annotate picard_EstimateLibraryComplexity.xml @ 6:4ff1e04010e6 draft

Uploaded
author devteam
date Thu, 15 Jan 2015 15:37:04 -0500
parents 3d4f1fa26f0e
children 3a3234d7a2e8
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
1 <tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="1.126.0">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
2 <description>assess sequence library complexity from read sequences</description>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
3 <requirements>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
4 <requirement type="package" version="1.126.0">picard</requirement>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
5 </requirements>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
6
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
7 <macros>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
8 <import>picard_macros.xml</import>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
9 </macros>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
10
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
11 <command>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
12 @java_options@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
13
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
14 java -jar \$JAVA_JAR_PATH/picard.jar
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
15 EstimateLibraryComplexity
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
16
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
17 INPUT="${inputFile}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
18 OUTPUT="${outFile}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
19
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
20 MIN_IDENTICAL_BASES="${min_identical_bases}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
21 MAX_DIFF_RATE="${max_diff_rate}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
22 MIN_MEAN_QUALITY="${min_mean_quality}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
23 MAX_GROUP_RATIO="${max_group_ratio}"
6
4ff1e04010e6 Uploaded
devteam
parents: 5
diff changeset
24 #import pipes
4ff1e04010e6 Uploaded
devteam
parents: 5
diff changeset
25 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
26 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
27
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
28 VALIDATION_STRINGENCY="${validation_stringency}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
29 QUIET=true
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
30 VERBOSITY=ERROR
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
31
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
32 </command>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
33 <inputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
34 <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" />
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
35 <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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
36 <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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
37 <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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
38 <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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
39
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
40 <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]+).*.">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
41 <sanitizer>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
42 <valid initial="string.printable">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
43 </valid>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
44 </sanitizer>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
45 </param>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
46 <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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
47
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
48 <expand macro="VS" />
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
49
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
50 </inputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
51
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
52 <outputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
53 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
54 </outputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
55
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
56 <tests>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
57 <test>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
58 <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
59 <param name="min_identical_bases" value="5"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
60 <param name="max_diff_rate" value="0.03"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
61 <param name="min_mean_quality" value="20"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
62 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
63 <param name="optical_duplicate_pixel_distance" value="100"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
64 <param name="max_group_ratio" value="500"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
65 <param name="validation_stringency" value="LENIENT"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
66 <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
67 </test>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
68 </tests>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
69
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
70 <stdio>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
71 <exit_code range="1:" level="fatal"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
72 </stdio>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
73
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
74 <help>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
75
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
76 **Purpose**
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
77
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
78 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)
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
79 of each read and then comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be duplicates
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
80 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).
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
81
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
82 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
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
83 N bases or with a mean base quality lower than MIN_MEAN_QUALITY across either the first or second read.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
84
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
85 Unpaired reads are ignored in this computation.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
86 The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the calculation of library size.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
87
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
88 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
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
89 is built of [#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are then removed from the Histogram
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
90 as outliers before library size is estimated.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
91
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
92 @dataset_collections@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
93
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
94 @description@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
95
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
96 MIN_IDENTICAL_BASES=Integer The minimum number of bases at the starts of reads that must be identical for reads to be
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
97 grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
98 will be compared at a time, so lower numbers will produce more accurate results but
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
99 consume exponentially more memory and CPU. Default value: 5.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
100
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
101 MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
102 0.03.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
103
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
104 MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
105 with lower average quality are filtered out and not considered in any calculations.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
106 Default value: 20.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
107
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
108 MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
109 size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
110 the mean expected group size would be approximately 10 reads. Default value: 500.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
111
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
112 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
113 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
114 These values are used to estimate the rate of optical duplication in order to give a more
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
115 accurate estimated library size. Set this option to null to disable optical duplicate
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
116 detection. The regular expression should contain three capture groups for the three
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
117 variables, in order. It must match the entire read name. Note that if the default regex
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
118 is specified, a regex match is not actually done, but instead the read name is split on
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
119 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
120 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
121 are assumed to be tile, x and y values. Default value:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
122 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
123
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
124 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
125 The maximum offset between two duplicte clusters in order to consider them optical
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
126 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
127 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
128 which case 50-100 is more normal. Default value: 100.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
129
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
130
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
131 @more_info@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
132
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
133 </help>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
134 </tool>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
135
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
136