comparison umi-tools_dedup.xml @ 11:7fa28eb10fed draft

"planemo upload commit 2da1197aac6a18df9252e5da096645d2ecaece88"

10:c6567483aa1e

<tool id="umi_tools_dedup" name="UMI-tools deduplicate" version="@VERSION@.0">
    <description>Extract UMI from fastq files</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">

            ln -sf '$input.metadata.bam_index' 'input.bam.bai' &&
            #set $input_file = 'input.bam'
        #end if

        umi_tools dedup
            --random-seed 0
            --extract-umi-method $extract_umi_method
            #if str($extract_umi_method) != 'read_id':
                --umi-separator '$umi_separator' --umi-tag '$umi_tag'
            #end if

        <param argument="--chrom" type="boolean" truevalue="--chrom" falsevalue="" label="Only consider a single chromosome" />
        <param name="per_contig" argument="--per-contig" type="boolean" truevalue="--per-contig" falsevalue="" label="Deduplicate per contig" help="Field 3 in BAM; RNAME. All reads with the same contig will be considered to have the same alignment position. This is useful if your library prep generates PCR duplicates with non identical alignment positions such as CEL-Seq. In this case, you would align to a reference transcriptome with one transcript per gene" />
        <param name="per_gene" argument="--per-gene" type="boolean" truevalue="--per-gene" falsevalue="" label="Deduplicate per gene" help="As above except with this option you can align to a reference transcriptome with more than one transcript per gene. You need to also provide a map of genes to transcripts. This will also add a metacontig ('MC') tag to the output BAM file." />
        <param name="gene_transcript_map" argument="--gene-transcript-map" type="data" format="tabular" optional="True" label="Tabular file mapping genes to transripts" />
        <param name="gene_tag" argument="--gene-tag" type="text" optional="True" label="Deduplicate by this gene tag" help="As --per-gene except here the gene information is encoded in the bam read tag specified so you do not need to supply the mapping file." />
    </inputs>
    <outputs>
        <data format="bam" name="output" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="group_in1.sam" ftype="sam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out1.bam" ftype="bam" sort="True"/>
        </test>
        <test>
            <param name="input" value="group_in2.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="paired" value="True" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out2.bam" ftype="bam" sort="True" />
        </test>
        <test>
            <param name="input" value="group_in3.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out3.bam" ftype="bam" sort="True" />
        </test>
        <test>
            <param name="input" value="group_in4.bam" ftype="bam" />
            <param name="extract_umi_method" value="tag" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out4.bam" ftype="bam" sort="True" />
        </test>
        <test>
            <param name="input" value="group_in5.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="cluster" />
            <output name="output" file="dedup_out5.bam" ftype="bam" sort="True" />
        </test>
        <test>
            <param name="input" value="group_in6.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="directional" />
            <output name="output" file="dedup_out6.bam" ftype="bam" sort="True" />
        </test>
    </tests>
    <help><![CDATA[
umi_tools dedup - Deduplicate reads based on their UMI
======================================================

11:7fa28eb10fed

<tool id="umi_tools_dedup" name="UMI-tools deduplicate" version="@VERSION@+galaxy1">
    <description>Extract UMI from fastq files</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">

            ln -sf '$input.metadata.bam_index' 'input.bam.bai' &&
            #set $input_file = 'input.bam'
        #end if

        umi_tools dedup
            '$output_stats_bool'
            --random-seed 0
            --extract-umi-method $extract_umi_method
            #if str($extract_umi_method) != 'read_id':
                --umi-separator '$umi_separator' --umi-tag '$umi_tag'
            #end if

        <param argument="--chrom" type="boolean" truevalue="--chrom" falsevalue="" label="Only consider a single chromosome" />
        <param name="per_contig" argument="--per-contig" type="boolean" truevalue="--per-contig" falsevalue="" label="Deduplicate per contig" help="Field 3 in BAM; RNAME. All reads with the same contig will be considered to have the same alignment position. This is useful if your library prep generates PCR duplicates with non identical alignment positions such as CEL-Seq. In this case, you would align to a reference transcriptome with one transcript per gene" />
        <param name="per_gene" argument="--per-gene" type="boolean" truevalue="--per-gene" falsevalue="" label="Deduplicate per gene" help="As above except with this option you can align to a reference transcriptome with more than one transcript per gene. You need to also provide a map of genes to transcripts. This will also add a metacontig ('MC') tag to the output BAM file." />
        <param name="gene_transcript_map" argument="--gene-transcript-map" type="data" format="tabular" optional="True" label="Tabular file mapping genes to transripts" />
        <param name="gene_tag" argument="--gene-tag" type="text" optional="True" label="Deduplicate by this gene tag" help="As --per-gene except here the gene information is encoded in the bam read tag specified so you do not need to supply the mapping file." />
        <param name="output_stats_bool" type="boolean" truevalue="--output-stats=stats_outputs" falsevalue="" checked="false" label="Output UMI related statistics files?"/>
    </inputs>
    <outputs>
        <data format="bam" name="output" />
        <collection name="output_stats" type="list" label="UMI_tools dedup stats">
            <filter>output_stats_bool</filter>
            <data name="edit_distance" format="tabular" from_work_dir="stats_outputs_edit_distance.tsv"/>
            <data name="per_umi" format="tabular" from_work_dir="stats_outputs_per_umi.tsv"/>
            <data name="per_umi_per_position" format="tabular" from_work_dir="stats_outputs_per_umi_per_position.tsv"/>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input" value="group_in1.sam" ftype="sam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out1.bam" ftype="bam" sort="True"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="group_in2.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="paired" value="True" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out2.bam" ftype="bam" sort="True" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="group_in3.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out3.bam" ftype="bam" sort="True" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="group_in4.bam" ftype="bam" />
            <param name="extract_umi_method" value="tag" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="unique" />
            <output name="output" file="dedup_out4.bam" ftype="bam" sort="True" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="group_in5.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="cluster" />
            <output name="output" file="dedup_out5.bam" ftype="bam" sort="True" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="group_in6.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="directional" />
            <output name="output" file="dedup_out6.bam" ftype="bam" sort="True" />
        </test>
        <test expect_num_outputs="5">
            <param name="input" value="group_in6.bam" ftype="bam" />
            <param name="extract_umi_method" value="read_id" />
            <param name="umi_tag" value="BX" />
            <param name="method" value="directional" />
            <param name="output_stats_bool" value="true"/>
            <output name="output" file="dedup_out6.bam" ftype="bam" sort="True" />
            <output_collection name="output_stats">
                <element name="edit_distance" file="stats_outputs_edit_distance.tsv" />
                <element name="per_umi" file="stats_outputs_per_umi.tsv" />
                <element name="per_umi_per_position" file="stats_outputs_per_umi_per_position.tsv" />
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
umi_tools dedup - Deduplicate reads based on their UMI
======================================================