annotate seurat_run_pca.xml @ 4:3fd59cdcb477 draft

"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit a1ad1ddd9b8e4db5bb82c3accae8311e0e488b19"

<tool id="seurat_run_pca" name="Seurat RunPCA" version="@SEURAT_VERSION@+galaxy0">
    <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@
#if $pc_genes:
    --pc-genes '$pc_genes'
#end if
#if $pc_cells
  --pc-cells '$pc_cells'
#end if
@OUTPUT_OBJECT@
--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 $reverse_pca
  '$reverse_pca'
#end if

]]></command>

    <inputs>
        <expand macro="input_object_params"/>
        <expand macro="output_object_params"/>
        <param name="pc_genes" type="data" format="tabular,txt" optional="True" label="Genes to scale" help="File with gene names to scale/center. Default is all genes in object@data." />
        <param label="Cells to scale" optional="true" name="pc_cells" argument="--pc-cells" type="text" help="File with cell names to scale/center. Default is all cells in object@data."/>
        <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 label="Reverse PCA" optional="true" name="reverse_pca" argument="--reverse-pca" type="boolean" truevalue="--reverse-pca" checked="false" help="Run PCA on reverse matrix (gene x cell; FALSE by default means cell x gene)."/>
    </inputs>

    <outputs>
        <expand macro="output_files"/>
        <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="rds_seurat_file" ftype="rdata" value="scaled_seurat.rds"/>
            <output name="rds_seurat_file" ftype="rdata" value="pca_seurat.rds" compare="sim_size" delta="10000000"/>
            <output name="output_embed" value="pca_embeddings.csv" compare="sim_size" delta="10000000" />
            <output name="output_load" value="pca_loadings.csv" compare="sim_size" delta="10000000" />
            <output name="output_sdev" value="pca_stdev.txt" compare="sim_size" delta="10000000" />
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

This tool runs a PCA dimensionality reduction.

@SEURAT_INTRO@

-----

**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>