Mercurial > repos > ebi-gxa > scanpy_find_cluster

changeset 1:ee181563bae7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"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 08:13:51 -0400
parents ce27ae8a36cd
children e232ea3fff07
files scanpy-find-cluster.xml scanpy_macros2.xml
diffstat 2 files changed, 147 insertions(+), 39 deletions(-) [+]
line wrap: on
line diff
--- a/scanpy-find-cluster.xml	Wed Apr 03 11:09:12 2019 -0400
+++ b/scanpy-find-cluster.xml	Mon Sep 16 08:13:51 2019 -0400
@@ -2,55 +2,68 @@
 <tool id="scanpy_find_cluster" name="Scanpy FindCluster" version="@TOOL_VERSION@+galaxy1">
   <description>based on community detection on KNN graph</description>
   <macros>
-    <import>scanpy_macros.xml</import>
+    <import>scanpy_macros2.xml</import>
   </macros>
   <expand macro="requirements"/>
   <command detect_errors="exit_code"><![CDATA[
 ln -s '${input_obj_file}' input.h5 &&
-PYTHONIOENCODING=utf-8 scanpy-find-cluster.py
-    -i input.h5
-    -f '${input_format}'
-    -o output.h5
-    -F '${output_format}'
-    #if $output_cluster
-        --output-text-file output.tsv
-    #end if
-    #if $settings.default == "false"
-        --flavor '${settings.flavor}'
+PYTHONIOENCODING=utf-8 scanpy-find-cluster
+    ${method}
+#if $settings.default == "false"
+    --use-graph '${settings.use_graph}'
+    #if $settings.key_added
         --key-added '${settings.key_added}'
-        -s '${settings.random_seed}'
-        #if $settings.flavor == "vtraag" and $settings.resolution_file
-            --resolution \$( cat $settings.resolution_file )
-        #elif $settings.flavor == "vtraag"
-            --resolution '${settings.resolution}'
-        #end if
-        #if $settings.restrict_to
-            --restrict-to '${settings.restrict_to}'
-        #end if
-        #if $settings.use_weights
-            --use-weights
-        #end if
+    #end if
+    #if $settings.resolution_file
+        --resolution \$( cat $settings.resolution_file )
+    #elif $settings.resolution
+        --resolution '${settings.resolution}'
+    #end if
+    #if $settings.restrict_to
+        --restrict-to '${settings.restrict_to}'
     #end if
+    #if $settings.use_weights
+        --use-weights
+    #end if
+    --random-state '${settings.random_seed}'
+    ${settings.directed}
+#end if
+#if $output_cluster
+    --export-cluster output.tsv
+#end if
+    @INPUT_OPTS@
+    @OUTPUT_OPTS@
 ]]></command>
 
   <inputs>
     <expand macro="input_object_params"/>
     <expand macro="output_object_params"/>
     <param name="output_cluster" type="boolean" checked="true" label="Output cluster in two column text format"/>
+
+    <param name="method" type="select" label="Clustering algorithm">
+      <option value="louvain" selected="true">Louvain</option>
+      <option value="leiden">Leiden</option>
+    </param>
+
     <conditional name="settings">
       <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
       <when value="true"/>
       <when value="false">
-        <param name="flavor" argument="--flavor" type="select" label="Use the indicated representation">
-          <option value="vtraag" selected="true">vtraag</option>
-          <option value="igraph">igraph</option>
-        </param>
-        <param name="resolution" argument="--resolution" type="float" value="1.0" label="Resolution, high value for more and smaller clusters"/>
-        <param name="resolution_file" argument="--resolution" type="data" format="txt,tsv" optional="true" label="File with resolution, use with parameter iterator. Overrides the resolution setting"/>
-        <param name="restrict_to" argument="--restrict-to" type="text" optional="true" label="Restrict clustering to certain sample categories"/>
-        <param name="key_added" argument="--key-added" type="text" value="louvain" label="Key under which to add the cluster labels (do not change unless you know what you are doing)"/>
+        <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 calculated trajectory"/>
+
+        <param name="resolution" argument="--resolution" type="float" min="0.0" value="1.0"
+               label="Resolution, high value for more and smaller clusters"/>
+        <param name="resolution_file" argument="--resolution" type="data" format="txt,tsv" optional="true"
+               label="File with resolution, use with parameter iterator. Overrides the resolution setting"/>
+        <param name="restrict_to" argument="--restrict-to" type="text" optional="true"
+               label="Restrict clustering to certain sample categories"/>
         <param name="use_weights" argument="--use-weights" type="boolean" checked="false" label="Use weights from knn graph"/>
         <param name="random_seed" argument="--random-seed" type="integer" value="0" label="Seed for random number generator"/>
+        <param name="directed" argument="--directed" type="boolean" truevalue="--directed" falsevalue="--undirected" checked="true"
+               label="Interpret the adjacency matrix as directed graph."/>
       </when>
     </conditional>
   </inputs>
@@ -69,7 +82,6 @@
       <param name="output_format" value="anndata"/>
       <param name="output_txt" value="true"/>
       <param name="default" value="false"/>
-      <param name="flavor" value="vtraag"/>
       <param name="resolution" value="1.0"/>
       <param name="random_seed" value="0"/>
       <output name="output_h5" file="find_cluster.h5" ftype="h5" compare="sim_size"/>
@@ -78,17 +90,18 @@
   </tests>
 
   <help><![CDATA[
-===========================================
-Cluster cells into subgroups (`tl.louvain`)
-===========================================
+======================================================================
+Cluster cells into subgroups (`scanpy.tl.louvain`, `scanpy.tl.leiden`)
+======================================================================
 
-Cluster cells using the Louvain algorithm (Blondel et al, 2008) in the implementation
-of Traag et al,2017. The Louvain algorithm has been proposed for single-cell
-analysis by Levine et al, 2015.
+Cluster cells using the Louvain algorithm (Blondel et al, 2008) in the
+implementation of Traag et al, 2017, or the Leiden algorithm (Traag et al,
+2019). The Louvain algorithm has been proposed for single-cell analysis by
+Levine et al, 2015.
 
 This requires to run `Scanpy ComputeGraph`, first.
 
-It yields `louvain`, generated cluster label.
+It by default yields `louvain` or `leiden`, generated cluster label.
 
 @HELP@
 
@@ -97,6 +110,7 @@
   <expand macro="citations">
     <citation type="doi">10.1088/1742-5468/2008/10/P10008</citation>
     <citation type="doi">10.1016/j.cell.2015.05.047</citation>
+    <citation type="doi">10.1038/s41598-019-41695-z</citation>
     <citation type="doi">10.5281/zenodo.35117</citation>
   </expand>
 </tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Mon Sep 16 08:13:51 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>