Mercurial > repos > yhoogstrate > samtools_parallel_mpileup

comparison samtools-parallel-mpileup.xml @ 0:460f0749aac5 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/samtools_parallel_mpileup_galaxy_wrapper commit ede01f67a8def5be7c88d5c31c2435b3946f1523-dirty
author yhoogstrate
date Thu, 05 Nov 2015 07:49:02 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:460f0749aac5
1 <?xml version="1.0" encoding="UTF-8"?>
2 <tool id="samtools_parallel_mpileup" name="Samtools parallel mpileup" version="0.1.19-a.a">
3 <description>Samtools mpileup (supporting parallelization)</description>
4
5 <requirements>
6 <requirement type="package" version="0.1.19-a">samtools_parallel_mpileup</requirement>
7 <requirement type="package" version="0.1.19">samtools</requirement>
8 </requirements>
9
10 <version_command>samtools-parallel-mpileup 2&gt;&amp;1 | grep Version</version_command>
11
12 <command>
13 #if $reference_genome_source.source_select == "attribute" and len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) != 1
14 echo "Invalid number of dbkeys are found: ${ len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) }, while only one should be used. Make sure that the alignments are done on the same reference genome and that 'tool-data/all_fasta.loc' is configured properly!" >&amp;2
15 #else
16 #if $mpileup_parallelization.mpileup_parallelization_select == "true"
17 samtools-parallel-mpileup mpileup
18 -t $mpileup_parallelization.samtools_threads
19 #else
20 samtools mpileup
21 #end if
22 -f
23 #if $reference_genome_source.source_select == "indexed_filtered"
24 "$reference_genome_source.reference_genome"
25 #else if $reference_genome_source.source_select == "indexed_all"
26 "$reference_genome_source.reference_genome"
27 #else if $reference_genome_source.source_select == "history"
28 "$reference_genome_source.reference_genome"
29 #else
30 <!--
31 This is a workaround to obtain the "genome.fa" file that
32 corresponds to the dbkey of the alignments.
33 Because this file is "calculated" during run-time, it can
34 be used in a workflow.
35 -->
36 "${ filter( lambda x: str( x[0] ) == str( { alignment.metadata.dbkey:True for alignment in $alignments }.keys()[0] ), $__app__.tool_data_tables[ 'all_fasta' ].get_fields() )[0][-1] }"
37 #end if
38
39 #if $extended_parameters_regions.samtools_regions == "region"
40 -r $extended_parameters_regions.$samtools_r
41 #elif $extended_parameters_regions.samtools_regions == "regions_file_pos" or $extended_parameters_regions.samtools_regions == "regions_file_bed"
42 -l $extended_parameters_regions.$samtools_l
43 #end if
44
45 #if $extended_parameters.parameters == "extended"
46 $extended_parameters.samtools_6
47 $extended_parameters.samtools_A
48 $extended_parameters.samtools_B
49 -C $extended_parameters.samtools_C
50 -d $extended_parameters.samtools_d
51 $extended_parameters.samtools_E
52 -M $extended_parameters.samtools_M
53 $extended_parameters.samtools_R
54 -q $extended_parameters.samtools_q
55 -Q $extended_parameters.samtools_Q
56
57 -e $extended_parameters.samtools_e
58 -F $extended_parameters.samtools_F
59 -h $extended_parameters.samtools_h
60 $extended_parameters.samtools_I
61 -L $extended_parameters.samtools_L
62 -m $extended_parameters.samtools_m
63 -o $extended_parameters.samtools_o
64 $extended_parameters.samtools_p
65 -P $extended_parameters.samtools_P
66 #end if
67
68 #for $alignment in $alignments
69 ${alignment}
70 #end for
71
72 2> stderr_1.txt
73
74 #if $sort_mpileup
75 | sort -k1,1V -k2,2g
76 #end if
77
78 > $output ;
79 cat stderr_1.txt
80 #end if
81 </command>
82
83 <inputs>
84 <param format="bam,sam" multiple="true" name="alignments" type="data" label="Alignment file" help="Mapped reads in BAM or SAM format."/>
85
86 <!-- Find out how to access the reference genome from the BAM file(s) -->
87 <conditional name="reference_genome_source">
88 <param name="source_select" type="select" label="Fasta Source">
89 <option value="indexed_filtered">Use a built-in index (which fits your reference)</option>
90 <option value="history">Use reference from the history</option>
91 <option value="indexed_all">Use a built-in index (entire list) - avoid this option if possible; only useful if you design a workflow</option>
92 <option value="attribute">Use a built-in index based on the 'metadata.dbkey' attribute; ideal in workflows</option>
93 </param>
94 <when value="indexed_filtered">
95 <param name="reference_genome" type="select" label="Reference Genome used during alignment (fasta)" >
96 <options from_data_table="all_fasta">
97 <column name="name" index="2"/>
98 <column name="dbkey" index="1"/>
99 <column name="value" index="3"/><!-- Value is the path of the fasta file -->
100 <filter type="data_meta" ref="alignments" multiple="false" key="dbkey" column="1" />
101 <validator type="no_options" message="No indexes are available for the selected input dataset" />
102 </options>
103 </param>
104 </when>
105 <when value="history">
106 <param name="reference_genome" format="fasta" type="data" label="Reference Genome used during alignment (fasta)" help="Reference genome (genome.fa) that corresponds to the *.bam file." />
