comparison analyze_diff_expr.xml @ 3:24d072085816 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/trinity commit 7efdf3224552d113a01043ee5bf4517d770df933

2:cfd497973b88

    <description>from a Trinity assembly</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="2.30.0">bioconductor-biobase</requirement>
        <requirement type="package" version="2.2.2">bioconductor-qvalue</requirement>
        <requirement type="package" version="1.22.0">bioconductor-goseq</requirement>
        <requirement type="package" version="3.3.0">bioconductor-go.db</requirement>
    </expand>
    <expand macro="stdio"/>
    <command><![CDATA[
    ## DE results input files must be in the working directory and have suffix .DE_results
    #import re
    #for $input in $DE_results
        ln -s "${input}" "${re.sub('[^\w\-_.]', '_', input.element_identifier)}.DE_results"
        &&
    #end for

    analyze_diff_expr.pl
        --matrix "${matrix}"

        --output results
    ]]></command>
    <inputs>
        <param format="tabular" name="matrix" argument="--matrix" type="data" label="Expression matrix" help="Raw counts matrix produced by 'Build expression matrix for a de novo assembly of RNA-Seq data by Trinity' tool"/>
        <param format="tabular" name="samples" argument="--samples" type="data" label="Sample description" help="File describing samples and replicates"/>
        <param format="tabular" name="DE_results" type="data_collection" collection_type="list" label="Differential expression results"/>
        <param name="p" type="float" argument="-P" value="0.001" label="p-value cutoff for FDR"/>
        <param name="c" type="float" argument="-C" value="2" label="min abs(log2(a/b)) fold change" help="Default: 2 (meaning 2^(2) or 4-fold"/>
        <section name="additional_params" title="Additional Options" expanded="False">
            <param name="max_DE_genes_per_comparison" argument="--max_DE_genes_per_comparison" type="integer" value="" optional="true" label="Maximum differential expression genes per comparison" help="Extract only up to the top number of DE features within each pairwise comparison. This is useful when you have massive numbers of DE features but still want to make useful heatmaps and other plots with more manageable numbers of data points."/>
            <param name="order_columns_by_samples_file" argument="--order_columns_by_samples_file" type="boolean" checked="false" truevalue="--order_columns_by_samples_file" falsevalue="" label="Order columns by samples file" help="Instead of clustering samples or replicates hierarchically based on gene expression patterns, order columns according to order in the --samples file."/>

                </when>
                <when value="yes">
                    <param format="tabular" name="GO_annots" argument="--GO_annots" type="data" label="Extracted GO assignments file" help="Generated by the Trinotate script extract_GO_assignments_from_Trinotate_xls.pl. Must have 2 columns: feature_id GO:000001,GO:00002,..."/>
                    <param format="tabular" name="gene_lengths" argument="--gene_lengths" type="data" label="Gene length file" help="Must have 2 columns: feature_id length"/>
                </when>
        </conditional> 
        </section>
    </inputs>
    <outputs>
        <collection name="extracted_DE_genes" type="list" label="${tool.name} on ${on_string}: extracted differentially expressed genes">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.subset$" ext="tabular" />

                    <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
              </collection>
            </param>
            <output_collection name="extracted_DE_genes">
                <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.0.wt_37-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.wt_37-UP.subset"/>
                <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.0.wt_GSNO-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.wt_GSNO-UP.subset"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.0.wt_37-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.wt_37-UP.subset"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.0.wt_ph8-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.wt_ph8-UP.subset"/>

                    <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
                </collection>
            </param>
            <section name="additional_params">
                <conditional name="GO_enrichment">
                    <param name="examine_GO_enrichment" value="yes"/>
                    <param name="GO_annots" value="count/trinotate/go_annotations.txt"/>
                    <param name="gene_lengths" value="count/trinotate/genes.lengths.txt"/>

        </test>
    </tests>
    <help>
<![CDATA[
Trinity_ assembles transcript sequences from Illumina RNA-Seq data.
This tool extracts the transcripts that are most differentially expressed (most significant FDR and fold-changes), once differential expression analyses have been runned. 

**Inputs**

This tool uses the raw counts matrix produced by 'Build expression matrix for a de novo assembly of RNA-Seq data by Trinity' tool.

