Mercurial > repos > 19zhang > iwa_mirna
diff genomeRetrival.xml @ 1:34b51ff7d639 draft default tip
Uploaded
author | 19zhang |
---|---|
date | Tue, 13 Oct 2020 07:08:31 +0000 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/genomeRetrival.xml Tue Oct 13 07:08:31 2020 +0000 @@ -0,0 +1,148 @@ +<tool id="genomeindex" name="genomePrepare" workflow_compatible="false" version="20.05"> + <!-- <description>get genome sequences, annotation and file path (built-in or uploaded)</description> --> + + <command><![CDATA[ + bash ${__tool_directory__}/scripts/obtainSpecies.sh + --curpath ${__tool_directory__} + #if $genometype.datainput == "UploadData": + --name "$genometype.speciename" + --genome $genometype.genomeData + --gff $genometype.annotationData + --otherrna $genometype.otherrna + --transcript $genometype.transcriptsData + --protein $genometype.proteinsData + --speciesout $filePath + --infout $infout1 + #else + --ensembl "$genometype.buildplant" + --verorder "$genometype.version" + + --outgenome $outgenome + --outgff3 $outgff3 + --outtranscript $outtranscript + --outtrsnsnoRNA $outtrsnsnoRNA + --outprotein $outprotein + + --speciesout $builtinPath + --infout $infout2 + #end if + + ]]></command> + + <inputs> + <conditional name="genometype"> + <!-- <param name="datainput" type="boolean" truevalue="yes" falsevalue="no" checked="true" + label="Upload your own genome data?" help ="User can also select built-in species by clicking the button-No " /> --> + <param type="select" name="datainput" display="radio" multiple="false" help="Note: for 'upload from local disk', please upload files by uploadFile function first." + label="Two ways for preparing genome data:" > + <option value="BuiltinSpecies" selected="true" > Download from EnsemblPlants database</option> + <option value="UploadData"> Upload from local disk</option> + </param> + + <when value="BuiltinSpecies"> + <param name="buildplant" type="select" + label="Species (support for 61 species)" + help=""> + <options from_data_table="ensembl_plant" > + <!-- <filter type="sort_by" column="1"/> + <validator type="no_options" message="No indexes are available for the selected input dataset"/> --> + </options> + </param> + + <param name="version" type="select" + label="Database version" + help=""> + <options from_data_table="ensembl_plant_version"> + <validator type="no_options" message="No indexes are available for the selected input dataset"/> + </options> + </param> + + </when> + + <when value="UploadData"> + <param type="text" name="speciename" value="" + label="Species" + help="e.g. Arabidopsis thaliana" /> + + <param name="genomeData" type="data" format="fasta" optional="true" label="Genome sequences (.fasta)" /> + <param name="annotationData" type="data" format="gff3" optional="true" label="Annotation file (.gff3)" /> + <param name="otherrna" type="data" format="fasta" optional="true" label="t/r/sn/snoRNA sequences (.fasta)" /> + <param name="transcriptsData" type="data" format="fasta" optional="true" label="cDNA sequences (.fasta)" /> + <param name="proteinsData" type="data" format="fasta" optional="true" label="Optional: Protein sequences (.fasta)" /> + </when> + </conditional> + </inputs> + + <stdio><exit_code range="1:" level="fatal" description="Error when running ${tool.name}"/></stdio> + + <outputs> + <data format="simple" name="filePath" label="${genometype.speciename.value}"> + <filter> genometype['datainput'] == "UploadData" </filter> + </data> + <data format="pdf" name="infout1" label="${genometype.speciename.value} | ${tool.name} | Summary of genomic features"> + <filter> genometype['datainput'] == "UploadData" </filter> + </data> + <data format="simple" name="builtinPath" label="${genometype.buildplant.value}_${genometype.version.value}"> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + <data format="pdf" name="infout2" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | Summary of genomic features"> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + <data format="gz" name="outgenome" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | Genome sequences "> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + <data format="fasta" name="outtrsnsnoRNA" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | t/r/sn/snoRNA sequences"> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + <data format="gff3" name="outgff3" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | GFF3 annotations"> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + <data format="fasta" name="outtranscript" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | cDNA sequences"> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + <data format="fasta" name="outprotein" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | Protein sequences"> + <filter> genometype['datainput'] == "BuiltinSpecies" </filter> + </data> + + </outputs> + + <tests> + <test> + <param name="genomeData" value="Arabidopsis_genome.fa" ftype="fasta" /> + <param name="annotationData" value="Arabidopsis_annotation.gff3" ftype="fasta" /> + <output name="filePath" file="genomePrepare: References_of_Arabidopsis_thaliana.simple" ftype="simple" /> + </test> + + </tests> + + +<help><![CDATA[ + +.. class:: donemark + +**What it does** + +This tool provides two ways for preparing genome data: + + 1. Automatically download genomes, annotations, t/r/sn/snoRNAs (i.e. tRNAs, rRNAs, snRNAs, and snoRNAs), cDNAs, and proteins from `EnsemblPlants database`_. + 2. Upload genomic data for species not included in EnsemblPlants. + +.. class:: infomark + +**Outputs** + + - A file containing the path of formatted genome sequences and annotations. Index files of the reference genome and t/r/sn/snoRNA sequences in this path are used for 'miRNAPredict' analysis. + - Summary of the number and length of genomic features. + - Genome sequences, annotation file in GFF3 format, t/r/sn/snoRNA sequences, cDNAs, and protein sequences. + +.. _`EnsemblPlants database`: ftp://ftp.ensemblgenomes.org/pub/plants + +| + + ]]></help> + + <citations> + <citation type="doi">10.1007/978-1-4939-6658-5_1</citation> + </citations> + +</tool>