annotate alevin.xml @ 14:c9944a2600f1 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/salmon commit 20eabb7209eb447bc66450e955291143694b419a

<tool id="alevin" name="Alevin" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE_VERSION@">
    <description>Quantification and analysis of 3-prime tagged-end single-cell sequencing data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="xrefs"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
        mkdir ./index
        && mkdir ./output
        #if $refTranscriptSource.TranscriptSource != "indexed":
            && salmon index -i ./index
                --kmerLen '${refTranscriptSource.s_index.kmer}'
                --gencode
                --transcripts '${refTranscriptSource.s_index.fasta}'
            #set $index_path = './index'
        #else
            #set $index_path = $refTranscriptSource.index.fields.path
        #end if
        #if $pairstraight.readselect == 'paired':
            #if $pairstraight.file1.is_of_type("fastq.gz"):
                && cp '${pairstraight.file1}' ./mate1.fastq.gz
                && gunzip ./mate1.fastq.gz
                && cp '${pairstraight.file2}' ./mate2.fastq.gz
                && gunzip ./mate2.fastq.gz
            #else if $pairstraight.file1.is_of_type("fastq.bz2"):
                && cp '${pairstraight.file1}' ./mate1.fastq.bz2
                && bzip2 -d ./mate1.fastq.bz2
                && cp '${pairstraight.file2}' ./mate2.fastq.bz2
                && bzip2 -d ./mate2.fastq.bz2
            #else:
                && ln -s '${pairstraight.file1}' ./mate1.fastq
                && ln -s '${pairstraight.file2}' ./mate2.fastq
            #end if
        #else:
            #if $pairstraight.unmatedreads.is_of_type("fastq.gz"):
                && cp '${pairstraight.unmatedreads}' ./unmate.fastq.gz
                && gunzip ./unmate.fastq.gz
            #else if $pairstraight.unmatedreads.is_of_type("fastq.bz2"):
                && cp '${pairstraight.unmatedreads}' ./unmate.fastq.bz2
                && bzip2 -d unmate.fastq.bz2
            #else:
                && ln -s '${pairstraight.unmatedreads}' ./unmate.fastq
            #end if
        #end if

        && ln -s '${tgmap}' ./alevinmap.tsv
        && salmon alevin -l
        #if $pairstraight.readselect == 'paired':
            #if $pairstraight.libtype.strandedness == 'A'
                A
            #else
                ${pairstraight.libtype.orientation}${pairstraight.libtype.strandedness}
            #end if
            -i $index_path
            -1 ./mate1.fastq
            -2 ./mate2.fastq
        #else:
            '${pairstraight.libtype.strandedness}'
            -i $index_path
            -r zcat ./unmate.fastq
        #end if
        -o ./output
        -p "\${GALAXY_SLOTS:-4}"
        ${protocol_cond.protocol}
        #if $protocol_cond.protocol == '--indropV2'
            --w1 '${protocol_cond.w1}'
        #end if
        --tgMap ./alevinmap.tsv
        #if $whitelist:
            --whitelist '${optional.whitelist}'
        #end if
        #if $optional.numCellBootstraps:
            --numCellBootstraps '${optional.numCellBootstraps}'
        #end if
        #if $optional.forceCells:
            --forceCells '${optional.forceCells}'
        #end if
        #if $optional.expectCells:
            --expectCells '${optional.expectCells}'
        #end if
        #if $optional.mrna:
            --mrna '${optional.mrna}'
        #end if
        #if $optional.rrna:
            --rrna '${optional.rrna}'
        #end if
        #if $optional.keepCBFraction:
            --keepCBFraction '${optional.keepCBFraction}'
        #end if
        ${optional.noDedup}
        #if 'dumpBfh' in $output_files:
            --dumpBfh
        #end if
        #if 'dumpFeatures' in $output_files:
            --dumpFeatures
        #end if
        #if 'dumpUmiGraph' in $output_files:
            --dumpUmiGraph
        #end if
        ${optional.dumpMtx}
        #if $optional.maxNumBarcodes:
            --maxNumBarcodes '${optional.maxNumBarcodes}'
        #end if
        #if $optional.freqThreshold:
            --freqThreshold '${optional.freqThreshold}'
        #end if
        ## && gunzip output/alevin/quants_tier_mat.gz -> the output is binary file
        #if $optional.dumpMtx != "--dumpMtx":
            && python '$__tool_directory__/vpolo_convert.py' -m
        #else:
            && gunzip output/alevin/quants_mat.mtx.gz
        #end if
        #if 'dumpUmiGraph' in $output_files:
            && python '$__tool_directory__/vpolo_convert.py' -u
            && sh '$__tool_directory__/umiout.sh'
        #end if
