comparison seurat_find_variable_genes.xml @ 1:a6077346f869 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 0463f230d18201c740851d72e31a5024f391207f

0:a56efad05337

<tool id="seurat_find_variable_genes" name="Seurat FindVariableGenes" version="2.3.1+galaxy1">
    <description>identify variable genes</description>
    <macros>
        <import>seurat_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version" />
    <command detect_errors="exit_code"><![CDATA[
seurat-find-variable-genes.R

--input-object-file '$input'
#if $mean:
    --mean-function '$mean'
#end if
#if $disp:
--dispersion-function $disp
#end if
#if $xlow:

--y-low-cutoff $ylow
#end if
#if $yhigh:
--y-high-cutoff $yhigh
#end if
--output-object-file '$output'
--output-text-file '$output_tab'
]]></command>

    <inputs>
        <param name="input" argument="--input-object-file" type="data" format="rdata" label="Seurat RDS object" help="R serialized object for Seurat, normally the one produced by Seurat FindVariableGenes" />
        <param name="mean" argument="--mean-function" type="text" optional="True" label="Mean function" help="Function to compute x-axis value (average expression). Default is to take the mean of the detected (i.e. non-zero) values."/>
        <param name="disp" argument="--dispersion-function" type="text" optional="True" label="Dispersion function" help="Function to compute y-axis value (dispersion). Default is to take the standard deviation of all values." />
        <param name="xlow" argument="--x-low-cutoff" type="float" optional="True" label="X-axis low cutoff" help="Bottom cutoff on x-axis for identifying variable genes."/>
        <param name="xhigh" argument="--x-high-cutoff" type="float" optional="True" label="X-axis high cutoff" help="Top cutoff on x-axis for identifying variable genes."/>
        <param name="ylow" argument="--y-low-cutoff" type="float" optional="True" label="Y-axis low cutoff" help="Bottom cutoff on y-axis for identifying variable genes."/>
        <param name="yhigh" argument="--y-high-cutoff" type="float" optional="True" label="Y-axis high cutoff" help="Top cutoff on y-axis for identifying variable genes."/>
    </inputs>

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

    <tests>
        <test>
            <param name="input" ftype="rdata" value="out_norm.rds"/>
            <output name="output" ftype="rdata" value="out_findvar.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 identifies genes that are outliers on a 'mean variability plot'. First, uses
a function to calculate average expression (mean.function) and dispersion (dispersion.function)
for each gene. Next, divides genes into num.bin (deafult 20) bins based on
their average expression, and calculates z-scores for dispersion within each
bin. The purpose of this is to identify variable genes while controlling for
the strong relationship between variability and average expression.

Exact parameter settings may vary empirically from dataset to dataset, and
based on visual inspection of the plot.

Setting the y.cutoff parameter to 2 identifies genes that are more than two standard
deviations away from the average dispersion within a bin. The default X-axis function
is the mean expression level, and for Y-axis it is the log(Variance/mean). All mean/variance
calculations are not performed in log-space, but the results are reported in log-space -
see relevant functions for exact details.

-----

**Inputs**

1:a6077346f869

<tool id="seurat_find_variable_genes" name="Seurat FindVariableGenes" version="@SEURAT_VERSION@_@VERSION@+galaxy0">
    <description>identify variable genes</description>
    <macros>
        <import>seurat_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version" />
    <command detect_errors="exit_code"><![CDATA[
seurat-find-variable-genes.R

@INPUT_OBJECT@
#if $mean:
    --mean-function '$mean'
#end if
#if $selection_method
  --selection-method '$selection_method'
#end if
#if $disp:
--dispersion-function $disp
#end if
#if $xlow:

--y-low-cutoff $ylow
#end if
#if $yhigh:
--y-high-cutoff $yhigh
#end if
@OUTPUT_OBJECT@
--output-text-file '$output_tab'
]]></command>

    <inputs>
        <expand macro="input_object_params"/>
        <expand macro="output_object_params"/>
        <param label="Number of features" optional="true" name="nfeatures" argument="--nfeatures" type="integer" help="Number of features to return."/>
        <param name="mean" argument="--mean-function" type="text" optional="True" label="Mean function" help="Function to compute x-axis value (average expression). Default is to take the mean of the detected (i.e. non-zero) values."/>
        <param name="disp" argument="--dispersion-function" type="text" optional="True" label="Dispersion function" help="Function to compute y-axis value (dispersion). Default is to take the standard deviation of all values." />
        <param name="xlow" argument="--x-low-cutoff" type="float" optional="True" label="X-axis low cutoff" help="Bottom cutoff on x-axis (mean) for identifying variable genes."/>
        <param name="xhigh" argument="--x-high-cutoff" type="float" optional="True" label="X-axis high cutoff" help="Top cutoff on x-axis (mean) for identifying variable genes."/>
        <param name="ylow" argument="--y-low-cutoff" type="float" optional="True" label="Y-axis low cutoff" help="Bottom cutoff on y-axis (dispersion) for identifying variable genes."/>
        <param name="yhigh" argument="--y-high-cutoff" type="float" optional="True" label="Y-axis high cutoff" help="Top cutoff on y-axis (dispersion) for identifying variable genes."/>
        <param label="Selection method" optional="true" name="selection_method" argument="--selection-method" type="select" help="How to choose top variable features. Choose one of: 'vst', 'mvp', disp.">
          <option value="vst" selected="true">vst</option>
          <option value="mbp">mbp</option>
          <option value="disp">disp</option>
        </param>
    </inputs>

    <outputs>
        <expand macro="output_files"/>
        <data name="output_tab" format="tabular" from_work_dir="*.tab" label="${tool.name} on ${on_string}: Variable genes tabular file"/>
    </outputs>

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

**What it does**

This tool identifies genes that are outliers on a 'mean variability plot'. First, uses
a function to calculate average expression (mean.function) and dispersion (dispersion.function)
for each gene. Next, divides genes into num.bin (deafult 20) bins based on
their average expression, and calculates z-scores for dispersion within each
bin. The purpose of this is to identify variable genes while controlling for
the strong relationship between variability and average expression.

For the mean.var.plot method: Exact parameter settings may vary empirically from
dataset to dataset, and based on visual inspection of the plot. Setting the
y.cutoff parameter to 2 identifies features that are more than two standard deviations
away from the average dispersion within a bin. The default X-axis function is the
mean expression level, and for Y-axis it is the log(Variance/mean). All
mean/variance calculations are not performed in log-space, but the results are
reported in log-space - see relevant functions for exact details.

@SEURAT_INTRO@

-----

**Inputs**