Mercurial > repos > iuc > umi_tools_group

comparison umi-tools_group.xml @ 13:cf25b50eff0a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
author iuc
date Mon, 13 Sep 2021 14:50:56 +0000
parents 30c3906fbf43
children
comparison
equal deleted inserted replaced
12:bc082a79d655 13:cf25b50eff0a
1 <tool id="umi_tools_group" name="UMI-tools group" version="@VERSION@.0"> 1 <tool id="umi_tools_group" name="UMI-tools group" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>Extract UMI from fastq files</description> 2 <description>Extract UMI from fastq files</description>
3 <expand macro="bio_tools"/>
3 <macros> 4 <macros>
4 <import>macros.xml</import> 5 <import>macros.xml</import>
5 </macros> 6 </macros>
6 <expand macro="requirements"> 7 <expand macro="requirements">
7 <requirement type="package" version="1.9">samtools</requirement> 8 <requirement type="package" version="1.12">samtools</requirement>
8 </expand> 9 </expand>
9 <command detect_errors="exit_code"><![CDATA[ 10 <command detect_errors="exit_code"><![CDATA[
10 #if $input.is_of_type("sam"): 11 @LINK_SAM_BAM_INPUT@
11 #set $input_file = $input
12 #else:
13 ln -sf '${input}' 'input.bam' &&
14 ln -sf '$input.metadata.bam_index' 'input.bam.bai' &&
15 #set $input_file = 'input.bam'
16 #end if
17 12
18 umi_tools group 13 umi_tools group
19 --random-seed 0
20 --extract-umi-method $extract_umi_method
21 #if str($extract_umi_method) != 'read_id':
22 --umi-separator '$umi_separator' --umi-tag '$umi_tag'
23 #end if
24 --method $method --edit-distance-threshold $edit_distance_threshold
25 $paired $spliced_is_unique --soft-clip-threshold $soft_clip_threshold
26 $read_length $whole_contig --subset $subset $per_contig $per_gene
27 #if $gene_transcript_map:
28 --gene-transcript-map '$gene_transcript_map'
29 #end if
30 #if len(str($gene_tag)) > 0:
31 --gene-tag '$gene_tag'
32 #end if
33 #if $group_output: 14 #if $group_output:
34 --group-out '$group_out' 15 --group-out '$group_out'
35 #end if 16 #end if
36 #if $input.is_of_type("sam"):
37 --in-sam
38 #end if
39 --output-bam 17 --output-bam
40 -I '$input_file' -S grouped.bam && 18 @GROUPDEDUP_OPTIONS@
41 samtools sort grouped.bam -@ \${GALAXY_SLOTS:-1} -T "\${TMPDIR:-.}" -o '$output' -O BAM 19 @BARCODE_OPTIONS@
20 @UMI_GROUPING_OPTIONS@
21 @SAMBAM_OPTIONS@
22 @FULLSC_OPTIONS@
23 -I '$input_file' -S grouped.bam
24 @ADVANCED_OPTIONS@
25 @LOG@
26 ## TODO using samtools sort is a workaround, for the following error that appears when Galaxy
27 ## compares the generated file with the one in test-data
28 ## `Converting history BAM to SAM failed: 'samtools returned with error 1: stdout=None, stderr=[main_samview] fail to read the header from "/tmp/tmpd8o61jykdedup_out6.bam".\n'. Will compare BAM files`
29 ## may be dropped in the future
30 --no-sort-output
31 && samtools sort --no-PG grouped.bam -@ \${GALAXY_SLOTS:-1} -T "\${TMPDIR:-.}" -o '$output' -O BAM
42 ]]></command> 32 ]]></command>
43 <inputs> 33 <inputs>
44 <param name="input" type="data" format="sam,bam" label="Reads to group in SAM or BAM format" /> 34 <param name="input" type="data" format="sam,bam" label="Reads to group in SAM or BAM format" />
45 <param name="extract_umi_method" argument="--extract-umi-method" type="select">
46 <option value="read_id" selected="True">Read ID</option>
47 <option value="tag">Tag</option>
48 </param>
49 <param name="group_output" argument="--group-out" type="boolean" truevalue="--group-out" falsevalue="" label="Output a flatfile describing the read groups" /> 35 <param name="group_output" argument="--group-out" type="boolean" truevalue="--group-out" falsevalue="" label="Output a flatfile describing the read groups" />
50 <param name="umi_separator" argument="--umi-separator" type="text" label="Separator between read id and UMI." help="Ignored unless extracting by tag" /> 36 <expand macro="groupdedup_options_macro"/>
51 <param name="umi_tag" argument="--umi-tag" type="text" label="Tag which contains UMI." /> 37 <expand macro="barcode_options_macro"/>
52 <param argument="--method" type="select" label="Method used to identify PCR duplicates within reads." help="All methods start by identifying the reads with the same mapping position"> 38 <expand macro="umi_grouping_options_macro"/>
53 <option value="unique">Reads group share the exact same UMI</option> 39 <expand macro="sambam_options_macro"/>