3:24d072085816

    <description>from a Trinity assembly</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="2.6.0">bioconductor-qvalue</requirement>
        <requirement type="package" version="1.26.0">bioconductor-goseq</requirement>
        <requirement type="package" version="3.4.0">bioconductor-go.db</requirement>
    </expand>
    <command detect_errors="aggressive"><![CDATA[
    ## DE results input files must be in the working directory and have suffix .DE_results
    #import re
    #for $input in $DE_results
        ln -s "${input}" "${re.sub('[^\w\-_.]', '_', input.element_identifier)}.DE_results"
        &&
    #end for
    #for $DE_matrix in $DE_matrices
        ln -s "${DE_matrix}" "${re.sub('[^\w\-_.]', '_', DE_matrix.element_identifier)}.count_matrix"
        &&
    #end for

    analyze_diff_expr.pl
        --matrix "${matrix}"

        --output results
    ]]></command>
    <inputs>
        <param format="tabular" name="matrix" argument="--matrix" type="data" label="Expression matrix" help="Raw counts matrix produced by 'Build expression matrix for a de novo assembly of RNA-Seq data by Trinity' tool"/>
        <param format="tabular" name="samples" argument="--samples" type="data" label="Sample description" help="File describing samples and replicates"/>
        <param format="tabular" name="DE_results" type="data_collection" collection_type="list" label="Differential expression results" help="Generated by 'Differential expression analysis using a Trinity assembly' tool"/>
        <param format="tabular" name="DE_matrices" type="data_collection" collection_type="list" label="Differential expression count matrices" help="Generated by 'Differential expression analysis using a Trinity assembly' tool"/>
        <param name="p" type="float" argument="-P" value="0.001" label="p-value cutoff for FDR"/>
        <param name="c" type="float" argument="-C" value="2" label="min abs(log2(a/b)) fold change" help="Default: 2 (meaning 2^(2) or 4-fold"/>
        <section name="additional_params" title="Additional Options" expanded="False">
            <param name="max_DE_genes_per_comparison" argument="--max_DE_genes_per_comparison" type="integer" value="" optional="true" label="Maximum differential expression genes per comparison" help="Extract only up to the top number of DE features within each pairwise comparison. This is useful when you have massive numbers of DE features but still want to make useful heatmaps and other plots with more manageable numbers of data points."/>
            <param name="order_columns_by_samples_file" argument="--order_columns_by_samples_file" type="boolean" checked="false" truevalue="--order_columns_by_samples_file" falsevalue="" label="Order columns by samples file" help="Instead of clustering samples or replicates hierarchically based on gene expression patterns, order columns according to order in the --samples file."/>

                </when>
                <when value="yes">
                    <param format="tabular" name="GO_annots" argument="--GO_annots" type="data" label="Extracted GO assignments file" help="Generated by the Trinotate script extract_GO_assignments_from_Trinotate_xls.pl. Must have 2 columns: feature_id GO:000001,GO:00002,..."/>
                    <param format="tabular" name="gene_lengths" argument="--gene_lengths" type="data" label="Gene length file" help="Must have 2 columns: feature_id length"/>
                </when>
        </conditional>
        </section>
    </inputs>
    <outputs>
        <collection name="extracted_DE_genes" type="list" label="${tool.name} on ${on_string}: extracted differentially expressed genes">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.subset$" ext="tabular" />

                    <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
              </collection>
            </param>
            <param name="DE_matrices">
                <collection type="list">
                    <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.count_matrix" ftype="tabular" />
                    <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.count_matrix" ftype="tabular" />
                    <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.count_matrix" ftype="tabular" />
              </collection>
            </param>
            <output_collection name="extracted_DE_genes">
                <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.0.wt_37-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.wt_37-UP.subset"/>
                <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.0.wt_GSNO-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.P0.001_C2.wt_GSNO-UP.subset"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.0.wt_37-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.wt_37-UP.subset"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.0.wt_ph8-UP" compare="sim_size" file="count/analyze_diff_expr/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.P0.001_C2.wt_ph8-UP.subset"/>

                    <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
                    <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results" ftype="tabular" />
                </collection>
            </param>
            <param name="DE_matrices">
                <collection type="list">
                    <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.count_matrix" ftype="tabular" />
                    <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.count_matrix" ftype="tabular" />
                    <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" value="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.count_matrix" ftype="tabular" />
                </collection>
            </param>
            <section name="additional_params">
                <conditional name="GO_enrichment">
                    <param name="examine_GO_enrichment" value="yes"/>
                    <param name="GO_annots" value="count/trinotate/go_annotations.txt"/>
                    <param name="gene_lengths" value="count/trinotate/genes.lengths.txt"/>

        </test>
    </tests>
    <help>
<![CDATA[
Trinity_ assembles transcript sequences from Illumina RNA-Seq data.
This tool extracts the transcripts that are most differentially expressed (most significant FDR and fold-changes), once differential expression analyses have been runned.

**Inputs**

This tool uses the raw counts matrix produced by 'Build expression matrix for a de novo assembly of RNA-Seq data by Trinity' tool.