Repository 'scanpy_filter_cells'
hg clone https://toolshed.g2.bx.psu.edu/repos/ebi-gxa/scanpy_filter_cells

Changeset 0:9f0ca1641ab2 (2019-04-03)
Next changeset 1:dcfb23758646 (2019-09-16)
Commit message:
planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 9bf9a6e46a330890be932f60d1d996dd166426c4
added:
scanpy-filter-cells.xml
scanpy_macros.xml
b
diff -r 000000000000 -r 9f0ca1641ab2 scanpy-filter-cells.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy-filter-cells.xml Wed Apr 03 11:12:31 2019 -0400
[
@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tool id="scanpy_filter_cells" name="Scanpy FilterCells" version="@TOOL_VERSION@+galaxy0">
+  <description>based on counts and numbers of genes expressed</description>
+  <macros>
+    <import>scanpy_macros.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <command detect_errors="exit_code"><![CDATA[
+ln -s '${input_obj_file}' input.h5 &&
+PYTHONIOENCODING=utf-8 scanpy-filter-cells.py
+    -i input.h5
+    -f '${input_format}'
+    -o output.h5
+    -F '${output_format}'
+    #if $parameters
+        #set pars = ','.join([str($p['name']) for $p in $parameters])
+        -p '${pars}'
+        #set mins = ','.join([str($p['min']) for $p in $parameters])
+        -l '${mins}'
+        #set maxs = ','.join([str($p['max']) for $p in $parameters])
+        -j '${maxs}'
+    #end if
+    #if $subset
+        -s '${subset}'
+    #end if
+    ]]></command>
+
+  <inputs>
+    <expand macro="input_object_params"/>
+    <expand macro="output_object_params"/>
+    <repeat name="parameters" title="Parameters used to filter cells" min="1">
+      <param name="name" type="text" value="n_genes" label="Name of parameter to filter on" help="for example n_genes or n_counts">
+        <option value="n_genes">n_genes</option>
+        <option value="n_counts">n_counts</option>
+      </param>
+      <param name="min" type="float" value="0" min="0" label="Min value"/>
+      <param name="max" type="float" value="1e9" label="Max value"/>
+    </repeat>
+    <param name="subset" argument="--subset-list" type="data" format="tsv" optional="true" label="List of barcodes"/>
+  </inputs>
+
+  <outputs>
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: Filtered cells"/>
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="input_obj_file" value="read_10x.h5"/>
+      <param name="input_format" value="anndata"/>
+      <param name="output_format" value="anndata"/>
+      <repeat name="parameters">
+        <param name="name" value="n_genes"/>
+        <param name="min" value="200"/>
+        <param name="max" value="2500"/>
+      </repeat>
+      <repeat name="parameters">
+        <param name="name" value="n_counts"/>
+        <param name="min" value="0"/>
+        <param name="max" value="1e9"/>
+      </repeat>
+      <output name="output_h5" file="filter_cells.h5" ftype="h5" compare="sim_size"/>
+    </test>
+  </tests>
+
+  <help><![CDATA[
+========================================================================================
+Filter cells outliers based on counts and numbers of genes expressed (`pp.filter_cells`)
+========================================================================================
+
+For instance, only keep cells with at least `min_counts` counts or
+`min_genes` genes expressed. This is to filter measurement outliers, i.e.,
+"unreliable" observations.
+
+@HELP@
+
+@VERSION_HISTORY@
+]]></help>
+  <expand macro="citations"/>
+</tool>
b
diff -r 000000000000 -r 9f0ca1641ab2 scanpy_macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros.xml Wed Apr 03 11:12:31 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>