54 <option value="cluster">Identify clusters based on hamming distance</option> 40 <expand macro="fullsc_options_macro"/>
55 <option value="directional">Identify clusters based on distance and counts, restrict network expansion by threshold</option> 41 <expand macro="advanced_options_macro"/>
56 </param> 42 <expand macro="log_input_macro"/>
57 <param name="edit_distance_threshold" argument="--edit-distance-threshold" type="integer" value="1" label="Edit distance threshold" help="For the adjacency and cluster methods the threshold for the edit distance to connect two UMIs in the network can be increased. The default value of 1 works best unless the UMI is very long (&gt;14bp)" />
58 <param argument="--paired" type="boolean" truevalue="--paired" falsevalue="" label="BAM is paired end" help="This will also force the use of the template length to determine reads with the same mapping coordinates." />
59 <param name="spliced_is_unique" argument="--spliced-is-unique" type="boolean" truevalue="--spliced-is-unique" falsevalue="" label="Spliced reads are unique" help="Causes two reads that start in the same position on the same strand and having the same UMI to be considered unique if one is spliced and the other is not. (Uses the 'N' cigar operation to test for splicing)" />
60 <param name="soft_clip_threshold" argument="--soft-clip-threshold" type="integer" value="4" label="Soft clip threshold" help="Mappers that soft clip, will sometimes do so rather than mapping a spliced read if there is only a small overhang over the exon junction. By setting this option, you can treat reads with at least this many bases soft-clipped at the 3' end as spliced." />
61 <param name="read_length" argument="--read-length" type="boolean" truevalue="--read-length" falsevalue="" label="Use the read length as as a criterion when deduping" />
62 <param name="whole_contig" argument="--whole-contig" type="boolean" truevalue="--whole-contig" falsevalue="" label="Consider all alignments to a single contig together" help="This is useful if you have aligned to a transcriptome multi-fasta" />
63 <param argument="--subset" type="float" min="0.0" max="1.0" value="1.0" label="Only consider a random selection of the reads" />
64 <param argument="--chrom" type="boolean" truevalue="--chrom" falsevalue="" label="Only consider a single chromosome" />
65 <param name="per_contig" argument="--per-contig" type="boolean" truevalue="--per-contig" falsevalue="" label="Deduplicate per contig" help="Field 3 in BAM; RNAME. All reads with the same contig will be considered to have the same alignment position. This is useful if your library prep generates PCR duplicates with non identical alignment positions such as CEL-Seq. In this case, you would align to a reference transcriptome with one transcript per gene" />
66 <param name="per_gene" argument="--per-gene" type="boolean" truevalue="--per-gene" falsevalue="" label="Deduplicate per gene" help="As above except with this option you can align to a reference transcriptome with more than one transcript per gene. You need to also provide a map of genes to transcripts. This will also add a metacontig ('MC') tag to the output BAM file." />
67 <param name="gene_transcript_map" argument="--gene-transcript-map" type="data" format="tabular" optional="True" label="Tabular file mapping genes to transripts" />
68 <param name="gene_tag" argument="--gene-tag" type="text" optional="True" label="Deduplicate by this gene tag" help="As --per-gene except here the gene information is encoded in the bam read tag specified so you do not need to supply the mapping file." />
69 </inputs> 43 </inputs>
70 <outputs> 44 <outputs>
71 <data format="bam" name="output" /> 45 <data format="bam" name="output" />
72 <data format="tabular" name="group_out"> 46 <data format="tabular" name="group_out">
73 <filter>group_out</filter> 47 <filter>group_output</filter>
74 </data> 48 </data>
49 <expand macro="log_output_macro"/>
75 </outputs> 50 </outputs>
76 <tests> 51 <tests>
77 <test> 52 <test expect_num_outputs="1">
78 <param name="input" value="group_in2.bam" ftype="bam" /> 53 <param name="input" value="group_in2.sam" ftype="sam" />
79 <param name="extract_umi_method" value="read_id" /> 54 <section name="advanced">
80 <param name="paired" value="True" /> 55 <param name="random_seed" value="0" />
