Mercurial > repos > devteam > picard_122_up

comparison picard_MergeBamAlignment.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="MergeBamAlignment" id="picard_MergeBamAlignment" version="1.122.0">
2 <description>merge alignment data with additional info stored in an unmapped BAM dataset</description>
3 <requirements><requirement type="package" version="1.122.0">picard</requirement></requirements>
4
5 <macros>
6 <import>picard_macros.xml</import>
7 </macros>
8
9 <command>
10 @java_options@
11 #set $picard_dict = "localref.dict"
12 #set $ref_fasta = "localref.fa" ## This is done because picards "likes" .fa extension
13
14 ln -s "${reference_source.ref_file}" "${ref_fasta}" &amp;&amp;
15
16 #if str( $reference_source.reference_source_selector ) == "history":
17
18 java -jar \$JAVA_JAR_PATH/CreateSequenceDictionary.jar REFERENCE="${ref_fasta}" OUTPUT="${picard_dict}"
19 QUIET=true
20 VERBOSITY=ERROR
21
22 &amp;&amp;
23
24 #else:
25
26 #set $ref_fasta = str( $reference_source.ref_file.fields.path )
27
28 #end if
29
30 java -jar \$JAVA_JAR_PATH/MergeBamAlignment.jar
31 UNMAPPED_BAM="${unmapped_bam}"
32
33 PAIRED_RUN=true ##This argument is ignored and will be removed. Required. Possible values: {true, false}
34
35 #if str( $aligned_or_read1_and_read2.aligned_or_read1_and_read2_selector ) == "paired_one_file":
36 #for $dataset in $aligned_or_read1_and_read2.aligned_bams:
37 ALIGNED_BAM="${dataset.aligned_bam}"
38 #end for
39 #elif str( $aligned_or_read1_and_read2.aligned_or_read1_and_read2_selector ) == "paired_two_files":
40 #for $dataset in $aligned_or_read1_and_read2.read1_aligned_bams:
41 READ1_ALIGNED_BAM="${dataset.read1_aligned_bam}"
42 #end for
43 #for $dataset in $aligned_or_read1_and_read2.read2_aligned_bams:
44 READ2_ALIGNED_BAM="${dataset.read1_aligned_bam}"
45 #end for
46 #else
47 #for $dataset in $aligned_or_read1_and_read2.read1_aligned_bams:
48 READ1_ALIGNED_BAM="${dataset.read1_aligned_bam}"
49 #end for
50 #end if
51
52 OUTPUT="${outFile}"
53 REFERENCE_SEQUENCE="${ref_fasta}"
54
55 CLIP_ADAPTERS="${clip_adapters}"
56 IS_BISULFITE_SEQUENCE="${is_bisulfite_sequence}"
57 ALIGNED_READS_ONLY="${aligned_reads_only}"
58 MAX_INSERTIONS_OR_DELETIONS="${max_insertions_or_deletions}"
59
60 #for $attribute in $attributes_to_retain:
61 ATTRIBUTES_TO_RETAIN="${$attribute.attribute}"
62 #end for
63
64 #for $attribute in $attributes_to_remove:
65 ATTRIBUTES_TO_REMOVE="${$attribute.attribute}"
66 #end for
67
68 READ1_TRIM="${read1_trim}"
69 READ2_TRIM="${read2_trim}"
70
71 #if str( $orientations ) != "None":
72 #for $orientation in str( $orientations ).split(','): ## See trello card https://trello.com/c/9nW02Zhd
73 EXPECTED_ORIENTATIONS="${orientation}"
74 #end for
75 #end if
76
77 ALIGNER_PROPER_PAIR_FLAGS="${aligner_proper_pair_flags}"
78 PRIMARY_ALIGNMENT_STRATEGY="${primary_alignment_strategy}"
79 CLIP_OVERLAPPING_READS="${clip_overlapping_reads}"
80 INCLUDE_SECONDARY_ALIGNMENTS="${include_secondary_alignments}"
81 ADD_MATE_CIGAR="${add_mate_cigar}"
82
83 VALIDATION_STRINGENCY="${validation_stringency}"
84
85 SORT_ORDER=coordinate
86 QUIET=true
87 VERBOSITY=ERROR
88
89 </command>
90
91 <inputs>
92
93 <conditional name="reference_source">
94 <param name="reference_source_selector" type="select" label="Load reference genome from">
95 <option value="cached">Local cache</option>
96 <option value="history">History</option>
97 </param>
98 <when value="cached">
99 <param name="ref_file" type="select" label="Use dictionary from the list" help="Select genome from the list">
100 <options from_data_table="picard_indexes">
101 <filter type="sort_by" column="2" />
102 <validator type="no_options" message="No indexes are available" />
103 </options>
104 <validator type="no_options" message="A built-in dictionary is not available for the build associated with the selected input file"/>
