annotate umi-tools_dedup.xml @ 18:362719583a9f draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
author iuc
date Fri, 28 Feb 2025 20:39:27 +0000
parents b63f68b03f4a
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
1 <tool id="umi_tools_dedup" name="UMI-tools deduplicate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
2 <description>Extract UMI from fastq files</description>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
3 <macros>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
4 <import>macros.xml</import>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
5 </macros>
16
b63f68b03f4a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bc1b362f6783d3fc0ed0f42c14687001d7ff5f7a
iuc
parents: 15
diff changeset
6 <expand macro="bio_tools"/>
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
7 <expand macro="requirements"/>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
8 <command detect_errors="exit_code"><![CDATA[
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
9 @LINK_SAM_BAM_INPUT@
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
10
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
11 echo $input.ext &&
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
12 umi_tools dedup
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
13 #if $output_stats_bool
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
14 --output-stats=stats_outputs
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
15 #end if
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
16 @GROUPDEDUP_OPTIONS@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
17 @BARCODE_OPTIONS@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
18 @UMI_GROUPING_OPTIONS@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
19 @SAMBAM_OPTIONS@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
20 @FULLSC_OPTIONS@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
21 @ADVANCED_OPTIONS@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
22 -I '$input_file' -S deduped.bam
16
b63f68b03f4a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bc1b362f6783d3fc0ed0f42c14687001d7ff5f7a
iuc
parents: 15
diff changeset
23 ## using samtools sort is a workaround, for the following error that appears when Galaxy
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
24 ## compares the generated file with the one in test-data
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
25 ## `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`
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
26 ## problem seems to be the BAM file generated with pysam
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
27 ## may be dropped in the future
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
28 --no-sort-output
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
29 @LOG@
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
30 && samtools sort --no-PG deduped.bam -@ \${GALAXY_SLOTS:-1} -T "\${TMPDIR:-.}" -o '$output' -O BAM
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
31
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
32 ]]></command>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
33 <inputs>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
34 <param name="input" type="data" format="sam,bam" label="Reads to deduplicate in SAM or BAM format" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
35 <param name="output_stats_bool" type="boolean" checked="false" label="Output UMI related statistics files?"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
36 <expand macro="groupdedup_options_macro"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
37 <expand macro="barcode_options_macro"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
38 <expand macro="umi_grouping_options_macro"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
39 <expand macro="sambam_options_macro"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
40 <expand macro="fullsc_options_macro"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
41 <expand macro="advanced_options_macro"/>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
42 <expand macro="log_input_macro"/>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
43 </inputs>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
44 <outputs>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
45 <data format="bam" name="output" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
46 <collection name="output_stats" type="list" label="${tool.name} on ${on_string} stats">
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
47 <filter>output_stats_bool</filter>
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
48 <data name="edit_distance" format="tabular" from_work_dir="stats_outputs_edit_distance.tsv"/>
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
49 <data name="per_umi" format="tabular" from_work_dir="stats_outputs_per_umi.tsv"/>
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
50 <data name="per_umi_per_position" format="tabular" from_work_dir="stats_outputs_per_umi_per_position.tsv"/>
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
51 </collection>
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
52 <expand macro="log_output_macro"/>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
53 </outputs>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
54 <tests>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
55 <test expect_num_outputs="1">
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
56 <param name="input" value="group_in1.sam" ftype="sam" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
57 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
58 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
59 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
60 <conditional name="bc">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
61 <param name="extract_umi_method" value="read_id" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
62 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
63 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
64 <param name="method" value="unique" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
65 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
66 <output name="output" file="dedup_out1.bam" ftype="bam" lines_diff="2"/><!--lines_diff won't be needed in later versions since umitools use \-\-no-PG internally -->
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
67 </test>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
68 <test expect_num_outputs="1">
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
69 <param name="input" value="group_in2.sam" ftype="sam" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
70 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
71 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
72 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
73 <conditional name="bc">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
74 <param name="extract_umi_method" value="read_id" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
75 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
76 <section name="sambam">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
77 <param name="paired" value="true" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
78 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
79 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
80 <param name="method" value="unique" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
