annotate summarize_poliovirus_alignment.xml @ 4:eae57366bc55 draft

planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
author sanbi-uwc
date Fri, 22 Jul 2022 10:01:30 +0000
parents 09b98e40ab59
children 7bcfc97b9284
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
4
eae57366bc55 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 3
diff changeset
1 <tool id="summarize_poliovirus_alignment" name="Summarize poliovirus alignment" version="0.2.0+galaxy1" profile="21.05">
0
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
2 <requirements>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
3 <requirement type="package" version="3.9">python</requirement>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
4 </requirements>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
5 <command detect_errors="exit_code"><![CDATA[
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
6 python $__tool_directory__/summarize_alignment.py
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
7 --summary_output_filename '$output1'
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
8 --variant_list_outputs
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
9 #for $key in $variant_list.keys()
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
10 '$variant_list[$key]'
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
11 #end for
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
12 --datasets
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
13 #for $dataset in $alignment_assessments
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
14 '$dataset'
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
15 #end for
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
16
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
17 ]]></command>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
18 <inputs>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
19 <!-- input is list of reports for poliovirus sabin 1, 2 and 3 -->
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
20 <param name="alignment_assessments" format="json" type="data_collection" collection_type="list" label="Poliovius alignment assessments" help="Input is a list of JSON reports from the assess_poliovirus_alignment tool" />
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
21 </inputs>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
22 <outputs>
3
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
23 <data name="output1" format="tabular" label="Poliovirus variant summary on ${on_string}">
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
24 <actions>
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
25 <action name="column_names" type="metadata" default="sample name,best matching reference,num variants,perc variants,quality,variant list" />
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
26 </actions>
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
27 </data>
0
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
28 <collection name="variant_list" type="list" label="Poliovirus variant lists on ${on_string}" structured_like="alignment_assessments" format="tabular">
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
29 <!-- todo - find a way to set the metadata columns for the tabular datasets -->
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
30 </collection>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
31 </outputs>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
32 <tests>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
33 <test expect_num_outputs="3">
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
34 <param name="alignment_assessments" ftype="json">
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
35 <collection type="list">
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
36 <element name="sample1" value="sample1_output.json" />
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
37 </collection>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
38 </param>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
39 <output name="output1" ftype="tabular">
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
40 <assert_contents>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
41 <has_text text="23:G:A;26:G:A;38:A:G;40:T:C;59:C:T;65:T:C;72:A:G;" />
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
42 </assert_contents>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
43 </output>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
44 <output_collection name="variant_list">
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
45 <element name="sample1" file="sample1_variants.tabular" ftype="tabular" />
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
46 </output_collection>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
47 </test>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
48 </tests>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
49 <help><![CDATA[
3
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
50 Given a list of outputs of the assess_poliovirus_alignment tool, make a summary and per sample variant list.
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
51
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
52 In the summary file the columns are:
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
53
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
54 1. sample name
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
55
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
56 2. best matching reference: the workflow compares sequences against Sabin 1, 2 and 3 poliovirus reference sequences and select the one that is the closest matching
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
57
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
58 3. number of variants relative to the best matching reference
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
59
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
60 4. percentage of variation: variants are only counted in the VP1 gene and this percentage is calculated by comparing the number of variants to the length of the VP1 gene in the best matching reference.
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
61
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
62 5. quality: this is an attempt at a quality score for the sequences
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
63
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
64 6. variant list: a semi-colon separated list of variants. variant positions are in 1-based coordinates counting from the first base of the VP1 gene. A variant list is produced for each sample, these might be more readable.
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
65
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
66 In the per-sample variant lists the columns are as follows:
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
67
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
68 1. variant position in the genome
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
69
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
70 2. variant position in VP1 (in 1-based coordinates)
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
71
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
72 3. base in reference
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
73
09b98e40ab59 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 2
diff changeset
74 4. base in sequenced sample
4
eae57366bc55 planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty
sanbi-uwc
parents: 3
diff changeset
75
0
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
76 ]]></help>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
77 <citations>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
78 <citation type="bibtex"><![CDATA[
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
79 @software{van_Heusden_Poliovirus_variation_reporting_2022,
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
80 author = {van Heusden, Peter},
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
81 month = {7},
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
82 title = {{Poliovirus variation reporting scripts}},
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
83 url = {https://github.com/pvanheus/polio_report},
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
84 version = {0.1.0},
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
85 year = {2022}
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
86 }
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
87 ]]></citation>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
88 </citations>
7e49c6b19f5e planemo upload commit a99e10fec2fac5aae70974c977eb3b362a1a8429
sanbi-uwc
parents:
diff changeset
89 </tool>