Mercurial > repos > iuc > umi_tools_group

annotate umi-tools_group.xml @ 8:aa5ec9b8c99a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit a7a086ce7d7d84f53d4a022fa1da25ef7b9a5b9a
author iuc
date Fri, 20 Jul 2018 03:48:54 -0400
parents f73f13641bb6
children a24f5b991320
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
1 <tool id="umi_tools_group" name="UMI-tools group" version="@VERSION@.0">
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
2 <description>Extract UMI from fastq files</description>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
3 <macros>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
4 <import>macros.xml</import>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
5 </macros>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
6 <expand macro="requirements">
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
7 <requirement type="package" version="1.6">samtools</requirement>
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
8 </expand>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
9 <command detect_errors="exit_code"><![CDATA[
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
10 #if $input.is_of_type("sam"):
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
11 #set $input_file = $input
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
12 #else:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
13 ln -sf '${input}' 'input.bam' &&
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
14 ln -sf '$input.metadata.bam_index' 'input.bam.bai' &&
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
15 #set $input_file = 'input.bam'
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
16 #end if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
17
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
18 umi_tools group
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
19 --random-seed 0
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
20 --extract-umi-method $extract_umi_method
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
21 #if str($extract_umi_method) != 'read_id':
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
22 --umi-separator '$umi_separator' --umi-tag '$umi_tag'
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
23 #end if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
24 --method $method --edit-distance-threshold $edit_distance_threshold
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
25 $paired $spliced_is_unique --soft-clip-threshold $soft_clip_threshold
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
26 $read_length $whole_contig --subset $subset $per_contig $per_gene
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
27 #if $gene_transcript_map:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
28 --gene-transcript-map '$gene_transcript_map'
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
29 #end if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
30 #if len(str($gene_tag)) > 0:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
31 --gene-tag '$gene_tag'
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
32 #end if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
33 #if $group_output:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
34 --group-out '$group_out'
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
35 #end if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
36 #if $input.is_of_type("sam"):
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
37 --in-sam
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
38 #end if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
39 --output-bam
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
40 -I '$input_file' -S grouped.bam &&
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
41 samtools sort grouped.bam -@ \${GALAXY_SLOTS:-1} -o '$output' -O BAM
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
42 ]]></command>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
43 <inputs>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
44 <param name="input" type="data" format="sam,bam" label="Reads to group in SAM or BAM format" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
45 <param name="extract_umi_method" argument="--extract-umi-method" type="select">
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
46 <option value="read_id" selected="True">Read ID</option>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
47 <option value="tag">Tag</option>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
48 </param>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
49 <param name="group_output" argument="--group-out" type="boolean" truevalue="--group-out" falsevalue="" label="Output a flatfile describing the read groups" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
50 <param name="umi_separator" argument="--umi-separator" type="text" label="Separator between read id and UMI." help="Ignored unless extracting by tag" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
51 <param name="umi_tag" argument="--umi-tag" type="text" label="Tag which contains UMI." />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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">
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
53 <option value="unique">Reads group share the exact same UMI</option>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
54 <option value="cluster">Identify clusters based on hamming distance</option>
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
55 <option value="directional">Identify clusters based on distance and counts, restrict network expansion by threshold</option>
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
56 </param>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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)" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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." />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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)" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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." />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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" />
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
63 <param argument="--subset" type="float" min="0.0" max="1.0" value="1.0" label="Only consider a random selection of the reads" />
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
64 <param argument="--chrom" type="boolean" truevalue="--chrom" falsevalue="" label="Only consider a single chromosome" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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." />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
67 <param name="gene_transcript_map" argument="--gene-transcript-map" type="data" format="tabular" optional="True" label="Tabular file mapping genes to transripts" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
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." />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
69 </inputs>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
70 <outputs>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
71 <data format="bam" name="output" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
72 <data format="tabular" name="group_out">
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
73 <filter>group_out</filter>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
74 </data>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
75 </outputs>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
76 <tests>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
77 <test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
78 <param name="input" value="group_in2.bam" ftype="bam" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
79 <param name="extract_umi_method" value="read_id" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
80 <param name="paired" value="True" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
81 <param name="method" value="unique" />
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
82 <output name="output" file="group_out2.bam" ftype="bam" sort="True" />
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
83 </test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
84 <test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
85 <param name="input" value="group_in3.bam" ftype="bam" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
86 <param name="extract_umi_method" value="read_id" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
87 <param name="group_output" value="True" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
88 <param name="method" value="unique" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
89 <output name="group_out" file="group_out3.tab" />
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
90 <output name="output" file="group_out3.bam" ftype="bam" sort="True" />
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
91 </test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
92 <test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
93 <param name="input" value="group_in4.bam" ftype="bam" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
94 <param name="extract_umi_method" value="tag" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
95 <param name="umi_tag" value="BX" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
96 <param name="method" value="unique" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
97 <output name="group_out" file="group_out4.tab" />
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
98 <output name="output" file="group_out4.bam" ftype="bam" sort="True" />
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
99 </test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
100 <test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
101 <param name="input" value="group_in5.bam" ftype="bam" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
102 <param name="extract_umi_method" value="read_id" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
103 <param name="umi_tag" value="BX" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
104 <param name="method" value="cluster" />
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
105 <output name="output" file="group_out5.bam" ftype="bam" sort="True" />
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
106 </test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
107 <test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
108 <param name="input" value="group_in6.bam" ftype="bam" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
109 <param name="extract_umi_method" value="read_id" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
110 <param name="umi_tag" value="BX" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
111 <param name="method" value="directional" />
1
f73f13641bb6 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents: 0
diff changeset
112 <output name="output" file="group_out6.bam" ftype="bam" sort="True" />
0
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
113 </test>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
114 </tests>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
115 <help><![CDATA[
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
116 umi_tools group - Group reads based on their UMI
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
117 ================================================
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
118
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
119 Purpose
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
120 -------
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
121
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
122 The purpose of this command is to identify groups of reads based on
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
123 their genomic coordinate and UMI. It is assumed that the FASTQ files
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
124 were processed with umi_tools extract before mapping and thus the UMI is
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
125 the last word of the read name. e.g:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
126
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
127 @HISEQ:87:00000000_AATT
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
128
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
129 where AATT is the UMI sequeuence.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
130
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
131 If you have used an alternative method which does not separate the
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
132 read id and UMI with a "_", such as bcl2fastq which uses ":", you can
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
133 specify the separator with the option "--umi-separator=<sep>",
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
134 replacing <sep> with e.g ":".
