Mercurial > repos > ebi-gxa > scanpy_read_10x

changeset 1:4af2017cbece 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 ba0c88ab1b077a0b1c60c8d3c529e72ca6946226"
author ebi-gxa
date Thu, 12 Mar 2020 09:13:10 +0000
parents c5e166a64abb
children b2c4f3eabcf1
files scanpy-read-10x.xml scanpy_macros.xml scanpy_macros2.xml
diffstat 3 files changed, 187 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/scanpy-read-10x.xml	Wed Mar 13 11:51:27 2019 -0400
+++ b/scanpy-read-10x.xml	Thu Mar 12 09:13:10 2020 +0000
@@ -1,34 +1,43 @@
 <?xml version="1.0" encoding="utf-8"?>
-<tool id="scanpy_read_10x" name="Scanpy Read10x" version="@TOOL_VERSION@+galaxy0">
+<tool id="scanpy_read_10x" name="Scanpy Read10x" version="@TOOL_VERSION@+galaxy10" profile="@PROFILE@">
   <description>into hdf5 object handled by scanpy</description>
   <macros>
-    <import>scanpy_macros.xml</import>
+    <import>scanpy_macros2.xml</import>
   </macros>
   <expand macro="requirements"/>
   <command detect_errors="exit_code"><![CDATA[
 ln -s '${matrix}' matrix.mtx &&
 ln -s '${genes}' genes.tsv &&
 ln -s '${barcodes}' barcodes.tsv &&
-PYTHONIOENCODING=utf-8 scanpy-read-10x.py
-    -d ./
-    -o read_10x.h5
-    -F '${output_format}'
-    -v '${var_names}'
+PYTHONIOENCODING=utf-8 scanpy-read-10x
+    --input-10x-mtx ./
+    --var-names '${var_names}'
+#if $cell_meta:
+    --extra-obs '${cell_meta}'
+#end if
+#if $gene_meta:
+    --extra-var '${gene_meta}'
+#end if
+    @OUTPUT_OPTS@
 ]]></command>
 
   <inputs>
     <param name="matrix" type="data" format="txt" label="Expression matrix in sparse matrix format (.mtx)"/>
     <param name="genes" type="data" format="tsv,tabular" label="Gene table"/>
     <param name="barcodes" type="data" format="tsv,tabular" label="Barcode/cell table"/>
+    <param name="cell_meta" type="data" format="tsv,tabular" label="Cell metadata table" optional="true"
+           help="Requires a header row and index column that matches the barcode/cell table"/>
+    <param name="gene_meta" type="data" format="tsv,tabular" label="Gene metadata table" optional="true"
+           help="Requires a header row and index column that matches the gene table"/>
     <expand macro="output_object_params"/>
-    <param name="var_names" type="select" label="Attribute used as annotation index">
+    <param name="var_names" type="select" label="Attribute used as annotation index" help="If Gene ID is selected the index will point to the gene identifiers (first columns expected) and the gene symbols will be left in a field called 'gene_symbols'.">
       <option value="gene_ids" selected="true">Gene ID</option>
       <option value="gene_symbols">Gene symbol</option>
     </param>
   </inputs>
 
   <outputs>
-    <data name="output_h5" format="h5" from_work_dir="read_10x.h5" label="${tool.name} on ${on_string}: ${output_format}"/>
+    <expand macro="output_data_obj" description="${output_format}"/>
   </outputs>
 
   <tests>
@@ -36,15 +45,16 @@
       <param name="matrix" value="matrix.mtx"/>
       <param name="genes" value="genes.tsv"/>
       <param name="barcodes" value="barcodes.tsv"/>
+      <!-- <param name="cell_meta" value=""/> -->
       <param name="output_format" value="anndata"/>
-      <output name="output_h5" file="read_10x.h5" ftype="h5" compare="sim_size"/>
+      <output name="output_h5" file="output.h5" ftype="h5" compare="sim_size"/>
     </test>
   </tests>
 
   <help><![CDATA[
-==========================================================
-Read 10x-Genomics-formatted mtx directory (`read_10x_mtx`)
-==========================================================
+=================================================================
+Read 10x-Genomics-formatted mtx directory (`scanpy.read_10x_mtx`)
+=================================================================
 
 The mtx directory should contain:
 
@@ -54,8 +64,9 @@
 
 3) A barcode/cell table of at least one column giving the barcode/cell IDs.
 
-The above-mentioned files can be obtained by running `EBI SCXA Data Retrieval`
-with a dataset accession.
+The above-mentioned files can be obtained by running `EBI SCXA Data Retrieval` with a dataset accession or `Human Cell Atlas Matrix Downloader` with a project name/label/UUID.
+
+Additionally, cell and/or gene metadata table can be provided as tab-separated text with a header row and an index column that matches the respective barcode/cell and/or gene table.
 