81 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
82 <output name="output" file="dedup_out2.bam" ftype="bam" lines_diff="2" />
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
83 </test>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
84 <test expect_num_outputs="1">
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
85 <param name="input" value="group_in3.bam" ftype="bam" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
86 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
87 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
88 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
89 <conditional name="bc">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
90 <param name="extract_umi_method" value="read_id" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
91 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
92 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
93 <param name="method" value="unique" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
94 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
95 <output name="output" file="dedup_out3.bam" ftype="bam" lines_diff="2" />
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
96 </test>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
97 <test expect_num_outputs="1">
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
98 <param name="input" value="group_in4.bam" ftype="bam" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
99 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
100 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
101 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
102 <conditional name="bc">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
103 <param name="extract_umi_method" value="tag" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
104 <param name="umi_tag" value="BX" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
105 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
106 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
107 <param name="method" value="unique" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
108 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
109 <output name="output" file="dedup_out4.bam" ftype="bam" lines_diff="2"/>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
110 </test>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
111 <test expect_num_outputs="1">
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
112 <param name="input" value="group_in4.bam" ftype="bam" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
113 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
114 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
115 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
116 <conditional name="bc">
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
117 <param name="extract_umi_method" value="tag" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
118 <param name="umi_tag" value="BX" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
119 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
120 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
121 <param name="method" value="cluster" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
122 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
123 <output name="output" file="dedup_out5.bam" ftype="bam" lines_diff="2"/>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
124 </test>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
125 <test expect_num_outputs="1">
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
126 <param name="input" value="group_in4.bam" ftype="bam" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
127 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
128 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
129 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
130 <conditional name="bc">
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
131 <param name="extract_umi_method" value="tag" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
132 <param name="umi_tag" value="BX" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
133 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
134 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
135 <param name="method" value="directional" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
136 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
137 <output name="output" file="dedup_out6.bam" ftype="bam" lines_diff="2"/>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
138 </test>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
139 <test expect_num_outputs="5">
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
140 <param name="input" value="group_in4.bam" ftype="bam" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
141 <section name="advanced">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
142 <param name="random_seed" value="0" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
143 </section>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
144 <conditional name="bc">
18
362719583a9f planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit 11a7415c7f8a44a3f990080533c1de43a41d1e2e
iuc
parents: 16
diff changeset
145 <param name="extract_umi_method" value="tag" />
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
146 <param name="umi_tag" value="BX" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
147 </conditional>
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
148 <section name="umi">
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
149 <param name="method" value="directional" />
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
150 </section>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
151 <param name="output_stats_bool" value="true"/>
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
152 <output name="output" file="dedup_out6.bam" ftype="bam" lines_diff="2"/>
11
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
153 <output_collection name="output_stats">
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
154 <element name="edit_distance" file="stats_outputs_edit_distance.tsv" />
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
155 <element name="per_umi" file="stats_outputs_per_umi.tsv" />
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
156 <element name="per_umi_per_position" file="stats_outputs_per_umi_per_position.tsv" />
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
157 </output_collection>
cf4494361a56 "planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"
iuc
parents: 10
diff changeset
158 </test>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
159 </tests>
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
160 <help><![CDATA[
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
161 umi_tools dedup - Deduplicate reads based on their UMI and mapping coordinates
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
162 ==============================================================================
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
163
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
164 Purpose
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
165 -------
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
166
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
167 The purpose of this command is to deduplicate BAM files based on the first
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
168 mapping co-ordinate and the UMI attached to the read.
