comparison alevin.xml @ 7:ff78e9c7b0d8 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/salmon commit dee6a6f4aa8cbee9f81692fc6f3a2e4ad1f3abf6"

6:53d74155bb52

<tool id="alevin" name="Alevin" version="@VERSION@+galaxy1">
    <description>Quantification and analysis of 3’ tagged-end single-cell sequencing data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>

            --freqThreshold '${optional.freqThreshold}'
        #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"/>
        <conditional name="pairstraight">

            <param name="dumpUmiGraph" type="boolean" truevalue="--dumpUmiGraph" falsevalue="" checked="false" help="Dump the per-cell level umi graph"/>
            <param name="dumpMtx" type="boolean" truevalue="--dumpMtx" falsevalue="" checked="false" help="Converts the default binary format of alevin for gene-count matrix into a human readable mtx (matrix market exchange) sparse format."/>
            <param name="forceCells" type="integer" optional="true" help="Explicitly specify the number of cells."/>
            <param name="expectCells" type="integer" optional="true" help="define a close upper bound on expected number of cells."/>
            <param name="numCellBootstraps" type="integer" optional="true" help="Performs certain number of bootstrap and generate the mean and variance of the count matrix"/>
            <param name="minScoreFraction" type="float" optional="true" 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 name="keepCBFraction" type="float" optional="true" help="Fraction of cellular barcodes to keep (Between 0 and 1)."/>
            <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"/>
            <param name="freqThreshold" type="integer" optional="true" help="Minimum frequency for a barcode to be considered. Defaults to 10"/>
        </section>
    </inputs>
    <outputs>
        <data name="quants_mat.tsv" label="quants_mat.tsv" format="txt" from_work_dir="quants_mat.tsv">
            <filter>optional["dumpMtx"] is not True</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="raw_cb_frequency.txt" label="raw_cb_frequency.txt" format="txt" from_work_dir="output/alevin/raw_cb_frequency.txt">
            <filter>optional["dumpFeatures"]</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">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_boot_rows.txt" label="quants_boot_rows.txt" format="txt" from_work_dir="output/alevin/quants_boot_rows.txt">
            <filter>optional["numCellBootstraps"]</filter>
        </data>

            <filter>allout</filter>
        </data>
        <data name="meta_info.json" format="json" label="meta_info.json" from_work_dir="output/aux_info/meta_info.json">
            <filter>allout</filter>
        </data>
        <data name="expected_bias.gz" format="txt" label="expected_bias.gz" from_work_dir="output/aux_info/fld.gz"/>
        <data name="observed_bias.gz" format="txt" label="observed_bias.gz" from_work_dir="output/aux_info/observed_bias.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">

            <param name="tgmap" value="minitxp.tsv"/>
            <param name="dumpMtx" value="Yes"/>
            <param name="freqThreshold" value="5"/>
            <param name="dumpFeatures" value="Yes"/>
            <param name="keepCBFraction" value="1"/>
            <output name="quants_mat.mtx.gz" file="alevin_mat.mtx.gz" ftype="mtx" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
        @salmonhelp@
        @alevinhelp@

7:ff78e9c7b0d8

<tool id="alevin" name="Alevin" version="@VERSION@+galaxy2">
    <description>Quantification and analysis of 3’ tagged-end single-cell sequencing data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>

            --freqThreshold '${optional.freqThreshold}'
        #end if

        #if $optional.dumpMtx != "--dumpMtx":
            && python '$__tool_directory__/vpolo_convert.py' -m
        #else:
            && gunzip output/alevin/quants_mat.mtx.gz
        #end if
        #if $optional.dumpUmiGraph:
            && python '$__tool_directory__/vpolo_convert.py' -u
            && sh '$__tool_directory__/umiout.sh'
        #end if

        && gunzip output/alevin/quants_tier_mat.gz
        #if $optional.numCellBootstraps:
            && gunzip output/alevin/quants_mean_mat.gz
            && gunzip output/alevin/quants_var_mat.gz
        #end if

