comparison cuffdiff_wrapper.xml @ 16:af3e173cad7f draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/cufflinks/cuffdiff commit 6b66cbbde16c35593fe95066ea2b91623bf35140"

15:43b36b3d4333

<tool id="cuffdiff" name="Cuffdiff" version="@VERSION@.5">
    <description>find significant changes in transcript expression, splicing, and promoter use</description>
    <macros>
        <import>cuff_macros.xml</import>
    </macros>
    <expand macro="requirements">

            '$gtf_input'

            @CONDITION_SAMPLES@
            #if $generate_sqlite:
                &&
                Rscript '$__tool_directory__/cummeRbund.R' && mv cummeRbund.sqlite '${output_cummerbund}'
            #end if
            ]]>
    </command>
    <inputs>
        <param format="gtf,gff3" name="gtf_input" type="data" label="Transcripts" help="A transcript GFF3 or GTF file produced by cufflinks, cuffcompare, or other source."/>

                <option value="No">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="Yes">
                <conditional name="seq_source">
                  <param name="index_source" type="select" label="Reference sequence data">
                    <option value="cached">Locally cached</option>
                    <option value="history">History</option>
                  </param>
                  <when value="cached">
                    <param name="index" type="select" label="Using reference genome">
                      <options from_data_table="fasta_indexes">
                        <filter type="data_meta" ref="gtf_input" key="dbkey" column="1" />
                        <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
                      </options>
                    </param>
                  </when>
                  <when value="history">
                      <param name="ref_file" type="data" format="fasta" label="Using reference file" />
                  </when>
                </conditional>
            </when>
            <when value="No"></when>
        </conditional>

        <data format="txt" name="run_info" label="${tool.name} on ${on_string}: run info" from_work_dir="run.info" >
            <filter>(include_read_group_files == 'Yes') and not omit_tabular_output</filter>
        </data>
        <!-- Standard datasets. -->
        <data format="tabular" name="splicing_diff" label="${tool.name} on ${on_string}: splicing differential expression testing" from_work_dir="splicing.diff">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="promoters_diff" label="${tool.name} on ${on_string}: promoters differential expression testing" from_work_dir="promoters.diff">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_diff" label="${tool.name} on ${on_string}: CDS overloading diffential expression testing" from_work_dir="cds.diff">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_exp_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM differential expression testing" from_work_dir="cds_exp.diff">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM tracking" from_work_dir="cds.fpkm_tracking">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_count_tracking" label="${tool.name} on ${on_string}: CDS count tracking" from_work_dir="cds.count_tracking" >
                <filter>(include_count_files == 'Yes') and not omit_tabular_output</filter>
        </data>

        <data format="tabular" name="tss_groups_exp" label="${tool.name} on ${on_string}: TSS groups differential expression testing" from_work_dir="tss_group_exp.diff">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="tss_groups_fpkm_tracking" label="${tool.name} on ${on_string}: TSS groups FPKM tracking" from_work_dir="tss_groups.fpkm_tracking">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="tss_groups_count_tracking" label="${tool.name} on ${on_string}: TSS count FPKM tracking" from_work_dir="tss_groups.count_tracking" >
                <filter>(include_count_files == 'Yes') and not omit_tabular_output</filter>
        </data>

        <data format="tabular" name="genes_exp" label="${tool.name} on ${on_string}: gene differential expression testing" from_work_dir="gene_exp.diff">
                <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="genes_fpkm_tracking" label="${tool.name} on ${on_string}: gene FPKM tracking" from_work_dir="genes.fpkm_tracking">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="genes_count_tracking" label="${tool.name} on ${on_string}: gene count tracking" from_work_dir="genes.count_tracking" >

            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="isoforms_count_tracking" label="${tool.name} on ${on_string}: transcript count tracking" from_work_dir="isoforms.count_tracking">
            <filter>(include_count_files == 'Yes') and not omit_tabular_output</filter>
        </data>
        <data format="sqlite" name="output_cummerbund" label="${tool.name} on ${on_string}: cummeRbund SQLite database">
            <filter>generate_sqlite</filter>
        </data>
    </outputs>

