changeset 0:df80f3d2f9d4 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 9bf9a6e46a330890be932f60d1d996dd166426c4
author ebi-gxa
date Wed, 03 Apr 2019 11:15:42 -0400
parents
children c4607a42113e
files README seurat_macros.xml seurat_run_pca.xml
diffstat 3 files changed, 135 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README	Wed Apr 03 11:15:42 2019 -0400
@@ -0,0 +1,1 @@
+Seurat tools
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/seurat_macros.xml	Wed Apr 03 11:15:42 2019 -0400
@@ -0,0 +1,50 @@
+<?xml version="1.0"?>
+<macros>
+
+    <token name="@VERSION@">0.0.5</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="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)."/>
+    </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="@VERSION_HISTORY@"><![CDATA[
+**Version history**
+
+0.0.1: Initial contribution. Maria Doyle, https://github.com/mblue9.
+
+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).
+      ]]></token>
+
+
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1038/nbt.4096</citation>
+            <citation type="bibtex">
+              @misc{r-seurat-scripts.git,
+              author = {Jonathan Manning, Pablo Moreno, EBI Gene Expression Team},
+              year = {2018},
+              title = {Seurat-scripts: command line interface for Seurat},
+              publisher = {GitHub},
+              journal = {GitHub repository},
+              url = {https://github.com/ebi-gene-expression-group/r-seurat-scripts.git},
+            }
+            </citation>
+        </citations>
+    </xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/seurat_run_pca.xml	Wed Apr 03 11:15:42 2019 -0400
@@ -0,0 +1,84 @@
+<tool id="seurat_run_pca" name="Seurat RunPCA" version="2.3.1+galaxy1">
+    <description>run a PCA dimensionality reduction</description>
+    <macros>
+        <import>seurat_macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <expand macro="version" />
+    <command detect_errors="exit_code"><![CDATA[
+seurat-run-pca.R
+
+--input-object-file '$input'
+#if $pc_genes:
+    --pc-genes '$pc-genes'
+#end if
+--output-object-file '$output'
+--output-embeddings-file output_embed
+--output-loadings-file output_load
+--output-stdev-file output_sdev
+#if $pcs_compute:
+    --pcs-compute '$pcs_compute'
+#end if
+#if $use_imputed:
+'$use_imputed'
+#end if
+
+]]></command>
+
+    <inputs>
+        <param name="input" type="data" format="rdata" label="RDS object" />
+        <param name="pc_genes" type="data" format="tabular, txt" optional="True" label="Genes to scale" help="File of gene names to scale/center. Default is all genes in object." />
+        <param name="pcs_compute" type="integer" optional="True" label="Principal components" help="Total Number of PCs to compute and store (20 by default). Less PCs might be faster, but will explain less variance."/>
+        <param name="use_imputed" type="boolean" truevalue="--use-imputed TRUE" falsevalue="" checked="false" label="Use imputed" help="Run PCA on imputed values."/>
+    </inputs>
+
+    <outputs>
+        <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/>
+        <data name="output_embed" format="csv" from_work_dir="output_embed" label="${tool.name} on ${on_string}: Seurat Embeddings"/>
+        <data name="output_load" format="csv" from_work_dir="output_load" label="${tool.name} on ${on_string}: Seurat Loadings"/>
+        <data name="output_sdev" format="csv" from_work_dir="output_sdev" label="${tool.name} on ${on_string}: Seurat Std dev"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="input" ftype="rdata" value="out_scale.rds"/>
+            <output name="output" ftype="rdata" value="out_runpca.rds" compare="sim_size"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+.. class:: infomark
+
+**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 runs a PCA dimensionality reduction
+
+-----
+
+**Inputs**
+
+    * Seurat RDS object, normalised and scaled potentially.
+    * Genes used to scale. File of gene names to scale/center. Default is all genes in object.
+    * Principal components to compute. Total Number of PCs to compute and store (20 by default). Less PCs might be faster, but will explain less variance.
+    * Use imputed. Boolean indicating whether to run PCA on imputed values or not.
+
+-----
+
+**Outputs**
+
+    * Seurat RDS object with PCA calculations and embeddings.
+    * Embeddings on CSV file. File with a csv-format embeddings table with principal components by cell.
+    * Loadings on CSV file. File with a csv-format loadings table with principal components by gene.
+    * Standard deviation on CSV file. Contains principal components std. deviations.
+
+.. _Seurat: https://www.nature.com/articles/nbt.4096
+.. _Satija Lab: https://satijalab.org/seurat/
+
+@VERSION_HISTORY@
+]]></help>
+      <expand macro="citations" />
+</tool>