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
169
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
170 @BARCODE_HELP@
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
171
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
172 @UMI_GROUPING_HELP@
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
173
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
174 Selecting the representative read
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
175 ---------------------------------
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
176 For every group of duplicate reads, a single representative read is
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
177 retained.The following criteria are applied to select the read that
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
178 will be retained from a group of duplicated reads:
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
179
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
180 1. The read with the lowest number of mapping coordinates (see
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
181 ``--multimapping-detection-method`` option)
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
182
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
183 2. The read with the highest mapping quality. Note that this is not
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
184 the read sequencing quality and that if two reads have the same
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
185 mapping quality then one will be picked at random regardless of the
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
186 read quality.
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
187
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
188 Otherwise a read is chosen at random.
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
189
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
190 Optional statistics output
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
191 --------------------------
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
192
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
193 One can use the edit distance between UMIs at the same position as an
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
194 quality control for the deduplication process by comparing with
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
195 a null expectation of random sampling. For the random sampling, the
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
196 observed frequency of UMIs is used to more reasonably model the null
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
197 expectation.
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
198
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
199 Use the option ``Output UMI related statistics files?`` generate stats outfiles:
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
200
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
201 edit_distance
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
202 Reports the (binned) average edit distance between the UMIs at each
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
203 position. Positions with a single UMI are reported seperately. The
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
204 edit distances are reported pre- and post-deduplication alongside
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
205 the null expectation from random sampling of UMIs from the UMIs
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
206 observed across all positions. Note that separate null
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
207 distributions are reported since the null depends on the observed
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
208 frequency of each UMI which is different pre- and
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
209 post-deduplication. The post-duplication values should be closer to
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
210 their respective null than the pre-deduplication vs null comparison
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
211
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
212 In addition, this option will trigger reporting of further summary
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
213 statistics for the UMIs which may be informative for selecting the
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
214 optimal deduplication method or debugging.
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
215
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
216 Each unique UMI sequence may be observed [0-many] times at multiple
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
217 positions in the BAM. The following files report the distribution for
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
218 the frequencies of each UMI.
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
219
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
220 per_umi_per_position
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
221 The `_stats_per_umi_per_position.tsv` file simply tabulates the
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
222 counts for unique combinations of UMI and position. E.g if prior to
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
223 deduplication, we have two positions in the BAM (POSa, POSb), at
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
224 POSa we have observed 2*UMIa, 1*UMIb and at POSb: 1*UMIc, 3*UMId,
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
225 then the stats file is populated thus:
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
226
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
227 ====== =============
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
228 counts instances_pre
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
229 ------ -------------
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
230 1 2
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
231 2 1
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
232 3 1
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
233 ====== =============
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
234
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
235 If post deduplication, UMIb is grouped with UMIa such that POSa:
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
236 3*UMIa, then the `instances_post` column is populated thus:
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
237
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
238 ====== ============= ==============
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
239 counts instances_pre instances_post
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
240 ------ ------------- --------------
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
241 1 2 1
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
242 2 1 0
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
243 3 1 2
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
244 ====== ============= ==============
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
245
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
246 per_umi_per
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
247 The `_stats_per_umi_per.tsv` table provides UMI-level summary
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
248 statistics. Keeping in mind that each unique UMI sequence can be
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
249 observed at [0-many] times across multiple positions in the BAM,
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
250
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
251 :times_observed: How many positions the UMI was observed at
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
252 :total_counts: The total number of times the UMI was observed across all positions
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
253 :median_counts: The median for the distribution of how often the UMI was observed at each position (excluding zeros)
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
254
12
083c516d19a9 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/umi_tools commit bf6a3aa532e8f9d122da4c1e39f3e256ae587b79"
iuc
parents: 11
diff changeset
255 Hence, whenever times_observed=1, total_counts==median_counts.]]></help>
0
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
256 <expand macro="citations" />
ec7b02a30ed3 planemo upload commit eea727c3bdfe36d9d16036d5ab79fb8b27c4e82e
iuc
parents:
diff changeset
257 </tool>