view summarize_cluster_table.xml @ 34:91996b991991 draft default tip

Uploaded
author petr-novak
date Fri, 16 Feb 2024 15:22:21 +0000
parents 628b235d76c7
children
line wrap: on
line source

<tool id="summarize_annotation" name="Repeat proportions from CLUSTER_TABLE"
      version="1.0.0.3">
    <description>Simple utility to summarize final annotations from RepeatExplorer
        CLUSTER_TABLE
    </description>
    <requirements>
        <requirement type="package">r-optparse</requirement>
    </requirements>
    <required_files>
        <include type="literal" path="summarize_cluster_table.R"/>
    </required_files>
    <command detect_errors="exit_code">
        Rscript $__tool_directory__/summarize_cluster_table.R
        --cluster_table=$cluster_table
        --output=$output

    </command>

    <inputs>
        <param format="txt" type="data" name="cluster_table"
               label="file from RepeatExplorer2 clustering - CLUSTER_TABLE.csv"
               help="CLUSTER_TABLE.csv must contains completed Final_annotation column"/>
    </inputs>

    <outputs>
        <data format="tabular" name="output"
              label="Summary of repeat proportions from ${cluster_table.hid}"/>
    </outputs>
    <help>
        **The tool calculates genome proportions of identified repeats based on cluster
        annotations in CLUSTER_TABLE.csv**

        The column "Final_annotation" must be filled in the input file CLUSTER_TABLE.csv.
        Contamination and organelle clusters are discarded from quantification. Table
        header with information about numbers of analyzed reads should remain unchanged -
        see example below.

        Example of CLUSTER_TABLE.csv: ::

        Number_of_reads_in_clusters 1185180
        Number_of_clusters 62148
        Number_of_superclusters 62031
        Number_of_singlets 314820
        Number_of_analyzed_reads 1500000
        Cluster Supercluster Size Size_adjusted Automatic_annotation TAREAN_annotation
        Final_annotation
        10 4 11967 11967 All/repeat/mobile_element/Class_I/LTR/Ty1_copia/SIRE Other
        All/repeat/mobile_element/Class_I/LTR/Ty1_copia/SIRE
        137 5 2094 2094 All/repeat Other All/repeat
        112 9 3117 3117 All/repeat/rDNA/45S_rDNA Other All/repeat/rDNA/45S_rDNA
        16 11 10078 10078 All/repeat/satellite Putative satellites (high confidence)
        All/repeat/satellite
        125 22 2630 2630 All/organelle/plastid Other All/organelle/plastid
        124 40 2645 2645 All/repeat/mobile_element/Class_I/LTR/Ty1_copia/Ivana Putative
        LTR elements All/repeat/mobile_element/Class_I/LTR/Ty1_copia/Ivana

    </help>
</tool>