Mercurial > repos > ebi-gxa > scanpy_run_pca

--- /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>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros.xml	Wed Apr 03 11:08:16 2019 -0400
@@ -0,0 +1,109 @@
+<macros>
+  <token name="@TOOL_VERSION@">1.3.2</token>
+  <token name="@HELP@">More information can be found at https://scanpy.readthedocs.io</token>
+  <token name="@PLOT_OPTS@">
+#if $do_plotting.plot
+                  -P output.png
+                  --projectio $do_plotting.projection
+                  --components $do_plotting.components
+    #if $do_plotting.color_by
+                  --color-by $do_plotting.color_by
+    #end if
+    #if $do_plotting.groups
+                  --group $do_plotting.groups
+    #end if
+    #if $do_plotting.use_raw
+                  --use-raw
+    #end if
+    #if $do_plotting.palette
+                  --palette $do_plotting.palette
+    #end if
+    #if $do_plotting.edges
+                  --edges
+    #end if
+    #if $do_plotting.arrows
+                  --arrows
+    #end if
+    #if not $do_plotting.sort_order
+                  --no-sort-order
+    #end if
+    #if $do_plotting.frameoff
+                  --frameoff
+    #end if
+#end if
+  </token>
+  <xml name="requirements">
+    <requirements>
+      <requirement type="package" version="0.0.5">scanpy-scripts</requirement>
+      <yield/>
+    </requirements>
+  </xml>
+  <token name="@EXPORT_MTX_OPTS@">
+      ${export_mtx}
+  </token>
+  <token name="@VERSION_HISTORY@"><![CDATA[
+**Version history**
+
+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>
+  <xml name="citations">
+    <citations>
+      <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>
+      <yield />
+    </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, current support is incomplete</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, current support is defective</option>
+    </param>
+  </xml>
+  <xml name="output_plot_params">
+    <param name="color_by" argument="--color-by" type="text" value="n_genes" label="Color by attributes, comma separated strings"/>
+    <param name="groups" argument="--groups" type="text" optional="ture" label="Restrict plotting to named groups, comma separated strings"/>
+    <param name="projection" argument="--projection" type="select" label="Plot projection">
+      <option value="2d" selected="true">2D</option>
+      <option value="3d">3D</option>
+    </param>
+    <param name="components" argument="--components" type="text" value="1,2" label="Components to plot, comma separated integers"/>
+    <param name="palette" argument="--palette" type="text" optional="true" label="Palette"/>
+    <param name="use_raw" argument="--use-raw" type="boolean" checked="false" label="Use raw attributes if present"/>
+    <param name="edges" argument="--edges" type="boolean" checked="false" label="Show edges"/>
+    <param name="arrows" argument="--arrows" type="boolean" checked="false" label="Show arrows"/>
+    <param name="sort_order" argument="--no-sort-order" type="boolean" checked="true" label="Element with high color-by value plot on top"/>
+    <param name="frameoff" argument="--frameoff" type="boolean" checked="false" label="Omit 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 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>