comparison sam_header.xml @ 0:37e44e7e2d50 draft

Imported from capsule None
author wolma
date Sat, 13 Dec 2014 17:20:06 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:37e44e7e2d50
1 <tool id="ngs_run_annotation" name="NGS Run Annotation">
2 <description>Create a SAM format header from run metadata for sample annotation.</description>
3 <requirements>
4 <requirement type="package" version="0.1.5">mimodd</requirement>
5 </requirements>
6 <version_command>mimodd version -q</version_command>
7 <command>
8 mimodd header
9
10 --rg-id "$rg_id"
11 --rg-sm "$rg_sm"
12
13 #if $str($rg_cn):
14 --rg-cn "$rg_cn"
15 #end if
16 #if $str($rg_ds):
17 --rg-ds "$rg_ds"
18 #end if
19 #if $str($rg_date):
20 --rg-dt "$rg_date"
21 #end if
22 #if $str($rg_lb):
23 --rg-lb "$rg_lb"
24 #end if
25 #if $str($rg_pl):
26 --rg-pl "$rg_pl"
27 #end if
28 #if $str($rg_pi):
29 --rg-pi "$rg_pi"
30 #end if
31 #if $str($rg_pu):
32 --rg-pu "$rg_pu"
33 #end if
34
35 --ofile $outputfile
36
37 </command>
38
39 <inputs>
40 <param name="rg_id" type="text" size="80" label="read-group ID (required)">
41 <sanitizer invalid_char="">
42 <valid initial="string.printable">
43 <remove value="&quot;" />
44 </valid>
45 <mapping initial="none">
46 <add source="&quot;" target="\&quot;"/>
47 </mapping>
48 </sanitizer>
49 </param>
50 <param name="rg_sm" type="text" size="80" label="sample name (required)">
51 <sanitizer invalid_char="">
52 <valid initial="string.printable">
53 <remove value="&quot;" />
54 </valid>
55 <mapping initial="none">
56 <add source="&quot;" target="\&quot;"/>
57 </mapping>
58 </sanitizer>
59 </param>
60 <param name="rg_ds" type="text" size="80" label="description">
61 <sanitizer invalid_char="">
62 <valid initial="string.printable">
63 <remove value="&quot;" />
64 </valid>
65 <mapping initial="none">
66 <add source="&quot;" target="\&quot;"/>
67 </mapping>
68 </sanitizer>
69 </param>
70 <param name="rg_date" type="text" label="date (YYYY-MM-DD) the run was produced" />
71 <param name="rg_cn" type="text" size="80" label="name of sequencing center">
72 <sanitizer invalid_char="">
73 <valid initial="string.printable">
74 <remove value="&quot;" />
75 </valid>
76 <mapping initial="none">
77 <add source="&quot;" target="\&quot;"/>
78 </mapping>
79 </sanitizer>
80 </param>
81 <param name="rg_lb" type="text" size="80" label="read-group library">
82 <sanitizer invalid_char="">
83 <valid initial="string.printable">
84 <remove value="&quot;" />
85 </valid>
86 <mapping initial="none">
87 <add source="&quot;" target="\&quot;"/>
88 </mapping>
89 </sanitizer>
90 </param>
91 <param name="rg_pl" type="text" label="platform/technology used to produce the reads" />
92 <param name="rg_pi" type="text" label="predicted median insert size" />
93 <param name="rg_pu" type="text" size="80" label="platform unit; unique identifier">
94 <sanitizer invalid_char="">
95 <valid initial="string.printable">
96 <remove value="&quot;" />
97 </valid>
98 <mapping initial="none">
99 <add source="&quot;" target="\&quot;"/>
100 </mapping>
101 </sanitizer>
102 </param>
103 </inputs>
104
105 <outputs>
106 <data name="outputfile" format="sam" label="${rg_sm} (${rg_id}) header information from MiModd ${tool.name} on ${on_string}"/>
107 </outputs>
108
109 <help>
110 .. class:: infomark
111
112 **What it does**
113
114 This tool takes the user-provided information about a next-generation sequencing run and constructs a valid header in the SAM file format from it.
115
116 The result file can be used by the tools *Convert* and *Reheader* or in the *SNAP Read Alignment* step to add run metadata to sequenced reads files (or to overwrite pre-existing information).
117
118 **Note:**
119
120 **MiModD requires run metadata for every input file at the Alignment step !**
121
122 **Tip:**
123
124 While you can do Alignments from fastq file format by providing a custom header file directly to the *SNAP Read Alignment* tool, we **recommend** you to first convert all input files to and archive all datasets in SAM/BAM format with appropriate header information prior to any downstream analysis. Although a bit more time-consuming, this practice protects against information loss and ensures that the input datasets will remain useful for others in the future.
125
126 </help>
127 </tool>
128