105 </param>
106 </when>
107 <when value="history">
108 <param name="ref_file" type="data" format="fasta" label="Use the following dataset to create dictionary" help="You can upload a FASTA sequence to the history from which Picard will automatically generate dictionary using CreateSequenceDictionary command" />
109 </when>
110 </conditional>
111
112 <param format="sam,bam" name="unmapped_bam" type="data" label="Selected unaligned SAM or BAM with original reads" help="UNMAPPED_BAM; This dataset must be sorted in queryname order (use picard_SortSam to do this)" />
113 <conditional name="aligned_or_read1_and_read2">
114 <param name="aligned_or_read1_and_read2_selector" type="select" label="What type of aligned data do you have?">
115 <option value="paired_one_file">Paired data in a single BAM file (ALIGNED_BAM)</option>
116 <option value="paired_two_files">Paired data in separate files (READ1_ALIGNED_BAM and READ2_ALIGNED_BAM)</option>
117 <option value="single_file">Singe end data (READ1_ALIGNED_BAM)</option>
118 </param>
119 <when value="paired_one_file">
120 <repeat name="aligned_bams" title="Aligned SAM or BAM dataset" min="1" help="You can provide multiple datasets">
121 <param name="aligned_bam" type="data" format="sam,bam" label="SAM or BAM dataset(s) with alignment data" help="ALIGNED_BAM"/>
122 </repeat>
123 </when>
124 <when value="paired_two_files">
125 <repeat name="read1_aligned_bams" title="Aligned SAM or BAM dataset for Read 1" min="1" help="You can provide multiple datasets">
126 <param name="read1_aligned_bam" type="data" format="sam,bam" label="SAM or BAM dataset(s) with alignment data for Read1" help="READ1_ALIGNED_BAM"/>
127 </repeat>
128 <repeat name="read2_aligned_bams" title="Aligned SAM or BAM dataset for Read 2" min="1" help="You can provide multiple datasets">
129 <param name="read2_aligned_bam" type="data" format="sam,bam" label="SAM or BAM dataset(s) with alignment data for Read2" help="READ2_ALIGNED_BAM"/>
130 </repeat>
131 </when>
132 <when value="single_file">
133 <repeat name="read1_aligned_bams" title="Aligned SAM or BAM dataset for Single Reads" min="1" help="You can provide multiple datasets">
134 <param name="read1_aligned_bam" type="data" format="sam,bam" label="SAM or BAM dataset(s) with alignment data" help="READ1_ALIGNED_BAM"/>
135 </repeat>
136 </when>
137 </conditional>
138
139 <param name="clip_adapters" type="boolean" checked="true" label="Whether to clip adapters where identified" help="CLIP_ADAPTERS; default=True"/>
140 <param name="is_bisulfite_sequence" type="boolean" label="Whether the data is from bisulfite sequencing (used when caculating the NM tag)" help="IS_BISULFITE_SEQUENCE; default=False"/>
141 <param name="aligned_reads_only" type="boolean" label="Whether to output only aligned reads" help="ALIGNED_READS_ONLY; default=False"/>
142 <param name="max_insertions_or_deletions" type="integer" value="1" label="The maximum number of insertions or deletions permitted for an alignment to be included" help="MAX_INSERTIONS_OR_DELETIONS; Alignments with more than this many insertions or deletions will be ignored. Set to -1 to allow any number of insertions or deletions. default=1"/>
143
144 <repeat name="attributes_to_retain" title="Retain the following alignment attribute" min="0" help="You can provide multiple attributes">
145 <param name="attribute" type="text" size="4" label="Reserved alignment attributes (tags starting with X, Y, or Z) that should be brought over from the alignment data when merging" help="ATTRIBUTES_TO_RETAIN; example: XA"/>
146 </repeat>
147
148 <repeat name="attributes_to_remove" title="Remove the following alignment attribute" min="0" help="You can provide multiple attributes">
149 <param name="attribute" type="text" size="4" label="Attributes from the alignment record that should be removed when merging." help="ATTRIBUTES_TO_REMOVE; This overrides ATTRIBUTES_TO_RETAIN if they share common tags"/>
