annotate temp.xml @ 17:e7d3dc3e0ec9 draft

planemo upload for repository https://github.com/portiahollyoak/Tools commit 22724a75342e3097cd0976e4bfcfe7a19308ac4f-dirty

<tool id ="run_TEMP" name="TEMP" version="0.2.0">
    <description></description>
    <requirements>
        <!-- The following are classical toolshed packages and should be removed
        once conda is deemed stable-->
        <requirement type="package" version="1.6.922">bioperl</requirement>
        <requirement type="package" version="0.7.12">bwa</requirement>
        <requirement type="package" version="2.24">bedtools</requirement>
        <!-- end of toolshed package definitions -->
        <requirement type="package" version="1.6.924">perl-bioperl</requirement>
        <requirement type="package" version="0.7.13">bwa</requirement>
        <requirement type="package" version="2.25.0">bedtools</requirement>
        <requirement type="package" version="324">ucsc-twobittofa</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
        ln -f -s "$alignment.metadata.bam_index" alignment.sorted.bam.bai &&
        ln -f -s "$alignment" alignment.sorted.bam &&
        bash $__tool_directory__/scripts/TEMP_Insertion.sh
        -x "$minimum_score_difference"
        -i alignment.sorted.bam
        -s $__tool_directory__/scripts
        -r "$consensus_te_seqs"
        -t "$te_locations"
        #if $te_families:
        -u "$te_families"
        #end if
        -m "$mismatches"
        -f "$median_insertsize"
        -c \${GALAXY_SLOTS:-2} &&
        bash $__tool_directory__/scripts/TEMP_Absence.sh
        -x "$minimum_score_difference"
        -i alignment.sorted.bam
        -s $__tool_directory__/scripts
        -r "$te_locations"
        -t "$reference2bit"
        -f "$median_insertsize"
        -c \${GALAXY_SLOTS:-2} &&
        zip archive.zip  *insertion* *excision* *absence* && mv archive.zip $archive &&
        mv alignment.insertion.refined.bp.summary $insertion_summary &&
        mv alignment.absence.refined.bp.summary $absence_summary
    ]]></command>
    <inputs>
        <param format="bam" name="alignment" type="data" label="Alignment bam file"/>
        <param format="twobit" name="reference2bit" type="data" label="Reference twobit file"/>
        <param format="fasta" name="consensus_te_seqs" type="data" label="Consensus TE Seqs fasta file"/>
        <param format="bed" name="te_locations" type="data" label="TE Annotations bed file"/>
        <param format="tabular" name="te_families" type="data" optional="True" label="TE Identifiers and Families"/>
        <param name="median_insertsize" value="" type="integer" label="Median Insert Length"/>
        <param name="mismatches" min="0" max="5" type="integer" value="3" label="Allow this many mismatches when aligning to TEs"/>
        <param name="minimum_score_difference" type="integer" min="10" max="37" value="30" label="Minimum difference between mapping scores"/>
    </inputs>
    <outputs>
        <data format="bed" type="data" name="insertion_summary" label="${alignment.element_identifier} Insertions" />
        <data format="bed" type="data" name="absence_summary" label="${alignment.element_identifier} Absences" />
        <data format="zip" type="data" name="archive" label="${alignment.element_identifier} Compressed output files" />
    </outputs>
    <tests>
        <test>
            <param name="alignment" value="chr2l_bwa_mem.bam" ftype="bam"/>
            <param name="reference2bit" value="dm6_chr2l.twobit" ftype="twobit"/>
            <param name="consensus_te_seqs" value="test_consensus.fa" ftype="fasta"/>
            <param name="te_locations" value="test_TE_annotation.gff3" ftype="bed"/>
            <param name="median_insertsize" value="500" ftype="integer"/>
            <output name="insertion_summary" file="test_chromosome.insertion.refined.bp.summary" ftype="bed"/>
            <output name="absence_summary" file="test_chromosome.absence.refined.bp.summary" ftype="bed"/>
        </test>
    </tests>
    <help> <![CDATA[


TEMP
-------------
TEMP is a software package for detecting transposable elements (TEs)  insertions and absences from pooled high-throughput sequencing data

Current version v1.04

Author: Jiali Zhuang ([e-mail]) and Jie Wang ([e-mail]) Weng Lab, University of Massachusetts Medical School, Worcester, MA, USA

*Input files/variables*
-------------------------
* Alignment file in BAM format
* Reference genome used in aligning, in fasta or twobit format.
* Transposable Elements' Consensus Sequences in fasta format.
* Annotations of TEs in reference genome in bed format.
* TE Identifiers and Families (optional) - A file containing in the first column the TE names/identifiers from the consensus sequences file, and in the second column, their respective TE family names as in the TE annotations file. When supplied, if a detected insertion overlaps with an annotated TE of the same family, the detected insertion will be excluded from the results.
* Median Insert Length
* Number of Mismatches allowed (default 3)
* Minimum difference between mapping scores. The minimum difference in scores between the optimal and suboptimal alignments to consider a read uniquely mapped.

*Output files*
-----------------
* **In the Insertions output file there are 14 columns:**
* Column 1: The chromosome where the detected insertion happens.
* Column 2: The coordinate of the start position of the detected insertion.
* Column 3: The coordinate of the end position of the detected insertion.
* Column 4: The TE family that the detected insertion belongs to.
* Column 5: The direction of the insertion. “Plus” means that the TE is integrated with the plus strand of the genome while “minus” means the TE is integrated with the minus strand.
* Column 6: The class of the insertion. “1p1” means that the detected insertion is supported by reads at both sides. “2p” means the detected insertion is supported by more than 1 read at only 1 side. “Singleton” means the detected insertion is supported by only 1 read at 1 side.
* Column 7: The total number of read pairs that support the detected insertion.
* Column 8: The estimated population frequency of the detected insertion.
* Columns 9 & 10: The coordinate of a junction and the number of the reads supporting it. If the junction is not found column 9 will be the arithmetic mean of the start and end coordinates and column 10 will have the value 0.
* Columns 11 & 12: Same as Columns 9 & 10 except for the junction on the other strand.
* Column 13: The number of reads supporting the detected insertion at the 5’ end of the TE (not including junction spanning reads).
* Column 13: The number of reads supporting the detected insertion at the 3’ end of the TE (not including junction spanning reads).


-----


* **In the Absences output file there are 14 columns:**
* Column 1: The chromosome where the detected absence happens.
* Column 2: The coordinate of the start position of the detected absence.
* Column 3: The coordinate of the end position of the detected absence.
* Column 4: The TE family that the detected insertion belongs to.
* Column 5: Junctions at 5’ of the excised TE. The two numbers are the coordinates of the junctions on the two strands.
* Column 6: Junctions at 3’ of the excised TE. The two numbers are the coordinates of the junctions on the two strands.
* Column 7: The number of reads supporting the absence.
* Column 8: The number of reads supporting the reference (no absence).
* Column 9: Estimated population frequency of the detected absence event.


    ]]> </help>
    <citations>
        <citation type="doi">10.1093/nar/gku323</citation>
    </citations>
</tool>