        ## those gzip file include binary datasets
        ## #if $optional.numCellBootstraps:
        ##    && gunzip output/alevin/quants_mean_mat.gz
        ##    && gunzip output/alevin/quants_var_mat.gz
        ## #end if
        #if 'auxiliar_info' in $output_files
            && tar -zcvf aux_info.tar.gz output/aux_info
        #end if
        ]]>
    </command>
    <inputs>
        <expand macro="index"/>
        <conditional name="pairstraight">
            <param name="readselect" label="Single or paired-end reads?" type="select">
                <option value="paired">Paired-end</option>
                <option value="unmated">Single-end</option>
            </param>
            <when value="paired">
                <param name="file1" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" label="Mate pair 1" help="CB+UMI raw sequence file(s)"/>
                <param name="file2" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" label="Mate pair 2" help="Read-sequence file(s)"/>
                <expand macro="stranded_pe"/>
            </when>
            <when value="unmated">
                <param name="unmatedreads" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" label="Unmated reads files"/>
                <expand macro="stranded_se"/>
            </when>
        </conditional>
        <conditional name="protocol_cond">
            <param name="protocol" type="select" label="Type of single-cell protocol" help="In cases where single-cell protocol supports variable length cellbarcodes, alevin adds nucleotide padding to make the lengths uniform. Furthermore, the padding scheme ensures that there are no collisions added in the process.">
                <option value="--dropseq">DropSeq Single Cell protocol</option>
                <option value="--chromium">10x chromium v2 Single Cell protocol</option>
                <option value="--chromiumV3">10x chromium v3 Single Cell protocol</option>
                <option value="--gemcode">Gemcode v1 Single Cell protocol</option>
                <option value="--celseq">CEL-Seq Single Cell protocol</option>
                <option value="--celseq2">CEL-Seq2 Single Cell protocol</option>
                <option value="--sciseq3">Sci-RNA-seq3 protocol</option>
                <option value="--indropV2">InDrop v2 protocol</option>
                <option value="--splitSeqV1">SplitSeqV1 protocol</option>
                <option value="--splitSeqV2">SplitSeqV2 protocol</option>
            </param>
            <when value="--dropseq"/>
            <when value="--chromium"/>
            <when value="--chromiumV3"/>
            <when value="--gemcode"/>
            <when value="--celseq"/>
            <when value="--celseq2"/>
            <when value="--sciseq3"/>
            <when value="--indropV2">
                <param argument="--w1" type="text" value="" label="w1 adapters">
                    <sanitizer invalid_char="">
                        <valid initial="string.letters"/>
                    </sanitizer>
                    <validator type="regex">[ATGC]+</validator>
                </param>
            </when>
            <when value="--splitSeqV1"/>
            <when value="--splitSeqV2"/>
        </conditional>
        <param name="tgmap" type="data" format="tsv,tabular" label="Transcript to gene map file" help="Tsv with no header, containing two columns mapping each transcript present in the reference to the corresponding gene (the first column is a transcript and the second is the corresponding gene)."/>
        <param name="output_files" type="select" multiple="true" display="checkboxes" label="Extra output files">
            <option value="salmon_log">Salmon Quant log file</option>
            <option value="fragment_length">Observed fragment length distribution</option>
            <option value="auxiliar_info">Auxiliar info files</option>
            <option value="dumpUmiGraph">Per cell level parsimonious Umi graph (--dumpUmiGraph)</option>
            <option value="dumpFeatures">Features used by the CB classification and their counts at each cell level (--dumpFeatures)</option>
            <option value="dumpBfh">Full CB-EC-UMI-count data-structure (--dumpBfh)</option>
            <option value="commands">Commands info file</option>
        </param>
        <section name="optional" title="Advanced options" expanded="false">
            <param argument="--whitelist" type="data" format="tsv,tabular" optional="true" label="Whitelist file" help="Explicitly specify whitelist CP for cell detection and CB sequence correction. If not specified, putative CBs generated."/>