    <tests>
        <test>
                <!--
                    cuffdiff cuffcompare_out5.gtf cuffdiff_in1.sam cuffdiff_in2.sam
                -->
                <param name="gtf_input" value="cuffdiff_in1.gtf" ftype="gtf" />
                <param name="generate_sqlite" value="yes" />
                <param name="omit_tabular_output" value="yes" />
                <conditional name="in_type">
                    <param name="set_in_type" value="BAM" />
                    <repeat name="conditions">
                        <param name="name" value="q1" />
                        <param name="samples" value="cuffdiff_in1.sam" ftype="sam" />
                    </repeat>
                    <repeat name="conditions">
                        <param name="name" value="q2" />
                        <param name="samples" value="cuffdiff_in2.sam" ftype="sam" />
                    </repeat>
                </conditional>
                <param name="fdr" value="0.05" />
                <param name="min_alignment_count" value="0" />
                <param name="do_bias_correction" value="No" />
                <param name="do_normalization" value="No" />
                <param name="multiread_correct" value="No"/>
                <param name="sAdditional" value="No"/>
                <output name="output_cummerbund" ftype="sqlite" file="cuffdiff_out.sqlite" compare="sim_size" />
        </test>
        <test>
                <!--
                    cuffdiff cuffcompare_out5.gtf cuffdiff_in1.sam cuffdiff_in2.sam
                -->
                <param name="gtf_input" value="cuffdiff_in1.gtf" ftype="gtf" />
                <param name="omit_tabular_output" value="no" />
                <conditional name="in_type">
                    <param name="set_in_type" value="BAM" />
                    <repeat name="conditions">
                        <param name="name" value="q1" />
                        <param name="samples" value="cuffdiff_in1.sam" ftype="sam" />
                    </repeat>
                    <repeat name="conditions">
                        <param name="name" value="q2" />
                        <param name="samples" value="cuffdiff_in2.sam" ftype="sam" />
                    </repeat>
                </conditional>
                <param name="fdr" value="0.05" />
                <param name="min_alignment_count" value="0" />
                <param name="do_bias_correction" value="No" />
                <param name="do_normalization" value="No" />
                <param name="multiread_correct" value="No"/>
                <param name="sAdditional" value="No"/>
                <output name="splicing_diff" file="splicing.diff"/>
                <output name="promoters_diff" file="promoters.diff"/>
                <output name="cds_diff" file="cds.diff"/>
                <output name="cds_exp_fpkm_tracking" file="cds.exp_fpkm_tracking"/>
                <output name="cds_fpkm_tracking" file="cds.fpkm_tracking"/>
                <output name="tss_groups_exp" file="tss.groups_exp" lines_diff="200"/>
                <output name="tss_groups_fpkm_tracking" file="tss.groups_fpkm_tracking"/>
                <output name="genes_exp" file="genes.exp" lines_diff="200"/>
                <output name="genes_fpkm_tracking" file="genes.fpkm_tracking" lines_diff="200"/>
                <output name="isoforms_exp" file="isoforms.exp" lines_diff="200"/>
                <output name="isoforms_fpkm_tracking" file="isoforms.fpkm_tracking" lines_diff="200"/>
        </test>
    </tests>
    <help>
**Cuffdiff Overview**

16:af3e173cad7f

<tool id="cuffdiff" name="Cuffdiff" version="@VERSION@.6">
    <description>find significant changes in transcript expression, splicing, and promoter use</description>
    <macros>
        <import>cuff_macros.xml</import>
    </macros>
    <expand macro="requirements">

            '$gtf_input'

