Mercurial > repos > ebi-gxa > seurat_find_variable_genes

changeset 1:a6077346f869 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 06:10:14 -0500
parents a56efad05337
children 8f67188f11c4
files seurat_find_variable_genes.xml seurat_macros.xml
diffstat 2 files changed, 110 insertions(+), 28 deletions(-) [+]
line wrap: on
line diff
--- a/seurat_find_variable_genes.xml	Wed Apr 03 11:17:53 2019 -0400
+++ b/seurat_find_variable_genes.xml	Mon Nov 25 06:10:14 2019 -0500
@@ -1,4 +1,4 @@
-<tool id="seurat_find_variable_genes" name="Seurat FindVariableGenes" version="2.3.1+galaxy1">
+<tool id="seurat_find_variable_genes" name="Seurat FindVariableGenes" version="@SEURAT_VERSION@_@VERSION@+galaxy0">
     <description>identify variable genes</description>
     <macros>
         <import>seurat_macros.xml</import>
@@ -8,10 +8,13 @@
     <command detect_errors="exit_code"><![CDATA[
 seurat-find-variable-genes.R
 
---input-object-file '$input'
+@INPUT_OBJECT@
 #if $mean:
     --mean-function '$mean'
 #end if
+#if $selection_method
+  --selection-method '$selection_method'
+#end if
 #if $disp:
 --dispersion-function $disp
 #end if
@@ -27,29 +30,36 @@
 #if $yhigh:
 --y-high-cutoff $yhigh
 #end if
---output-object-file '$output'
+@OUTPUT_OBJECT@
 --output-text-file '$output_tab'
 ]]></command>
 
     <inputs>
-        <param name="input" argument="--input-object-file" type="data" format="rdata" label="Seurat RDS object" help="R serialized object for Seurat, normally the one produced by Seurat FindVariableGenes" />
+        <expand macro="input_object_params"/>
+        <expand macro="output_object_params"/>
+        <param label="Number of features" optional="true" name="nfeatures" argument="--nfeatures" type="integer" help="Number of features to return."/>
         <param name="mean" argument="--mean-function" type="text" optional="True" label="Mean function" help="Function to compute x-axis value (average expression). Default is to take the mean of the detected (i.e. non-zero) values."/>
         <param name="disp" argument="--dispersion-function" type="text" optional="True" label="Dispersion function" help="Function to compute y-axis value (dispersion). Default is to take the standard deviation of all values." />
-        <param name="xlow" argument="--x-low-cutoff" type="float" optional="True" label="X-axis low cutoff" help="Bottom cutoff on x-axis for identifying variable genes."/>
-        <param name="xhigh" argument="--x-high-cutoff" type="float" optional="True" label="X-axis high cutoff" help="Top cutoff on x-axis for identifying variable genes."/>
-        <param name="ylow" argument="--y-low-cutoff" type="float" optional="True" label="Y-axis low cutoff" help="Bottom cutoff on y-axis for identifying variable genes."/>
-        <param name="yhigh" argument="--y-high-cutoff" type="float" optional="True" label="Y-axis high cutoff" help="Top cutoff on y-axis for identifying variable genes."/>
+        <param name="xlow" argument="--x-low-cutoff" type="float" optional="True" label="X-axis low cutoff" help="Bottom cutoff on x-axis (mean) for identifying variable genes."/>
+        <param name="xhigh" argument="--x-high-cutoff" type="float" optional="True" label="X-axis high cutoff" help="Top cutoff on x-axis (mean) for identifying variable genes."/>
+        <param name="ylow" argument="--y-low-cutoff" type="float" optional="True" label="Y-axis low cutoff" help="Bottom cutoff on y-axis (dispersion) for identifying variable genes."/>
+        <param name="yhigh" argument="--y-high-cutoff" type="float" optional="True" label="Y-axis high cutoff" help="Top cutoff on y-axis (dispersion) for identifying variable genes."/>
+        <param label="Selection method" optional="true" name="selection_method" argument="--selection-method" type="select" help="How to choose top variable features. Choose one of: 'vst', 'mvp', disp.">
+          <option value="vst" selected="true">vst</option>
+          <option value="mbp">mbp</option>
+          <option value="disp">disp</option>
+        </param>
     </inputs>
 
     <outputs>
-        <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/>
+        <expand macro="output_files"/>
         <data name="output_tab" format="tabular" from_work_dir="*.tab" label="${tool.name} on ${on_string}: Variable genes tabular file"/>
     </outputs>
 
     <tests>
         <test>
             <param name="input" ftype="rdata" value="out_norm.rds"/>
-            <output name="output" ftype="rdata" value="out_findvar.rds" compare="sim_size"/>
+            <output name="rds_seurat_file" ftype="rdata" value="out_findvar.rds" compare="sim_size"/>
         </test>
     </tests>
     <help><![CDATA[
@@ -57,11 +67,6 @@
 
 **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 identifies genes that are outliers on a 'mean variability plot'. First, uses
 a function to calculate average expression (mean.function) and dispersion (dispersion.function)
 for each gene. Next, divides genes into num.bin (deafult 20) bins based on
@@ -69,14 +74,15 @@
 bin. The purpose of this is to identify variable genes while controlling for
 the strong relationship between variability and average expression.
 
-Exact parameter settings may vary empirically from dataset to dataset, and
-based on visual inspection of the plot.
+For the mean.var.plot method: Exact parameter settings may vary empirically from
+dataset to dataset, and based on visual inspection of the plot. Setting the
+y.cutoff parameter to 2 identifies features that are more than two standard deviations
+away from the average dispersion within a bin. The default X-axis function is the
+mean expression level, and for Y-axis it is the log(Variance/mean). All
+mean/variance calculations are not performed in log-space, but the results are
+reported in log-space - see relevant functions for exact details.
 
-Setting the y.cutoff parameter to 2 identifies genes that are more than two standard
-deviations away from the average dispersion within a bin. The default X-axis function
-is the mean expression level, and for Y-axis it is the log(Variance/mean). All mean/variance
-calculations are not performed in log-space, but the results are reported in log-space -
-see relevant functions for exact details.
+@SEURAT_INTRO@
 
 -----
 
--- a/seurat_macros.xml	Wed Apr 03 11:17:53 2019 -0400
+++ b/seurat_macros.xml	Mon Nov 25 06:10:14 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>