<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_read_10x" name="Scanpy Read10x" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
  <description>into hdf5 object handled by scanpy</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${matrix}' matrix.mtx &&
ln -s '${genes}' genes.tsv &&
ln -s '${barcodes}' barcodes.tsv &&
PYTHONIOENCODING=utf-8 scanpy-read-10x
    --input-10x-mtx ./
    --var-names '${var_names}'
#if $cell_meta:
    --extra-obs '${cell_meta}'
#end if
#if $gene_meta:
    --extra-var '${gene_meta}'
#end if
    @OUTPUT_OPTS@
]]></command>

  <inputs>
    <param name="matrix" type="data" format="txt" label="Expression matrix in sparse matrix format (.mtx)"/>
    <param name="genes" type="data" format="tsv,tabular" label="Gene table"/>
    <param name="barcodes" type="data" format="tsv,tabular" label="Barcode/cell table"/>
    <param name="cell_meta" type="data" format="tsv,tabular" label="Cell metadata table" optional="true"
           help="Requires a header row and index column that matches the barcode/cell table"/>
    <param name="gene_meta" type="data" format="tsv,tabular" label="Gene metadata table" optional="true"
           help="Requires a header row and index column that matches the gene table"/>
    <expand macro="output_object_params"/>
    <param name="var_names" type="select" label="Attribute used as annotation index" help="If Gene ID is selected the index will point to the gene identifiers (first columns expected) and the gene symbols will be left in a field called 'gene_symbols'.">
      <option value="gene_ids" selected="true">Gene ID</option>
      <option value="gene_symbols">Gene symbol</option>
    </param>
  </inputs>

  <outputs>
    <expand macro="output_data_obj" description="${output_format}"/>
  </outputs>

  <tests>
    <test>
      <param name="matrix" value="matrix.mtx"/>
      <param name="genes" value="genes.tsv"/>
      <param name="barcodes" value="barcodes.tsv"/>
      <!-- <param name="cell_meta" value=""/> -->
      <param name="output_format" value="anndata"/>
      <output name="output_h5ad" ftype="h5">
        <assert_contents>
          <has_h5_keys keys="var/gene_symbols"/>
        </assert_contents>
      </output>
    </test>
  </tests>

  <help><![CDATA[
=================================================================
Read 10x-Genomics-formatted mtx directory (`scanpy.read_10x_mtx`)
=================================================================

The mtx 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 or `Human Cell Atlas Matrix Downloader` with a project name/label/UUID.

Additionally, cell and/or gene metadata table can be provided as tab-separated text with a header row and an index column that matches the respective barcode/cell and/or gene table.


@HELP@

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