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
135
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
136 Alternatively, if your UMIs are encoded in a tag, you can specify this
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
137 by setting the option --extract-umi-method=tag and set the tag name
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
138 with the --umi-tag option. For example, if your UMIs are encoded in
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
139 the 'UM' tag, provide the following options:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
140 "--extract-umi-method=tag --umi-tag=UM"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
141
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
142 By default, reads are considered identical if they have the same start
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
143 coordinate, are on the same strand, and have the same UMI. Optionally,
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
144 splicing status can be considered (see below).
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
145
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
146 The start postion of a read is considered to be the start of its alignment
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
147 minus any soft clipped bases. A read aligned at position 500 with
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
148 cigar 2S98M will be assumed to start at postion 498.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
149
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
150 Methods
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
151 -------
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
152
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
153 group can be run with multiple methods to identify group of reads with
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
154 the same (or similar) UMI(s). All methods start by identifying the
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
155 reads with the same mapping position.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
156
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
157 The simpliest method, "unique", groups reads with the exact same
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
158 UMI. The network-based methods, "cluster", "adjacency" and
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
159 "directional", build networks where nodes are UMIs and edges connect
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
160 UMIs with an edit distance <= threshold (usually 1). The groups of
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
161 reads are then defined from the network in a method-specific manner.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
162
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
163 Note that the "percentile" method used with the dedup command is not
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
164 available with group. This is because this method does not group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
165 similar UMIs as per the network methods. Instead it applies a
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
166 threshold for inclusion of the UMI in the output and excluded UMIs are
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
167 not assigned to a "true" UMI.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
168
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
169 "unique"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
170 Reads group share the exact same UMI
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
171
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
172 "cluster"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
173 Identify clusters of connected UMIs (based on hamming distance
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
174 threshold). Each network is a read group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
175
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
176 "directional"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
177 Identify clusters of connected UMIs (based on hamming distance
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
178 threshold) and umi A counts >= (2* umi B counts) - 1. Each
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
179 network is a read group.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
180
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
181 The group command can be used to create two types of outfile: a tagged
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
182 BAM or a flatfile describing the read groups
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
183
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
184 To generate the tagged-BAM file, use the option --output-bam and
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
185 provide a filename with the -S option. Alternatively, if you do not
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
186 provide a filename, the bam file will be outputted to the stdout. If
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
187 you have provided the --log/-L option to send the logging output
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
188 elsewhere, you can pipe the output from the group command directly to
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
189 e.g samtools sort like so:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
190
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
191 ``umi_tools group -I inf.bam --group-out=grouped.tsv --output-bam --log=group.log --paired | samtools sort - -o grouped_sorted.bam``
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
192
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
193 The tagged-BAM file will have two tagged per read:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
194
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
195 - UG = Unique_id.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
196 0-indexed unique id number for each group of reads with the same genomic position and UMI or UMIs inferred to be from the same true UMI + errors
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
197
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
198 - BX = Final UMI.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
199 The inferred true UMI for the group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
200
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
201 To generate the flatfile describing the read groups, include the
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
202 --group-out=<filename> option. The columns of the read groups file are
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
203 below. The first five columns relate to the read. The final 3 columns
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
204 relate to the group.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
205
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
206 - read_id
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
207 read identifier
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
208
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
209 - contig
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
210 alignment contig
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
211
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
212 - position
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
213 Alignment position. Note that this position is not the start position of the read in the BAM file but the start of the read taking into account the read strand and cigar
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
214
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
215 - umi
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
216 The read UMI
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
217
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
218 - umi_count
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
219 The number of times this UMI is observed for reads at the same position
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
220
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
221 - final_umi
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
222 The inferred true UMI for the group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
223
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
224 - final_umi_count
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
225 The total number of reads within the group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
226
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
227 - unique_id
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
228 The unique id for the group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
229
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
230
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
231 Options
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
232 -------
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
233
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
234 --extract-umi-method (choice)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
