view 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

<tool id="proteomicsr_intensity_workflow" name="proteomicsr: intensity workflow" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
        Rscript '$rscript'
        && mv Rdata/dat_calculated.csv .
    ]]></command>
    <configfiles>
        <configfile name="rscript"><![CDATA[
library(proteomicsr)

@READ_INPUTS@

#set controlSamples = 'c("' + '", "'.join(str($control_samples).split(",")) + '")'

null <- run_intensity_workflow(
    @COMMON_WF_PARAMETERS@,
    control_samples = $controlSamples,
    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")
    run_vsn = $run_vsn,
#if $impute.run_imputation == "TRUE"
    run_imputation = $impute.run_imputation,
    imp_fun = $impute.imp_fun,
    imp_q = $impute.imp_q,
    impute_completely_missing_only = $impute_completely_missing_only,
#end if

)
        ]]></configfile>
    </configfiles>
    <inputs>
        <param argument="control_samples" type="text" label="Control samples" help="Comma separated list of sample names, as used in the input table"/>
        <expand macro="common_wf_paramerters">
            <param argument="run_vsn" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Apply variance stabilization using the DEP package" help=""/>
            <conditional name="impute">
                <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">
                    <option value="TRUE">TRUE</option>
                    <option value="FALSE" selected="true">FALSE</option>
                </param>
                <when value="TRUE">
                    <param argument="impute_completely_missing_only" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Decide which missing data should be imputed." help=""/>
                    <param argument="imp_fun" type="select" label="Method for imputation" help="">
                        <option value="MLE">Maximum likelihood-based imputation method using the EM algorithm</option>
                        <option value="bpca">Bayesian missing value imputation</option>
                        <option value="knn">Nearest neighbour averaging</option>
                        <option value="QRILC"> Imputation of left-censored missing data using random draws from a truncated distribution with parameters estimated using quantile regression</option>
                        <option value="MinDet">Imputation of left-censored missing data using a deterministic minimal value approach</option>
                        <option value="MinProb" selected="true"> Imputation of left-censored missing data by random draws from a Gaussian distribution centred to a minimal value</option>
                        <option value="min">Replaces the missing values by the smallest non-missing value in the data</option>
                        <option value="zero">Replaces the missing values by 0</option>
                        <option value="nbavg">Average neighbour imputation for fractions collected along a fractionation/separation gradient</option>
                        <option value="none">No imputation</option>
                    </param>
                    <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."/>
                </when>
                <when value="FALSE"/>
            </conditional>
        </expand>
        <param name="out_select" type="select" multiple="true" optional="true" label="Optional outputs">
            <option value="tables">Detailed tables</option>
            <option value="plots">Plots</option>
        </param>
    </inputs>
    <outputs>
        <data name="dat_calculated" format="csv" from_work_dir="dat_calculated.csv"/>
        <collection name="output" type="list" label="${tool.name} on ${on_string}: additional tables">
            <discover_datasets pattern="__name_and_ext__" directory="Rdata"/>
            <filter>out_select and "tables" in out_select</filter>
        </collection>
        <collection name="plots" type="list" label="${tool.name} on ${on_string}: plots">
            <discover_datasets pattern="__name_and_ext__" directory="Plots"/>
            <filter>out_select and "plots" in out_select</filter>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="sampleTable" value="sampleTable.csv" ftype="csv"/>
            <param name="control_samples" value="control_04h_plusLPS_vs_control_04h_noLPS"/>
            <output name="dat_calculated">
                <assert_contents>
                    <has_n_lines n="4269"/>
                    <has_n_columns sep="," n="31"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

Intensity workflow

1. Evaluating data quality
2. Identification (and removal) of outliers (param: remove_outliers)
3. Log2 transformation 
4. Optional: median normalization (param: median_normalize)
5. Filtering for reliably identified candidates (param: number_replicates_reliable, reliable_all_comparisons)
6. Optional: variance stabilization (param: run_vsn)
7. Optional: imputation, which includes variance stabilization as data preparation step (param: run_imputation, imp_fun, imp_q, impute_completely_missing_only)
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)
9. Visualization of the results (param: pvalue_decision, significance_cutoff, color_up, color_none, color_down)
    ]]></help>
    <expand macro="citations"/>
</tool>