            @CONDITION_SAMPLES@
            #if $generate_sqlite:
                &&
                Rscript '$__tool_directory__/cummeRbund.R'
            #end if
            ]]>
    </command>
    <inputs>
        <param format="gtf,gff3" name="gtf_input" type="data" label="Transcripts" help="A transcript GFF3 or GTF file produced by cufflinks, cuffcompare, or other source."/>

                <option value="No">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="Yes">
                <conditional name="seq_source">
                    <param name="index_source" type="select" label="Reference sequence data">
                        <option value="cached">Locally cached</option>
                        <option value="history">History</option>
                    </param>
                    <when value="cached">
                        <param name="index" type="select" label="Using reference genome">
                        <options from_data_table="fasta_indexes">
                            <filter type="data_meta" ref="gtf_input" key="dbkey" column="1" />
                            <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
                        </options>
                        </param>
                    </when>
                    <when value="history">
                        <param name="ref_file" type="data" format="fasta" label="Using reference file" />
                    </when>
                </conditional>
            </when>
            <when value="No"></when>
        </conditional>

        <data format="txt" name="run_info" label="${tool.name} on ${on_string}: run info" from_work_dir="run.info" >
            <filter>(include_read_group_files == 'Yes') and not omit_tabular_output</filter>
        </data>
        <!-- Standard datasets. -->
        <data format="tabular" name="splicing_diff" label="${tool.name} on ${on_string}: splicing differential expression testing" from_work_dir="splicing.diff">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="promoters_diff" label="${tool.name} on ${on_string}: promoters differential expression testing" from_work_dir="promoters.diff">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_diff" label="${tool.name} on ${on_string}: CDS overloading diffential expression testing" from_work_dir="cds.diff">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_exp_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM differential expression testing" from_work_dir="cds_exp.diff">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM tracking" from_work_dir="cds.fpkm_tracking">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="cds_count_tracking" label="${tool.name} on ${on_string}: CDS count tracking" from_work_dir="cds.count_tracking" >
            <filter>(include_count_files == 'Yes') and not omit_tabular_output</filter>
        </data>

        <data format="tabular" name="tss_groups_exp" label="${tool.name} on ${on_string}: TSS groups differential expression testing" from_work_dir="tss_group_exp.diff">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="tss_groups_fpkm_tracking" label="${tool.name} on ${on_string}: TSS groups FPKM tracking" from_work_dir="tss_groups.fpkm_tracking">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="tss_groups_count_tracking" label="${tool.name} on ${on_string}: TSS count FPKM tracking" from_work_dir="tss_groups.count_tracking" >
            <filter>(include_count_files == 'Yes') and not omit_tabular_output</filter>
        </data>

        <data format="tabular" name="genes_exp" label="${tool.name} on ${on_string}: gene differential expression testing" from_work_dir="gene_exp.diff">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="genes_fpkm_tracking" label="${tool.name} on ${on_string}: gene FPKM tracking" from_work_dir="genes.fpkm_tracking">
            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="genes_count_tracking" label="${tool.name} on ${on_string}: gene count tracking" from_work_dir="genes.count_tracking" >

