annotate data_manager/macros.xml @ 9:c520a52b5174 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_star_index_builder commit 1f8b01701c5b81d155617267a179ba42a0d4a307"

<macros>
    <!-- REMEMBER to bump the version of rna_star_index_builder_data_manager
    whenever you make changes to the following two version tokens!
    The data manager uses a symlink to this macro file to keep the STAR and
    the index versions in sync, but you should manually adjust the +galaxy
    version number. -->
    <!-- STAR version to be used -->
    <token name="@VERSION@">2.7.8a</token>
    <!-- STAR index version compatible with this version of STAR
    This is the STAR version that introduced the index structure expected
    by the current version.
    It can be found for any specific version of STAR with:
    STAR -h | grep versionGenome
    or by looking for the versionGenome parameter in source/parametersDefault
    of STAR's source code -->
    <token name="@IDX_VERSION@">2.7.4a</token>
    <token name="@IDX_DATA_TABLE@">rnastar_index2x_versioned</token>

    <xml name="requirements">
        <requirements>
            <requirement type="package" version="@VERSION@">star</requirement>
            <requirement type="package" version="1.9">samtools</requirement>
            <yield />
        </requirements>
    </xml>

    <xml name="edam">
        <edam_topics>
            <edam_topic>topic_3170</edam_topic>
            <edam_topic>topic_3308</edam_topic>
        </edam_topics>
        <edam_operations>
            <edam_operation>operation_0292</edam_operation>
        </edam_operations>
    </xml>

    <xml name="index_selection" token_with_gene_model="0">
        <param argument="--genomeDir" name="genomeDir" type="select"
        label="Select reference genome"
        help="If your genome of interest is not listed, contact the Galaxy team">
            <options from_data_table="@IDX_DATA_TABLE@">
                <filter type="static_value" column="4" value="@WITH_GENE_MODEL@" />
                <filter type="static_value" column="5" value="@IDX_VERSION@" />
                <filter type="sort_by" column="2" />
                <validator type="no_options" message="No indexes are available for the selected input dataset" />
            </options>
        </param>
    </xml>