        && gunzip output/aux_info/fld.gz
        && gunzip output/aux_info/observed_bias.gz
        && gunzip output/aux_info/observed_bias_3p.gz
        ]]>
    </command>
    <inputs>
        <expand macro="index"/>
        <conditional name="pairstraight">

            <param name="dumpUmiGraph" type="boolean" truevalue="--dumpUmiGraph" falsevalue="" checked="false" help="Dump the per-cell level umi graph"/>
            <param name="dumpMtx" type="boolean" truevalue="--dumpMtx" falsevalue="" checked="false" help="Converts the default binary format of alevin for gene-count matrix into a human readable mtx (matrix market exchange) sparse format."/>
            <param name="forceCells" type="integer" optional="true" help="Explicitly specify the number of cells."/>
            <param name="expectCells" type="integer" optional="true" help="define a close upper bound on expected number of cells."/>
            <param name="numCellBootstraps" type="integer" optional="true" help="Performs certain number of bootstrap and generate the mean and variance of the count matrix"/>
            <param name="minScoreFraction" type="float" optional="true" 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 name="keepCBFraction" type="float" optional="true" help="Fraction of cellular barcodes to keep (Between 0 and 1)."/>
            <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"/>
            <param name="freqThreshold" type="integer" optional="true" help="Minimum frequency for a barcode to be considered. Defaults to 10"/>
        </section>
    </inputs>
    <outputs>
        <data name="quants_mat.tsv" label="quants_mat.tsv" format="txt" from_work_dir="quants_mat.tsv">
            <filter>optional["dumpMtx"] is not True</filter>
        </data>
        <data name="quants_mat.mtx" label="quants_mat.mtx" format="mtx" from_work_dir="output/alevin/quants_mat.mtx">
            <filter>optional["dumpMtx"]</filter>
        </data>
        <data name="raw_cb_frequency.txt" label="raw_cb_frequency.txt" format="txt" from_work_dir="output/alevin/raw_cb_frequency.txt">
            <filter>optional["dumpFeatures"]</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" label="quants_tier_mat" format="mtx" from_work_dir="output/alevin/quants_tier_mat"/>
        <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" label="quants_mean_mat" format="mtx" from_work_dir="output/alevin/quants_mean_mat">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_var_mat" label="quants_var_mat" format="mtx" from_work_dir="output/alevin/quants_var_mat">
            <filter>optional["numCellBootstraps"]</filter>
        </data>
        <data name="quants_boot_rows.txt" label="quants_boot_rows.txt" format="txt" from_work_dir="output/alevin/quants_boot_rows.txt">
            <filter>optional["numCellBootstraps"]</filter>
        </data>

            <filter>allout</filter>
        </data>
        <data name="meta_info.json" format="json" label="meta_info.json" from_work_dir="output/aux_info/meta_info.json">
            <filter>allout</filter>
        </data>
        <data name="expected_bias" format="txt" label="expected_bias" from_work_dir="output/aux_info/fld"/>
        <data name="observed_bias" format="txt" label="observed_bias" from_work_dir="output/aux_info/observed_bias"/>
        <data name="observed_bias_3p" format="txt" label="observed_bias_3p" from_work_dir="output/aux_info/observed_bias_3p"/>
        <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">

            <param name="tgmap" value="minitxp.tsv"/>
            <param name="dumpMtx" value="Yes"/>
            <param name="freqThreshold" value="5"/>
            <param name="dumpFeatures" value="Yes"/>
            <param name="keepCBFraction" value="1"/>
            <output name="quants_mat.mtx" file="alevin_mat.mtx" ftype="mtx"/>
        </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>
            <param name="protocol" value="--chromium"/>
            <param name="tgmap" value="minitxp.tsv"/>
            <param name="dumpMtx" value="Yes"/>
            <param name="freqThreshold" value="5"/>
            <param name="dumpFeatures" value="Yes"/>
            <param name="keepCBFraction" value="1"/>
            <section name="optional">
                <param name="numCellBootstraps" value="2"/>
            </section>
            <output name="quants_mat.mtx" file="alevin_mat.mtx" ftype="mtx"/>
        </test>
    </tests>
    <help><![CDATA[
        @salmonhelp@
        @alevinhelp@