150 </repeat>
151
152 <param name="read1_trim" type="integer" value="0" label="The number of bases trimmed from the beginning of read 1 prior to alignment" help="READ1_TRIM; default=0"/>
153 <param name="read2_trim" type="integer" value="0" label="The number of bases trimmed from the beginning of read 2 prior to alignment" help="READ2_TRIM; default=0"/>
154
155 <param name="orientations" type="select" multiple="True" display="checkboxes" label="The expected orientation of proper read pairs" help="EXPECTED_ORIENTATIONS; multiple orinetations can be selected">
156 <option value="FR">Forward/Reverse (FR)</option>
157 <option value="RF">Reverse/Forward (RF)</option>
158 <option value="TANDEM">Tandem</option>
159 </param>
160
161
162 <param name="aligner_proper_pair_flags" type="boolean" label="Use the aligner's idea of what a proper pair is rather than computing in this program" help="ALIGNER_PROPER_PAIR_FLAGS; default=False"/>
163
164 <param name="primary_alignment_strategy" type="select" label="Strategy for selecting primary alignment when the aligner has provided more than one alignment for a pair or fragments" help="PRIMARY_ALIGNMENT_STRATEGY; see help below for more info; default=BestMapq">
165 <option value="BestMapq" selected="True">BestMapq</option>
166 <option value="EarliestFragment">EarliestFragment</option>
167 <option value="BestEndMapq">BestEndMapq</option>
168 <option value="MostDistant">MostDistant</option>
169 </param>
170
171 <param name="clip_overlapping_reads" type="boolean" checked="True" label="For paired reads, soft clip the 3' end of each read if necessary so that it does not extend past the 5' end of its mate" help="CLIP_OVERLAPPING_READS; default=True"/>
172 <param name="include_secondary_alignments" type="boolean" checked="True" label="If false, do not write secondary alignments to output" help="INCLUDE_SECONDARY_ALIGNMENTS; default=True"/>
173 <param name="add_mate_cigar" type="boolean" checked="True" label="Adds the mate CIGAR tag (MC) if true, does not if false" help="ADD_MATE_CIGAR; default=True"/>
174 <expand macro="VS" />
175 </inputs>
176 <outputs>
177 <data name="outFile" format="bam" label="${tool.name} on ${on_string}: BAM with merged alignments"/>
178 </outputs>
179 <tests>
180 <test>
181 <param name="reference_source_selector" value="history" />
182 <param name="ref_file" value="picard_MergeBamAlignment_ref.fa" ftype="fasta" />
183 <param name="unmapped_bam" value="picard_MergeBamAlignment_unaligned.bam" ftype="bam"/>
184 <param name="aligned_or_read1_and_read2_selector" value="paired_one_file"/>
185 <param name="aligned_bam" value="picard_MergeBamAlignment_aligned.bam" ftype="bam"/>
186 <param name="clip_adapters" value="True"/>
187 <param name="is_bisulfite_sequence" value="False"/>
188 <param name="aligned_reads_only" value="False"/>
189 <param name="max_insertions_or_deletions" value="1"/>
190 <param name="read1_trim" value="0"/>
191 <param name="read2_trim" value="0"/>
192 <param name="orientation" value="FR"/>
193 <param name="aligner_proper_pair_flags" value="False"/>
194 <param name="primary_alignment_strategy" value="BestMapq"/>
195 <param name="clip_overlapping_reads" value="True"/>
196 <param name="include_secondary_alignments" value="True"/>
197 <param name="add_mate_cigar" value="True"/>
198 <output name="outFile" file="picard_MergeBamAlignment_test1.bam" ftype="bam" lines_diff="2"/>
199 </test>
200 </tests>
201
202 <stdio>
203 <exit_code range="1:" level="fatal"/>
204 </stdio>
205
206 <help>
207
208 .. class:: infomark
209
210 **Purpose**
211
212 Merges alignment data from a SAM or BAM dataset with additional data stored in an unmapped BAM dataset and produces a third SAM or BAM dataset of aligned and unaligned reads.
