annotate seurat_read10x.xml @ 6:f5db0e853f57 draft default tip

planemo upload commit 0264c359f1d638bbbbab515a3502231f679cdcf6

<tool id="seurat_read10x" name="Seurat Read10x" profile="18.01" version="@SEURAT_VERSION@+galaxy0">
<description>Loads Tabular or 10x data into a serialized seurat R object</description>
  <macros>
      <import>seurat_macros.xml</import>
  </macros>
  <expand macro="requirements" />
<stdio>
<exit_code range="1:" />
</stdio>
<command><![CDATA[

#if str($input.format) == "mtx":
    ln -s "$matrix" matrix.mtx;
    ln -s "$genes" genes.tsv;
    ln -s "$barcodes" barcodes.tsv;
#end if

seurat-read-10x.R
#if str($input.format) == "mtx":
 -d ./
#else
 -f $input.file
#end if
#if $metadata
  --metadata '$metadata'
#end if
#if $min_cells
  --min-cells '$min_cells'
#end if
#if $min_features
  --min-features '$min_features'
#end if

@OUTPUT_OBJECT@

]]></command>
<inputs>
     <conditional name="input" label="Input expression data">
       <param type="select" name="format" label="Choose the format of the input" help="10X MTX or tabular">
         <option value="mtx" selected="true">10X-type MTX</option>
         <option value="tab" selected="true">tab-delimited text</option>
       </param>
       <when value="tab">
         <param type="data" name="file" label="Expression table" help="Tab-delimted expression table" format="tabular"/>
       </when>
       <when value="mtx">
        <param type="data" name="matrix" help="Raw expression quantification as a sparse matrix in Matrix Market format, where each column is a gene and each row is a barcode/cell." format="txt" label="Expression matrix in sparse matrix format (.mtx)" />
        <param type="data" name="genes" help="Matrix market column file for genes" label="Gene table" format="tsv,tabular"/>
        <param type="data" name="barcodes" help="Matrix market row file for genes" label="Barcode/cell table" format="tsv,tabular"/>
       </when>
     </conditional>
    <param label="Cell Metadata" optional="true" name="metadata" argument="--metadata" type="data" format="tsv,tabular" help="File with metdata for the cells, first column should be cell identifiers as used in the cells 10x file."/>
    <param label="Minimum cells to include features" optional="true" name="min_cells" argument="--min-cells" type="integer" help="Include features detected in at least this many cells. Will subset the counts matrix as well. To reintroduce excluded features, create a new object with a lower cutoff."/>
    <param label="Minimum features to include cells" optional="true" name="min_features" argument="--min-features" type="integer" help="Include cells where at least this many features are detected."/>
    <expand macro="output_object_params"/>
</inputs>
<outputs>
    <expand macro="output_files"/>
</outputs>

<tests>
    <test>
       <conditional name="input">
         <param name="format" value="mtx"/>
       </conditional>
       <param name="matrix" ftype="txt" value="E-MTAB-6077_3k_features_90_cells_matrix.txt"/>
       <param name="genes" ftype="txt" value="E-MTAB-6077_3k_features_90_cells_genes.tsv"/>
       <param name="barcodes" ftype="txt" value="E-MTAB-6077_3k_features_90_cells_barcodes.tsv"/>
       <output name="rds_seurat_file" ftype="rdata">
         <assert_contents>
           <has_size value="2260044" delta="200000"/>
         </assert_contents>
       </output>
    </test>
</tests>


<help><![CDATA[
  .. class:: infomark

  **What it does**

  @SEURAT_INTRO@

  **Read expression data from a tabular file or a 10x-Genomics-formatted mtx directory (`read_10x_mtx`)**

  For mtx, the  directory should contain:

  1) Raw expression quantification as a sparse matrix in Matrix Market format, where the each column is a gene and each row is a barcode/cell.

  2) A gene table of at least two columns where the first column gives the gene IDs.

  3) A barcode/cell table of at least one column giving the barcode/cell IDs.

  The above-mentioned files can be obtained by running `EBI SCXA Data Retrieval`
  with a dataset accession. Otherwise, they need to be provided as separate Galaxy
  datasets.

  **Inputs**
      * A tabular file of expression data OR
          * Raw expression quantification as a sparse matrix in Matrix Market format, where the each column is a gene and each row is a barcode/cell.
          * A gene table of at least two columns where the first column gives the gene IDs.
          * A barcode/cell table of at least one column giving the barcode/cell IDs.
      * Optionally, a file with cell metadata.

  **Outputs**
      * R object for Seurat

  .. _Seurat: https://www.nature.com/articles/nbt.4096
  .. _Satija Lab: https://satijalab.org/seurat/
  .. _Seurat Guided Clustering tutorial: https://satijalab.org/seurat/pbmc3k_tutorial.html

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