Mercurial > repos > ebi-gxa > scanpy_integrate_harmony

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy-integrate-harmony.xml	Mon Sep 07 13:10:56 2020 +0000
@@ -0,0 +1,134 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tool id="scanpy_integrate_harmony" name="Scanpy Harmony" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
+  <description>adjust principal components for variables that might introduce batch effect</description>
+  <macros>
+    <import>scanpy_macros2.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <command detect_errors="exit_code"><![CDATA[
+#if $batch_key
+  ln -s '${input_obj_file}' input.h5 &&
+  PYTHONIOENCODING=utf-8 scanpy-integrate harmony
+  --batch-key '${batch_key}'
+  #if $basis
+    --basis '${basis}'
+  #end if
+  --adjusted-basis '${adjusted_basis}'
+  #if not $settings.default
+      #if $settings.theta
+      --theta '${settings.theta}'
+      #end if
+      #if $settings.lambda
+      --lambda '${settings.lambda}'
+      #end if
+      #if $settings.sigma
+      --sigma '${settings.sigma}'
+      #end if
+      #if $settings.nclust
+      --nclust '${settings.nclust}'
+      #end if
+      #if $settings.tau
+      --tau '${settings.tau}'
+      #end if
+      #if $settings.block_size
+      --block-size '${settings.block_size}'
+      #end if
+      #if $settings.max_iter_cluster
+      --max-iter-cluster '${settings.max_iter_cluster}'
+      #end if
+      #if $settings.max_iter_harmony
+      --max-iter-harmony '${settings.max_iter_harmony}'
+      #end if
+      #if $settings.epsilon_cluster
+      --epsilon-cluster '${settings.epsilon_cluster}'
+      #end if
+      #if $settings.epsilon_harmony
+      --epsilon-harmony '${settings.epsilon_harmony}'
+      #end if
+      #if $settings.random_state
+      --random-state '${settings.random_state}'
+      #end if
+  #end if
+  @INPUT_OPTS@
+  @OUTPUT_OPTS@
+#else
+  echo "No batch variables passed, simply passing original input as output unchanged.";
+  cp '${input_obj_file}' '${output_h5}'
+#end if
+]]></command>
+
+  <inputs>
+    <expand macro="input_object_params"/>
+    <expand macro="output_object_params"/>
+    <param name="batch_key" type="text" argument="--batch-key" label="The name of the column in adata.obs that differentiates among experiments/batches.">
+      <sanitizer>
+        <valid initial="string.printable"/>
+      </sanitizer>
+    </param>
+    <param name="basis" argument="--basis" type="text" value='X_pca' label="The name of the field in adata.obsm where the PCA table is stored. Defaults to 'X_pca', which is the default for sc.tl.pca().">
+      <sanitizer>
+        <valid initial="string.printable"/>
+      </sanitizer>
+    </param>
+    <param name="adjusted_basis" argument="--adjusted-basis" type="text" value='X_pca_harmony' label="he name of the field in adata.obsm where the adjusted PCA table will be stored after running this function.">
+      <sanitizer>
+        <valid initial="string.printable"/>
+      </sanitizer>
+    </param>
+    <conditional name="settings">
+      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
+      <when value="true"/>
+      <when value="false">
+        <param name="theta" argument="--theta" type="float" value="2.0"
+              label="Diversity clustering penalty parameter" help="theta=0 does not encourage any diversity. Larger values of theta result in more diverse clusters." />
+        <param name="lambda" argument="--lambda" type="float" min="0" value="1.0"
+              label="Ridge regression penalty parameter" help="Lambda must be strictly positive. Smaller values result in more aggressive correction." />
+        <param name="sigma" argument="--sigma" type="float" value="0.1"
+              label="Ridge regression penalty parameter" help="Width of soft kmeans clusters. Sigma scales the distance from a cell to cluster centroids. Larger values of sigma result in cells assigned to more clusters. Smaller values of sigma make soft kmeans cluster approach hard clustering." />
+        <param name="nclust" argument="--nclust" type="integer" value="" optional="true"
+              label="Number of clusters in model." help="nclust=1 equivalent to simple linear regression." />