81 <param name="method" value="unique" /> 56 </section>
82 <output name="output" file="group_out2.bam" ftype="bam" sort="True" /> 57 <conditional name="bc">
58 <param name="extract_umi_method" value="read_id" />
59 </conditional>
60 <section name="sambam">
61 <param name="paired" value="true" />
62 </section>
63 <section name="umi">
64 <param name="method" value="unique" />
65 </section>
66 <output name="output" file="group_out2.bam" ftype="bam" />
83 </test> 67 </test>
84 <test> 68 <test expect_num_outputs="2">
85 <param name="input" value="group_in3.bam" ftype="bam" /> 69 <param name="input" value="group_in3.bam" ftype="bam" />
86 <param name="extract_umi_method" value="read_id" /> 70 <section name="advanced">
87 <param name="group_output" value="True" /> 71 <param name="random_seed" value="0" />
88 <param name="method" value="unique" /> 72 </section>
73 <conditional name="bc">
74 <param name="extract_umi_method" value="read_id" />
75 </conditional>
76 <param name="group_output" value="true" />
77 <section name="umi">
78 <param name="method" value="unique" />
79 </section>
89 <output name="group_out" file="group_out3.tab" /> 80 <output name="group_out" file="group_out3.tab" />
90 <output name="output" file="group_out3.bam" ftype="bam" sort="True" /> 81 <output name="output" file="group_out3.bam" ftype="bam" />
91 </test> 82 </test>
92 <test> 83 <test expect_num_outputs="2">
93 <param name="input" value="group_in4.bam" ftype="bam" /> 84 <param name="input" value="group_in4.bam" ftype="bam" />
94 <param name="extract_umi_method" value="tag" /> 85 <section name="advanced">
95 <param name="umi_tag" value="BX" /> 86 <param name="random_seed" value="0" />
96 <param name="method" value="unique" /> 87 </section>
88 <conditional name="bc">
89 <param name="extract_umi_method" value="tag" />
90 <param name="umi_tag" value="BX" />
91 </conditional>
92 <param name="group_output" value="true" />
93 <section name="umi">
94 <param name="method" value="unique" />
95 </section>
97 <output name="group_out" file="group_out4.tab" /> 96 <output name="group_out" file="group_out4.tab" />
98 <output name="output" file="group_out4.bam" ftype="bam" sort="True" /> 97 <output name="output" file="group_out4.bam" ftype="bam" />
99 </test> 98 </test>
100 <test> 99 <test expect_num_outputs="1">
101 <param name="input" value="group_in5.bam" ftype="bam" /> 100 <param name="input" value="group_in5.bam" ftype="bam" />
102 <param name="extract_umi_method" value="read_id" /> 101 <section name="advanced">
103 <param name="umi_tag" value="BX" /> 102 <param name="random_seed" value="0" />
104 <param name="method" value="cluster" /> 103 </section>
105 <output name="output" file="group_out5.bam" ftype="bam" sort="True" /> 104 <conditional name="bc">
105 <param name="extract_umi_method" value="read_id" />
106 </conditional>
107 <section name="umi">
108 <param name="method" value="cluster" />
109 </section>
110 <output name="output" file="group_out5.bam" ftype="bam"/>
106 </test> 111 </test>
107 <test> 112 <test expect_num_outputs="1">
108 <param name="input" value="group_in6.bam" ftype="bam" /> 113 <param name="input" value="group_in6.bam" ftype="bam" />
109 <param name="extract_umi_method" value="read_id" /> 114 <section name="advanced">
110 <param name="umi_tag" value="BX" /> 115 <param name="random_seed" value="0" />
111 <param name="method" value="directional" /> 116 </section>
112 <output name="output" file="group_out6.bam" ftype="bam" sort="True" /> 117 <conditional name="bc">
118 <param name="extract_umi_method" value="read_id" />
119 </conditional>
120 <section name="umi">
121 <param name="method" value="directional" />
122 </section>
123 <output name="output" file="group_out6.bam" ftype="bam"/>
113 </test> 124 </test>
114 </tests> 125 </tests>
115 <help><![CDATA[ 126 <help><![CDATA[
116 umi_tools group - Group reads based on their UMI 127 umi_tools group - Group reads based on their UMI
117 ================================================ 128 ================================================
118 129
119 Purpose 130 Purpose
120 ------- 131 -------
121 132
122 The purpose of this command is to identify groups of reads based on 133 The purpose of this command is to identify groups of reads based on
123 their genomic coordinate and UMI. It is assumed that the FASTQ files 134 their genomic coordinate and UMI.