107 </when>
108 <when value="indexed_all">
109 <param name="reference_genome" type="select" label="Reference Genome used during alignment (fasta)" >
110 <options from_data_table="all_fasta">
111 <column name="name" index="2"/>
112 <column name="dbkey" index="1"/>
113 <column name="value" index="3"/><!-- Value is the path of the fasta file -->
114 <validator type="no_options" message="No indexes are available for the selected input dataset" />
115 </options>
116 </param>
117 </when>
118 <when value="attribute" />
119 </conditional>
120
121 <conditional name="extended_parameters_regions">
122 <param name="samtools_regions" type="select" label="Region specific parameters" help="Let samtools target specific genomic locations.">
123 <option value="entire_genome">Entire genome</option>
124 <option value="region">Specific region</option>
125 <option value="regions_file_pos">Specific positions (file); list of positions</option>
126 <option value="regions_file_bed">Specific regions (file); list of regions in BED</option>
127 </param>
128 <when value="entire_genome">
129 </when>
130 <when value="region">
131 <param type="text" name="samtools_r" label="Samtools: region in which pileup is generated" help="chr:pos or chr:start-end" />
132 </when>
133 <when value="regions_file_pos">
134 <param type="data" name="samtools_l" format="tabular" label="Samtools: list of positions (chr pos)" />
135 </when>
136 <when value="regions_file_bed">
137 <param type="data" name="samtools_l" format="bed" label="Samtools: specific regions (BED)" />
138 </when>
139 </conditional>
140
141 <conditional name="mpileup_parallelization">
142 <param name="mpileup_parallelization_select" type="select" label="Use parallelization for the mpileup generation" help="Especially if larger numbers of bam/sam files are processed, or the file infrastructure is optimized for IO-paralellization, this feature might improve performance.">
143 <option value="false">No (uses original build of samtools)</option>
144 <option value="true" selected="true">Yes (uses samtools-parallel-mpileup)</option>
145 </param>
146 <when value="false" />
147 <when value="true">
148 <param type="integer" name="samtools_threads" value="2" min="1" label="Samtools: mpileup threads" />
149 </when>
150 </conditional>
151
152 <param name="sort_mpileup" type="boolean" truevalue="true" falsevalue="false" label="Sort mpileup file" help="Because parallelization may disrupt the outputs order, sorting can be conveniet for e.g. testing. Notice that this function has only use in a limited number of situations but consumes (much) resources. Only use it if it's really neccesairy." />
153
154 <conditional name="extended_parameters">
155 <param name="parameters" type="select" label="Advanced parameters" help="For more advanced VarScan and samtools settings.">
156 <option value="default">Default settings</option>
157 <option value="extended">Extended settings</option>
158 </param>
159 <when value="default" />
160 <when value="extended">
161 <param type="boolean" name="samtools_6" falsevalue="" truevalue=" -6" label="Samtools: assume the quality is in the Illumina-1.3+ encoding" />
162 <param type="boolean" name="samtools_A" falsevalue="" truevalue=" -A" label="Samtools: count anomalous read pairs" />
163 <param type="boolean" name="samtools_B" falsevalue="" truevalue=" -B" label="Samtools: disable BAQ computation" />
164 <param type="integer" name="samtools_C" value="0" label="Samtools: parameter for adjusting mapQ; 0 to disable [0]" />
165 <param type="integer" name="samtools_d" value="250" label="Samtools: max per-BAM depth to avoid excessive memory usage [250]" />
166 <param type="boolean" name="samtools_E" falsevalue="" truevalue=" -E" label="Samtools: recalculate extended BAQ on the fly thus ignoring existing BQs" />
167 <param type="integer" name="samtools_M" value="60" label="cap mapping quality at INT [60]" />
168 <param type="boolean" name="samtools_R" falsevalue="" truevalue=" -R" label="Samtools: ignore RG tags" />
169 <param type="integer" name="samtools_q" value="0" label="Samtools: skip alignments with mapQ smaller than INT [0]" />
170 <param type="integer" name="samtools_Q" value="13" label="Samtools: skip bases with baseQ/BAQ smaller than INT [13]" />
171
172 <param type="integer" name="samtools_e" value="20" label="Samtools: Phred-scaled gap extension seq error probability [20]" />
173 <param type="float" name="samtools_F" value="0.002" label="Samtools: minimum fraction of gapped reads for candidates [0.002]" help="Alias: -F" />
174 <param type="integer" name="samtools_h" value="100" label="Samtools: coefficient for homopolymer errors [100]" />
175 <param type="boolean" name="samtools_I" falsevalue="" truevalue=" -I" label="Samtools: do not perform indel calling" />
176 <param type="integer" name="samtools_L" value="250" label="Samtools: max per-sample depth for INDEL calling [250]" />
177 <param type="integer" name="samtools_m" value="1" label="Samtools: minimum gapped reads for indel candidates [1]" help="Alias: -m" />