+        <param name="tau" argument="--tau" type="integer" value="0"
+              label="Protection against overclustering small datasets with large ones." help="'tau is the expected number of cells per cluster." />
+        <param name="block_size" argument="--block-size" type="float" value="0.05"
+              label="What proportion of cells to update during clustering" min="0" max="1" help="Between 0 to 1, default 0.05. Larger values may be faster but less accurate." />
+        <param name="max_iter_cluster" argument="--max-iter-cluster" type="integer" value="20"
+              label="Maximum number of rounds to run clustering at each round of Harmony" />
+        <param name="max_iter_harmony" argument="--max-iter-harmony" type="integer" value="10"
+              label="Maximum number of rounds to run Harmony. One round of Harmony involves one clustering and one correction step." />
+        <param name="epsilon_cluster" argument="--epsilon-cluster" type="float" value="0.00001"
+              label="Convergence tolerance for clustering round of Harmony" help="Set to -Inf to never stop early." />
+        <param name="epsilon_harmony" argument="--epsilon-harmony" type="float" value="0.00001"
+              label="Convergence tolerance for Harmony." help="Set to -Inf to never stop early." />
+        <param name="random_state" argument="--random-state" type="integer" value="0"
+              label="Seed for random number generator." />
+      </when>
+    </conditional>
+  </inputs>
+
+  <outputs>
+    <expand macro="output_data_obj" description="Batch-corrected for ${batch_key}"/>
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="input_obj_file" value="find_cluster.h5"/>
+      <param name="input_format" value="anndata"/>
+      <param name="output_format" value="anndata"/>
+      <param name="batch_key" value="louvain"/>
+      <output name="output_h5" file="harmony.h5" ftype="h5" compare="sim_size"/>
+    </test>
+  </tests>
+
+  <help><![CDATA[
+    .. class:: infomark
+
+    **What it does**
+
+    Uses harmonypy [Korunsky19] to integrate different experiments at the principal components level.
+
+    @HELP@
+
+    @VERSION_HISTORY@
+]]></help>
+  <expand macro="citations"/>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros.xml	Mon Sep 07 13:10:56 2020 +0000
@@ -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 ${on_string}: 10x barcodes">
+      <filter>export_mtx</filter>
+    </data>
+  </xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scanpy_macros2.xml	Mon Sep 07 13:10:56 2020 +0000
@@ -0,0 +1,146 @@
+<macros>
+  <token name="@TOOL_VERSION@">1.6.0</token>
+  <token name="@HELP@">More information can be found at https://scanpy.readthedocs.io</token>
+  <token name="@PROFILE@">18.01</token>
+  <token name="@VERSION_HISTORY@"><![CDATA[
+**Version history**
+
+1.6.0+galaxy0: Update to scanpy-scripts 0.2.13 (running scanpy ==1.6.0) to incorporate new options, code simplifications, and batch integration methods. Jonathan Manning, Expression Atlas team https://www.ebi.ac.uk/gxa/home  at
+EMBL-EBI https://www.ebi.ac.uk/
+
+1.4.3+galaxy10: Update to scanpy-scripts 0.2.10 (running scanpy ==1.4.3) to address bugfixes in run-pca.
+
+1.4.3+galaxy10: Update to scanpy-scripts 0.2.9 (running scanpy ==1.4.3) to address bugfixes in find-variable-genes.
+
+1.4.3+galaxy10: Use profile 18.01 for modules.
+
+1.4.3+galaxy6: Update to scanpy-scripts 0.2.8 (running scanpy ==1.4.3) and wider compatibility with other Galaxy modules. Bug fixes in filtering and plotting improvements.
+
+1.4.3+galaxy0: Update to scanpy-scripts 0.2.5 (running scanpy ==1.4.3).
+
+1.4.2+galaxy0: Update to scanpy-scripts 0.2.4 (requires scanpy >=1.4.2).
+
+1.3.2+galaxy1: Normalise-data and filter-genes: Exposes ability to output 10x files.
+
+1.3.2+galaxy0: Initial contribution. Ni Huang and Pablo Moreno, Expression Atlas team https://www.ebi.ac.uk/gxa/home  at
+EMBL-EBI https://www.ebi.ac.uk/ and Teichmann Lab at Wellcome Sanger Institute.
+    ]]></token>
+  <token name="@INPUT_OPTS@">
+    --input-format '${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="0.3.0">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>
+      <citation type="doi">10.1101/2020.04.08.032698</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>