124 were processed with umi_tools extract before mapping and thus the UMI is
125 the last word of the read name. e.g:
126
127 @HISEQ:87:00000000_AATT
128
129 where AATT is the UMI sequeuence.
130
131 If you have used an alternative method which does not separate the
132 read id and UMI with a "_", such as bcl2fastq which uses ":", you can
133 specify the separator with the option "--umi-separator=<sep>",
134 replacing <sep> with e.g ":".
135
136 Alternatively, if your UMIs are encoded in a tag, you can specify this
137 by setting the option --extract-umi-method=tag and set the tag name
138 with the --umi-tag option. For example, if your UMIs are encoded in
139 the 'UM' tag, provide the following options:
140 "--extract-umi-method=tag --umi-tag=UM"
141
142 By default, reads are considered identical if they have the same start
143 coordinate, are on the same strand, and have the same UMI. Optionally,
144 splicing status can be considered (see below).
145
146 The start postion of a read is considered to be the start of its alignment
147 minus any soft clipped bases. A read aligned at position 500 with
148 cigar 2S98M will be assumed to start at postion 498.
149
150 Methods
151 -------
152
153 group can be run with multiple methods to identify group of reads with
154 the same (or similar) UMI(s). All methods start by identifying the
155 reads with the same mapping position.
156
157 The simpliest method, "unique", groups reads with the exact same
158 UMI. The network-based methods, "cluster", "adjacency" and
159 "directional", build networks where nodes are UMIs and edges connect
160 UMIs with an edit distance <= threshold (usually 1). The groups of
161 reads are then defined from the network in a method-specific manner.
162
163 Note that the "percentile" method used with the dedup command is not
164 available with group. This is because this method does not group
165 similar UMIs as per the network methods. Instead it applies a
166 threshold for inclusion of the UMI in the output and excluded UMIs are
167 not assigned to a "true" UMI.
168
169 "unique"
170 Reads group share the exact same UMI
171
172 "cluster"
173 Identify clusters of connected UMIs (based on hamming distance
174 threshold). Each network is a read group
175
176 "directional"
177 Identify clusters of connected UMIs (based on hamming distance
178 threshold) and umi A counts >= (2* umi B counts) - 1. Each
179 network is a read group.
180 135
181 The group command can be used to create two types of outfile: a tagged 136 The group command can be used to create two types of outfile: a tagged
182 BAM or a flatfile describing the read groups 137 BAM or a flatfile describing the read groups
183 138
184 To generate the tagged-BAM file, use the option --output-bam and 139 To generate the tagged-BAM file, use the option --output-bam and
225 The total number of reads within the group 180 The total number of reads within the group
226 181
227 - unique_id 182 - unique_id
228 The unique id for the group 183 The unique id for the group
229 184
185 @BARCODE_HELP@
230 186
231 Options 187 @UMI_GROUPING_HELP@
232 -------
233
234 --extract-umi-method (choice)
