<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_normalise_data" name="Scanpy NormaliseData" version="@TOOL_VERSION@+galaxy2">
  <description>to make all cells having the same total expression</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-normalise-data
    --normalize-to ${scale_factor}
    --fraction ${fraction}
    --save-raw ${save_raw}
    ${log_transform}
    @INPUT_OPTS@
    @OUTPUT_OPTS@
    @EXPORT_MTX_OPTS@
]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>
    <param name="scale_factor" argument="--normalize-to" type="float" value="1e4" min="0"
           label="Target number to normalise to" help="Aimed counts per cell after normalisation."/>
    <param name="fraction" argument="--fraction" type="float" value="1" min="0" max="1"
           label="Exclude top expressed genes until the remaining account for no greater than specified fraction of total counts"
           help="Only non-excluded genes will sum up the target number."/>
    <param name="log_transform" argument="--no-log-transform" type="boolean" truevalue="" falsevalue="--no-log-tranform" checked="True" 
           label="Apply log transform?" help="If enabled, will apply a log transformation following normalisation."/>
    <param name="save_raw" argument="--save-raw" type="boolean" truevalue="yes" falsevalue="no" checked="true"
           label="Save normalised data in `.raw`" help="The saved normalised data are log1p transformed."/>
    <expand macro="export_mtx_params"/>
  </inputs>

  <outputs>
    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: Normalised data"/>
    <expand macro="export_mtx_outputs"/>
  </outputs>

  <tests>
    <test>
      <param name="input_obj_file" value="filter_genes.h5"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <param name="scale_factor" value="1e4"/>
      <param name="save_raw" value="false"/>
      <output name="output_h5" file="normalise_data.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
=============================================================
Normalise total counts per cell (`scanpy.pp.normalize_total`)
=============================================================

Normalise each cell by total counts over all genes (excluding top expressed
genes if so required), so that every cell has the same total count after
normalisation.

Similar functions are used, for example, by Seurat, Cell Ranger or SPRING.

@HELP@

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