Mercurial > repos > ebi-gxa > seurat_run_tsne

--- a/seurat_macros.xml	Wed Apr 03 11:19:13 2019 -0400
+++ b/seurat_macros.xml	Mon Nov 25 06:11:40 2019 -0500
@@ -1,34 +1,110 @@
 <?xml version="1.0"?>
 <macros>
-
-    <token name="@VERSION@">0.0.5</token>
-
+    <token name="@VERSION@">0.0.6</token>
+    <token name="@SEURAT_VERSION@">3.1.1</token>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@VERSION@">seurat-scripts</requirement>
         </requirements>
     </xml>
-
     <xml name="version">
     	<version_command><![CDATA[
 echo $(R --version | grep version | grep -v GNU)", seurat version" $(R --vanilla --slave -e "library(seurat); cat(sessionInfo()\$otherPkgs\$seurat\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
     ]]></version_command>
     </xml>

+   <xml name="input_object_params">
+     <conditional name="input" label="Input format">
+       <param type="select" name="format" label="Choose the format of the input" help="RData, Loom or AnnData">
+         <option value="rds_seurat" selected="true">RDS with a Seurat object</option>
+         <option value="loom">Loom</option>
+         <option value="anndata">AnnData</option>
+         <option value="rds_sce">RDS with a Single Cell Experiment object</option>
+       </param>
+       <when value="anndata">
+         <param type="data" name="anndata_file" label="AnnData file" help="The AnnData format provided by Scanpy" format="h5,h5ad"/>
+       </when>
+       <when value="loom">
+         <param type="data" name="loom_file" label="Loom file" help="Input as Loom v? file" format="h5,h5loom"/>
+       </when>
+       <when value="rds_seurat">
+         <param type="data" name="rds_seurat_file" label="RDS file" help="Input as RDS file with Seurat 3 object" format="rdata"/>
+       </when>
+       <when value="rds_sce">
+         <param type="data" name="rds_sce_file" label="RDS file" help="Input as RDS file with Single Cell Experiment object" format="rdata"/>
+       </when>
+     </conditional>
+   </xml>
+
+   <token name="@INPUT_OBJECT@">
+    #if $input.format == "anndata"
+        --input-object-file '$input.anndata_file' --input-format anndata
+    #else if $input.format == "loom"
+        --input-object-file '$input.loom_file' --input-format loom
+    #else if $input.format == "rds_seurat"
+        --input-object-file '$input.rds_seurat_file' --input-format seurat
+    #else if $input.format == "rds_sce"
+        --input-object-file '$input.rds_sce_file' --input-format singlecellexperiment
+    #end if
+   </token>
+
+   <xml name="output_object_params">
+     <param type="select" name="format" label="Choose the format of the output" help="Seurat, Single Cell Experiment or Loom">
+       <option value="rds_seurat" selected="true">RDS with a Seurat object</option>
+       <option value="loom">Loom</option>
+       <option value="rds_sce">RDS with a Single Cell Experiment object</option>
+     </param>
+   </xml>
+
+   <xml name="output_files">
+    <data name="loom_file" from_work_dir="seurat_obj.loom" format="h5" label="${tool.name} on ${on_string}: Seurat Loom">
+      <filter>format == 'loom'</filter>
+    </data>
+    <data name="rds_seurat_file" format="rdata" label="${tool.name} on ${on_string}: Seurat RDS">
+      <filter>format == 'rds_seurat'</filter>
+    </data>
+    <data name="rds_sce_file" format="rdata" label="${tool.name} on ${on_string}: Seurat Single Cell Experiment RDS">
+      <filter>format == 'rds_sce'</filter>
+    </data>
+   </xml>
+
+   <token name="@OUTPUT_OBJECT@">
+    #if $format == "anndata"
+        --output-object-file '$anndata_file' --output-format anndata
+    #else if $format == "loom"
+        --output-object-file seurat_obj.loom --output-format loom
+    #else if $format == "rds_seurat"
+        --output-object-file '$rds_seurat_file' --output-format seurat
+    #else if $format == "rds_sce"
+        --output-object-file '$rds_sce_file' --output-format singlecellexperiment
+    #end if
+   </token>
+
     <xml name="genes-use-input">
-      <param name="genes_use" argument="--genes-use" optional="true" type="data" format="tsv, txt" label="Genes to use" help="A file with gene names to use in construction of SNN graph if building directly based on expression data rather than a dimensionally reduced representation (i.e. PCs)."/>
+      <param name="genes_use" argument="--genes-use" optional="true" type="data" format="tsv,txt,tabular" label="Genes to use" help="A file with gene names to use in construction of SNN graph if building directly based on expression data rather than a dimensionally reduced representation (i.e. PCs)."/>
     </xml>
     <xml name="dims-use-input">
       <param name="dims_use" argument="--dims-use" min="1" optional="true" type="integer" label="PCA Dimensions to use" help="Number of PCs (dimensions) to use in construction of the SNN graph."/>
     </xml>

+    <token name="@SEURAT_INTRO@"><![CDATA[
+Seurat_ is a toolkit for quality control, analysis, and exploration of single cell RNA sequencing data.
+It is developed and maintained by the `Satija Lab`_ at NYGC. Seurat aims to enable users to identify and
+interpret sources of heterogeneity from single cell transcriptomic measurements, and to integrate diverse
+types of single cell data.
+      ]]></token>
+
     <token name="@VERSION_HISTORY@"><![CDATA[
 **Version history**

-0.0.1: Initial contribution. Maria Doyle, https://github.com/mblue9.
+3.1.1_0.0.6+galaxy0: Moved to Seurat 3.
+
+  Find clusters: removed dims-use, k-param, prune-snn.

