Mercurial > repos > devteam > picard
annotate picard_EstimateLibraryComplexity.xml @ 30:b502c227b5e6 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 0244aa33464cc27d1ce881cb310b8eda36e9a89c
author | iuc |
---|---|
date | Mon, 22 Aug 2022 09:56:00 +0000 |
parents | 6f9c0884a3e7 |
children | f9242e01365a |
rev | line source |
---|---|
19
5053a18d9bc8
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 7036343b9ac0a0ffc2ce4f6db465b9298ef05e73
iuc
parents:
14
diff
changeset
|
1 <tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="@TOOL_VERSION@.@WRAPPER_VERSION@"> |
5 | 2 <description>assess sequence library complexity from read sequences</description> |
3 <macros> | |
4 <import>picard_macros.xml</import> | |
20
2a17c789e0a5
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 5ebd6c8453b49dd6a36e372eb1eb6e323bb7ad8a
iuc
parents:
19
diff
changeset
|
5 <token name="@WRAPPER_VERSION@">1</token> |
5 | 6 </macros> |
8
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
6
diff
changeset
|
7 <expand macro="requirements" /> |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
8 <command detect_errors="exit_code"><![CDATA[ |
5 | 9 @java_options@ |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
10 @symlink_element_identifier@ |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
11 picard |
5 | 12 EstimateLibraryComplexity |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
13 |
14
465cbb0cf2eb
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f
devteam
parents:
13
diff
changeset
|
14 INPUT='$escaped_element_identifier' |
5 | 15 OUTPUT="${outFile}" |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
16 |
5 | 17 MIN_IDENTICAL_BASES="${min_identical_bases}" |
18 MAX_DIFF_RATE="${max_diff_rate}" | |
19 MIN_MEAN_QUALITY="${min_mean_quality}" | |
20 MAX_GROUP_RATIO="${max_group_ratio}" | |
21
6f9c0884a3e7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 78c3dea7dcd0c854fe7e6dc1d2b2349956167661
iuc
parents:
20
diff
changeset
|
21 READ_NAME_REGEX='${ str( $read_name_regex ) }' |
5 | 22 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
23 |
5 | 24 VALIDATION_STRINGENCY="${validation_stringency}" |
25 QUIET=true | |
26 VERBOSITY=ERROR | |
20
2a17c789e0a5
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 5ebd6c8453b49dd6a36e372eb1eb6e323bb7ad8a
iuc
parents:
19
diff
changeset
|
27 @TMPDIR_OPTION@ |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
28 |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
29 ]]></command> |
5 | 30 <inputs> |
31 <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" /> | |
32 <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"/> | |
33 <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"/> | |
34 <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"/> | |
35 <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"/> | |
36 | |
9
5eaa8a968300
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents:
8
diff
changeset
|
37 <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]+).*."> |
21
6f9c0884a3e7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 78c3dea7dcd0c854fe7e6dc1d2b2349956167661
iuc
parents:
20
diff
changeset
|
38 <expand macro="sanitize_query" /> |
5 | 39 </param> |
40 <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"/> | |
41 | |
42 <expand macro="VS" /> | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
43 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
44 </inputs> |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
45 |
5 | 46 <outputs> |
47 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/> | |
48 </outputs> | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
49 |
5 | 50 <tests> |
51 <test> | |
52 <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/> | |
53 <param name="min_identical_bases" value="5"/> | |
54 <param name="max_diff_rate" value="0.03"/> | |
55 <param name="min_mean_quality" value="20"/> | |
56 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/> | |
57 <param name="optical_duplicate_pixel_distance" value="100"/> | |
58 <param name="max_group_ratio" value="500"/> | |
59 <param name="validation_stringency" value="LENIENT"/> | |
60 <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/> | |
61 </test> | |
62 </tests> | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
63 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
64 |
5 | 65 <help> |
66 | |
67 **Purpose** | |
68 | |
69 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) | |
70 of each read and then comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be duplicates | |
71 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). | |
72 | |
73 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 | |
74 N bases or with a mean base quality lower than MIN_MEAN_QUALITY across either the first or second read. | |
75 | |
76 Unpaired reads are ignored in this computation. | |
77 The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the calculation of library size. | |
78 | |
79 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 | |
80 is built of [#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are then removed from the Histogram | |
81 as outliers before library size is estimated. | |
82 | |
83 @dataset_collections@ | |
84 | |
85 @description@ | |
86 | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
87 MIN_IDENTICAL_BASES=Integer The minimum number of bases at the starts of reads that must be identical for reads to be |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
88 grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
89 will be compared at a time, so lower numbers will produce more accurate results but |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
90 consume exponentially more memory and CPU. Default value: 5. |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
91 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
92 MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value: |
5 | 93 0.03. |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
94 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
95 MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
96 with lower average quality are filtered out and not considered in any calculations. |
5 | 97 Default value: 20. |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
98 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
99 MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
100 size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then |
5 | 101 the mean expected group size would be approximately 10 reads. Default value: 500. |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
102 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
103 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
104 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
105 These values are used to estimate the rate of optical duplication in order to give a more |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
106 accurate estimated library size. Set this option to null to disable optical duplicate |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
107 detection. The regular expression should contain three capture groups for the three |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
108 variables, in order. It must match the entire read name. Note that if the default regex |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
109 is specified, a regex match is not actually done, but instead the read name is split on |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
110 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
111 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
112 are assumed to be tile, x and y values. Default value: |
5 | 113 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
114 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
115 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
116 The maximum offset between two duplicte clusters in order to consider them optical |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
117 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
118 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in |
5 | 119 which case 50-100 is more normal. Default value: 100. |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
120 |
5 | 121 |
122 @more_info@ | |
123 | |
124 </help> | |
19
5053a18d9bc8
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 7036343b9ac0a0ffc2ce4f6db465b9298ef05e73
iuc
parents:
14
diff
changeset
|
125 <expand macro="citations" /> |
5 | 126 </tool> |