235 How are the UMIs encoded in the read?
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
236
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
237 Options are:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
238
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
239 - "read_id" (default)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
240 UMIs contained at the end of the read separated as
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
241 specified with --umi-separator option
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
242
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
243 - "tag"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
244 UMIs contained in a tag, see --umi-tag option
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
245
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
246 --umi-separator (string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
247 Separator between read id and UMI. See --extract-umi-method above
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
248
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
249 --umi-tag (string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
250 Tag which contains UMI. See --extract-umi-method above
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
251
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
252 --method (choice, string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
253 Method used to identify PCR duplicates within reads. All methods
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
254 start by identifying the reads with the same mapping position
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
255
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
256 Options are:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
257
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
258 - "unique"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
259 Reads group share the exact same UMI
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
260
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
261 - "cluster"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
262 Identify clusters of connected UMIs (based on edit distance
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
263 threshold). Each network is a read group
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
264
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
265 - "directional"
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
266 Identify clusters of connected UMIs (based on edit distance
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
267 threshold) and umi A counts >= (2* umi B counts) - 1. Each
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
268 network is a read group.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
269
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
270 --edit-distance-threshold (int)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
271 For the adjacency and cluster methods the threshold for the
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
272 edit distance to connect two UMIs in the network can be
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
273 increased. The default value of 1 works best unless the UMI is
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
274 very long (>14bp)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
275
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
276 --paired
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
277 BAM is paired end - output both read pairs. This will also
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
278 force the use of the template length to determine reads with
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
279 the same mapping coordinates.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
280
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
281 --spliced-is-unique
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
282 Causes two reads that start in the same position on the same
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
283 strand and having the same UMI to be considered unique if one is
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
284 spliced and the other is not. (Uses the 'N' cigar operation to test
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
285 for splicing)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
286
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
287 --soft-clip-threshold (int)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
288 Mappers that soft clip, will sometimes do so rather than mapping a
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
289 spliced read if there is only a small overhang over the exon
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
290 junction. By setting this option, you can treat reads with at least
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
291 this many bases soft-clipped at the 3' end as spliced.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
292
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
293 --multimapping-detection-method (string, choice)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
294 If the sam/bam contains tags to identify multimapping reads, you can
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
295 specify for use when selecting the best read at a given loci.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
296 Supported tags are "NH", "X0" and "XT". If not specified, the read
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
297 with the highest mapping quality will be selected
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
298
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
299 --read-length
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
300 Use the read length as as a criteria when deduping, for e.g sRNA-Seq
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
301
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
302 --whole-contig
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
303 Consider all alignments to a single contig together. This is useful if
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
304 you have aligned to a transcriptome multi-fasta
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
305
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
306 --subset (float, [0-1])
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
307 Only consider a fraction of the reads, chosen at random. This is useful
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
308 for doing saturation analyses.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
309
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
310 --chrom
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
311 Only consider a single chromosome. This is useful for debugging purposes
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
312
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
313 --per-contig (string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
314 Deduplicate per contig (field 3 in BAM; RNAME).
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
315 All reads with the same contig will be
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
316 considered to have the same alignment position. This is useful
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
317 if your library prep generates PCR duplicates with non identical
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
318 alignment positions such as CEL-Seq. In this case, you would
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
319 align to a reference transcriptome with one transcript per gene
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
320
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
321 --per-gene (string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
322 Deduplicate per gene. As above except with this option you can
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
323 align to a reference transcriptome with more than one transcript
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
324 per gene. You need to also provide --gene-transcript-map option.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
325 This will also add a metacontig ('MC') tag to the reads if used
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
326 in conjunction with --output-bam
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
327
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
328 --gene-transcript-map (string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
329 File mapping genes to transripts (tab separated), e.g:
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
330
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
331 gene1 transcript1
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
332 gene1 transcript2
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
333 gene2 transcript3
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
334
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
335 --gene-tag (string)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
336 Deduplicate per gene. As per --per-gene except here the gene
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
337 information is encoded in the bam read tag specified so you do
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
338 not need to supply --gene-transcript-map
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
339
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
340 --group-out (string, filename)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
341 Output a flatfile describing the read groups
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
342
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
343 --output-bam (string, filename)
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
344 Output a tagged bam file to stdout or -S <filename>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
345
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
346 -i, --in-sam/-o, --out-sam
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
347 By default, inputs are assumed to be in BAM format and output are output
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
348 in BAM format. Use these options to specify the use of SAM format for
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
349 inputs or outputs.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
350
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
351 -I (string, filename) input file name
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
352 The input file must be sorted and indexed.
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
353
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
354 -S (string, filename) output file name
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
355
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
356 -L (string, filename) log file name
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
357
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
358 Usage
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
359 -----
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
360 umi_tools group -I infile.bam --output-bam -S grouped.bam -L group.log --
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
361
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
362 ]]></help>
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
363 <expand macro="citations" />
860bc357b678 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents:
diff changeset
364 </tool>