 2.3.1+galaxy0: Improved documentation and further exposition of all script's options. Pablo Moreno, Jonathan Manning and Ni Huang, Expression Atlas team https://www.ebi.ac.uk/gxa/home  at
 EMBL-EBI https://www.ebi.ac.uk/. Parts obtained from wrappers from Christophe Antoniewski(https://github.com/drosofff) and Lea Bellenger(https://github.com/bellenger-l).
+
+0.0.1: Initial contribution. Maria Doyle, https://github.com/mblue9.
       ]]></token>
--- a/seurat_run_tsne.xml	Wed Apr 03 11:19:13 2019 -0400
+++ b/seurat_run_tsne.xml	Mon Nov 25 06:11:40 2019 -0500
@@ -1,4 +1,4 @@
-<tool id="seurat_run_tsne" name="Seurat RunTSNE" version="2.3.1+galaxy1">
+<tool id="seurat_run_tsne" name="Seurat RunTSNE" version="@SEURAT_VERSION@_@VERSION@+galaxy0">
     <description>run t-SNE dimensionality reduction</description>
     <macros>
         <import>seurat_macros.xml</import>
@@ -8,8 +8,7 @@
     <command detect_errors="exit_code"><![CDATA[
 seurat-run-tsne.R

---input-object-file '$input'
-
+@INPUT_OBJECT@
 #if $genes_use:
   --genes-use '$genes_use'
 #end if
@@ -23,29 +22,48 @@
 #if not $adv.do_fast:
     --do-fast '$adv.do_fast'
 #end if
+#if $adv.tsne_method
+  --tsne-method '$adv.tsne_method'
+#end if
+#if $adv.dim_embed
+  --dim_embed '$adv.dim_embed'
+#end if
+#if $adv.random_seed
+  --random-seed '$adv.random_seed'
+#end if

---output-object-file '$output'
+@OUTPUT_OBJECT@
 --output-embeddings-file output_embed
 ]]></command>

     <inputs>
-        <param name="input" argument="--input-obj-file" type="data" format="rdata" label="Seurat RDS object" help="The RDS/Rdata result of Seurat FindClusters."/>
+        <expand macro="input_object_params"/>
+        <expand macro="output_object_params"/>
         <expand macro="genes-use-input"/>
         <section name="adv" title="Advanced Options">
             <expand macro="dims-use-input"/>
             <param name="do_fast" label="Faster execution" argument="--do-fast" checked="true" type="boolean" truevalue="" falsevalue="FALSE" help="If TRUE, uses the Barnes-hut implementation, which runs faster, but is less flexible. TRUE by default."/>
+            <param label="tSNE method" optional="true" name="tsne_method" argument="--tsne-method" type="select" help="Select the method to use to compute the tSNE. Available methods are: Rtsne, Flt-SNE">
+              <option value="Rtsne" selected="true">Rtsne</option>
+              <option value="Flt-SNE">Flt-SNE</option>
+            </param>
+            <param label="tSNE dimensions" optional="true" name="dim_embed" argument="--dim_embed" type="select" help="The dimensional space of the resulting tSNE embedding (default is 2). For example, set to 3 for a 3d tSNE">
+              <option value="2" selected="true">2</option>
+              <option value="3">3</option>
+            </param>
+            <param label="Random seed" optional="true" name="random_seed" argument="--random-seed" type="integer" help="Seed of the random number generator"/>
         </section>
     </inputs>

     <outputs>
-        <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/>
+        <expand macro="output_files"/>
         <data name="output_embed" format="csv" from_work_dir="output_embed" label="${tool.name} on ${on_string}: Seurat Embeddings"/>
     </outputs>

     <tests>
         <test>
             <param name="input" ftype="rdata" value="out_findclust.rds"/>
-            <output name="output" ftype="rdata" value="out_runtsne.rds" compare="sim_size"/>
+            <output name="rds_seurat_file" ftype="rdata" value="out_runtsne.rds" compare="sim_size"/>
         </test>
     </tests>
     <help><![CDATA[
@@ -58,10 +76,9 @@
 interpret sources of heterogeneity from single cell transcriptomic measurements, and to integrate diverse
 types of single cell data.

-Run t-SNE dimensionality reduction on selected features. Has the option of
-running in a reduced dimensional space (i.e. spectral tSNE, recommended),
-or running based on a set of genes. For details about stored TSNE calculation
-parameters, see standard output of the tool.
+Run t-SNE dimensionality reduction on selected features. Has the option of running
+in a reduced dimensional space (i.e. spectral tSNE, recommended), or
+running based on a set of genes.

 -----