Mercurial > repos > ebi-gxa > seurat_find_variable_genes

comparison seurat_find_variable_genes.xml @ 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
comparison
equal deleted inserted replaced
0:a56efad05337 1:a6077346f869
1 <tool id="seurat_find_variable_genes" name="Seurat FindVariableGenes" version="2.3.1+galaxy1"> 1 <tool id="seurat_find_variable_genes" name="Seurat FindVariableGenes" version="@SEURAT_VERSION@_@VERSION@+galaxy0">
2 <description>identify variable genes</description> 2 <description>identify variable genes</description>
3 <macros> 3 <macros>
4 <import>seurat_macros.xml</import> 4 <import>seurat_macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements" /> 6 <expand macro="requirements" />
7 <expand macro="version" /> 7 <expand macro="version" />
8 <command detect_errors="exit_code"><![CDATA[ 8 <command detect_errors="exit_code"><![CDATA[
9 seurat-find-variable-genes.R 9 seurat-find-variable-genes.R
10 10
11 --input-object-file '$input' 11 @INPUT_OBJECT@
12 #if $mean: 12 #if $mean:
13 --mean-function '$mean' 13 --mean-function '$mean'
14 #end if
15 #if $selection_method
16 --selection-method '$selection_method'
14 #end if 17 #end if
15 #if $disp: 18 #if $disp:
16 --dispersion-function $disp 19 --dispersion-function $disp
17 #end if 20 #end if
18 #if $xlow: 21 #if $xlow:
25 --y-low-cutoff $ylow 28 --y-low-cutoff $ylow
26 #end if 29 #end if
27 #if $yhigh: 30 #if $yhigh:
28 --y-high-cutoff $yhigh 31 --y-high-cutoff $yhigh
29 #end if 32 #end if
30 --output-object-file '$output' 33 @OUTPUT_OBJECT@
31 --output-text-file '$output_tab' 34 --output-text-file '$output_tab'
32 ]]></command> 35 ]]></command>
33 36
34 <inputs> 37 <inputs>
35 <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" /> 38 <expand macro="input_object_params"/>
39 <expand macro="output_object_params"/>
40 <param label="Number of features" optional="true" name="nfeatures" argument="--nfeatures" type="integer" help="Number of features to return."/>
36 <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."/> 41 <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."/>
37 <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." /> 42 <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." />
38 <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."/> 43 <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."/>
39 <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."/> 44 <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."/>
40 <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."/> 45 <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."/>
41 <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."/> 46 <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."/>
47 <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.">
48 <option value="vst" selected="true">vst</option>
49 <option value="mbp">mbp</option>
50 <option value="disp">disp</option>
51 </param>
42 </inputs> 52 </inputs>
43 53
44 <outputs> 54 <outputs>
45 <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/> 55 <expand macro="output_files"/>
46 <data name="output_tab" format="tabular" from_work_dir="*.tab" label="${tool.name} on ${on_string}: Variable genes tabular file"/> 56 <data name="output_tab" format="tabular" from_work_dir="*.tab" label="${tool.name} on ${on_string}: Variable genes tabular file"/>
47 </outputs> 57 </outputs>
48 58
49 <tests> 59 <tests>
50 <test> 60 <test>
51 <param name="input" ftype="rdata" value="out_norm.rds"/> 61 <param name="input" ftype="rdata" value="out_norm.rds"/>
52 <output name="output" ftype="rdata" value="out_findvar.rds" compare="sim_size"/> 62 <output name="rds_seurat_file" ftype="rdata" value="out_findvar.rds" compare="sim_size"/>
53 </test> 63 </test>
54 </tests> 64 </tests>
55 <help><![CDATA[ 65 <help><![CDATA[
56 .. class:: infomark 66 .. class:: infomark
57 67
58 **What it does** 68 **What it does**
59
60 Seurat_ is a toolkit for quality control, analysis, and exploration of single cell RNA sequencing data.
61 It is developed and maintained by the `Satija Lab`_ at NYGC. Seurat aims to enable users to identify and
62 interpret sources of heterogeneity from single cell transcriptomic measurements, and to integrate diverse
63 types of single cell data.
64 69
65 This tool identifies genes that are outliers on a 'mean variability plot'. First, uses 70 This tool identifies genes that are outliers on a 'mean variability plot'. First, uses
66 a function to calculate average expression (mean.function) and dispersion (dispersion.function) 71 a function to calculate average expression (mean.function) and dispersion (dispersion.function)
67 for each gene. Next, divides genes into num.bin (deafult 20) bins based on 72 for each gene. Next, divides genes into num.bin (deafult 20) bins based on
68 their average expression, and calculates z-scores for dispersion within each 73 their average expression, and calculates z-scores for dispersion within each
69 bin. The purpose of this is to identify variable genes while controlling for 74 bin. The purpose of this is to identify variable genes while controlling for
70 the strong relationship between variability and average expression. 75 the strong relationship between variability and average expression.
71 76
72 Exact parameter settings may vary empirically from dataset to dataset, and 77 For the mean.var.plot method: Exact parameter settings may vary empirically from
73 based on visual inspection of the plot. 78 dataset to dataset, and based on visual inspection of the plot. Setting the
79 y.cutoff parameter to 2 identifies features that are more than two standard deviations
80 away from the average dispersion within a bin. The default X-axis function is the
81 mean expression level, and for Y-axis it is the log(Variance/mean). All
82 mean/variance calculations are not performed in log-space, but the results are
83 reported in log-space - see relevant functions for exact details.
74 84
75 Setting the y.cutoff parameter to 2 identifies genes that are more than two standard 85 @SEURAT_INTRO@
76 deviations away from the average dispersion within a bin. The default X-axis function
77 is the mean expression level, and for Y-axis it is the log(Variance/mean). All mean/variance
78 calculations are not performed in log-space, but the results are reported in log-space -
79 see relevant functions for exact details.
80 86
81 ----- 87 -----
82 88
83 **Inputs** 89 **Inputs**
84 90