213
214 @dataset_collections@
215
216 @description@
217
218 UNMAPPED_BAM=File
219 UNMAPPED=File Original SAM or BAM file of unmapped reads, which must be in queryname order. Required.
220
221 ALIGNED_BAM=File
222 ALIGNED=File SAM or BAM file(s) with alignment data. This option may be specified 0 or more times.
223 Cannot be used in conjuction with option(s) READ1_ALIGNED_BAM (R1_ALIGNED)
224 READ2_ALIGNED_BAM (R2_ALIGNED)
225
226 READ1_ALIGNED_BAM=File
227 R1_ALIGNED=File SAM or BAM file(s) with alignment data from the first read of a pair. This option may be
228 specified 0 or more times. Cannot be used in conjuction with option(s) ALIGNED_BAM
229 (ALIGNED)
230
231 READ2_ALIGNED_BAM=File
232 R2_ALIGNED=File SAM or BAM file(s) with alignment data from the second read of a pair. This option may
233 be specified 0 or more times. Cannot be used in conjuction with option(s) ALIGNED_BAM
234 (ALIGNED)
235
236 PAIRED_RUN=Boolean
237 PE=Boolean This argument is ignored and will be removed. Required. Possible values: {true, false}
238
239 JUMP_SIZE=Integer
240 JUMP=Integer The expected jump size (required if this is a jumping library). Deprecated. Use
241 EXPECTED_ORIENTATIONS instead Default value: null. Cannot be used in conjuction with
242 option(s) EXPECTED_ORIENTATIONS (ORIENTATIONS)
243
244 CLIP_ADAPTERS=Boolean Whether to clip adapters where identified. Default value: true. Possible values: {true, false}
245
246 IS_BISULFITE_SEQUENCE=Boolean Whether the lane is bisulfite sequence (used when caculating the NM tag). Default value:
247 false. Possible values: {true, false}
248
249 ALIGNED_READS_ONLY=Boolean Whether to output only aligned reads. Default value: false. Possible values: {true, false}
250
251 MAX_INSERTIONS_OR_DELETIONS=Integer
252 MAX_GAPS=Integer The maximum number of insertions or deletions permitted for an alignment to be included.
253 Alignments with more than this many insertions or deletions will be ignored. Set to -1 to
254 allow any number of insertions or deletions. Default value: 1.
255
256 ATTRIBUTES_TO_RETAIN=String Reserved alignment attributes (tags starting with X, Y, or Z) that should be brought over
257 from the alignment data when merging. This option may be specified 0 or more times.
258
259 ATTRIBUTES_TO_REMOVE=String Attributes from the alignment record that should be removed when merging. This overrides
260 ATTRIBUTES_TO_RETAIN if they share common tags. This option may be specified 0 or more
261 times.
262
263 READ1_TRIM=Integer
264 R1_TRIM=Integer The number of bases trimmed from the beginning of read 1 prior to alignment Default
265 value: 0.
266
267 READ2_TRIM=Integer
268 R2_TRIM=Integer The number of bases trimmed from the beginning of read 2 prior to alignment Default
269 value: 0.
270
271 EXPECTED_ORIENTATIONS=PairOrientation
272 ORIENTATIONS=PairOrientation The expected orientation of proper read pairs. Replaces JUMP_SIZE Possible values: {FR,
273 RF, TANDEM} This option may be specified 0 or more times. Cannot be used in conjuction
274 with option(s) JUMP_SIZE (JUMP)
275
276 ALIGNER_PROPER_PAIR_FLAGS=Boolean
277 Use the aligner's idea of what a proper pair is rather than computing in this program.
278 Default value: false. Possible values: {true, false}
279
280 SORT_ORDER=SortOrder
281 SO=SortOrder The order in which the merged reads should be output. Default value: coordinate.
282 Possible values: {unsorted, queryname, coordinate}
283
284 PRIMARY_ALIGNMENT_STRATEGY=PrimaryAlignmentStrategy
285 Strategy for selecting primary alignment when the aligner has provided more than one
286 alignment for a pair or fragment, and none are marked as primary, more than one is marked
287 as primary, or the primary alignment is filtered out for some reason. BestMapq expects
288 that multiple alignments will be correlated with HI tag, and prefers the pair of
289 alignments with the largest MAPQ, in the absence of a primary selected by the aligner.
290 EarliestFragment prefers the alignment which maps the earliest base in the read. Note
291 that EarliestFragment may not be used for paired reads. BestEndMapq is appropriate for
292 cases in which the aligner is not pair-aware, and does not output the HI tag. It simply
293 picks the alignment for each end with the highest MAPQ, and makes those alignments
294 primary, regardless of whether the two alignments make sense together.MostDistant is also
295 for a non-pair-aware aligner, and picks the alignment pair with the largest insert size.
296 If all alignments would be chimeric, it picks the alignments for each end with the best
297 MAPQ. For all algorithms, ties are resolved arbitrarily. Default value: BestMapq.
298 Possible values: {BestMapq, EarliestFragment, BestEndMapq, MostDistant}
299
300 CLIP_OVERLAPPING_READS=BooleanFor paired reads, soft clip the 3' end of each read if necessary so that it does not
301 extend past the 5' end of its mate. Default value: true. Possible values: {true, false}
302
303 INCLUDE_SECONDARY_ALIGNMENTS=Boolean
304 If false, do not write secondary alignments to output. Default value: true.
305 Possible values: {true, false}
306
307 ADD_MATE_CIGAR=Boolean
308 MC=Boolean Adds the mate CIGAR tag (MC) if true, does not if false. Possible values: {true, false}
309
310
311
312
313 @more_info@
314 </help>
315 </tool>
316
317
318
319
320
321
322
323
324
325
326
327
328