            <filter>not omit_tabular_output</filter>
        </data>
        <data format="tabular" name="isoforms_count_tracking" label="${tool.name} on ${on_string}: transcript count tracking" from_work_dir="isoforms.count_tracking">
            <filter>(include_count_files == 'Yes') and not omit_tabular_output</filter>
        </data>
        <data format="sqlite" name="output_cummerbund" label="${tool.name} on ${on_string}: cummeRbund SQLite database" from_work_dir="cummeRbund.sqlite">
            <filter>generate_sqlite</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <!--
                cuffdiff cuffcompare_out5.gtf cuffdiff_in1.sam cuffdiff_in2.sam
            -->
            <param name="gtf_input" value="cuffdiff_in1.gtf" ftype="gtf" />
            <param name="generate_sqlite" value="yes" />
            <param name="omit_tabular_output" value="yes" />
            <conditional name="in_type">
                <param name="set_in_type" value="BAM" />
                <repeat name="conditions">
                    <param name="name" value="q1" />
                    <param name="samples" value="cuffdiff_in1.sam" ftype="sam" />
                </repeat>
                <repeat name="conditions">
                    <param name="name" value="q2" />
                    <param name="samples" value="cuffdiff_in2.sam" ftype="sam" />
                </repeat>
            </conditional>
            <param name="fdr" value="0.05" />
            <param name="min_alignment_count" value="0" />
            <param name="do_bias_correction" value="No" />
            <param name="do_normalization" value="No" />
            <param name="multiread_correct" value="No"/>
            <param name="sAdditional" value="No"/>
            <output name="output_cummerbund" ftype="sqlite" file="cuffdiff_out.sqlite" compare="sim_size" />
        </test>
        <test>
            <!--
                Use a list collection as conditions input
                cuffdiff cuffcompare_out5.gtf cuffdiff_in1.sam cuffdiff_in2.sam
            -->
            <param name="gtf_input" value="cuffdiff_in1.gtf" ftype="gtf" />
            <param name="generate_sqlite" value="yes" />
            <param name="omit_tabular_output" value="yes" />
            <conditional name="in_type">
                <param name="set_in_type" value="CONDITION_LIST" />
                <param name="conditions">
                    <collection type="list">
                        <element name="q1" value="cuffdiff_in1.sam" />
                        <element name="q2" value="cuffdiff_in2.sam" />
                    </collection>
                </param>
            </conditional>
            <param name="fdr" value="0.05" />
            <param name="min_alignment_count" value="0" />
            <param name="do_bias_correction" value="No" />
            <param name="do_normalization" value="No" />
            <param name="multiread_correct" value="No"/>
            <param name="sAdditional" value="No"/>
            <output name="output_cummerbund" ftype="sqlite" file="cuffdiff_out.sqlite" compare="sim_size" />
        </test>
        <test>
            <!--
                cuffdiff cuffcompare_out5.gtf cuffdiff_in1.sam cuffdiff_in2.sam
            -->
            <param name="gtf_input" value="cuffdiff_in1.gtf" ftype="gtf" />
            <param name="omit_tabular_output" value="no" />
            <conditional name="in_type">
                <param name="set_in_type" value="BAM" />
                <repeat name="conditions">
                    <param name="name" value="q1" />
                    <param name="samples" value="cuffdiff_in1.sam" ftype="sam" />
                </repeat>
                <repeat name="conditions">
                    <param name="name" value="q2" />
                    <param name="samples" value="cuffdiff_in2.sam" ftype="sam" />
                </repeat>
            </conditional>
            <param name="fdr" value="0.05" />
            <param name="min_alignment_count" value="0" />
            <param name="do_bias_correction" value="No" />
            <param name="do_normalization" value="No" />
            <param name="multiread_correct" value="No"/>
            <param name="sAdditional" value="No"/>
            <output name="splicing_diff" file="splicing.diff"/>
            <output name="promoters_diff" file="promoters.diff"/>
            <output name="cds_diff" file="cds.diff"/>
            <output name="cds_exp_fpkm_tracking" file="cds.exp_fpkm_tracking"/>
            <output name="cds_fpkm_tracking" file="cds.fpkm_tracking"/>
            <output name="tss_groups_exp" file="tss.groups_exp" lines_diff="200"/>
            <output name="tss_groups_fpkm_tracking" file="tss.groups_fpkm_tracking"/>
            <output name="genes_exp" file="genes.exp" lines_diff="200"/>
            <output name="genes_fpkm_tracking" file="genes.fpkm_tracking" lines_diff="200"/>
            <output name="isoforms_exp" file="isoforms.exp" lines_diff="200"/>
            <output name="isoforms_fpkm_tracking" file="isoforms.fpkm_tracking" lines_diff="200"/>
        </test>
    </tests>
    <help>
**Cuffdiff Overview**