annotate fc_workflow.xml @ 0:f2cb63ca02fa 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_fc_workflow" name="proteomicsr: fold change 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@

null <- run_FC_workflow(
    @COMMON_WF_PARAMETERS@
)
        ]]></configfile>
    </configfiles>
    <inputs>
        <expand macro="common_wf_paramerters"/>
        <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"/>
            <output name="dat_calculated" value="dat_calculated.csv">
                <assert_contents>
                    <has_n_lines n="4269"/>
                    <has_n_columns sep="," n="35"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="3">
            <param name="sampleTable" value="sampleTable.csv" ftype="csv"/>
            <param name="out_select" value="tables,plots"/>
            <output name="dat_calculated">
                <assert_contents>
                    <has_n_lines n="4269"/>
                    <has_n_columns sep="," n="35"/>
                </assert_contents>
            </output>
            <output_collection name="output" count="7" type="list">
                <element name="Mahalanobis_Outliers" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="25"/>
                        <has_n_columns sep="," n="3"/>
                    </assert_contents>
                </element>
                <element name="dat_log2" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="5058"/>
                        <has_n_columns sep="," n="25"/>
                    </assert_contents>
                </element>
                <element name="dat_reliable" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="4269"/>
                        <has_n_columns sep="," n="25"/>
                    </assert_contents>
                </element>

            </output_collection>
            <output_collection name="plots" count="19" type="list"/>
        </test>
        <!-- tests with optional sampleGenes input -->
        <test expect_num_outputs="3">
            <param name="sampleTable" value="sampleTable.csv" ftype="csv"/>
            <param name="sampleGenes" value="sampleGenes.csv" ftype="csv"/>
            <param name="out_select" value="tables,plots"/>
            <output name="dat_calculated">
                <assert_contents>
                    <has_n_lines n="4269"/>
                    <has_n_columns sep="," n="35"/>
                </assert_contents>
            </output>
            <output_collection name="output" count="9" type="list">
                <element name="Mahalanobis_Outliers" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="25"/>
                        <has_n_columns sep="," n="3"/>
                    </assert_contents>
                </element>
                <element name="dat_log2" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="5058"/>
                        <has_n_columns sep="," n="25"/>
                    </assert_contents>
                </element>
                <element name="dat_reliable" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="4269"/>
                        <has_n_columns sep="," n="25"/>
                    </assert_contents>
                </element>

            </output_collection>
            <output_collection name="plots" count="19" type="list"/>
        </test>
        <!-- tests with both optional inputs -->
        <test expect_num_outputs="3">
            <param name="sampleTable" value="sampleTable.csv" ftype="csv"/>
            <param name="sampleGenes" value="sampleGenes.csv" ftype="csv"/>
            <param name="sampleMapping" value="sampleMapping.csv" ftype="csv"/>
            <param name="out_select" value="tables,plots"/>
            <output name="dat_calculated">
                <assert_contents>
                    <has_n_lines n="4269"/>
                    <has_n_columns sep="," n="35"/>
                </assert_contents>
            </output>
            <output_collection name="output" count="9" type="list">
                <element name="Mahalanobis_Outliers" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="25"/>
                        <has_n_columns sep="," n="3"/>
                    </assert_contents>
                </element>
                <element name="dat_log2" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="5058"/>
                        <has_n_columns sep="," n="25"/>
                    </assert_contents>
                </element>
                <element name="dat_reliable" ftype="csv">
                    <assert_contents>
                        <has_n_lines n="4269"/>
                        <has_n_columns sep="," n="25"/>
                    </assert_contents>
                </element>

            </output_collection>
            <output_collection name="plots" count="19" type="list"/>
        </test>
    </tests>
    <help><![CDATA[

Fold change 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. Principal component analysis of processed data
7. Calculation of average log2 fold changes and (adjusted) p-values (param: alternative, var.equal, paired, pvalue_adjustment)
8. Visualization of the results (param: pvalue_decision, significance_cutoff, color_up, color_none, color_down)

sampleMapping

A dataframe, which can be used to relate different
conditions to ggplot facets. The treatments, which should
also appear in the sampleTable, have to be the rownames. The
following columns should be present: "Xname" (the sample
name, which will be shown on the X-axis), "Order" (numbers
indicating the preferred order of the treatments/comparisons
on the X-axis - from left to right), Condition1 (character,
which will be used for the first level ggplot facet),
Condition2 (character, which will be used for the second
level ggplot facet). If no sampleMapping dataframe is
available, use sampleMapping = NULL, which is also the
default.
    ]]></help>
    <expand macro="citations"/>
</tool>