            <param argument="--noDedup" type="boolean" truevalue="--noDedup" falsevalue="" checked="false" label="Skip deduplication step" help="Causes pipeline to only perform CB correction, then maps the read-sequences to the transcriptome generating the interim data-structure of CB-EqClass-UMI-count. Used in parallel with --dumpBarcodeEq or --dumpBfh for the purposes of obtaining raw information or debugging."/>
            <param argument="--mrna" type="data" format="tsv" optional="true" label="Mito-RNA genes file" help="Single column tsv of mitochondrial genes which are to be used as a feature for CB whitelising naive Bayes classification."/>
            <param argument="--rrna" type="data" format="tsv" optional="true" label="Ribosomal RNA file" help="Single column tsv of ribosomal genes which are to be used as a feature for CB whitelising naive Bayes classification."/>
            <param argument="--dumpMtx" type="boolean" truevalue="--dumpMtx" falsevalue="" checked="false" label=" Dump cell v transcripts count matrix in MTX format" help="Converts the default binary format of alevin for gene-count matrix into a human readable mtx (matrix market exchange) sparse format."/>
            <param argument="--forceCells" type="integer" min="0" optional="true" label="Number of cells" help="Explicitly specify the number of cells."/>
            <param argument="--expectCells" type="integer" min="0" optional="true" label="Upper bound on expected number of cells" help="define a close upper bound on expected number of cells."/>
            <param argument="--numCellBootstraps" type="integer" min="0" value="0" optional="true" label="Generate mean and variance for cell x gene matrix by boostrap" help="Performs certain number of bootstrap and generate the mean and variance of the count matrix"/>
            <param argument="--minScoreFraction" type="float" optional="true" label="Minimum allowed score for a mapping" help="This value controls the minimum allowed score for a mapping to be considered valid. It matters only when --validateMappings has been passed to Salmon. The maximum possible score for a fragment is ms = read_len * ma (or ms = (left_read_len + right_read_len) * ma for paired-end reads).
                The argument to --minScoreFraction determines what fraction of the maximum score s a mapping must achieve to be potentially retained. For a minimum score fraction of f, only mappings with a score less than (f * s) will be kept. Mappings with lower scores will be considered as low-quality, and will be discarded."/>
            <param argument="--keepCBFraction" type="float" min="0" max="1" optional="true" label="Fraction of cellular barcodes to keep" help="Use 1 to quantify all"/>
            <param argument="--maxNumBarcodes" type="integer" min="0" value="100000" label="Maximum allowable limit to process the cell barcodes" help="Default: 100000"/>
            <param argument="--freqThreshold" type="integer" min="0" value="10" optional="true" label="Minimum frequency for a barcode to be considered" help="Default: 10"/>
        </section>
    </inputs>
    <outputs>
        <data name="quants_mat_tsv" label="${tool.name} on ${on_string}: per-cell gene-count matrix (tabular)" format="txt" from_work_dir="quants_mat.tsv">
            <filter>optional["dumpMtx"] is not True</filter>
        </data>
        <data name="quants_mat_mtx" label="${tool.name} on ${on_string}: per-cell gene-count matrix (MTX)" format="mtx" from_work_dir="output/alevin/quants_mat.mtx">
            <filter>optional["dumpMtx"]</filter>
        </data>
        <data name="quants_mat_gz" label="${tool.name} on ${on_string}: per-cell level gene-count matrix (binary)" format="gz" from_work_dir="output/alevin/quants_mat.gz"/>
        <data name="quants_mat_cols_txt" label="${tool.name} on ${on_string}: column headers (gene-ids)" format="txt" from_work_dir="output/alevin/quants_mat_cols.txt"/>
        <data name="quants_mat_rows_txt" label="${tool.name} on ${on_string}: row index (CB-ids)" format="txt" from_work_dir="output/alevin/quants_mat_rows.txt"/>
        <data name="quants_tier_mat" label="${tool.name} on ${on_string}: tier categorization" format="gz" from_work_dir="output/alevin/quants_tier_mat.gz"/>
        <data name="featureDump_txt" label="${tool.name} on ${on_string}: cell-level information (featureDump)" format="txt" from_work_dir="output/alevin/featureDump.txt"/>
        <data name="raw_cb_frequency_txt" label="${tool.name} on ${on_string}: raw CB classification frequencies" format="txt" from_work_dir="output/alevin/raw_cb_frequency.txt">
            <filter>output_files and 'dumpFeatures' in output_files</filter>
        </data>
