Mercurial > repos > ebi-gxa > seurat_find_markers

changeset 1:7895b4bb6247 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/ commit 0463f230d18201c740851d72e31a5024f391207f
author ebi-gxa
date Mon, 25 Nov 2019 06:09:57 -0500
parents fde95fe95f15
children 4039a99ae846
files seurat_find_markers.xml seurat_macros.xml
diffstat 2 files changed, 96 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/seurat_find_markers.xml	Wed Apr 03 11:17:29 2019 -0400
+++ b/seurat_find_markers.xml	Mon Nov 25 06:09:57 2019 -0500
@@ -1,4 +1,4 @@
-<tool id="seurat_find_markers" name="Seurat FindMarkers" version="2.3.1+galaxy1">
+<tool id="seurat_find_markers" name="Seurat FindMarkers" version="@SEURAT_VERSION@_@VERSION@+galaxy0">
     <description>find markers (differentially expressed genes)</description>
     <macros>
         <import>seurat_macros.xml</import>
@@ -8,7 +8,7 @@
     <command detect_errors="exit_code"><![CDATA[
 seurat-find-markers.R
 
---input-object-file '$input'
+@INPUT_OBJECT@
 --output-text-file output.txt
 
 #if $genes_use:
@@ -49,7 +49,7 @@
 ]]></command>
 
     <inputs>
-        <param name="input" type="data" format="rdata" label="RDS object" />
+        <expand macro="input_object_params"/>
         <expand macro="genes-use-input"/>
         <param name="logfc_threshold" label="LogFC logfc_threshold" optional="true" argument="--logfc-threshold" type="float" help="Limit testing to genes which show, on average, at least X-fold difference (log-scale) between the two groups of cells. Default is 0.25 Increasing logfc.threshold speeds up the function, but can miss weaker signals."/>
         <param name="max_cells_per_ident" label="Max cells per ident" optional="true" argument="--max-cells-per-ident" type="integer" help="Down sample each identity class to a max number. Default is no downsampling. Not activated by default (set to Inf)."/>
@@ -74,7 +74,7 @@
     </inputs>
 
     <outputs>
-        <data name="output" format="txt" from_work_dir="output.txt" label="${tool.name} on ${on_string}: Text file"/>
+        <data name="output" format="csv" from_work_dir="output.txt" label="${tool.name} on ${on_string}: Text file"/>
     </outputs>
 
     <tests>
@@ -88,12 +88,17 @@
 
 **What it does**
 
-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.
+This tool finds markers (differentially expressed genes) for each of the identity classes in a dataset.
+It outputs a text file containing a ranked list of putative markers, and associated statistics (p-values, ROC score, etc.)
 
-This tool finds markers (differentially expressed genes) for each of the identity classes in a dataset. It outputs a text file containing a ranked list of putative markers, and associated statistics (p-values, ROC score, etc.)
+p-value adjustment is performed using bonferroni correction based on the total
+number of genes in the dataset. Other correction methods are not recommended,
+as Seurat pre-filters genes using the arguments above, reducing the number of
+tests performed. Lastly, as Aaron Lun has pointed out, p-values should be
+interpreted cautiously, as the genes used for clustering are the same genes
+tested for differential expression.
+
+@SEURAT_INTRO@
 
 -----
 
--- a/seurat_macros.xml	Wed Apr 03 11:17:29 2019 -0400
+++ b/seurat_macros.xml	Mon Nov 25 06:09:57 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>