Mercurial > repos > ebi-gxa > scanpy_run_pca

--- a/scanpy-run-pca.xml	Wed Apr 03 11:08:16 2019 -0400
+++ b/scanpy-run-pca.xml	Mon Sep 16 08:12:12 2019 -0400
@@ -1,94 +1,64 @@
 <?xml version="1.0" encoding="utf-8"?>
-<tool id="scanpy_run_pca" name="Scanpy RunPCA" version="@TOOL_VERSION@+galaxy1">
+<tool id="scanpy_run_pca" name="Scanpy RunPCA" version="@TOOL_VERSION@+galaxy0">
   <description>for dimensionality reduction</description>
   <macros>
-    <import>scanpy_macros.xml</import>
+    <import>scanpy_macros2.xml</import>
   </macros>
   <expand macro="requirements"/>
   <command detect_errors="exit_code"><![CDATA[
 ln -s '${input_obj_file}' input.h5 &&
-PYTHONIOENCODING=utf-8 scanpy-run-pca.py
-    -i input.h5
-    -f '${input_format}'
-    -o output.h5
-    -F '${output_format}'
-    -n '${n_pcs}'
-    #if $run_mode.chunked
-        -c
-        --chunk-size '${run_mode.chunk_size}'
-    #else
-        #if $run_mode.zero_center
-            -z
-        #else
-            -Z
-        #end if
-        #if $run_mode.svd_solver
-            --svd-solver '${run_mode.svd_solver}'
-        #end if
-        #if $run_mode.random_seed is not None
-            -s '${run_mode.random_seed}'
-        #end if
+PYTHONIOENCODING=utf-8 scanpy-run-pca
+    --n-comps '${n_pcs}'
+#if $run_mode.chunked
+    --chunked
+    --chunk-size '${run_mode.chunk_size}'
+#else
+    ${run_mode.zero_center}
+    #if $run_mode.svd_solver
+        --svd-solver '${run_mode.svd_solver}'
     #end if
-    #if $extra_outputs:
-        #set extras = ' '.join(['--output-{}-file {}.csv'.format(x, x) for x in str($extra_outputs).split(',')])
-        ${extras}
+    #if $run_mode.random_seed is not None
+        --random-state '${run_mode.random_seed}'
     #end if
-
-@PLOT_OPTS@
+#end if
+#if $extra_outputs and "embeddings" in str($extra_outputs).split(','):
+    --export-embedding embeddings.tsv
+#end if
+    @INPUT_OPTS@
+    @OUTPUT_OPTS@
 ]]></command>

   <inputs>
     <expand macro="input_object_params"/>
     <expand macro="output_object_params"/>
-    <param name="n_pcs" argument="--n-pcs" type="integer" value="50" label="Number of PCs to produce"/>
+    <param name="n_pcs" argument="--n-comps" type="integer" min="2" value="50" label="Number of PCs to produce"/>
     <conditional name="run_mode">
       <param name="chunked" argument="--chunked" type="boolean" checked="false" label="Perform incremental PCA by chunks"/>
       <when value="true">
         <param name="chunk_size" argument="--chunk-size" type="integer" value="0" label="Chunk size"/>
       </when>
       <when value="false">
-        <param name="zero_center" argument="--zero-center" type="boolean" checked="true" label="Zero center data before scaling"/>
+        <param name="zero_center" argument="--zero-center" type="boolean" truevalue="" falsevalue="--no-zero-center" checked="true"
+               label="Zero center data before scaling"/>
         <param name="svd_solver" argument="--svd-solver" type="select" optional="true" label="SVD solver">
           <option value="arpack">ARPACK</option>
-          <option value="randomised">Randomised</option>
+          <option value="randomized">Randomised</option>
         </param>
-        <param name="random_seed" argument="--random-seed" type="integer" value="0" label="random_seed for numpy random number generator"/>
+        <param name="random_seed" argument="--random-state" type="integer" value="0" label="random seed for numpy random number generator"/>
       </when>
     </conditional>

-    <param name="extra_outputs" type="select" multiple="true" optional="true" label="Type of output">
+    <param name="extra_outputs" type="select" multiple="true" display="checkboxes" optional="true" label="Export extra output">
       <option value="embeddings">PCA embeddings</option>
-      <option value="loadings">PCA loadings</option>
-      <option value="stdev">PCs stdev</option>
-      <option value="var-ratio">PCs proportion of variance</option>
     </param>

-    <conditional name="do_plotting">
-      <param name="plot" type="boolean" checked="false" label="Make PCA plot"/>
-      <when value="true">
-        <expand macro="output_plot_params"/>
-      </when>
-      <when value="false"/>
-    </conditional>
   </inputs>

   <outputs>
     <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: PCA object"/>
-    <data name="output_png" format="png" from_work_dir="output.png" label="${tool.name} on ${on_string}: PCA plot">
-      <filter>do_plotting['plot']</filter>
-    </data>
-    <data name="output_embed" format="csv" from_work_dir="embeddings.csv" label="${tool.name} on ${on_string}: PCA embeddings">
+    <data name="output_embed" format="tsv" from_work_dir="embeddings.tsv" label="${tool.name} on ${on_string}: PCA embeddings">
       <filter>extra_outputs and 'embeddings' in extra_outputs.split(',')</filter>
     </data>
-    <data name="output_load" format="csv" from_work_dir="loadings.csv" label="${tool.name} on ${on_string}: PCA loadings">
-      <filter>extra_outputs and 'loadings' in extra_outputs.split(',')</filter>
-    </data>
-    <data name="output_stdev" format="csv" from_work_dir="stdev.csv" label="${tool.name} on ${on_string}: PCA stdev">
-      <filter>extra_outputs and 'stdev' in extra_outputs.split(',')</filter>
-    </data>
-    <data name="output_vprop" format="csv" from_work_dir="var-ratio.csv" label="${tool.name} on ${on_string}: PC explained proportion of variance">
-      <filter>extra_outputs and 'var-ratio' in extra_outputs.split(',')</filter>
-    </data>
   </outputs>

   <tests>
@@ -102,10 +72,7 @@
       <param name="svd_solver" value="arpack"/>
       <param name="random_seed" value="0"/>
       <param name="chunked" value="false"/>
-      <param name="plot" value="true"/>
-      <param name="color_by" value="n_genes"/>
       <output name="output_h5" file="run_pca.h5" ftype="h5" compare="sim_size"/>
-      <output name="output_png" file="run_pca.png" ftype="png" compare="sim_size"/>
       <output name="output_embed" file="run_pca.embeddings.csv" ftype="csv" compare="sim_size">
         <assert_contents>
           <has_n_columns n="50" sep=","/>
@@ -115,9 +82,9 @@
   </tests>

   <help><![CDATA[
-=======================================================================================================
-Computes PCA (principal component analysis) coordinates, loadings and variance decomposition (`tl.pca`)
-=======================================================================================================
+================================================================================
+Dimensionality reduction by PCA (principal component analysis) (`scanpy.pp.pca`)
+================================================================================

 It uses the implementation of *scikit-learn*.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Mon Sep 16 08:12:12 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>