comparison data_manager/rna_star_index_builder.xml @ 4:6ef6520f14fc draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_star_index_builder commit 39b9b154845ecf517f7d9e9d76c386b473c3ebd2

3:50ca9af6db2e

<tool id="rna_star_index_builder_data_manager" name="rnastar index2" tool_type="manage_data" version="0.0.4" profile="17.01">
    <description>builder</description>
    
    <macros>
        <import>macros.xml</import>
    </macros>
    
    <expand macro="requirements" />
    
    <command><![CDATA[
        #import json, os
        #set params = json.loads( open( str($out_file) ).read() )
        #set target_directory = $params[ 'output_data' ][0]['extra_files_path'].encode('ascii', 'replace')
        #set subdir = os.path.basename(target_directory)

        mkdir -p '${target_directory}/${subdir}' &&

        STAR
            --runMode genomeGenerate
            --genomeFastaFiles '${all_fasta_source.fields.path}'
            --genomeDir '${target_directory}/${subdir}'
            #if str($GTFconditional.GTFselect) == "withGTF":
                --sjdbGTFfile '${GTFconditional.sjdbGTFfile}'
                --sjdbOverhang '${GTFconditional.sjdbOverhang}'
            #end if
            --runThreadN \${GALAXY_SLOTS:-2} &&

        python ${__tool_directory__}/rna_star_index_builder.py
            --config-file '${out_file}'
            --value '${all_fasta_source.fields.value}'
            --dbkey '${all_fasta_source.fields.dbkey}'
            #if $name:
                --name '$name'
            #else
                --name '${all_fasta_source.fields.name}'
            #end if
            #if str($GTFconditional.GTFselect) == "withGTF":
                --withGTF 1
            #end if
            --data-table 'rnastar_index2'
            --subdir '${subdir}'
    ]]></command>
    <inputs>
        <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
            <options from_data_table="all_fasta"/>
        </param>
        <param name="name"
               type="text"
               value=""
               label="Informative name for sequence index"
               help="By using different settings, you may have several indices per reference genome. Give an appropriate description to the index to distinguish between indices"/>
        <conditional name="GTFconditional">
            <param name="GTFselect" type="select" label="Reference genome with or without an annotation" help="Must the index have been created WITH a GTF file (if not you can specify one afterward).">
                <option value="withoutGTF">use genome reference without builtin gene-model</option>
                <option value="withGTF">use genome reference with builtin gene-model</option>
            </param>
            <when value="withGTF">
                <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/>
                <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/>
            </when>
            <when value="withoutGTF" />
        </conditional>
    </inputs>

    <outputs>
        <data name="out_file" format="data_manager_json"/>

            <output name="out_file" file="test_star_01.data_manager_json"/>
        </test>
    </tests>
    -->

    <help>

.. class:: infomark

<![CDATA[
*What it does*

This is a Galaxy datamanager for the rna STAR gap-aware RNA aligner.

Please read the fine manual - that and the google group are the places to learn about the options above.

*Memory requirements*

To run efficiently, RNA-STAR requires enough free memory to
hold the SA-indexed reference genome in RAM. For Human Genome hg19 this
index is about 27GB and running RNA-STAR requires approximately ~30GB of RAM.
For custom genomes, the rule of thub is to multiply the size of the
reference FASTA file by 9 to estimated required amount of RAM.

*Note on sjdbOverhang*

From https://groups.google.com/forum/#!topic/rna-star/h9oh10UlvhI::

    3. 'transcript_id' attribute that assigns each exon to a transcript (--this name can be changed with --sjdbGTFtagExonParentTranscript)

    Cheers
    Alex

**Notice:** If you leave name, description, or id blank, it will be generated automatically. 
]]>
    </help>
    <expand macro="citations" />
</tool>

4:6ef6520f14fc

<tool id="rna_star_index_builder_data_manager" name="rnastar index2" tool_type="manage_data" version="0.0.5" profile="17.01">
    <description>builder</description>

    <macros>
        <import>macros.xml</import>
    </macros>

    <expand macro="requirements" />

    <command><![CDATA[
if [ -z "\$GALAXY_MEMORY_MB" ] ; then
    GALAXY_MEMORY_BYTES=31000000000 ;
else
    GALAXY_MEMORY_BYTES=\$((GALAXY_MEMORY_MB * 1000000)) ;
fi ;

