comparison alevin.xml @ 2:b579f36923d9 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/salmon commit c17bc974bf9bbaa1fc1e47ea72162fd244f0e612"

1:505d2b4959b1

            --rrna '${optional.rrna}'
        #end if
        #if $optional.keepCBFraction:
            --keepCBFraction '${optional.keepCBFraction}'
        #end if
        ${optional.dumpBfh}
        ${optional.dumpFeatures}
        ${optional.dumpUmiGraph}
        ${optional.dumpMtx}
        #if $optional.lowRegionMinNumBarcodes:
            --lowregionMinNumBarcodes '${optional.lowRegionMinNumBarcodes}'
        #end if
        #if $optional.maxNumBarcodes:
            --maxNumBarcodes '${optional.maxNumBarcodes}'
        #end if
        ]]>
    </command>
    <inputs>
        <expand macro="index"/>

        </param>
        <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="allout" type="boolean" label="Retrieve all output files" truevalue="Yes" falsevalue="No" checked="false" help="If not selected, all log, info.txt, and json files output by Alevin will not be retrieved"/>
        <section name="optional" title="Optional commands" expanded="false">
            <param name="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 name="noDedup" type="boolean" truevalue="Yes" falsevalue="No" checked="false" 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 name="mrna" type="data" format="tsv" optional="true" help="Single column tsv of mitochondrial genes which are to be used as a feature for CB whitelising naive Bayes classification."/>
            <param name="rrna" type="data" format="tsv" optional="true" help="Single column tsv of ribosomal genes which are to be used as a feature for CB whitelising naive Bayes classification."/>
            <param name="dumpBfh" type="boolean" truevalue="--dumpBfh" falsevalue="" checked="false" help="Dumps the full CB-EqClass-UMI-count data-structure for the purposed of allowing raw data analysis and debugging."/>
            <param name="dumpFeatures" type="boolean" truevalue="--dumpFeatures" falsevalue="" checked="false" help="Dumps all features used by the CB classification and their counts at each cell level. Generally, this is used for the purposes of debugging."/>
            <param name="dumpUmiGraph" type="boolean" truevalue="--dumpUmiGraph" falsevalue="" checked="false" help="Dump the per-cell level umi graph"/>

            <param name="lowRegionMinNumBarcodes" type="integer" optional="true" help="Minimum number of cell barcodes to use fo learning low confidence region (defaults to 200)"/>
            <param name="maxNumBarcodes" type="integer" optional="true" help="Maximum allowable limit to process the cell barcodes. Defaults to 100000"/>
        </section>
    </inputs>
    <outputs>
        <data name="quants_mat.gz" label="quants_mat.gz" format="txt" from_work_dir="output/alevin/quants_mat.gz">
            <filter>optional["dumpMtx"] != "Yes"</filter>
        </data>
        <data name="quants_mat.mtx.gz" label="quants_mat.mtx.gz" format="mtx" from_work_dir="output/alevin/quants_mat.mtx.gz"/>
        <data name="quants_mat_cols.txt" label="quants_mat_cols.txt" format="txt" from_work_dir="output/alevin/quants_mat_cols.txt"/>
        <data name="quants_mat_rows.txt" label="quants_mat_rows.txt" format="txt" from_work_dir="output/alevin/quants_mat_rows.txt"/>
        <data name="quants_tier_mat.gz" label="quants_tier_mat.gz" format="mtx" from_work_dir="output/alevin/quants_tier_mat.gz"/>
        <data name="alevin.log" label="alevin.log" format="txt" from_work_dir="output/alevin/alevin.log">
            <filter>allout</filter>
        </data>
        <data name="featureDump.txt" label="featureDump.txt" format="txt" from_work_dir="output/alevin/featureDump.txt"/>
        <data name="whitelist.txt" label="whitelist.txt" format="txt" from_work_dir="output/alevin/whitelist.txt"/>
        <data name="bfh.txt" label="bfh.txt" format="txt" from_work_dir="output/alevin/bfh.txt">
            <filter>optional["dumpBfh"] == "Yes"</filter>
        </data>
        <data name="quants_mean_mat.gz" label="quants_mean_mat.gz" format="mtx" from_work_dir="output/alevin/quants_mean_mat.gz">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_var_mat.gz" label="quants_var_mat.gz" format="mtx" from_work_dir="output/alevin/quants_var_mat.gz">

        <data name="observed_bias_3p.gz" format="txt" label="observed_bias_3p.gz" from_work_dir="output/aux_info/observed_bias_3p.gz"/>
        <data name="flenDist.txt" format="txt" label="flenDist.txt" from_work_dir="output/libParams/flenDist.txt"/>
        <data name="salmon_quant.log" format="txt" label="salmon_quant.log" from_work_dir="output/logs/salmon_quant.log">
            <filter>allout</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="11">
            <conditional name="refTranscriptSource">
                <param name="TranscriptSource" value="history"/>
                <section name="s_index">
                    <param name="fasta" value="minitranscript.fa"/>
                </section>