    <token name="@FASTQ_GZ_OPTION@">
        --readFilesCommand zcat
    </token>
    <xml name="citations">
        <citations>
            <citation type="doi">10.1093/bioinformatics/bts635</citation>
        </citations>
    </xml>
    <xml name="@SJDBOPTIONS@" token_optional="true">
         <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="@OPTIONAL@" 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"/>
    </xml>
    <xml name="dbKeyActions">
        <actions>
            <conditional name="refGenomeSource.geneSource">
                <when value="indexed">
                    <action type="metadata" name="dbkey">
                        <option type="from_data_table" name="@IDX_DATA_TABLE@" column="1" offset="0">
                            <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                            <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
                        </option>
                    </action>
                </when>
                <when value="history">
                    <action type="metadata" name="dbkey">
                        <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
                    </action>
                </when>
            </conditional>
        </actions>
    </xml>
    <token name="@TEMPINDEX@"><![CDATA[
    ## Create temporary index for custom reference
    #if str($refGenomeSource.geneSource) == 'history':
        mkdir -p tempstargenomedir &&
        STAR
            --runMode genomeGenerate
            --genomeDir 'tempstargenomedir'
            --genomeFastaFiles '${refGenomeSource.genomeFastaFiles}'
            ## Handle difference between indices with/without annotations
            #if 'GTFconditional' in $refGenomeSource:
                ## GTFconditional exists only in STAR, but not STARsolo
                #if str($refGenomeSource.GTFconditional.GTFselect) == 'with-gtf':
                    --sjdbOverhang '${refGenomeSource.GTFconditional.sjdbOverhang}'
                    --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}'
                    #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3':
                        --sjdbGTFtagExonParentTranscript Parent
                    #end if
                #end if
            #else:
                ## ref genome selection is less complex for STARsolo cause
                ## with-gtf is mandatory there
                --sjdbOverhang '${refGenomeSource.sjdbOverhang}'
                --sjdbGTFfile '${refGenomeSource.sjdbGTFfile}'
                #if str($refGenomeSource.sjdbGTFfile.ext) == 'gff3':
                    --sjdbGTFtagExonParentTranscript Parent
                #end if
            #end if
            #if str($refGenomeSource.genomeSAindexNbases):
                --genomeSAindexNbases ${refGenomeSource.genomeSAindexNbases}
            #end if
            --runThreadN \${GALAXY_SLOTS:-4}
        &&
    #end if
    ]]></token>
    <token name="@REFGENOMEHANDLING@" ><![CDATA[
    --runThreadN \${GALAXY_SLOTS:-4}
    --genomeLoad NoSharedMemory
    --genomeDir
    #if str($refGenomeSource.geneSource) == 'history':
        tempstargenomedir
    #else:
        '${refGenomeSource.GTFconditional.genomeDir.fields.path}'
        ## Handle difference between indices with/without annotations
        #if str($refGenomeSource.GTFconditional.GTFselect) == 'without-gtf':
            #if $refGenomeSource.GTFconditional.sjdbGTFfile:
                --sjdbOverhang $refGenomeSource.GTFconditional.sjdbOverhang
                --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}'
                #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3':
                    --sjdbGTFtagExonParentTranscript Parent
                #end if
            #end if
        #end if
        #end if
        ]]></token>
    <token name="@READSHANDLING@" ><![CDATA[
    ## Check that the input pairs are of the same type
    ## otherwise STARsolo will run for a long time and then error out.
    ## We consume either repeats of two inputs R1 + R2
    ## or a collection of paired reads.
    #if str($sc.input_types.use) == "repeat":
        #set $reads1 = []
        #set $reads2 = []
        #for $r1, $r2 in zip($sc.input_types.input1, $sc.input_types.input2):
            #assert $r1.datatype == $r2.datatype
            #silent $reads1.append(str($r1))
            #silent $reads2.append(str($r2))
        #end for
        #set $reads1 = ','.join($reads1)
        #set $reads2 = ','.join($reads2)
    #elif str($sc.input_types.use) == "list_paired":
        #set $r1 = $sc.input_types.input_collection.forward
        #set $r2 = $sc.input_types.input_collection.reverse
        #set $reads1 = $r1
        #set $reads2 = $r2
    #end if
    ## cDNA sequence(s) [R2] always go first, then barcode(s) [R1]
    ## see: Section 3.2 of STAR manual for multiple inputs, and Section 13 for STARsolo inputs
    --readFilesIn $reads2 $reads1
    --soloCBmatchWLtype $sc.soloCBmatchWLtype
    #if $r1.is_of_type('fastq.gz', 'fastqsanger.gz'):
        @FASTQ_GZ_OPTION@
    #end if
    ]]></token>
    <xml name="ref_selection">
        <param argument="--genomeFastaFiles" type="data" format="fasta" label="Select a reference genome" />
          <param argument="--genomeSAindexNbases" type="integer" min="2" max="16" value="14" label="Length 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)"/>
    </xml>
    <xml name="stdio" >
        <stdio>
            <regex match="FATAL error" source="both" level="fatal"/>
            <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/>
            <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/>
            <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/>
            <yield />
        </stdio>
    </xml>
    <xml name="input_selection">
        <conditional name="input_types" >
            <param name="use" type="select" label="Input Type" >
                <option value="repeat" >Separate barcode and cDNA reads</option>
                <option value="list_paired" >Paired collection of barcode and cDNA reads</option>
            </param>
            <when value="repeat">
                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data"  multiple="true"
                label="RNA-Seq FASTQ/FASTA file, Barcode reads" />
                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data"  multiple="true"
                label="RNA-Seq FASTQ/FASTA file, cDNA reads"/>
            </when>
            <when value="list_paired">
                <param name="input_collection" collection_type="paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="Collection of Pairs" />
            </when>
        </conditional>
    </xml>
    <xml name="input_selection_smart_seq">
        <conditional name="input_types_smart_seq" >
            <param name="use" type="select" label="Input Type" >
                <option value="list_single_end" >Single-end FASTQ collection</option>
                <option value="list_paired_end" >Paired FASTQ collection</option>
            </param>
            <when value="list_single_end">
                <param name="single_end_collection" collection_type="list" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of single-end FASTQ files" />
            </when>
            <when value="list_paired_end">
                <param name="paired_end_collection" collection_type="list:paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of paired-end FASTQ files" />
            </when>
        </conditional>
    </xml>
    <xml name="umidedup_options">
        <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other</option>
        <option value="1MM_Directional_UMItools" >Directional method from the UMI-tool</option>
        <option value="1MM_Directional" >Directional with stringent UMI deduplication</option>
    </xml>
    <xml name="anchor_types">
        <option value="0">Read start</option>
        <option value="1">Read end</option>
        <option value="2">Adapter start</option>
        <option value="3">Adapter end</option>
    </xml>
    <xml name="cb_match_wl_common">
        <option value="Exact" >Exact</option>
        <option value="1MM" >Single match</option>
    </xml>
    <xml name="cb_match_wl_cellranger">
        <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2)</option>
        <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3)</option>
        <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3)</option>
    </xml>
    <xml name="solo_adapter_params">
        <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes." >
            <sanitizer>
                <valid initial="string.digits">
                    <add value="-"/>
                    <add value="A"/>
                    <add value="T"/>
                    <add value="C"/>
                    <add value="G"/>
                    <add value="N"/>
                </valid>
            </sanitizer>
        </param>
        <param argument="--soloAdapterMismatchesNmax" type="integer" min="1" value="1" label="Maximum number of mismatches allowed in adapter sequence" />
        <param argument="--clipAdapterType" type="select" >
            <option value="Hamming" selected="true" >Adapter clipping based on Hamming distance</option>
            <option value="CellRanger4" >5p and 3p adapter clipping similar to CellRanger4</option>
            <option value="None" >No adapter clipping</option>
        </param>
    </xml>
</macros>