annotate seurat_run_pca.xml @ 0:df80f3d2f9d4 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 9bf9a6e46a330890be932f60d1d996dd166426c4

<tool id="seurat_run_pca" name="Seurat RunPCA" version="2.3.1+galaxy1">
    <description>run a PCA dimensionality reduction</description>
    <macros>
        <import>seurat_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version" />
    <command detect_errors="exit_code"><![CDATA[
seurat-run-pca.R

--input-object-file '$input'
#if $pc_genes:
    --pc-genes '$pc-genes'
#end if
--output-object-file '$output'
--output-embeddings-file output_embed
--output-loadings-file output_load
--output-stdev-file output_sdev
#if $pcs_compute:
    --pcs-compute '$pcs_compute'
#end if
#if $use_imputed:
'$use_imputed'
#end if

]]></command>

    <inputs>
        <param name="input" type="data" format="rdata" label="RDS object" />
        <param name="pc_genes" type="data" format="tabular, txt" optional="True" label="Genes to scale" help="File of gene names to scale/center. Default is all genes in object." />
        <param name="pcs_compute" type="integer" optional="True" label="Principal components" help="Total Number of PCs to compute and store (20 by default). Less PCs might be faster, but will explain less variance."/>
        <param name="use_imputed" type="boolean" truevalue="--use-imputed TRUE" falsevalue="" checked="false" label="Use imputed" help="Run PCA on imputed values."/>
    </inputs>

    <outputs>
        <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/>
        <data name="output_embed" format="csv" from_work_dir="output_embed" label="${tool.name} on ${on_string}: Seurat Embeddings"/>
        <data name="output_load" format="csv" from_work_dir="output_load" label="${tool.name} on ${on_string}: Seurat Loadings"/>
        <data name="output_sdev" format="csv" from_work_dir="output_sdev" label="${tool.name} on ${on_string}: Seurat Std dev"/>
    </outputs>

    <tests>
        <test>
            <param name="input" ftype="rdata" value="out_scale.rds"/>
            <output name="output" ftype="rdata" value="out_runpca.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 runs a PCA dimensionality reduction

-----

**Inputs**

    * Seurat RDS object, normalised and scaled potentially.
    * Genes used to scale. File of gene names to scale/center. Default is all genes in object.
    * Principal components to compute. Total Number of PCs to compute and store (20 by default). Less PCs might be faster, but will explain less variance.
    * Use imputed. Boolean indicating whether to run PCA on imputed values or not.

-----

**Outputs**

    * Seurat RDS object with PCA calculations and embeddings.
    * Embeddings on CSV file. File with a csv-format embeddings table with principal components by cell.
    * Loadings on CSV file. File with a csv-format loadings table with principal components by gene.
    * Standard deviation on CSV file. Contains principal components std. deviations.

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

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