changeset 1:0ac2f9f2313b draft

"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 4846776f55931e176f7e77af7c185ec6fec7d142"
author ebi-gxa
date Mon, 16 Sep 2019 08:16:59 -0400
parents 88c1516e25e0
children 01750c193a83
files scanpy-run-umap.xml scanpy_macros2.xml
diffstat 2 files changed, 129 insertions(+), 52 deletions(-) [+]
line wrap: on
line diff
--- a/scanpy-run-umap.xml	Wed Apr 03 11:10:27 2019 -0400
+++ b/scanpy-run-umap.xml	Mon Sep 16 08:16:59 2019 -0400
@@ -2,50 +2,46 @@
 <tool id="scanpy_run_umap" name="Scanpy RunUMAP" version="@TOOL_VERSION@+galaxy1">
   <description>visualise cell clusters using UMAP</description>
   <macros>
-    <import>scanpy_macros.xml</import>
+    <import>scanpy_macros2.xml</import>
   </macros>
   <expand macro="requirements"/>
   <command detect_errors="exit_code"><![CDATA[
 ln -s '${input_obj_file}' input.h5 &&
-PYTHONIOENCODING=utf-8 scanpy-run-umap.py
-    -i input.h5
-    -f '${input_format}'
-    -o output.h5
-    -F '${output_format}'
-    #if $embeddings
-        --output-embeddings-file embeddings.csv
+PYTHONIOENCODING=utf-8 scanpy-run-umap
+    --use-graph '${use_graph}'
+    --key-added '${key_added}'
+#if $embeddings
+    --export-embedding embeddings.csv
+#end if
+#if $settings.default == "false"
+    --n-components ${settings.n_components}
+    --min-dist ${settings.min_dist}
+    --spread ${settings.spread}
+    --alpha ${settings.alpha}
+    --gamma ${settings.gamma}
+    --negative-sample-rate ${settings.negative_sample_rate}
+    --random-state ${settings.random_seed}
+    #if $settings.init_pos
+        --init-pos '${settings.init_pos}'
     #end if
-    #if $settings.default == "false"
-        -n '${settings.n_components}'
-        --min-dist '${settings.min_dist}'
-        --spread '${settings.spread}'
-        --alpha '${settings.alpha}'
-        --gamma '${settings.gamma}'
-        --negative-sample-rate '${settings.negative_sample_rate}'
-        #if $settings.init_pos
-            --init-pos '${settings.init_pos}'
-        #end if
-        #if $settings.maxiter
-            --maxiter '${settings.maxiter}'
-        #end if
-        #if $settings.a
-            -a '${settings.a}'
-        #end if
-        #if $settings.b
-            -b '${settings.b}'
-        #end if
-        #if $settings.random_seed is not None
-            -s '${settings.random_seed}'
-        #end if
-   #end if
+    #if $settings.maxiter
+        --maxiter ${settings.maxiter}
+    #end if
+#end if
+    @INPUT_OPTS@
+    @OUTPUT_OPTS@
 
-@PLOT_OPTS@
 ]]></command>
 
   <inputs>
     <expand macro="input_object_params"/>
     <expand macro="output_object_params"/>
     <param name="embeddings" type="boolean" checked="true" label="Output embeddings in csv format"/>
+    <param name="use_graph" argument="--use-graph" value="neighbors" type="text"
+           label="Name of the slot that holds the KNN graph"/>
+    <param name="key_added" argument="--key-added" type="text" optional="true"
+           label="Additional suffix to the name of the slot to save the embedding"/>
+
     <conditional name="settings">
       <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
       <when value="true"/>
@@ -62,26 +58,13 @@
           <option value="random">random</option>
         </param>
         <param name="maxiter" argument="--maxiter" type="integer" optional="true" label="Number of iterations of optimisation"/>
-        <param name="a" argument="-a" type="float" optional="true" label="More specific parameter controlling embedding, automatically determined from --min-dist and --spread if unset"/>
-        <param name="b" argument="-b" type="float" optional="true" label="More specific parameter controlling embedding, automatically determined from --min-dist and --spread if unset"/>
-        <param name="random_seed" argument="--random-seed" type="integer" value="0" label="Seed for numpy random number generator"/>
+        <param name="random_seed" argument="--random-state" type="integer" value="0" label="Seed for numpy random number generator"/>
       </when>
     </conditional>
-    <conditional name="do_plotting">
-      <param name="plot" type="boolean" checked="false" label="Make UMAP plot"/>
-      <when value="true">
-        <expand macro="output_plot_params"/>
-        <param name="color_by" argument="--color-by" type="text" value="louvain" label="Color by attributes, comma separated strings"/>
-      </when>
-      <when value="false"/>
-    </conditional>
   </inputs>
 
   <outputs>
     <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: UMAP object"/>
-    <data name="output_png" format="png" from_work_dir="output.png" label="${tool.name} on ${on_string}: UMAP plot">
-      <filter>do_plotting['plot']</filter>
-    </data>
     <data name="output_embed" format="csv" from_work_dir="embeddings.csv" label="${tool.name} on ${on_string}: UMAP embeddings">
       <filter>embeddings</filter>
     </data>
@@ -95,10 +78,7 @@
       <param name="default" value="false"/>
       <param name="embeddings" value="true"/>
       <param name="random_seed" value="0"/>
-      <param name="plot" value="true"/>
-      <param name="color_by" value="louvain"/>
       <output name="output_h5" file="run_umap.h5" ftype="h5" compare="sim_size"/>
-      <output name="output_png" file="run_umap.png" ftype="png" compare="sim_size"/>
       <output name="output_embed" file="run_umap.embeddings.csv" ftype="csv" compare="sim_size">
         <assert_contents>
           <has_n_columns n="2" sep=","/>
@@ -108,9 +88,12 @@
   </tests>
 
   <help><![CDATA[
-========================================================
-Embed the neighborhood graph using UMAP (`tl.umap`)
-========================================================
+==========================================================
+Embed the neighborhood graph using UMAP (`scanpy.tl.umap`)
+==========================================================
+
+For making UMAP plots, please use `Scanpy PlotEmbed` with the output of this tool and enter "umap" as the
+name of the embedding to plot.
 
 UMAP (Uniform Manifold Approximation and Projection) is a manifold learning
 technique suitable for visualizing high-dimensional data. Besides tending to
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Mon Sep 16 08:16:59 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>