comparison nugen_nudup.xml @ 1:24693e595caf draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/nugen_nudup commit 772d7fb670aaa4ad131909bf2aef5d7dd016e621

0:0ad51e73587e

<tool id="nugen_nudup" name="NuDUP" version="2.2_post2016104">
    <description>mark/remove PCR duplicates based on molecular tags</description>
    <requirements>
        <requirement type="package" version="2.2_post2016104">nudup</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <version_command>nudup.py --version</version_command>
    <command><![CDATA[
         ln -f -s '$input' 'input.bam' &&
         ln -f -s '$input.metadata.bam_index' 'input.bai' &&
        nudup.py $paired_end
        -f '$umi_fastq'
        --start $start
        --length $length
        'input.bam'
        ]]>
    </command>
    <inputs>
        <param type="data" name="input" label="Input SAM/BAM file"
            format="sam,bam" help="Input SAM/BAM containing only unique
            alignments" />
        <param type="data" name="umi_fastq" label="Fastq file containing
            molecular tag sequence" format="fastq,fastqsanger" help="FASTQ
            file containing the molecular tag sequence for each read name in
            the corresponding SAM/BAM file" />
        <param type="boolean" argument="--paired-end"
            label="Paired-end deduping" name="paired_end"
            truevalue="--paired-end" falsevalue=""

            position from 3' end" value="6" help="position in index read where
            molecular tag sequence begins. This should be a 1-based value that
            counts in from the 3' END of the read." />
        <param type="integer" argument="--length" label="Tag sequence length"
            value="6" help="length of molecular tag sequence" />
    </inputs>
    <outputs>
        <data format="bam" name="markdup" from_work_dir="prefix.sorted.markdup.bam" />
        <data format="bam" name="dedup" from_work_dir="prefix.sorted.dedup.bam" />
        <data format="txt" name="log" from_work_dir="prefix_dup_log.txt" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="nudup_test_1.bam" ftype="bam" />
            <param name="umi_fastq" value="nudup_umis.fastq" ftype="fastqsanger" />
            <param name="start" value="8" />
            <param name="length" value="8" />
            <output name="markdup" file="nudup_markdup_1.bam" ftype="bam" />
            <output name="dedup" file="nudup_dedup_1.bam" ftype="bam" />
            <output name="log" file="nudup_log_1.txt" ftype="txt" />

                            position in index read where molecular tag sequence
                            begins. This should be a 1-based value that counts in
                            from the 3' END of the read. (default = 6)
      -l LENGTH, --length LENGTH
                            length of molecular tag sequence (default = 6)
      -v, --version         show program's version number and exit
      -h, --help            show this help message and exit
        ]]></help>
    <citations>
        <citation type="bibtex">@misc{Patel2016,
  author = {Patel, Anand},
  title = {NuDUP},
  year = {2016},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/nugentechnologies/nudup}},
  commit = {740d9fe439dd8917605a56483a8796b377eb24c6}
}
        </citation>
    </citations>
</tool>

1:24693e595caf

<tool id="nugen_nudup" name="NuDUP" version="2.3.1" profile="17.01">
    <description>
        mark/remove PCR duplicates based on molecular tags
    </description>
    <requirements>
        <requirement type="package" version="2.3.1">nudup</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <version_command>nudup.py --version</version_command>
    <command><![CDATA[
        ln -f -s '$input' 'input.bam' &&
        ln -f -s '$input.metadata.bam_index' 'input.bai' &&
        mkdir 'tmp' &&
        #if $umi_fastq.is_of_type('fastq.gz','fastqsanger.gz'):
            #set umi_file = 'umi.fastq.gz'
        #else:
            #set umi_file = 'umi.fastq'
        #end if
        ln -f -s '$umi_fastq' '$umi_file' &&
        nudup.py
        -T \$PWD'/tmp'
        $paired_end
        -f '$umi_file'
        --start $start
        --length $length
        $rmdup_only
        'input.bam'
        ]]>
    </command>
    <inputs>
        <param type="data" name="input" label="Input SAM/BAM file"
            format="sam,bam" help="Input SAM/BAM containing only unique
            alignments" />
        <param type="data" name="umi_fastq"
            label="Fastq file containing molecular tag sequence"
            format="fastq,fastq.gz,fastqsanger,fastqsanger.gz" help="FASTQ
            file containing the molecular tag sequence for each read name in
            the corresponding SAM/BAM file" />
        <param type="boolean" argument="--paired-end"
            label="Paired-end deduping" name="paired_end"
            truevalue="--paired-end" falsevalue=""

            position from 3' end" value="6" help="position in index read where
            molecular tag sequence begins. This should be a 1-based value that
            counts in from the 3' END of the read." />
        <param type="integer" argument="--length" label="Tag sequence length"
            value="6" help="length of molecular tag sequence" />
        <param type="boolean" argument="--rmdup-only" name="rmdup_only"
            label="Only output BAM with duplicates removed"
            truevalue="--rmdup-only" falsevalue="" checked="false"
            help="Do not ouput BAM with duplicates marked. Default is to ouput
            both marked duplicates and removed duplicates BAM files." />
    </inputs>
    <outputs>
        <data format="bam" name="markdup" metadata_source="input"
              label="${tool.name} on ${on_string}: MarkDup"
              from_work_dir="prefix.sorted.markdup.bam">
              <filter>not rmdup_only</filter>
        </data>
        <data format="bam" name="dedup" metadata_source="input"
              label="${tool.name} on ${on_string}: DeDup"
              from_work_dir="prefix.sorted.dedup.bam" />
        <data format="txt" name="log"
              label="${tool.name} on ${on_string}: Log"
              from_work_dir="prefix_dup_log.txt" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="nudup_test_1.bam" ftype="bam" />
            <param name="umi_fastq" value="nudup_umis.fastq"
                ftype="fastqsanger" />
            <param name="start" value="8" />
            <param name="length" value="8" />
            <output name="markdup" file="nudup_markdup_1.bam" ftype="bam" />
            <output name="dedup" file="nudup_dedup_1.bam" ftype="bam" />
            <output name="log" file="nudup_log_1.txt" ftype="txt" />
        </test>
        <test>
            <param name="input" value="nudup_test_1.bam" ftype="bam" />
            <param name="umi_fastq" value="nudup_umis.fastq.gz"
                ftype="fastqsanger.gz" />
            <param name="start" value="8" />
            <param name="length" value="8" />
            <output name="markdup" file="nudup_markdup_1.bam" ftype="bam" />
            <output name="dedup" file="nudup_dedup_1.bam" ftype="bam" />
            <output name="log" file="nudup_log_1.txt" ftype="txt" />

                            position in index read where molecular tag sequence
                            begins. This should be a 1-based value that counts in
                            from the 3' END of the read. (default = 6)
      -l LENGTH, --length LENGTH
                            length of molecular tag sequence (default = 6)
      -T TEMP_DIR           directory for reading and writing to temporary files
                            and named pipes (default: /tmp)
      --old-samtools        required for compatibility with samtools sort style in
                            samtools versions <=0.1.19
      --rmdup-only          required for only outputting duplicates removed file
      -v, --version         show program's version number and exit
      -h, --help            show this help message and exit
        ]]></help>
    <citations>
        <citation type="bibtex">@misc{Patel2017,
  author = {Patel, Anand},
  title = {NuDUP},
  year = {2017},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/nugentechnologies/nudup}},
  commit = {7451de86680d24f19638ed6ac88f6504f0817753}
}
        </citation>
    </citations>
</tool>