annotate remove_selected_features_samples.xml @ 1:2e7d47c0b027 draft

"planemo upload for repository https://[e-mail]/repos/malex/secimtools"

<tool id="secimtools_remove_selected_features" name="Remove Selected Features or Samples" version="@WRAPPER_VERSION@">
    <description>from the data using a flag file.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command><![CDATA[
remove_selected_features_samples.py
--input $input
--design $design
--ID $uniqID
--flags $flags
--outWide $outWide
--outFlags $outFlags
--flagDrop $flagToDrop
--value $reference
--flagfiletype $typeofdrop

#if $flagUniqID
    --flagUniqID $flagUniqID
#end if
#if str( $conditional ) == '0'
    --condition '0'
#end if
#if str( $conditional ) == '1'
    --condition '1'
#end if
#if str( $conditional ) == '2'
    --condition '2'
#end if
    ]]></command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Wide Dataset"
               help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
        <param name="design" type="data" format="tabular" label="Design File"
               help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
        <param name="flags" type="data" format="tabular" label="Flag File"
               help="Input dataset containing binary indicator flag value for each feature or sample."/>
        <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID"
               help="Name of the column in your wide dataset that has unique identifiers."/>
        <param name="flagUniqID" type="text" size="30" value="" label="Unique ID for Flag file (feature ID or sample ID)"
               help="Name of the column in your flag file that has unique identifiers.."/>
        <param name="flagToDrop" type="text" size="30" value="" label="Flag to Drop"
               help="Name of the column/row in your flag file to use for dropping."/>
        <param name="conditional" size="30" type="select" value="" label="Condition of drop." help="Select type of conditional to use.">
            <option value="0" selected="true">Equals to</option>
            <option value="1" selected="false">Greater than</option>
            <option value="2" selected="false">Less than</option>
        </param>
        <param name="reference" type="text" size="30"  value="1" label="Cutoff Value"
               help="Any rows or columns with a flag value equal to, greater than or less than (as set above) this Cutoff Value will be dropped."/>
        <param name="typeofdrop" type="select" size="30" display="radio" value="row" label="Type of drop to be carried out." help="Select whether you want to drop by rows or by columns, default = rows.">
            <option value="row">Drop Rows</option>
            <option value="column">Drop Columns</option>
        </param>
    </inputs>
    <outputs>
        <data format="tabular" name="outWide" label="${tool.name} on ${on_string}: Dropped wide"/>
        <data format="tabular" name="outFlags" label="${tool.name} on ${on_string}: Dropped flags"/>
    </outputs>
    <tests>
        <test>
            <param name="input"       value="ST000006_data.tsv"/>
            <param name="design"      value="ST000006_design.tsv"/>
            <param name="uniqID"      value="Retention_Index" />
            <param name="flags"       value="ST000006_kruskal_wallis_with_group_flags.tsv"/>
            <param name="typeofdrop"  value="row"/>
            <param name="flagUniqID"  value="Retention_Index" />
            <param name="flagToDrop"  value="flag_significant_0p10_on_all_groups" />
            <param name="reference"   value="0" />
            <param name="conditional" value="0" />
            <output name="outWide"    file="ST000006_remove_selected_features_samples_wide.tsv" />
            <output name="outFlags"   file="ST000006_remove_selected_features_samples_flags.tsv" />
        </test>
    </tests>
    <help><![CDATA[

@TIP_AND_WARNING@

**Tool Description**

The tool removes features (rows) or samples (columns) from a wide format dataset based on the flags in a separate flag file.
The user specifies a flag file and column to indicate removal.
Features or samples with a flag value equal to, greater than, or less than a user specified Cutoff Value (Default = 1) will be dropped from the wide dataset.

The flag file should be either a wide format flag file (used for dropping features) or design format flag file (used for dropping samples).
The difference between the flag file formats is described in the beginning of the user manual (Kirpich et al. 2017).

**NOTE:** Flag files generated outside of SECIM Tools can be used.

--------------------------------------------------------------------------------

**Input**

    - Two input datasets are required.

@WIDE@

**NOTE:** The sample IDs must match the sample IDs in the Design File
(below). Extra columns will automatically be ignored.

@METADATA@

@FLAGS@

@UNIQID@

**Unique ID for Flag file (feature ID or sample ID).**

    - Name of the column in your Flag file that contains unique Feature IDs.

**Flag to use for Drop.**

    - Name of the column/row in your Flag File to use drop.

**Condition of drop.**

    -Select type of conditional.

**Cutoff Value**

    - Any row (or column) with a flag value equals to, greater than or less than this Cutoff Value (Default = 1) will be dropped.

**Type of drop.**

    - Select whether you want to drop rows or columns, default = rows.

--------------------------------------------------------------------------------

**Output**

This tool outputs two TSV files:

(1) The first TSV file is a wide format dataset generated from the input wide format dataset where features (or samples) flagged in the flag file have been removed.

(2) The second TSV file is the flag file generated from the input flag file where the flagged features (or samples) have been dropped. The resulting flag file contains only features (or samples) that have not been dropped from the wide format dataset.

    ]]></help>
    <expand macro="citations"/>
</tool>