Mercurial > repos > ebi-gxa > scanpy_normalise_data

--- a/scanpy-normalise-data.xml	Wed Apr 03 11:07:51 2019 -0400
+++ b/scanpy-normalise-data.xml	Mon Sep 16 08:11:56 2019 -0400
@@ -2,33 +2,34 @@
 <tool id="scanpy_normalise_data" name="Scanpy NormaliseData" version="@TOOL_VERSION@+galaxy1">
   <description>to make all cells having the same total expression</description>
   <macros>
-    <import>scanpy_macros.xml</import>
+    <import>scanpy_macros2.xml</import>
   </macros>
   <expand macro="requirements"/>
   <command detect_errors="exit_code"><![CDATA[
 ln -s '${input_obj_file}' input.h5 &&
-PYTHONIOENCODING=utf-8 scanpy-normalise-data.py
-    -i input.h5
-    -f '${input_format}'
-    -o output.h5
-    -F '${output_format}'
-    -s '${scale_factor}'
-    #if $save_raw
-        '${save_raw}'
-    #end if
-    @EXPORT_MTX_OPTS@
+PYTHONIOENCODING=utf-8 scanpy-normalise-data
+    --normalize-to ${scale_factor}
+    --fraction ${fraction}
+    --save-raw ${save_raw}
+    @INPUT_OPTS@
+    @OUTPUT_OPTS@
 ]]></command>

   <inputs>
     <expand macro="input_object_params"/>
     <expand macro="output_object_params"/>
-    <param name="scale_factor" argument="--scale-factor" type="float" value="1e4" label="Target number to normalise to" help="Aimed counts per cell after normalisation, default: 1e4"/>
-    <param name="save_raw" argument="--save-raw" type="boolean" truevalue="--save-raw" falsevalue="" checked="true" label="Save pre-normalised data" help="Save raw quantification in log scale before normalisation."/>
+    <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="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 ${on_string}: Normalized data" />
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: Normalised data"/>
     <expand macro="export_mtx_outputs"/>
   </outputs>

@@ -44,12 +45,13 @@
   </tests>

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

-Normalize each cell by total counts over all genes, so that every cell has
-the same total count after normalization.
+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.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Mon Sep 16 08:11:56 2019 -0400
@@ -0,0 +1,94 @@
+<macros>
+  <token name="@TOOL_VERSION@">1.4.2</token>
+  <token name="@HELP@">More information can be found at https://scanpy.readthedocs.io</token>
+  <token name="@VERSION_HISTORY@"><![CDATA[
+**Version history**
+
+1.4.2+galaxy0: Update to scanpy-scripts 0.2.4 (requires scanpy >=1.4.2).
+
+1.3.2+galaxy1: Normalise-data and filter-genes: Exposes ability to output 10x files.
+
+1.3.2+galaxy0: Initial contribution. Ni Huang and Pablo Moreno, Expression Atlas team https://www.ebi.ac.uk/gxa/home  at
+EMBL-EBI https://www.ebi.ac.uk/ and Teichmann Lab at Wellcome Sanger Institute.
+    ]]></token>
+  <token name="@INPUT_OPTS@">
+    --input-format '${input_format}' input.h5
+  </token>
+  <token name="@OUTPUT_OPTS@">
+    --show-obj stdout --output-format '${output_format}' output.h5
+  </token>
+  <token name="@PLOT_OPTS@">
+#if $fig_title
+    --title '${fig_title}'
+#end if
+    --fig-size '${fig_size}'
+    --fig-dpi ${fig_dpi}
+    --fig-fontsize ${fig_fontsize}
+    ${fig_frame}
+    ./output.png
+  </token>
+  <token name="@EXPORT_MTX_OPTS@">${export_mtx}</token>
+
+  <xml name="requirements">
+    <requirements>
+      <requirement type="package" version="0.2.4.post4">scanpy-scripts</requirement>
+      <yield/>
+    </requirements>
+  </xml>
+
+  <xml name="citations">
+    <citations>
+      <yield />
+      <citation type="doi">10.1186/s13059-017-1382-0</citation>
+      <citation type="bibtex">
+	@misc{githubscanpy-scripts,
+	author = {Ni Huang, EBI Gene Expression Team},
+	year = {2018},
+	title = {Scanpy-scripts: command line interface for Scanpy},
+	publisher = {GitHub},
+	journal = {GitHub repository},
+	url = {https://github.com/ebi-gene-expression-group/scanpy-scripts},
+      }</citation>
+    </citations>
+  </xml>
+
+  <xml name="input_object_params">
+    <param name="input_obj_file" argument="input-object-file" type="data" format="h5" label="Input object in hdf5 format"/>
+    <param name="input_format" argument="--input-format" type="select" label="Format of input object">
+      <option value="anndata" selected="true">AnnData format hdf5</option>
+      <option value="loom">Loom format hdf5</option>
+    </param>
+  </xml>
+
+  <xml name="output_object_params">
+    <param name="output_format" argument="--output-format" type="select" label="Format of output object">
+      <option value="anndata" selected="true">AnnData format hdf5</option>
+      <option value="loom">Loom format hdf5</option>
+    </param>
+  </xml>
+
+  <xml name="output_plot_params">
+    <param name="fig_title" argument="--title" type="text" label="Figure title"/>
+    <param name="fig_size" argument="--fig-size" type="text" value="4,4" label="Figure size as 'width,height', e.g, '7,7'"/>
+    <param name="fig_dpi" argument="--fig-dpi" type="integer" min="1" value="80" label="Figure dpi"/>
+    <param name="fig_fontsize" argument="--fig-fontsize" type="integer" min="0" value="10" label="Figure font size"/>
+    <param name="fig_frame" type="boolean" truevalue="--frameon" falsevalue="--frameoff" checked="false"
+           label="Show plot frame"/>
+  </xml>
+
+  <xml name="export_mtx_params">
+    <param name="export_mtx" argument="--export-mtx" type="boolean" truevalue="--export-mtx ./" falsevalue="" checked="false" label="Save normalised data to 10x mtx format" help="If enabled, it will generate in addition to the main output in Loom or AnnData an export in 10x format of the normalised data."/>
+  </xml>
+
+  <xml name="export_mtx_outputs">
+    <data name="matrix_10x" format="txt" from_work_dir="matrix.mtx" label="${tool.name} on ${on_string}: 10x matrix">
+      <filter>export_mtx</filter>
+    </data>
+    <data name="genes_10x" format="tsv" from_work_dir="genes.tsv" label="${tool.name} on ${on_string}: 10x genes">
+      <filter>export_mtx</filter>
+    </data>
+    <data name="barcodes_10x" format="tsv" from_work_dir="barcodes.tsv" label="${tool.name} on ${on_string}: 10x barcodes">
+      <filter>export_mtx</filter>
+    </data>
+  </xml>
+</macros>