        <data name="whitelist_txt" label="${tool.name} on ${on_string}: whitelist" format="txt" from_work_dir="output/alevin/whitelist.txt"/>

        <data name="auxiliar_files" label="${tool.name} on ${on_string}: auxiliar info files" format="tgz" from_work_dir="aux_info.tar.gz">
            <filter>output_files and 'auxiliar_info' in output_files</filter>
        </data>
        <data name="salmon_quant_log" format="txt" label="${tool.name} on ${on_string}: Salmon log file" from_work_dir="output/logs/salmon_quant.log">
            <filter>output_files and 'salmon_log' in output_files</filter>
        </data>
        <data name="cmd_info" label="${tool.name} on ${on_string}: command info (JSON)" format="json" from_work_dir="output/cmd_info.json">
            <filter>output_files and 'commands' in output_files</filter>
        </data>
        <data name="flenDist_txt" format="txt" label="${tool.name} on ${on_string}: observed fragment length distribution" from_work_dir="output/libParams/flenDist.txt">
            <filter>output_files and 'fragment_length' in output_files</filter>
        </data>
        <data name="bfh_txt" label="${tool.name} on ${on_string}: full CB-EC-UMI-count data-structure" format="txt" from_work_dir="output/alevin/bfh.txt">
            <filter>output_files and 'dumpBfh' in output_files</filter>
        </data>
        <data name="quants_mean_mat" label="${tool.name} on ${on_string}: count matrix mean file" format="gz" from_work_dir="output/alevin/quants_mean_mat.gz">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_var_mat" label="${tool.name} on ${on_string}: count matrix variance file" format="gz" from_work_dir="output/alevin/quants_var_mat.gz">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_boot_rows_txt" label="${tool.name} on ${on_string}: bootstraps rows" format="txt" from_work_dir="output/alevin/quants_boot_rows.txt">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <collection name="umigraphs" type="list" label="${tool.name} on ${on_string}: UMI graph PDFs">
            <filter>output_files and 'dumpUmiGraph' in output_files</filter>
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.pdf" format="pdf" directory="fixed"/>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="8">
            <conditional name="refTranscriptSource">
                <param name="TranscriptSource" value="history"/>
                <section name="s_index">
                    <param name="fasta" value="minitranscript.fa"/>
                </section>
            </conditional>
            <conditional name="pairstraight">
                <param name="readselect" value="paired"/>
                <param name="file1" value="fastqs/moreminifastq1.fastq.gz"/>
                <param name="file2" value="fastqs/moreminifastq2.fastq.gz"/>
                <param name="orientation" value="I"/>
                <param name="strandedness" value="SR"/>
            </conditional>
            <conditional name="protocol_cond">
                <param name="protocol" value="--chromium"/>
            </conditional>
            <param name="tgmap" value="minitxp.tsv"/>
            <param name="output_files" value="dumpFeatures"/>
            <section name="optional">
                <param name="keepCBFraction" value="1"/>
                <param name="freqThreshold" value="5"/>
                <param name="dumpMtx" value="true"/>
            </section>
            <output name="quants_mat_mtx" file="alevin_mat_01.mtx" compare="sim_size" ftype="mtx">
                <assert_contents>
                    <has_text text="MatrixMarket" />
                    <has_n_columns n="5" />
                    <has_n_lines n="105" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="11">
            <conditional name="refTranscriptSource">
                <param name="TranscriptSource" value="history"/>
                <section name="s_index">
                    <param name="fasta" value="minitranscript.fa"/>
                </section>
            </conditional>
            <conditional name="pairstraight">
                <param name="readselect" value="paired"/>
                <param name="file1" value="fastqs/moreminifastq1.fastq.gz"/>
                <param name="file2" value="fastqs/moreminifastq2.fastq.gz"/>
                <param name="orientation" value="I"/>
                <param name="strandedness" value="SR"/>
            </conditional>
            <conditional name="protocol_cond">
                <param name="protocol" value="--chromium"/>
            </conditional>
            <param name="tgmap" value="minitxp.tsv"/>
            <param name="output_files" value="dumpFeatures"/>
