Mercurial > repos > ebi-gxa > scanpy_find_markers

changeset 1:71668dd2d47b 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 08:12:48 -0400
parents c608fd80ec15
children af5e4efa9e66
files scanpy-find-markers.xml scanpy_macros2.xml
diffstat 2 files changed, 124 insertions(+), 27 deletions(-) [+]
line wrap: on
line diff
--- a/scanpy-find-markers.xml	Wed Apr 03 11:08:46 2019 -0400
+++ b/scanpy-find-markers.xml	Mon Sep 16 08:12:48 2019 -0400
@@ -2,56 +2,59 @@
 <tool id="scanpy_find_markers" name="Scanpy FindMarkers" version="@TOOL_VERSION@+galaxy1">
   <description>to find differentially expressed genes between groups</description>
   <macros>
-    <import>scanpy_macros.xml</import>
+    <import>scanpy_macros2.xml</import>
   </macros>
   <expand macro="requirements"/>
   <command detect_errors="exit_code"><![CDATA[
 ln -s '${input_obj_file}' input.h5 &&
-PYTHONIOENCODING=utf-8 scanpy-find-markers.py
-    -i input.h5
-    -f '${input_format}'
-    -o output.h5
-    -F '${output_format}'
-    -n '${n_genes}'
-    #if $output_markers
-        --output-text-file output.csv
+PYTHONIOENCODING=utf-8 scanpy-find-markers
+#if $output_markers
+    --save output.csv
+#end if
+    --n-genes '${n_genes}'
+    --groupby '${groupby}'
+#if $settings.default == "false"
+    --method '${settings.method}'
+    ${settings.use_raw}
+    ${settings.rankby_abs}
+    #if $settings.groups
+        --groups '${settings.groups}'
     #end if
-    #if $settings.default == "false"
-        -g '${settings.groupby}'
-        --reference '${settings.reference}'
-        --method '${settings.method}'
-        #if $settings.use_raw == "false"
-            --no-raw
-        #end if
-        #if $settings.rankby_abs
-            --rankby_abs
-        #end if
-        #if $settings.groups
-            --groups '${settings.groups}'
-        #end if
+    --reference '${settings.reference}'
+    --filter-params 'min_in_group_fraction:${settings.min_in_group_fraction},max_out_group_fraction:${settings.max_out_group_fraction},min_fold_change:${settings.min_fold_change}'
 #end if
+    @INPUT_OPTS@
+    @OUTPUT_OPTS@
 ]]></command>
 
   <inputs>
     <expand macro="input_object_params"/>
     <expand macro="output_object_params"/>
+    <param name="output_markers" type="boolean" checked="true" label="Output markers table in csv format"/>
     <param name="n_genes" argument="--n-genes" type="integer" value="50" label="Number of top genes to show per group/cluster"/>
-    <param name="output_markers" type="boolean" checked="true" label="Output markers table in csv format"/>
+    <param name="groupby" argument="--groupby" type="text" value="louvain" label="The sample grouping/clustering to use."/>
     <conditional name="settings">
       <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
       <when value="true"/>
       <when value="false">
-        <param name="groupby" argument="--groupby" type="text" value="louvain" label="The sample grouping/clustering to use."/>
-        <param name="use_raw" type="boolean" checked="true" label="Use raw attribute if present"/>
-        <param name="reference" argument="--reference" type="text" value="rest" label="If 'rest', compare to the union of the rest of the group/cluster. If a group identifier, compare to that group"/>
         <param name="method" argument="--method" type="select" label="Method for testing differentially expressed genes">
           <option value="t-test_overestim_var" selected="true">t-test with over-estimated variance</option>
           <option value="t-test">t-test</option>
           <option value="wilcoxon">wilcoxon test, currently broken don't use</option>
           <option value="logreg">logistic regression</option>
         </param>
-        <param name="rankby_abs" argument="--rankby_abs" type="boolean" checked="false" label="Rank by absolute value of the scores instead of the scores"/>
+        <param name="use_raw" type="boolean" truevalue="--use-raw" falsevalue="--no-raw" checked="true"
+               label="Use raw attribute if present"/>
+        <param name="rankby_abs" argument="--rankby_abs" type="boolean" truevalue="--rankby-abs" falsevalue="" checked="false"
+               label="Rank by absolute value of the scores instead of the scores"/>
         <param name="groups" argument="--groups" optional="true" type="text" label="Subset of groups/clusters to which comparisons shell be restricted."/>
+        <param name="reference" argument="--reference" type="text" value="rest" label="If 'rest', compare to the union of the rest of the group/cluster. If a group identifier, compare to that group"/>
+        <param name="min_in_group_fraction" type="float" min="0.0" max="1.0" value="0.25" label="Minimum in-group fraction"
+               help="Post-test filtering to only keep genes expressed in at least this fraction of cells in the test group."/>
+        <param name="max_out_group_fraction" type="float" min="0.0" max="1.0" value="0.5" label="Maximum out-group fraction"
+               help="Post-test filtering to only keep genes expressed in at most this fraction of cells in the reference group."/>
+        <param name="min_fold_change" type="float" value="2" label="Minimum fold change"
+               help="Post-test filtering to only keep genes with at least this fold change of expression relative to the reference group."/>
       </when>
     </conditional>
   </inputs>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Mon Sep 16 08:12:48 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>