comparison intensity_workflow.xml @ 0:31212f7e7611 draft default tip

planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/master/tools/proteomicsr commit a73787be689a9af5641ff1b594c9a35d29093247-dirty
author mbernt
date Tue, 19 Dec 2023 15:50:36 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:31212f7e7611
1 <tool id="proteomicsr_intensity_workflow" name="proteomicsr: intensity workflow" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
2 <macros>
3 <import>macros.xml</import>
4 </macros>
5 <expand macro="requirements"/>
6 <command detect_errors="exit_code"><![CDATA[
7 Rscript '$rscript'
8 && mv Rdata/dat_calculated.csv .
9 ]]></command>
10 <configfiles>
11 <configfile name="rscript"><![CDATA[
12 library(proteomicsr)
13
14 @READ_INPUTS@
15
16 #set controlSamples = 'c("' + '", "'.join(str($control_samples).split(",")) + '")'
17
18 null <- run_intensity_workflow(
19 @COMMON_WF_PARAMETERS@,
20 control_samples = $controlSamples,
21 comparisons_relevant = NULL, ## if NULL, script continues with all possible comparisons. Otherwise, a vector should be provided, e.g. c("treatment1_vs_ctrl", "treatment2_vs_ctrl", "treatment2_vs_treatment1")
22 run_vsn = $run_vsn,
23 #if $impute.run_imputation == "TRUE"
24 run_imputation = $impute.run_imputation,
25 imp_fun = $impute.imp_fun,
26 imp_q = $impute.imp_q,
27 impute_completely_missing_only = $impute_completely_missing_only,
28 #end if
29
30 )
31 ]]></configfile>
32 </configfiles>
33 <inputs>
34 <param argument="control_samples" type="text" label="Control samples" help="Comma separated list of sample names, as used in the input table"/>
35 <expand macro="common_wf_paramerters">
36 <param argument="run_vsn" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Apply variance stabilization using the DEP package" help=""/>
37 <conditional name="impute">
38 <param argument="run_imputation" type="select" label="Apply imputation using the DEP package" help="If TRUE, variance stabilization is performed anyway and also the parameters imp_fun, imp_q, and impute_completely_missing_only should be double-checked and adjusted if necessary">
39 <option value="TRUE">TRUE</option>
40 <option value="FALSE" selected="true">FALSE</option>
41 </param>
42 <when value="TRUE">
43 <param argument="impute_completely_missing_only" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Decide which missing data should be imputed." help=""/>
44 <param argument="imp_fun" type="select" label="Method for imputation" help="">
45 <option value="MLE">Maximum likelihood-based imputation method using the EM algorithm</option>
46 <option value="bpca">Bayesian missing value imputation</option>
47 <option value="knn">Nearest neighbour averaging</option>
48 <option value="QRILC"> Imputation of left-censored missing data using random draws from a truncated distribution with parameters estimated using quantile regression</option>
49 <option value="MinDet">Imputation of left-censored missing data using a deterministic minimal value approach</option>
50 <option value="MinProb" selected="true"> Imputation of left-censored missing data by random draws from a Gaussian distribution centred to a minimal value</option>
51 <option value="min">Replaces the missing values by the smallest non-missing value in the data</option>
52 <option value="zero">Replaces the missing values by 0</option>
53 <option value="nbavg">Average neighbour imputation for fractions collected along a fractionation/separation gradient</option>
54 <option value="none">No imputation</option>
55 </param>
56 <param argument="imp_q" type="float" value="0.01" min="0" max="1" label="q-th quantile for left-censored imputation" help="The minimal value observed is estimated as being the q-th quantile of the observed values in that sample."/>
57 </when>
58 <when value="FALSE"/>
59 </conditional>
60 </expand>
61 <param name="out_select" type="select" multiple="true" optional="true" label="Optional outputs">
62 <option value="tables">Detailed tables</option>
63 <option value="plots">Plots</option>
64 </param>
65 </inputs>
66 <outputs>
67 <data name="dat_calculated" format="csv" from_work_dir="dat_calculated.csv"/>
68 <collection name="output" type="list" label="${tool.name} on ${on_string}: additional tables">
69 <discover_datasets pattern="__name_and_ext__" directory="Rdata"/>
70 <filter>out_select and "tables" in out_select</filter>
71 </collection>
72 <collection name="plots" type="list" label="${tool.name} on ${on_string}: plots">
73 <discover_datasets pattern="__name_and_ext__" directory="Plots"/>
74 <filter>out_select and "plots" in out_select</filter>
75 </collection>
76 </outputs>
77 <tests>
78 <test expect_num_outputs="1">
79 <param name="sampleTable" value="sampleTable.csv" ftype="csv"/>
80 <param name="control_samples" value="control_04h_plusLPS_vs_control_04h_noLPS"/>
81 <output name="dat_calculated">
82 <assert_contents>
83 <has_n_lines n="4269"/>
84 <has_n_columns sep="," n="31"/>
85 </assert_contents>
86 </output>
87 </test>
88 </tests>
89 <help><![CDATA[
90
91 Intensity workflow
92
93 1. Evaluating data quality
94 2. Identification (and removal) of outliers (param: remove_outliers)
95 3. Log2 transformation
96 4. Optional: median normalization (param: median_normalize)
97 5. Filtering for reliably identified candidates (param: number_replicates_reliable, reliable_all_comparisons)
98 6. Optional: variance stabilization (param: run_vsn)
99 7. Optional: imputation, which includes variance stabilization as data preparation step (param: run_imputation, imp_fun, imp_q, impute_completely_missing_only)
100 8. Principal component analysis of processed dataCalculation of average log2 fold changes and (adjusted) p-values (param: control_samples, comparisons_relevant, alternative, var.equal, paired, pvalue_adjustment)
101 9. Visualization of the results (param: pvalue_decision, significance_cutoff, color_up, color_none, color_down)
102 ]]></help>
103 <expand macro="citations"/>
104 </tool>