2:b579f36923d9

            --rrna '${optional.rrna}'
        #end if
        #if $optional.keepCBFraction:
            --keepCBFraction '${optional.keepCBFraction}'
        #end if
        ${optional.noDedup}
        ${optional.dumpBfh}
        ${optional.dumpFeatures}
        ${optional.dumpUmiGraph}
        ${optional.dumpMtx}
        #if $optional.lowRegionMinNumBarcodes:
            --lowregionMinNumBarcodes '${optional.lowRegionMinNumBarcodes}'
        #end if
        #if $optional.maxNumBarcodes:
            --maxNumBarcodes '${optional.maxNumBarcodes}'
        #end if

        #if $optional.dumpMtx != "--dumpMtx":
            && python '$__tool_directory__/vpolo_convert.py' -m
        #end if
        #if $optional.dumpUmiGraph:
            && python '$__tool_directory__/vpolo_convert.py' -u
            && sh '$__tool_directory__/umiout.sh'
        #end if
        ]]>
    </command>
    <inputs>
        <expand macro="index"/>

        </param>
        <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="allout" type="boolean" label="Retrieve all output files" truevalue="Yes" falsevalue="No" checked="false" help="If not selected, all log, info.txt, and json files output by Alevin will not be retrieved"/>
        <section name="optional" title="Optional commands" expanded="false">
            <param name="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 name="noDedup" type="boolean" truevalue="--noDedup" falsevalue="" checked="false" 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 name="mrna" type="data" format="tsv" optional="true" help="Single column tsv of mitochondrial genes which are to be used as a feature for CB whitelising naive Bayes classification."/>
            <param name="rrna" type="data" format="tsv" optional="true" help="Single column tsv of ribosomal genes which are to be used as a feature for CB whitelising naive Bayes classification."/>
            <param name="dumpBfh" type="boolean" truevalue="--dumpBfh" falsevalue="" checked="false" help="Dumps the full CB-EqClass-UMI-count data-structure for the purposed of allowing raw data analysis and debugging."/>
            <param name="dumpFeatures" type="boolean" truevalue="--dumpFeatures" falsevalue="" checked="false" help="Dumps all features used by the CB classification and their counts at each cell level. Generally, this is used for the purposes of debugging."/>
            <param name="dumpUmiGraph" type="boolean" truevalue="--dumpUmiGraph" falsevalue="" checked="false" help="Dump the per-cell level umi graph"/>

            <param name="lowRegionMinNumBarcodes" type="integer" optional="true" help="Minimum number of cell barcodes to use fo learning low confidence region (defaults to 200)"/>
            <param name="maxNumBarcodes" type="integer" optional="true" help="Maximum allowable limit to process the cell barcodes. Defaults to 100000"/>
        </section>
    </inputs>
    <outputs>
        <data name="quants_mat.tsv" label="quants_mat.tsv" format="txt" from_work_dir="quants_mat.tsv">
            <filter>not optional["dumpMtx"]</filter>
        </data>
        <data name="quants_mat.mtx.gz" label="quants_mat.mtx.gz" format="mtx" from_work_dir="output/alevin/quants_mat.mtx.gz">
            <filter>optional["dumpMtx"]</filter>
        </data>
        <data name="quants_mat_cols.txt" label="quants_mat_cols.txt" format="txt" from_work_dir="output/alevin/quants_mat_cols.txt"/>
        <data name="quants_mat_rows.txt" label="quants_mat_rows.txt" format="txt" from_work_dir="output/alevin/quants_mat_rows.txt"/>
        <data name="quants_tier_mat.gz" label="quants_tier_mat.gz" format="mtx" from_work_dir="output/alevin/quants_tier_mat.gz"/>
        <data name="alevin.log" label="alevin.log" format="txt" from_work_dir="output/alevin/alevin.log">
            <filter>allout</filter>
        </data>
        <data name="featureDump.txt" label="featureDump.txt" format="txt" from_work_dir="output/alevin/featureDump.txt"/>
        <data name="whitelist.txt" label="whitelist.txt" format="txt" from_work_dir="output/alevin/whitelist.txt"/>
        <data name="bfh.txt" label="bfh.txt" format="txt" from_work_dir="output/alevin/bfh.txt">
            <filter>optional["dumpBfh"]</filter>
        </data>
        <data name="quants_mean_mat.gz" label="quants_mean_mat.gz" format="mtx" from_work_dir="output/alevin/quants_mean_mat.gz">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_var_mat.gz" label="quants_var_mat.gz" format="mtx" from_work_dir="output/alevin/quants_var_mat.gz">

        <data name="observed_bias_3p.gz" format="txt" label="observed_bias_3p.gz" from_work_dir="output/aux_info/observed_bias_3p.gz"/>
        <data name="flenDist.txt" format="txt" label="flenDist.txt" from_work_dir="output/libParams/flenDist.txt"/>
        <data name="salmon_quant.log" format="txt" label="salmon_quant.log" from_work_dir="output/logs/salmon_quant.log">
            <filter>allout</filter>
        </data>
        <collection name="umigraphs" type="list" label="Umi graph PDFs">
            <filter>optional["dumpUmiGraph"]</filter>
            <discover_datasets pattern="__name_and_ext__" ext="pdf" directory="fixed"/>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="10">
            <conditional name="refTranscriptSource">
                <param name="TranscriptSource" value="history"/>
                <section name="s_index">
                    <param name="fasta" value="minitranscript.fa"/>
                </section>