Mercurial > repos > ebi-gxa > seurat_run_pca
changeset 1:c4607a42113e draft
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 06:08:09 -0500 |
parents | df80f3d2f9d4 |
children | e534a73143b1 |
files | seurat_macros.xml seurat_run_pca.xml |
diffstat | 2 files changed, 100 insertions(+), 22 deletions(-) [+] |
line wrap: on
line diff
--- a/seurat_macros.xml Wed Apr 03 11:15:42 2019 -0400 +++ b/seurat_macros.xml Mon Nov 25 06:08:09 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_pca.xml Wed Apr 03 11:15:42 2019 -0400 +++ b/seurat_run_pca.xml Mon Nov 25 06:08:09 2019 -0500 @@ -1,4 +1,4 @@ -<tool id="seurat_run_pca" name="Seurat RunPCA" version="2.3.1+galaxy1"> +<tool id="seurat_run_pca" name="Seurat RunPCA" version="@SEURAT_VERSION@_@VERSION@+galaxy0"> <description>run a PCA dimensionality reduction</description> <macros> <import>seurat_macros.xml</import> @@ -8,32 +8,37 @@ <command detect_errors="exit_code"><![CDATA[ seurat-run-pca.R ---input-object-file '$input' +@INPUT_OBJECT@ #if $pc_genes: - --pc-genes '$pc-genes' + --pc-genes '$pc_genes' #end if ---output-object-file '$output' +#if $pc_cells + --pc-cells '$pc_cells' +#end if +@OUTPUT_OBJECT@ --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' +#if $reverse_pca + '$reverse_pca' #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." /> + <expand macro="input_object_params"/> + <expand macro="output_object_params"/> + <param name="pc_genes" type="data" format="tabular,txt" optional="True" label="Genes to scale" help="File with gene names to scale/center. Default is all genes in object@data." /> + <param label="Cells to scale" optional="true" name="pc_cells" argument="--pc-cells" type="text" help="File with cell names to scale/center. Default is all cells in object@data."/> <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."/> + <param label="Reverse PCA" optional="true" name="reverse_pca" argument="--reverse-pca" type="boolean" truevalue="--reverse-pca" checked="false" help="Run PCA on reverse matrix (gene x cell; FALSE by default means cell x gene)."/> </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 ${on_string}: Seurat Embeddings"/> <data name="output_load" format="csv" from_work_dir="output_load" label="${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"/> @@ -42,7 +47,7 @@ <tests> <test> <param name="input" ftype="rdata" value="out_scale.rds"/> - <output name="output" ftype="rdata" value="out_runpca.rds" compare="sim_size"/> + <output name="rds_seurat_file" ftype="rdata" value="out_runpca.rds" compare="sim_size"/> </test> </tests> <help><![CDATA[ @@ -50,12 +55,9 @@ **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. -This tool runs a PCA dimensionality reduction +@SEURAT_INTRO@ -----