diff scanpy-run-pca.xml @ 0:5063cd7f8c89 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 9bf9a6e46a330890be932f60d1d996dd166426c4

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy-run-pca.xml	Wed Apr 03 11:08:16 2019 -0400
@@ -0,0 +1,129 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tool id="scanpy_run_pca" name="Scanpy RunPCA" version="@TOOL_VERSION@+galaxy1">
+  <description>for dimensionality reduction</description>
+  <macros>
+    <import>scanpy_macros.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
+    #end if
+    #if $extra_outputs:
+        #set extras = ' '.join(['--output-{}-file {}.csv'.format(x, x) for x in str($extra_outputs).split(',')])
+        ${extras}
+    #end if
+
+@PLOT_OPTS@
+]]></command>
+
+  <inputs>
+    <expand macro="input_object_params"/>
+    <expand macro="output_object_params"/>
+    <param name="n_pcs" argument="--n-pcs" type="integer" value="50" label="Number of PCs to produce"/>
+    <conditional name="run_mode">
+      <param name="chunked" argument="--chunked" type="boolean" checked="false" label="Perform incremental PCA by chunks"/>
+      <when value="true">
+        <param name="chunk_size" argument="--chunk-size" type="integer" value="0" label="Chunk size"/>
+      </when>
+      <when value="false">
+        <param name="zero_center" argument="--zero-center" type="boolean" checked="true" label="Zero center data before scaling"/>
+        <param name="svd_solver" argument="--svd-solver" type="select" optional="true" label="SVD solver">
+          <option value="arpack">ARPACK</option>
+          <option value="randomised">Randomised</option>
+        </param>
+        <param name="random_seed" argument="--random-seed" type="integer" value="0" label="random_seed for numpy random number generator"/>
+      </when>
+    </conditional>
+
+    <param name="extra_outputs" type="select" multiple="true" optional="true" label="Type of output">
+      <option value="embeddings">PCA embeddings</option>
+      <option value="loadings">PCA loadings</option>
+      <option value="stdev">PCs stdev</option>
+      <option value="var-ratio">PCs proportion of variance</option>
+    </param>
+
+    <conditional name="do_plotting">
+      <param name="plot" type="boolean" checked="false" label="Make PCA plot"/>
+      <when value="true">
+        <expand macro="output_plot_params"/>
+      </when>
+      <when value="false"/>
+    </conditional>
+  </inputs>
+
+  <outputs>
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${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 ${on_string}: PCA embeddings">
+      <filter>extra_outputs and 'embeddings' in extra_outputs.split(',')</filter>
+    </data>
+    <data name="output_load" format="csv" from_work_dir="loadings.csv" label="${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>
+    <test>
+      <param name="input_obj_file" value="scale_data.h5"/>
+      <param name="input_format" value="anndata"/>
+      <param name="output_format" value="anndata"/>
+      <param name="extra_outputs" value="embeddings"/>
+      <param name="n_pcs" value="50"/>
+      <param name="zero_center" value="true"/>
+      <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=","/>
+        </assert_contents>
+      </output>
+    </test>
+  </tests>
+
+  <help><![CDATA[
+=======================================================================================================
+Computes PCA (principal component analysis) coordinates, loadings and variance decomposition (`tl.pca`)
+=======================================================================================================
+
+It uses the implementation of *scikit-learn*.
+
+@HELP@
+
+@VERSION_HISTORY@
+]]></help>
+  <expand macro="citations"/>
+</tool>