Mercurial > repos > ebi-gxa > seurat_find_markers
changeset 0:fde95fe95f15 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 11:17:29 -0400 |
parents | |
children | 7895b4bb6247 |
files | README seurat_find_markers.xml seurat_macros.xml |
diffstat | 3 files changed, 167 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Wed Apr 03 11:17:29 2019 -0400 @@ -0,0 +1,1 @@ +Seurat tools
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/seurat_find_markers.xml Wed Apr 03 11:17:29 2019 -0400 @@ -0,0 +1,116 @@ +<tool id="seurat_find_markers" name="Seurat FindMarkers" version="2.3.1+galaxy1"> + <description>find markers (differentially expressed genes)</description> + <macros> + <import>seurat_macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="version" /> + <command detect_errors="exit_code"><![CDATA[ +seurat-find-markers.R + +--input-object-file '$input' +--output-text-file output.txt + +#if $genes_use: + --genes-use '$genes_use' +#end if + +#if str($logfc_threshold): + --logfc-threshold '$logfc_threshold' +#end if + +#if str($adv.min_pct): + --min-pct '$adv.min_pct' +#end if + +#if str($adv.min_diff_pct): + --min-diff-pct '$adv.min_diff_pct' +#end if + +#if $adv.only_pos: + --only-pos '$adv.only_pos' +#end if + +--test-use '$adv.test_use' + +#if str($max_cells_per_ident): + --max-cells-per-ident '$max_cells_per_ident' +#end if + +#if str($min_cells_per_gene): + --min-cells-gene '$min_cells_per_gene' +#end if + +#if str($min_cells_group): + --min-cells-group '$min_cells_group' +#end if + + +]]></command> + + <inputs> + <param name="input" type="data" format="rdata" label="RDS object" /> + <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)."/> + <param name="min_cells_per_gene" label="Min cells per gene" optional="true" argument="--min-cells-gene" type="integer" help="Minimum number of cells expressing the gene in at least one of the two groups, currently only used for poisson and negative binomial tests."/> + <param name="min_cells_group" label="Min cells in one of the groups" optional="true" argument="--min-cells-group" type="integer"/> + <section name="adv" title="Advanced Options"> + <param name="min_pct" type="float" label="Min Pct" optional="true" help="Only test genes that are detected in a minimum fraction of min.pct cells in either of the two populations. Meant to speed up the function by not testing genes that are very infrequently expressed. Default is 0.1."/> + <param name="min_diff_pct" type="float" label="Min diff Pct" optional="true" help="Only test genes that show a minimum difference in the fraction of detection between the two groups. Set to -Inf by default."/> + <param name="only_pos" type="boolean" label="Only positive markers" truevalue="TRUE" falsevalue="" help="Only return positive markers (FALSE by default)."/> + <param name="test_use" type="select" label="Test to use" help=""> + <option value="wilcox" selected="true">Wilcoxon</option> + <option value="bimod">Bi-modal</option> + <option value="roc">ROC</option> + <option value="t">t-Test</option> + <option value="tobit">tobit</option> + <option value="poisson">Poisson</option> + <option value="negbinom">Negative binomia</option> + <option value="MAST">MAST</option> + <option value="DESeq2">DESeq2</option> + </param> + </section> + </inputs> + + <outputs> + <data name="output" format="txt" from_work_dir="output.txt" label="${tool.name} on ${on_string}: Text file"/> + </outputs> + + <tests> + <test> + <param name="input" ftype="rdata" value="out_runtsne.rds"/> + <output name="output" ftype="txt" value="out_findmark.txt"/> + </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 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.) + +----- + +**Inputs** + + * RDS object + +----- + +**Outputs** + + * Text file + +.. _Seurat: https://www.nature.com/articles/nbt.4096 +.. _Satija Lab: https://satijalab.org/seurat/ + +@VERSION_HISTORY@ +]]></help> + <expand macro="citations" /> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/seurat_macros.xml Wed Apr 03 11:17:29 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>