#import json, os
#set params = json.loads(open(str($out_file)).read())
#set target_directory = $params['output_data'][0]['extra_files_path'].encode('ascii', 'replace')
#set subdir = os.path.basename(target_directory)

mkdir -p '${target_directory}/${subdir}' &&

STAR
--runMode genomeGenerate
--genomeFastaFiles '${all_fasta_source.fields.path}'
--genomeDir '${target_directory}/${subdir}'
--limitGenomeGenerateRAM \${GALAXY_MEMORY_BYTES}
#if $GTFconditional.GTFselect == "withGTF":
    --sjdbGTFfile '${GTFconditional.sjdbGTFfile}'
    --sjdbOverhang ${GTFconditional.sjdbOverhang}
#end if
#if $advanced_options.advanced_options_selector == "advanced":
    --genomeSAindexNbases ${advanced_options.genomeSAindexNbases}
    --genomeChrBinNbits ${advanced_options.genomeChrBinNbits}
    --genomeSAsparseD ${advanced_options.genomeSAsparseD}
#end if
--runThreadN \${GALAXY_SLOTS:-2} &&

python '${__tool_directory__}/rna_star_index_builder.py'
--config-file '${out_file}'
--value '${all_fasta_source.fields.value}'
--dbkey '${all_fasta_source.fields.dbkey}'
#if $name:
    --name '$name'
#else
    --name '${all_fasta_source.fields.name}'
#end if
#if str($GTFconditional.GTFselect) == "withGTF":
    --withGTF 1
#end if
--data-table rnastar_index2
--subdir '${subdir}'
    ]]></command>
    <inputs>
        <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
            <options from_data_table="all_fasta"/>
        </param>
        <param name="name" type="text" value="" label="Informative name for sequence index"
            help="By using different settings, you may have several indices per reference genome. Give an appropriate description to the index to distinguish between indices"/>
        <conditional name="GTFconditional">
            <param name="GTFselect" type="select" label="Reference genome with or without an annotation" help="Must the index have been created WITH a GTF file (if not you can specify one afterward).">
                <option value="withoutGTF">use genome reference without builtin gene-model</option>
                <option value="withGTF">use genome reference with builtin gene-model</option>
            </param>
            <when value="withGTF">
                <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/>
                <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/>
            </when>
            <when value="withoutGTF" />
        </conditional>
        <conditional name="advanced_options">
            <param name="advanced_options_selector" type="select" label="Advanced options">
                <option value="default" selected="true">Use default options</option>
                <option value="advanced">Set advanced options</option>
            </param>
            <when value="default" />
            <when value="advanced">
                <param argument="--genomeSAindexNbases" type="integer" min="1" value="14"
                    label="Length (bases) of the SA pre-indexing string"
                    help="Typically between 10 and 15. Longer strings will use much more memory, but allow
                        faster searches. For small genomes, the parameter –genomeSAindexNbases must be scaled
                        down to min(14, log2(GenomeLength)/2 - 1). For example, for 1 megaBase genome, this is
                        equal to 9, for 100 kiloBase genome, this is equal to 7."/>
                <param argument="--genomeChrBinNbits" type="integer" min="1" value="18"
                    label="Log2(chrBin), where chrBin is the size of the bins for genome storage"
                    help="Each chromosome will occupy an integer number of bins. For a genome with large number
                        of contigs, it is recommended to scale this parameter as min(18,
                        log2[max(GenomeLength/NumberOfReferences,ReadLength)]). For example, for 3 gigaBase
                        genome with 100,000 chromosomes/scaffolds, this is equal to 15."/>
                <param argument="--genomeSAsparseD" type="integer" min="1" value="1" label="Suffix array sparsity"
                    help="The distance between indices: use bigger numbers to decrease needed RAM at the cost of
                        mapping speed reduction"/>
            </when>
        </conditional>
    </inputs>

    <outputs>
        <data name="out_file" format="data_manager_json"/>

            <output name="out_file" file="test_star_01.data_manager_json"/>
        </test>
    </tests>
    -->

    <help><![CDATA[
.. class:: infomark

*What it does*

This is a Galaxy datamanager for the rna STAR gap-aware RNA aligner.

Please read the fine manual - that and the google group are the places to learn about the options above.

*Memory requirements*

To run efficiently, RNA-STAR requires enough free memory to
hold the SA-indexed reference genome in RAM. For Human Genome hg19 this
index is about 27GB and running RNA-STAR requires approximately ~30GB of RAM.
For custom genomes, the rule of thumb is to multiply the size of the
reference FASTA file by 9 to estimated required amount of RAM.

*Note on sjdbOverhang*

From https://groups.google.com/forum/#!topic/rna-star/h9oh10UlvhI::

    3. 'transcript_id' attribute that assigns each exon to a transcript (--this name can be changed with --sjdbGTFtagExonParentTranscript)

    Cheers
    Alex

**Notice:** If you leave name, description, or id blank, it will be generated automatically.
    ]]></help>
    <expand macro="citations" />
</tool>