Add Spapros (#6191)

* add evaluation.xml * first version of macros.xml * first version of shed.yml * adding second test to evaluation * finished evaluation tool, ready for review * Changes to shed.yml * some fixes and code improvements for evaluatio.xml * fix typo in macros.xml * Adding selection.xml for spapros selction * adding test data for spapros * change to 240cells data evaluation.xml * changes to selection.xml to optimize tests * optimize test data * Review changed to evaluation.xml * Review changes to macros.xml * Review changes to selection.xml * adding image asserts * Update tools/spapros/selection.xml * Update selection.xml * synthax fix selection.xml * bugfix selection.xml * changes to marker_out_test4.tsv * solving issue with line switches of marker files * fix to slection.xml tests * changes to ci and pr yaml to take tifffile into account * Revert "changes to ci and pr yaml to take tifffile into account" This reverts commit 1b71a09. * remove file comparisions * rsolve merge conflict for selection.xml * resolve assert for evaluation.xml * remove pngs * bugfix selection.xml * updating marker_out.tsvs * fixing image differnece for slection.xml * fixing image differnece for slection.xml * fix typo * figuring out reproducibility isse * Try to fix reproducibility issue * Try to fix reproducibility issue * Try to fix reproducibility issue * Try to fix reproducibility issue * figureing out what is going on * figureing out what is going on --------- Co-authored-by: Björn Grüning <bjoern@gruenings.eu>
galaxyproject · Aug 25, 2024 · a773446 · a773446
1 parent 91090b1
commit a773446
Show file tree

Hide file tree

Showing 12 changed files with 1,313 additions and 0 deletions.
diff --git a/tools/spapros/.shed.yml b/tools/spapros/.shed.yml
@@ -0,0 +1,19 @@
+name: spapros
+owner: iuc
+description: "Select and evaluate probe sets for targeted spatial transcriptomics."
+homepage_url: https://github.com/theislab/spapros
+long_description: |
+    Spapros is a python package that provides a pipeline for probe set selection and evaluation for targeted spatial transcriptomics data.
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/spapros/
+type: unrestricted
+categories:
+- Transcriptomics
+- Sequence Analysis
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for the spapros tool suite: {{ tool_name }}"
+suite:
+  name: "suite_spapros"
+  description: "Spapros - Probe selection and evaluation"
+  long_description: |
+    Spapros is a python package that provides a pipeline for probe set selection and evaluation for targeted spatial transcriptomics data.
diff --git a/tools/spapros/evaluation.xml b/tools/spapros/evaluation.xml
diff --git a/tools/spapros/macros.xml b/tools/spapros/macros.xml
@@ -0,0 +1,96 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.1.5</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@profile@">22.05</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">spapros</requirement>
+            <yield />
+        </requirements>
+    </xml>
+    <xml name="creators">
+        <creator>
+            <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/" />
+        </creator>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1101/2022.08.16.504115</citation>
+            <citation type="doi">10.1093/gigascience/giaa102</citation>
+        </citations>
+    </xml>
+    <xml name="version_command">
+        <version_command><![CDATA[python -c "import spapros;print('%s' % spapros.__version__ )"]]></version_command>
+    </xml>
+    <token name="@CMD@"><![CDATA[
+cp '$adata' 'anndata.h5ad' &&
+cat '$script_file' > '$hidden_output' &&
+python '$script_file' >> '$hidden_output' &&
+ls . >> '$hidden_output'
+    ]]>
+    </token>
+    <token name="@CMD_imports@"><![CDATA[
+import spapros as sp
+import os
+import pandas as pd
+import scanpy as sc
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+import random
+    ]]>
+    </token>
+    <token name="@CMD_plot@"><![CDATA[
+#if $method.set_ids != 'all' and $method.set_ids != '':
+set_ids=[$method.set_ids],
+#end if
+save='plot.$format',
+show=False
+    ]]>
+    </token>
+    <xml name="set_ids">
+        <param name="set_ids" type="text" value="all" optional="true" label="List of probeset ids (comma seperated, e.g., DE,HVG,random)" help="Kepp it with all or empty to select all probeset ids."/>
+    </xml>
+    <xml name="sanitize_query" token_validinitial="string.printable">
+        <sanitizer>
+            <valid initial="@VALIDINITIAL@">
+                <remove value="&apos;" />
+            </valid>
+       </sanitizer>
+    </xml>
+    <xml name="sanitize_vectors" token_validinitial="string.digits">
+        <sanitizer>
+            <valid initial="@VALIDINITIAL@">
+                <add value=","/>
+            </valid>
+        </sanitizer>
+    </xml>
+    <xml name="inputs_anndata">
+        <param name="adata" type="data" format="h5ad" label="Annotated data matrix"/>
+    </xml>
+    <token name="@CMD_read_inputs@"><![CDATA[
+adata = sc.read_h5ad('anndata.h5ad')
+]]>
+    </token>
+    <xml name="inputs_common_advanced">
+        <param name="show_log" type="boolean" checked="false" label="Output Log?" />
+    </xml>
+    <xml name="param_plot_format">
+        <param name="format" type="select" label="Format for saving figures">
+            <option value="png">png</option>
+            <option value="pdf">pdf</option>
+            <option value="svg">svg</option>
+        </param>
+    </xml>
+    <xml name="param_markerset">
+        <param name="markerset" type="data" format="tabular" label="Markerset tabular file with rows=conditions (e.g., celltypes) and column=features (e.g., genes)" help="This is beeing used to calculate the corelations betweens your probeset features and marker features. Marker features are for example genes that you know are important for your condition (e.g., celltypes)."/>
+        <param name="header_markerset" type="select" optional="false" label="Header in the list of markers?">
+            <option value="included">Header included</option>
+            <option value="not_included">Header not included</option>
+        </param>
+    </xml>
+    <xml name="hidden_outputs">
+        <data name="hidden_output" format="txt" label="Log file" >
+            <filter>show_log</filter>
+        </data>
+    </xml>
+</macros>