Mercurial > repos > wolma > mimodd_ngs_run_annotation
diff sam_header.xml @ 0:37e44e7e2d50 draft
Imported from capsule None
| author | wolma |
|---|---|
| date | Sat, 13 Dec 2014 17:20:06 -0500 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/sam_header.xml Sat Dec 13 17:20:06 2014 -0500 @@ -0,0 +1,128 @@ +<tool id="ngs_run_annotation" name="NGS Run Annotation"> + <description>Create a SAM format header from run metadata for sample annotation.</description> + <requirements> + <requirement type="package" version="0.1.5">mimodd</requirement> + </requirements> + <version_command>mimodd version -q</version_command> + <command> + mimodd header + + --rg-id "$rg_id" + --rg-sm "$rg_sm" + + #if $str($rg_cn): + --rg-cn "$rg_cn" + #end if + #if $str($rg_ds): + --rg-ds "$rg_ds" + #end if + #if $str($rg_date): + --rg-dt "$rg_date" + #end if + #if $str($rg_lb): + --rg-lb "$rg_lb" + #end if + #if $str($rg_pl): + --rg-pl "$rg_pl" + #end if + #if $str($rg_pi): + --rg-pi "$rg_pi" + #end if + #if $str($rg_pu): + --rg-pu "$rg_pu" + #end if + + --ofile $outputfile + + </command> + + <inputs> + <param name="rg_id" type="text" size="80" label="read-group ID (required)"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value=""" /> + </valid> + <mapping initial="none"> + <add source=""" target="\""/> + </mapping> + </sanitizer> + </param> + <param name="rg_sm" type="text" size="80" label="sample name (required)"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value=""" /> + </valid> + <mapping initial="none"> + <add source=""" target="\""/> + </mapping> + </sanitizer> + </param> + <param name="rg_ds" type="text" size="80" label="description"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value=""" /> + </valid> + <mapping initial="none"> + <add source=""" target="\""/> + </mapping> + </sanitizer> + </param> + <param name="rg_date" type="text" label="date (YYYY-MM-DD) the run was produced" /> + <param name="rg_cn" type="text" size="80" label="name of sequencing center"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value=""" /> + </valid> + <mapping initial="none"> + <add source=""" target="\""/> + </mapping> + </sanitizer> + </param> + <param name="rg_lb" type="text" size="80" label="read-group library"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value=""" /> + </valid> + <mapping initial="none"> + <add source=""" target="\""/> + </mapping> + </sanitizer> + </param> + <param name="rg_pl" type="text" label="platform/technology used to produce the reads" /> + <param name="rg_pi" type="text" label="predicted median insert size" /> + <param name="rg_pu" type="text" size="80" label="platform unit; unique identifier"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value=""" /> + </valid> + <mapping initial="none"> + <add source=""" target="\""/> + </mapping> + </sanitizer> + </param> + </inputs> + + <outputs> + <data name="outputfile" format="sam" label="${rg_sm} (${rg_id}) header information from MiModd ${tool.name} on ${on_string}"/> + </outputs> + +<help> +.. class:: infomark + + **What it does** + +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. + +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). + +**Note:** + +**MiModD requires run metadata for every input file at the Alignment step !** + +**Tip:** + +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. + +</help> +</tool> +