<tool id="seurat_scale_data" name="Seurat ScaleData" version="2.3.1+galaxy1">
    <description>scale and center genes</description>
    <macros>
        <import>seurat_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version" />
    <command detect_errors="exit_code"><![CDATA[
seurat-scale-data.R

--input-object-file '$input'
#if $vars:
    --vars-to-regress '$vars'
#else
    --vars-to-regress nUMI
#end if

#if $genes:
    --genes-use '$genes'
#end if

--model-use '$model'

$use_umi
$do_center

#if $scale_max:
    --scale-max '$scale_max'
#end if

#if $block_size:
    --block-size '$block_size'
#end if

#if $min_cells_to_block:
    --min-cells-to-block '$min_cells_to_block'
#end if

$check_for_norm



--output-object-file '$output'
]]></command>

    <inputs>
        <param name="input" argument="--input-object-file" type='data' format='rdata' help="File name in where a serialized R matrix object can be found." label="Seurat RDS object"/>
        <param name="genes" argument="--genes-use" type='data' format='txt' optional='true' help="File to be used to derive a vector of gene names to scale/center (one gene per line). Default is all genes in object@data."/>
        <param name="vars" argument="--vars-to-regress" type='text' optional='True' label="Vars to regress" help="Comma-separated list of variables to regress out (previously latent.vars in RegressOut). For example, nUMI, or percent.mito."/>
        <param name="model" argument="--model-use" type="select" label="Statistical model" help="Use a linear model or generalized linear model (poisson, negative binomial) for the regression.">
          <option value="linear" selected="true">Linear model</option>
          <option value="poisson">Poisson model</option>
          <option value="negbinom">Negative binomial model</option>
        </param>
        <param name="use_umi" argument="--use-umi" type="boolean" truevalue="--use-umi TRUE" falsevalue="" checked="false" label="Use UMIs." help="Regress on UMI count data. Default is FALSE for linear modeling, but automatically set to TRUE if model.use is 'negbinom' or 'poisson'."/>
        <param name="do_center" argument="--do-center" type="boolean" falsevalue="--do-center FALSE" truevalue="" checked="true" label="Perform centering" help="Whether to center the data."/>
        <param name="scale_max" argument="--scale-max" optional="true" type="float" label="Scale maximum" help = "Max value to return for scaled data. The default is 10. Setting this can help reduce the effects of genes that are only expressed in a very small number of cells. If regressing out latent variables and using a non-linear model, the default is 50."/>
        <param name="block_size" argument="--block-size" optional="true" type="integer" label="Block size" help = "Default size for number of genes to scale at in a single computation. Increasing block.size may speed up calculations but at an additional memory cost. Defaults to 1000 if not specified."/>
        <param name="min_cells_to_block" argument="--min-cells-to-block" optional="true" type="integer" label="Minimum number of cells to block" help="If object contains fewer than this number of cells, don't block for scaling calculations. Defaults to 1000."/>
        <param name="check_for_norm" argument="--check-for-norm" optional="true" type="boolean" falsevalue="--check-for-norm FALSE" truevalue="" label="Check that data is normalized" help="Check to see if data has been normalized, if not, output a warning (TRUE by default). Data can be normalised by Seurat normalise module."/>
    </inputs>

    <outputs>
        <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/>
    </outputs>

    <tests>
        <test>
            <param name="input" ftype="rdata" value="out_findvar.rds"/>
            <output name="output" ftype="rdata" value="out_scale.rds" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

Seurat_ is a toolkit for quality control, analysis, and exploration of single cell RNA sequencing data.
It is developed and maintained by the `Satija Lab`_ at NYGC. Seurat aims to enable users to identify and
interpret sources of heterogeneity from single cell transcriptomic measurements, and to integrate diverse
types of single cell data.

This tool regresses out variables in a Seurat object to mitigate the effect of confounding factors.


-----

**Inputs**

    * Seurat RDS object, probably normalised.
    * Genes to use. A file with a vector of gene names to scale/center (one gene per line). Default is all genes in object@data.
    * Variables to regress
    * Statistical model to use.
    * Use UMIs (boolean)
    * Do centering (boolean)
    * Scale maximum
    * Block size
    * Minimum number of cells to block
    * Check that data is normalised

-----

**Outputs**

    * Seurat RDS object, scaled.

.. _Seurat: https://www.nature.com/articles/nbt.4096
.. _Satija Lab: https://satijalab.org/seurat/

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