235 How are the UMIs encoded in the read?
236
237 Options are:
238
239 - "read_id" (default)
240 UMIs contained at the end of the read separated as
241 specified with --umi-separator option
242
243 - "tag"
244 UMIs contained in a tag, see --umi-tag option
245
246 --umi-separator (string)
247 Separator between read id and UMI. See --extract-umi-method above
248
249 --umi-tag (string)
250 Tag which contains UMI. See --extract-umi-method above
251
252 --method (choice, string)
253 Method used to identify PCR duplicates within reads. All methods
254 start by identifying the reads with the same mapping position
255
256 Options are:
257
258 - "unique"
259 Reads group share the exact same UMI
260
261 - "cluster"
262 Identify clusters of connected UMIs (based on edit distance
263 threshold). Each network is a read group
264
265 - "directional"
266 Identify clusters of connected UMIs (based on edit distance
267 threshold) and umi A counts >= (2* umi B counts) - 1. Each
268 network is a read group.
269
270 --edit-distance-threshold (int)
271 For the adjacency and cluster methods the threshold for the
272 edit distance to connect two UMIs in the network can be
273 increased. The default value of 1 works best unless the UMI is
274 very long (>14bp)
275
276 --paired
277 BAM is paired end - output both read pairs. This will also
278 force the use of the template length to determine reads with
279 the same mapping coordinates.
280
281 --spliced-is-unique
282 Causes two reads that start in the same position on the same
283 strand and having the same UMI to be considered unique if one is
284 spliced and the other is not. (Uses the 'N' cigar operation to test
285 for splicing)
286
287 --soft-clip-threshold (int)
288 Mappers that soft clip, will sometimes do so rather than mapping a
289 spliced read if there is only a small overhang over the exon
290 junction. By setting this option, you can treat reads with at least
291 this many bases soft-clipped at the 3' end as spliced.
292
293 --multimapping-detection-method (string, choice)
294 If the sam/bam contains tags to identify multimapping reads, you can
295 specify for use when selecting the best read at a given loci.
296 Supported tags are "NH", "X0" and "XT". If not specified, the read
297 with the highest mapping quality will be selected
298
299 --read-length
300 Use the read length as as a criteria when deduping, for e.g sRNA-Seq
301
302 --whole-contig
303 Consider all alignments to a single contig together. This is useful if
304 you have aligned to a transcriptome multi-fasta
305
306 --subset (float, [0-1])
307 Only consider a fraction of the reads, chosen at random. This is useful
308 for doing saturation analyses.
309
310 --chrom
311 Only consider a single chromosome. This is useful for debugging purposes
312
313 --per-contig (string)
314 Deduplicate per contig (field 3 in BAM; RNAME).
315 All reads with the same contig will be
316 considered to have the same alignment position. This is useful
317 if your library prep generates PCR duplicates with non identical
318 alignment positions such as CEL-Seq. In this case, you would
319 align to a reference transcriptome with one transcript per gene
320
321 --per-gene (string)
322 Deduplicate per gene. As above except with this option you can
323 align to a reference transcriptome with more than one transcript
324 per gene. You need to also provide --gene-transcript-map option.
325 This will also add a metacontig ('MC') tag to the reads if used
326 in conjunction with --output-bam
327
328 --gene-transcript-map (string)
329 File mapping genes to transripts (tab separated), e.g:
330
331 gene1 transcript1
332 gene1 transcript2
333 gene2 transcript3
334
335 --gene-tag (string)
336 Deduplicate per gene. As per --per-gene except here the gene
337 information is encoded in the bam read tag specified so you do
338 not need to supply --gene-transcript-map
339
340 --group-out (string, filename)
341 Output a flatfile describing the read groups
342
343 --output-bam (string, filename)
344 Output a tagged bam file to stdout or -S <filename>
345
346 -i, --in-sam/-o, --out-sam
347 By default, inputs are assumed to be in BAM format and output are output
348 in BAM format. Use these options to specify the use of SAM format for
349 inputs or outputs.
350
351 -I (string, filename) input file name
352 The input file must be sorted and indexed.
353
354 -S (string, filename) output file name
355
356 -L (string, filename) log file name
357
358 Usage
359 -----
360 umi_tools group -I infile.bam --output-bam -S grouped.bam -L group.log --
361
362 ]]></help> 188 ]]></help>
363 <expand macro="citations" /> 189 <expand macro="citations" />
364 </tool> 190 </tool>