178 <param type="integer" name="samtools_o" value="40" label="Samtools: Phred-scaled gap open sequencing error probability [40]" />
179 <param type="boolean" name="samtools_p" falsevalue="" truevalue=" -p" label="Samtools: apply -m and -F per-sample to increase sensitivity" />
180 <param type="text" name="samtools_P" value="all" label="Samtools: comma separated list of platforms for indels [all]" />
181 </when>
182 </conditional>
183 </inputs>
184
185 <outputs>
186 <data format="mpileup" name="output" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}" />
187 </outputs>
188
189 <tests>
190 <test><!-- Use classical samtools -->
191 <param name="alignments" value="example.bam" ftype="bam" />
192
193 <param name="source_select" value="history" />
194 <param name="reference_genome" value="example.fa" ftypet="fasta" />
195
196 <param name="samtools_regions" value="entire_genome" />
197
198 <param name="mpileup_parallelization_select" value="false" />
199 <param name="sort_mpileup" value="true" />
200
201 <param name="parameters" value="default" />
202
203
204 <output name="output" file="example.mpileup" />
205 </test>
206 <test><!-- Use parallelized samtools - @todo replace with sambamba! -->
207 <param name="alignments" value="example.bam" ftype="bam" />
208
209 <param name="source_select" value="history" />
210 <param name="reference_genome" value="example.fa" ftypet="fasta" />
211
212 <param name="samtools_regions" value="entire_genome" />
213
214 <param name="mpileup_parallelization_select" value="true" />
215 <param name="samtools_threads" value="2" />
216 <param name="sort_mpileup" value="true" />
217
218 <param name="parameters" value="default" />
219
220
221 <output name="output" file="example.mpileup.parallel" />
222 </test>
223 </tests>
224
225 <help>
226 **Samtools mpileup (supporting parallelization)**
227
228 SAM (Sequence Alignment/Map) format is a generic format for storing large nucleotide sequence alignments. SAM aims to be a format that:
229
230 Is flexible enough to store all the alignment information generated by various alignment programs;
231 Is simple enough to be easily generated by alignment programs or converted from existing alignment formats;
232 Is compact in file size;
233 Allows most of operations on the alignment to work on a stream without loading the whole alignment into memory;
234 Allows the file to be indexed by genomic position to efficiently retrieve all reads aligning to a locus.
235 SAM Tools provide various utilities for manipulating alignments in the SAM format, including sorting, merging, indexing and generating alignments in a per-position format.
236
237 SAMtools is hosted by SourceForge.net. The project page is http://samtools.sourceforge.net/. The source code releases are available from the download page. You can check out the most recent source code from the github project page with:
238 git clone git://github.com/samtools/samtools.git
239 https://github.com/mydatascience/parallel-mpileup/
240
241 Because samtools does not support parallization of the mpileup command, the project was forked to include paralellization support:
242
243
244 However, since the project seems to lack support and contains fatal bugs this project was forked at:
245 https://github.com/yhoogstrate/parallel-mpileup/
246
247
248 **Input formats**
249
250 Satmools accepts sequencing alignments in the same, either SAM or BAM format (http://samtools.sourceforge.net/). The alignment files have to be linked to a reference genome by galaxy. This is indicated under every history item with e.g.: *"database: hg19"* for a link to hg19, or *"database: ?"* if the link is missing.
251
252 **Installation**
253
254 The installation is fully automatic.
255
256 **License**
257
258 * parallel-mpileup: MIT License (https://github.com/yhoogstrate/parallel-mpileup/blob/master/samtools-0.1.19/COPYING)
259 * samtool: MIT License
260
261
262 Contact
263 -------
264
265 The tool wrapper has been written by Youri Hoogstrate from the Erasmus
266 Medical Center (Rotterdam, Netherlands) on behalf of the Translational
267 Research IT (TraIT) project:
268
269 http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch
270
271 More tools by the Translational Research IT (TraIT) project can be found
272 in the following toolsheds:
273
274 http://toolshed.g2.bx.psu.edu/
275
276 http://testtoolshed.g2.bx.psu.edu/
277 </help>
278 <citations>
279 <citation type="bibtex">
280 @unpublished{samtools_parallel_mpileup,
281 author = {Youri Hoogstrate},
282 title = { Samtools parallel-mpileup, fork of classical samtools },
283 year = 2014,
284 url = { https://github.com/yhoogstrate/parallel-mpileup }
285 }
286 </citation>
287 <citation type="bibtex">
288 @misc{SAM_def,
289 title={Definition of SAM/BAM format},
290 url = {https://samtools.github.io/hts-specs/SAMv1.pdf},}
291 </citation>
292 <citation type="bibtex">
293 @misc{SamTools_github,
294 title={SAMTools GitHub page},
295 url = {https://github.com/samtools/samtools},}
296 </citation>
297 </citations>
298 </tool>