 
 @HELP@
--- a/scanpy_macros.xml	Wed Mar 13 11:51:27 2019 -0400
+++ b/scanpy_macros.xml	Thu Mar 12 09:13:10 2020 +0000
@@ -38,9 +38,14 @@
       <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>
@@ -87,4 +92,18 @@
     <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 ${on_string}: 10x barcodes">
+      <filter>export_mtx</filter>
+    </data>
+  </xml>
 </macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Thu Mar 12 09:13:10 2020 +0000
@@ -0,0 +1,142 @@
+<macros>
+  <token name="@TOOL_VERSION@">1.4.3</token>
+  <token name="@HELP@">More information can be found at https://scanpy.readthedocs.io</token>
+  <token name="@PROFILE@">18.01</token>
+  <token name="@VERSION_HISTORY@"><![CDATA[
+**Version history**
+
+1.4.3+galaxy10: Update to scanpy-scripts 0.2.10 (running scanpy ==1.4.3) to address bugfixes in run-pca.
+
+1.4.3+galaxy10: Update to scanpy-scripts 0.2.9 (running scanpy ==1.4.3) to address bugfixes in find-variable-genes.
+
+1.4.3+galaxy10: Use profile 18.01 for modules.
+
+1.4.3+galaxy6: Update to scanpy-scripts 0.2.8 (running scanpy ==1.4.3) and wider compatibility with other Galaxy modules. Bug fixes in filtering and plotting improvements.
+
+1.4.3+galaxy0: Update to scanpy-scripts 0.2.5 (running scanpy ==1.4.3).
+
+1.4.2+galaxy0: Update to scanpy-scripts 0.2.4 (requires scanpy >=1.4.2).
+
+1.3.2+galaxy1: Normalise-data and filter-genes: Exposes ability to output 10x files.
+
+1.3.2+galaxy0: Initial contribution. Ni Huang and Pablo Moreno, Expression Atlas team https://www.ebi.ac.uk/gxa/home  at
+EMBL-EBI https://www.ebi.ac.uk/ and Teichmann Lab at Wellcome Sanger Institute.
+    ]]></token>
+  <token name="@INPUT_OPTS@">
+    --input-format '${input_format}' input.h5
+  </token>
+  <token name="@OUTPUT_OPTS@">
+#if str($output_format).startswith('anndata')
+    --show-obj stdout --output-format anndata output.h5
+#else
+    --show-obj stdout --output-format loom output.h5
+#end if
+  </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="0.2.10">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,h5ad" label="Input object in AnnData/Loom 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_h5ad" selected="true">AnnData format</option>
+      <option value="anndata">AnnData format (h5 for older versions)</option>
+      <option value="loom">Loom format</option>
+      <option value="loom_legacy">Loom format (h5 for older versions)</option>
+    </param>
+  </xml>
+
+  <xml name="output_object_params_no_loom">
+    <param name="output_format" argument="--output-format" type="select" label="Format of output object">
+      <option value="anndata_h5ad" selected="true">AnnData format</option>
+      <option value="anndata">AnnData format (h5 for older versions)</option>
+    </param>
+  </xml>
+
+  <xml name="output_data_obj_no_loom" token_description="operation">
+    <data name="output_h5ad" format="h5ad" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData">
+      <filter>output_format == 'anndata_h5ad'</filter>
+    </data>
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData">
+      <filter>output_format == 'anndata'</filter>
+    </data>
+  </xml>
+
+  <xml name="output_data_obj" token_description="operation">
+    <data name="output_h5ad" format="h5ad" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData">
+      <filter>output_format == 'anndata_h5ad'</filter>
+    </data>
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData">
+      <filter>output_format == 'anndata'</filter>
+    </data>
+    <data name="output_loom_legacy" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ Loom">
+      <filter>output_format == 'loom_legacy'</filter>
+    </data>
+    <data name="output_loom" format="loom" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ Loom">
+      <filter>output_format == 'loom'</filter>
+    </data>
+  </xml>
+
+  <xml name="output_plot_params">
+    <param name="fig_title" argument="--title" type="text" label="Figure title"/>
+    <param name="fig_size" argument="--fig-size" type="text" value="4,4" label="Figure size as 'width,height', e.g, '7,7'"/>
+    <param name="fig_dpi" argument="--fig-dpi" type="integer" min="1" value="80" label="Figure dpi"/>
+    <param name="fig_fontsize" argument="--fig-fontsize" type="integer" min="0" value="10" label="Figure font size"/>
+    <param name="fig_frame" type="boolean" truevalue="--frameon" falsevalue="--frameoff" checked="false"
+           label="Show plot frame"/>
+  </xml>
+
+  <xml name="export_mtx_params">
+    <param name="export_mtx" argument="--export-mtx" type="boolean" truevalue="--export-mtx ./" falsevalue="" checked="false" label="Save to 10x mtx format" help="If enabled, it will generate in addition to the main output in Loom or AnnData an export in 10x format."/>
+  </xml>
+
+  <xml name="export_mtx_outputs">
+    <data name="matrix_10x" format="txt" from_work_dir="matrix.mtx" label="${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>