picard: picard_EstimateLibraryComplexity.xml annotate

annotate picard_EstimateLibraryComplexity.xml @ 14:465cbb0cf2eb draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f

author	devteam
date	Wed, 07 Dec 2016 14:56:30 -0500
parents	7e6fd3d0f16e
children	5053a18d9bc8

rev	line source
8 3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty devteam parents: 6 diff changeset	1 <tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="@TOOL_VERSION@.0">
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	2 <description>assess sequence library complexity from read sequences</description>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	3 <macros>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	4 <import>picard_macros.xml</import>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	5 </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	6 <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	7 <command detect_errors="exit_code"><![CDATA[
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	8 @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	9 @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	10 picard
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	11 EstimateLibraryComplexity
13 7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	12
14 465cbb0cf2eb planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f devteam parents: 13 diff changeset	13 INPUT='$escaped_element_identifier'
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	14 OUTPUT="${outFile}"
13 7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	15
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	16 MIN_IDENTICAL_BASES="${min_identical_bases}"
3d4f1fa26f0e Uploaded devteam parents: diff changeset	17 MAX_DIFF_RATE="${max_diff_rate}"
3d4f1fa26f0e Uploaded devteam parents: diff changeset	18 MIN_MEAN_QUALITY="${min_mean_quality}"
3d4f1fa26f0e Uploaded devteam parents: diff changeset	19 MAX_GROUP_RATIO="${max_group_ratio}"
6 4ff1e04010e6 Uploaded devteam parents: 5 diff changeset	20 #import pipes
4ff1e04010e6 Uploaded devteam parents: 5 diff changeset	21 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	22 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${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 3d4f1fa26f0e Uploaded devteam parents: diff changeset	24 VALIDATION_STRINGENCY="${validation_stringency}"
3d4f1fa26f0e Uploaded devteam parents: diff changeset	25 QUIET=true
3d4f1fa26f0e Uploaded devteam parents: diff changeset	26 VERBOSITY=ERROR
13 7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	27
12 05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92 devteam parents: 9 diff changeset	28 ]]></command>
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	29 <inputs>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	30 <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	31 <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	32 <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	33 <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	34 <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	35
9 5eaa8a968300 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1 devteam parents: 8 diff changeset	36 <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]+)..">
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	37 <sanitizer>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	38 <valid initial="string.printable">
3d4f1fa26f0e Uploaded devteam parents: diff changeset	39 </valid>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	40 </sanitizer>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	41 </param>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	42 <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	43
3d4f1fa26f0e Uploaded devteam parents: diff changeset	44 <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	45
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	46 </inputs>
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	47
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	48 <outputs>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	49 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	50 </outputs>
13 7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	51
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	52 <tests>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	53 <test>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	54 <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	55 <param name="min_identical_bases" value="5"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	56 <param name="max_diff_rate" value="0.03"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	57 <param name="min_mean_quality" value="20"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	58 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	59 <param name="optical_duplicate_pixel_distance" value="100"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	60 <param name="max_group_ratio" value="500"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	61 <param name="validation_stringency" value="LENIENT"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	62 <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	63 </test>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	64 </tests>
13 7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	65
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	66
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	67 <help>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	68
3d4f1fa26f0e Uploaded devteam parents: diff changeset	69 Purpose
3d4f1fa26f0e Uploaded devteam parents: diff changeset	70
3d4f1fa26f0e Uploaded devteam parents: diff changeset	71 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	72 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	73 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	74
3d4f1fa26f0e Uploaded devteam parents: diff changeset	75 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	76 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	77
3d4f1fa26f0e Uploaded devteam parents: diff changeset	78 Unpaired reads are ignored in this computation.
3d4f1fa26f0e Uploaded devteam parents: diff changeset	79 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	80
3d4f1fa26f0e Uploaded devteam parents: diff changeset	81 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	82 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	83 as outliers before library size is estimated.
3d4f1fa26f0e Uploaded devteam parents: diff changeset	84
3d4f1fa26f0e Uploaded devteam parents: diff changeset	85 @dataset_collections@
3d4f1fa26f0e Uploaded devteam parents: diff changeset	86
3d4f1fa26f0e Uploaded devteam parents: diff changeset	87 @description@
3d4f1fa26f0e Uploaded devteam parents: diff changeset	88
13 7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	89 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	90 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	91 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	92 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	93
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	94 MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value:
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	95 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	96
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	97 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	98 with lower average quality are filtered out and not considered in any calculations.
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	99 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	100
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	101 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	102 size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	103 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	104
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	105 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	106 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	107 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	108 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	109 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	110 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	111 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	112 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	113 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	114 are assumed to be tile, x and y values. Default value:
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	115 [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	116
7e6fd3d0f16e planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e devteam parents: 12 diff changeset	117 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	118 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	119 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	120 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	121 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	122
5 3d4f1fa26f0e Uploaded devteam parents: diff changeset	123
3d4f1fa26f0e Uploaded devteam parents: diff changeset	124 @more_info@
3d4f1fa26f0e Uploaded devteam parents: diff changeset	125
3d4f1fa26f0e Uploaded devteam parents: diff changeset	126 </help>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	127 </tool>
3d4f1fa26f0e Uploaded devteam parents: diff changeset	128
3d4f1fa26f0e Uploaded devteam parents: diff changeset	129

Mercurial > repos > devteam > picard

annotate picard_EstimateLibraryComplexity.xml @ 14:465cbb0cf2eb draft