 <param name="validation_stringency" value="LENIENT"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
64 <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
65 </test> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
66 </tests> |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
67 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
68 |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
69 <help> |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
70 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
71 **Purpose** |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
72 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
73 Attempts to estimate library complexity from sequence of read pairs alone. Does so by sorting all reads by the first N bases (5 by default) |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
74 of each read and then comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be duplicates |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
75 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). |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
76 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
77 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 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
78 N bases or with a mean base quality lower than MIN_MEAN_QUALITY across either the first or second read. |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
79 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
80 Unpaired reads are ignored in this computation. |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
81 The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the calculation of library size. |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
82 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
83 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 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
84 is built of [#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are then removed from the Histogram |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
85 as outliers before library size is estimated. |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
86 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
87 @dataset_collections@ |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
88 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
89 @description@ |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
90 |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
91 MIN_IDENTICAL_BASES=Integer The minimum number of bases at the starts of reads that must be identical for reads to be |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
92 grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
93 will be compared at a time, so lower numbers will produce more accurate results but |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
94 consume exponentially more memory and CPU. Default value: 5. |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
95 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
96 MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value: |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
97 0.03. |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
98 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
99 MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
100 with lower average quality are filtered out and not considered in any calculations. |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
101 Default value: 20. |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
102 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
103 MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
104 size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
105 the mean expected group size would be approximately 10 reads. Default value: 500. |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
106 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
107 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
108 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
109 These values are used to estimate the rate of optical duplication in order to give a more |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
110 accurate estimated library size. Set this option to null to disable optical duplicate |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
111 detection. The regular expression should contain three capture groups for the three |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
112 variables, in order. It must match the entire read name. Note that if the default regex |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
113 is specified, a regex match is not actually done, but instead the read name is split on |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
114 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
115 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
116 are assumed to be tile, x and y values. Default value: |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
117 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
118 |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
119 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
120 The maximum offset between two duplicte clusters in order to consider them optical |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
121 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) |
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
122 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
123 which case 50-100 is more normal. Default value: 100. |
8
e417b1d6288d
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
7
diff
changeset
|
124 |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
125 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
126 @more_info@ |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
127 |
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
128 </help> |
14
486d7500da69
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 7036343b9ac0a0ffc2ce4f6db465b9298ef05e73
iuc
parents:
9
diff
changeset
|
129 <expand macro="citations" /> |
3
52fdfc45590a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
diff
changeset
|
130 </tool> |