Mercurial > repos > ebi-gxa > seurat_read10x

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README	Wed Apr 03 11:18:21 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 11:18:21 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_read10x.xml	Wed Apr 03 11:18:21 2019 -0400
@@ -0,0 +1,75 @@
+<tool id="seurat_read10x" name="Seurat Read10x" version="2.3.1+galaxy1">
+<description>Loads 10x data into a serialized seurat R object</description>
+  <macros>
+      <import>seurat_macros.xml</import>
+  </macros>
+  <expand macro="requirements" />
+<stdio>
+<exit_code range="1:" />
+</stdio>
+<command><![CDATA[
+ln -s "$matrix" matrix.mtx;
+ln -s "$genes" genes.tsv;
+ln -s "$barcodes" barcodes.tsv;
+
+seurat-read-10x.R -d ./ -o "$R_seurat_serialized"
+]]></command>
+<inputs>
+    <param type="data" name="matrix" help="Raw expression quantification as a sparse matrix in Matrix Market format, where each column is a gene and each row is a barcode/cell." format="txt" label="Expression matrix in sparse matrix format (.mtx)" />
+    <param type="data" name="genes" help="Matrix market column file for genes" label="Gene table" format="tsv,tabular"/>
+    <param type="data" name="barcodes" help="Matrix market row file for genes" label="Barcode/cell table" format="tsv,tabular"/>
+</inputs>
+<outputs>
+    <data name="R_seurat_serialized" format="rdata" label="${tool.name} on ${on_string}: RData file" />
+</outputs>
+
+<tests>
+    <test>
+       <param name="matrix" ftype="txt" value="test_matrix.txt"/>
+       <param name="genes" ftype="txt" value="test_genes.txt"/>
+       <param name="barcodes" ftype="txt" value="test_barcodes.txt"/>
+       <output name="R_seurat_serialized" ftype="rdata" value="out_scale.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. See the `Seurat Guided Clustering tutorial`_ for more information.
+
+  **Read 10x-Genomics-formatted mtx directory (`read_10x_mtx`)**
+
+  The mtx directory should contain:
+
+  1) Raw expression quantification as a sparse matrix in Matrix Market format, where the each column is a gene and each row is a barcode/cell.
+
+  2) A gene table of at least two columns where the first column gives the gene IDs.
+
+  3) A barcode/cell table of at least one column giving the barcode/cell IDs.
+
+  The above-mentioned files can be obtained by running `EBI SCXA Data Retrieval`
+  with a dataset accession. Otherwise, they need to be provided as separate Galaxy
+  datasets.
+
+  **Inputs**
+      * Raw expression quantification as a sparse matrix in Matrix Market format, where the each column is a gene and each row is a barcode/cell.
+      * A gene table of at least two columns where the first column gives the gene IDs.
+      * A barcode/cell table of at least one column giving the barcode/cell IDs.
+
+  **Outputs**
+      * R object for Seurat
+
+  .. _Seurat: https://www.nature.com/articles/nbt.4096
+  .. _Satija Lab: https://satijalab.org/seurat/
+  .. _Seurat Guided Clustering tutorial: https://satijalab.org/seurat/pbmc3k_tutorial.html
+
+@VERSION_HISTORY@
+]]></help>
+<expand macro="citations"/>
+</tool>