            <section name="optional">
                <param name="keepCBFraction" value="1"/>
                <param name="numCellBootstraps" value="2"/>
                <param name="freqThreshold" value="5"/>
                <param name="dumpMtx" value="true"/>
            </section>
            <output name="quants_mat_mtx" file="alevin_mat_02.mtx" compare="sim_size" ftype="mtx" >
                <assert_contents>
                    <has_text text="MatrixMarket" />
                    <has_n_columns n="5" />
                    <has_n_lines n="105" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="8">
            <conditional name="refTranscriptSource">
                <param name="TranscriptSource" value="history"/>
                <section name="s_index">
                    <param name="fasta" value="minitranscript.fa"/>
                </section>
            </conditional>
            <conditional name="pairstraight">
                <param name="readselect" value="paired"/>
                <param name="file1" value="fastqs/moreminifastq1.fastq.gz"/>
                <param name="file2" value="fastqs/moreminifastq2.fastq.gz"/>
                <param name="orientation" value="I"/>
                <param name="strandedness" value="SR"/>
            </conditional>
            <conditional name="protocol_cond">
                <param name="protocol" value="-\-indropV2"/>
                <param name="w1" value="ATCAT"/>
            </conditional>
            <param name="tgmap" value="minitxp.tsv"/>
            <param name="output_files" value="dumpFeatures"/>
            <section name="optional">
                <param name="keepCBFraction" value="1"/>
                <param name="freqThreshold" value="5"/>
                <param name="dumpMtx" value="true"/>
            </section>
            <output name="quants_mat_mtx" file="alevin_mat_indropV2.mtx"  compare="sim_size" ftype="mtx">
                <assert_contents>
                    <has_text text="MatrixMarket" />
                    <has_n_columns n="5" />
                    <has_n_lines n="105" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="14">
            <conditional name="refTranscriptSource">
                <param name="TranscriptSource" value="history"/>
                <section name="s_index">
                    <param name="fasta" value="minitranscript.fa"/>
                </section>
            </conditional>
            <conditional name="pairstraight">
                <param name="readselect" value="paired"/>
                <param name="file1" value="fastqs/moreminifastq1.fastq.gz"/>
                <param name="file2" value="fastqs/moreminifastq2.fastq.gz"/>
                <param name="orientation" value="I"/>
                <param name="strandedness" value="SR"/>
            </conditional>
            <conditional name="protocol_cond">
                <param name="protocol" value="--chromium"/>
            </conditional>
            <param name="tgmap" value="minitxp.tsv"/>
            <param name="output_files" value="dumpFeatures,salmon_log,fragment_length,auxiliar_info,dumpUmiGraph,dumpBfh,commands"/>
            <section name="optional">
                <param name="dumpMtx" value="true"/>
            </section>
            <output name="quants_mat_mtx" file="alevin_mat.mtx"  compare="sim_size" ftype="mtx">
                <assert_contents>
                    <has_text text="MatrixMarket" />
                    <has_n_columns n="5" />
                    <has_n_lines n="17" />
                </assert_contents>
            </output>
            <output name="salmon_quant_log" ftype="txt">
                <assert_contents>
                    <has_text text="Index contained 322 targets"/>
                    <has_text text="Counted 14 total reads in the equivalence classes"/>
                </assert_contents>
            </output>
            <output name="flenDist_txt" file="length_distribution.txt" ftype="txt"/>
            <output name="auxiliar_files" ftype="tgz">
                <assert_contents>
                    <has_size value="1898" delta="100"/>
                </assert_contents>
            </output>
            <output_collection name="umigraphs" type="list" count="14">
                <element name="AGTGGGATCTTAACCT">
                    <assert_contents>
                        <has_size value="4661" delta="1000"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="bfh_txt" file="full_data_structure.txt" ftype="txt"/>
        </test>
    </tests>
    <help><![CDATA[
        @salmonhelp@
        @alevinhelp@
    ]]></help>
    <expand macro="citations"/>
</tool>