annotate picard_EstimateLibraryComplexity.xml @ 1:f3e98264fbdd draft

Deleted selected files
author devteam
date Thu, 23 Oct 2014 11:34:04 -0400
parents b76a4f17bbbb
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
1 <tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="1.122.0">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
2 <description>assess sequence library complexity from read sequences</description>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
3 <requirements>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
4 <requirement type="package" version="1.122.0">picard</requirement>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
5 </requirements>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
6
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
7 <macros>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
8 <import>picard_macros.xml</import>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
9 </macros>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
10
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
11 <command>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
12 @java_options@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
13
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
14 java -jar \$JAVA_JAR_PATH/EstimateLibraryComplexity.jar
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
15
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
16 INPUT="${inputFile}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
17 OUTPUT="${outFile}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
18
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
19 MIN_IDENTICAL_BASES="${min_identical_bases}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
20 MAX_DIFF_RATE="${max_diff_rate}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
21 MIN_MEAN_QUALITY="${min_mean_quality}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
22 MAX_GROUP_RATIO="${max_group_ratio}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
23 READ_NAME_REGEX="${read_name_regex}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
24 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
25
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
26 VALIDATION_STRINGENCY="${validation_stringency}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
27 QUIET=true
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
28 VERBOSITY=ERROR
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
29
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
30 </command>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
31 <inputs>
b76a4f17bbbb Uploaded
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" />
b76a4f17bbbb Uploaded
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"/>
b76a4f17bbbb Uploaded
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"/>
b76a4f17bbbb Uploaded
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"/>
b76a4f17bbbb Uploaded
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"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
37
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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]+).*.">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
39 <sanitizer>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
40 <valid initial="string.printable">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
41 </valid>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
42 </sanitizer>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
43 </param>
b76a4f17bbbb Uploaded
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"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
45
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
46 <expand macro="VS" />
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
47
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
48 </inputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
49
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
50 <outputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
51 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
52 </outputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
53
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
54 <tests>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
55 <test>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
56 <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
57 <param name="min_identical_bases" value="5"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
58 <param name="max_diff_rate" value="0.03"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
59 <param name="min_mean_quality" value="20"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
60 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
61 <param name="optical_duplicate_pixel_distance" value="100"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
62 <param name="max_group_ratio" value="500"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
63 <param name="validation_stringency" value="LENIENT"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
64 <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
65 </test>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
66 </tests>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
67
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
68 <stdio>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
69 <exit_code range="1:" level="fatal"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
70 </stdio>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
71
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
72 <help>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
73
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
74 **Purpose**
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
75
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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)
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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).
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
79
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
81 N bases or with a mean base quality lower than MIN_MEAN_QUALITY across either the first or second read.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
82
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
83 Unpaired reads are ignored in this computation.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
84 The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the calculation of library size.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
85
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
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
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
88 as outliers before library size is estimated.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
89
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
90 @dataset_collections@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
91
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
92 @description@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
93
b76a4f17bbbb Uploaded
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
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
95 grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
96 will be compared at a time, so lower numbers will produce more accurate results but
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
97 consume exponentially more memory and CPU. Default value: 5.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
98
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
99 MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
100 0.03.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
101
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
102 MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
103 with lower average quality are filtered out and not considered in any calculations.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
104 Default value: 20.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
105
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
106 MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
107 size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
108 the mean expected group size would be approximately 10 reads. Default value: 500.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
109
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
110 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
111 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
112 These values are used to estimate the rate of optical duplication in order to give a more
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
113 accurate estimated library size. Set this option to null to disable optical duplicate
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
114 detection. The regular expression should contain three capture groups for the three
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
115 variables, in order. It must match the entire read name. Note that if the default regex
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
116 is specified, a regex match is not actually done, but instead the read name is split on
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
117 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
118 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
119 are assumed to be tile, x and y values. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
120 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
121
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
122 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
123 The maximum offset between two duplicte clusters in order to consider them optical
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
124 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
125 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
126 which case 50-100 is more normal. Default value: 100.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
127
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
128
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
129 @more_info@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
130
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
131 </help>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
132 </tool>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
133
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
134