Mercurial > repos > devteam > picard_122_up

comparison picard_EstimateLibraryComplexity.xml @ 0:b76a4f17bbbb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Thu, 23 Oct 2014 11:31:30 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:b76a4f17bbbb
1 <tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="1.122.0">
2 <description>assess sequence library complexity from read sequences</description>
3 <requirements>
4 <requirement type="package" version="1.122.0">picard</requirement>
5 </requirements>
6
7 <macros>
8 <import>picard_macros.xml</import>
9 </macros>
10
11 <command>
12 @java_options@
13
14 java -jar \$JAVA_JAR_PATH/EstimateLibraryComplexity.jar
15
16 INPUT="${inputFile}"
17 OUTPUT="${outFile}"
18
19 MIN_IDENTICAL_BASES="${min_identical_bases}"
20 MAX_DIFF_RATE="${max_diff_rate}"
21 MIN_MEAN_QUALITY="${min_mean_quality}"
22 MAX_GROUP_RATIO="${max_group_ratio}"
23 READ_NAME_REGEX="${read_name_regex}"
24 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
25
26 VALIDATION_STRINGENCY="${validation_stringency}"
27 QUIET=true
28 VERBOSITY=ERROR
29
30 </command>
31 <inputs>
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" />
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"/>
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"/>
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"/>
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"/>
37
38 <param name="read_name_regex" type="text" size="40" 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]+).*.">
39 <sanitizer>
40 <valid initial="string.printable">
41 </valid>
42 </sanitizer>
43 </param>
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"/>
45
46 <expand macro="VS" />
47
48 </inputs>
49
50 <outputs>
51 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/>
52 </outputs>
53
54 <tests>
55 <test>
56 <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/>
57 <param name="min_identical_bases" value="5"/>
58 <param name="max_diff_rate" value="0.03"/>
59 <param name="min_mean_quality" value="20"/>
60 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
61 <param name="optical_duplicate_pixel_distance" value="100"/>
62 <param name="max_group_ratio" value="500"/>
63 <param name="validation_stringency" value="LENIENT"/>
64 <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/>
65 </test>
66 </tests>
67
68 <stdio>
69 <exit_code range="1:" level="fatal"/>
70 </stdio>
71
72 <help>
73
74 **Purpose**
75
76 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)
77 of each read and then comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be duplicates
78 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).
79
80 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
81 N bases or with a mean base quality lower than MIN_MEAN_QUALITY across either the first or second read.
82
83 Unpaired reads are ignored in this computation.
84 The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the calculation of library size.
85
86 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
87 is built of [#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are then removed from the Histogram
88 as outliers before library size is estimated.
89
90 @dataset_collections@
91
92 @description@
93
94 MIN_IDENTICAL_BASES=Integer The minimum number of bases at the starts of reads that must be identical for reads to be
95 grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads
96 will be compared at a time, so lower numbers will produce more accurate results but
97 consume exponentially more memory and CPU. Default value: 5.
98
99 MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value:
100 0.03.
101
102 MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads
103 with lower average quality are filtered out and not considered in any calculations.
104 Default value: 20.
105
106 MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group
107 size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then
108 the mean expected group size would be approximately 10 reads. Default value: 500.
109
110 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
111 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
112 These values are used to estimate the rate of optical duplication in order to give a more
113 accurate estimated library size. Set this option to null to disable optical duplicate
114 detection. The regular expression should contain three capture groups for the three
115 variables, in order. It must match the entire read name. Note that if the default regex
116 is specified, a regex match is not actually done, but instead the read name is split on
117 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
118 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
119 are assumed to be tile, x and y values. Default value:
120 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
121
122 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
123 The maximum offset between two duplicte clusters in order to consider them optical
124 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
125 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
126 which case 50-100 is more normal. Default value: 100.
127
128
129 @more_info@
130
131 </help>
132 </tool>
133
134