annotate tools/count_roi_variants/count_roi_variants.xml @ 2:167765a633c0 draft default tip

"Update all the pico_galaxy tools on main Tool Shed"
author peterjc
date Fri, 16 Apr 2021 22:34:00 +0000
parents 3ee6f4d0ac80
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
167765a633c0 "Update all the pico_galaxy tools on main Tool Shed"
peterjc
parents: 1
diff changeset
1 <tool id="count_roi_variants" name="Count sequence variants in region of interest" version="0.0.6">
0
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
2 <description>using samtools view</description>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
3 <requirements>
1
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
4 <requirement type="package" version="1.2">samtools</requirement>
0
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
5 </requirements>
1
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
6 <version_command>
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
7 python $__tool_directory__/count_roi_variants.py --version
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
8 </version_command>
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
9 <command detect_errors="aggressive">
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
10 python $__tool_directory__/count_roi_variants.py '$input_bam' '${input_bam.metadata.bam_index}' '$out_tabular' '$region'
3ee6f4d0ac80 v0.0.5 Fix version inconsistency, using samtools v1.2 now.
peterjc
parents: 0
diff changeset
11 </command>
0
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
12 <inputs>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
13 <param name="input_bam" type="data" format="bam" label="Input BAM file" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
14 <param name="region" type="text" label="Region of interest" help="Use the reference:start-end syntax as in samtools.">
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
15 <sanitizer>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
16 <!--
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
17 SAM/BAM spec says the name must match regex [!-)+-<>-~][!-~]*
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
18 but will focus on ASCII 33 ("!") to ASCII 126 ("~"), i.e.
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
19 !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
20 of which some are going to be potential trouble like !, ", $, &, ', \, `, {, |, }
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
21 which is how I came to this hopefully safe set..
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
22 -->
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
23 <valid initial="string.letters,string.digits">
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
24 <add value="#%+,-./:;=@^_|~" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
25 <remove value=" " />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
26 </valid>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
27 <mapping initial="none" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
28 </sanitizer>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
29 </param>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
30 </inputs>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
31 <outputs>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
32 <data name="out_tabular" format="tabular" label="$input_bam.name $region variants" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
33 </outputs>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
34 <tests>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
35 <test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
36 <param name="input_bam" value="ex1.bam" ftype="bam" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
37 <param name="region" value="chr2:400-406" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
38 <output name="out_tabular" file="ex1.count_roi_variants.tabular" ftype="tabular" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
39 <assert_stdout>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
40 <has_line line="Counted 2 variants from 40 reads spanning chr2:400-406" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
41 </assert_stdout>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
42 </test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
43 <test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
44 <param name="input_bam" value="coverage_test.bam" ftype="bam" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
45 <param name="region" value="ref:10-15" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
46 <output name="out_tabular" file="coverage_test.count_roi_variants.tabular" ftype="tabular" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
47 <assert_stdout>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
48 <has_line line="Counted 1 variants from 1 reads spanning ref:10-15" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
49 </assert_stdout>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
50 </test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
51 <!-- This test is a tricky one due to the NCBI's love of pipe characters in identifiers -->
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
52 <test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
53 <param name="input_bam" value="SRR639755_mito_pairs_vs_NC_010642_clc.bam" ftype="bam" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
54 <param name="region" value="gi|187250362|ref|NC_010642.1|:1695-1725" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
55 <output name="out_tabular" file="SRR639755_mito_pairs_vs_NC_010642_clc.count-1695-1725.tabular" ftype="tabular" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
56 <assert_stdout>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
57 <has_line line="Counted 3 variants from 16 reads spanning gi|187250362|ref|NC_010642.1|:1695-1725" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
58 </assert_stdout>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
59 </test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
60 <test expect_failure="true" expect_exit_code="1">
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
61 <param name="input_bam" value="SRR639755_mito_pairs_vs_NC_010642_clc.bam" ftype="bam" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
62 <param name="region" value="ref:1695-1725" />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
63 <assert_stderr>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
64 <has_line line="ERROR: samtools did not recognise the region requested, can't count any variants." />
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
65 </assert_stderr>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
66 </test>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
67 </tests>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
68 <help>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
69 **What it does**
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
70
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
71 This tool runs the command ``samtools view`` from the SAMtools toolkit, getting
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
72 all the reads in your BAM file mapped to the given region of interest (ROI).
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
73 It then counts all the different sequence variants in reads spanning that ROI,
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
74 which are returned as a tab-separated table.
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
75
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
76 Reads mapped to the ROI but not spanning it completely are ignored.
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
77
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
78 Input is a sorted and indexed BAM file, the output is tabular. The first column
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
79 is the observed sequence variants within the ROI, the second column is the number
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
80 of reads with that sequence, and the third column gives this as a percentage of
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
81 the reads spanning the ROI.
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
82
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
83 ====== =================================================================================
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
84 Column Description
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
85 ------ ---------------------------------------------------------------------------------
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
86 1 Sequence variant from ROI
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
87 2 Number of reads with that sequence variant
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
88 3 Percentage of reads with that sequence variant (2 dp)
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
89 ====== =================================================================================
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
90
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
91
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
92 **Citation**
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
93
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
94 If you use this Galaxy tool in work leading to a scientific publication please
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
95 cite:
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
96
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
97 Heng Li et al (2009). The Sequence Alignment/Map format and SAMtools.
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
98 Bioinformatics 25(16), 2078-9.
2
167765a633c0 "Update all the pico_galaxy tools on main Tool Shed"
peterjc
parents: 1
diff changeset
99 https://doi.org/10.1093/bioinformatics/btp352
0
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
100
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
101 Peter J.A. Cock (2016), Count sequence variants in region of interest in BAM file.
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
102 http://toolshed.g2.bx.psu.edu/view/peterjc/count_roi_variants
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
103
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
104 This wrapper is available to install into other Galaxy Instances via the Galaxy
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
105 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/count_roi_variants
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
106 </help>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
107 <citations>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
108 <citation type="doi">10.1093/bioinformatics/btp352</citation>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
109 </citations>
95efbdb72961 v0.0.4 - Previously only on Test Tool Shed
peterjc
parents:
diff changeset
110 </tool>