annotate tools/venn_list/venn_list.xml @ 8:ee50d9ef9d69 draft

v0.0.11 Python 3 compatible print; capture script version

<tool id="venn_list" name="Venn Diagram" version="0.0.11">
    <description>from lists</description>
    <requirements>
        <requirement type="package" version="1.0.1">galaxy_sequence_utils</requirement>
        <requirement type="package" version="1.0.3">rpy</requirement>
        <requirement type="package" version="3.25.3">limma</requirement>
        <requirement type="package" version="1.67">biopython</requirement>
    </requirements>
    <version_command>
python $__tool_directory__/venn_list.py --version
    </version_comman>
    <command detect_errors="aggressive">
python $__tool_directory__/venn_list.py
#if $universe.type_select=="implicit":
  - -
#else:
  '$main' $main.ext
#end if
'$main_lab'
#for $s in $sets:
  '$s.set' $s.set.ext '$s.lab'
#end for
$PDF
    </command>
    <inputs>
        <param name="main_lab" size="30" type="text" value="Venn Diagram" label="Plot title"/>
        <conditional name="universe">
            <param name="type_select" type="select" label="Implicit or explicit full ID list?">
                <option value="explicit">Explicit</option>
                <option value="implicit">Implicit (use union of sets below)</option>
            </param>
            <when value="explicit">
                 <param name="main" type="data" format="tabular,fasta,fastq,sff" label="Full dataset (with all identifiers)" help="Tabular file (uses column one), FASTA, FASTQ or SFF file."/>
            </when>
            <when value="implicit"/>
        </conditional>
        <repeat name="sets" min="1" max="3" title="Sets">
            <param name="set" type="data" format="tabular,fasta,fastq,sff" label="Members of set" help="Tabular file (uses column one), FASTA, FASTQ or SFF file."/>
            <param name="lab" size="30" type="text" value="Group" label="Caption for set"/>
        </repeat>
    </inputs>
    <outputs>
        <data format="pdf" name="PDF" />
    </outputs>
    <tests>
         <!-- Doesn't seem to work properly, manages to get two sets, both
              with same FASTA file, but second with default "Group" label. -->
        <test>
            <param name="type_select" value="explicit"/>
            <param name="main" value="venn_list.tabular" ftype="tabular"/>
            <param name="main_lab" value="Some Proteins"/>
            <param name="set" value="rhodopsin_proteins.fasta"/>
            <param name="lab" value="Rhodopsins"/>
            <output name="PDF" file="magic.pdf" ftype="pdf" compare="contains" />
            <assert_stdout>
                <has_line line="Doing 1-way Venn Diagram" />
                <has_line line="Total of 10 IDs" />
                <has_line line="6 in Rhodopsins" />
            </assert_stdout>
        </test>
        <test>
            <param name="type_select" value="implicit"/>
            <param name="sets_0|set" value="rhodopsin_proteins.fasta"/>
            <param name="sets_0|lab" value="Rhodopsins"/>
            <param name="sets_1|set" value="four_human_proteins.fasta"/>
            <param name="sets_1|lab" value="Human"/>
            <param name="sets_2|set" value="blastp_four_human_vs_rhodopsin.tabular"/>
            <param name="sets_2|lab" value="Human vs Rhodopsin BLAST"/>
            <output name="PDF" file="magic.pdf" ftype="pdf" compare="contains" />
            <assert_stdout>
                <has_line line="Doing 3-way Venn Diagram" />
                <has_line line="Inferred total of 10 IDs" />
                <has_line line="6 in Rhodopsins" />
                <has_line line="4 in Human" />
                <has_line line="1 in Human vs Rhodopsin BLAST" />
            </assert_stdout>
        </test>
        <test expect_failure="true" expect_exit_code="1">
            <param name="type_select" value="explicit"/>
            <param name="main" value="venn_list.tabular" ftype="tabular"/>
            <param name="main_lab" value="Some Proteins"/>
            <param name="sets_0|set" value="rhodopsin_proteins.fasta"/>
            <param name="sets_0|lab" value="Rhodopsins"/>
            <param name="sets_1|set" value="four_human_proteins.fasta"/>
            <param name="sets_1|lab" value="Human"/>
            <param name="sets_2|set" value="blastp_four_human_vs_rhodopsin.tabular"/>
            <param name="sets_2|lab" value="Human vs Rhodopsin BLAST"/>
            <assert_stdout>
                <has_line line="Doing 3-way Venn Diagram" />
                <has_line line="Total of 10 IDs" />
            </assert_stdout>
            <assert_stderr>
                <has_text_matching expression="Unexpected ID sp|Q9BS26|ERP44_HUMAN in fasta file *" />
            </assert_stderr>
        </test>
    </tests>
    <help>

.. class:: infomark

**TIP:** If your data is in tabular files, the identifier is assumed to be in column one.

**What it does**

Draws Venn Diagram for one, two or three sets (as a PDF file).

You must supply one, two or three sets of identifiers -- corresponding
to one, two or three circles on the Venn Diagram.

In general you should also give the full list of all the identifiers
explicitly. This is used to calculate the number of identifers outside
the circles (and check the identifiers in the other files match up).
The full list can be omitted by implicitly taking the union of the
category sets. In this case, the count outside the categories (circles)
will always be zero.

The identifiers can be taken from the first column of a tabular file
(e.g. query names in BLAST tabular output, or signal peptide predictions
after filtering, etc), or from a sequence file (FASTA, FASTQ, SFF).

For example, you may have a set of NGS reads (as a FASTA, FASTQ or SFF
file), and the results of several different read mappings (e.g. to
different references) as tabular files (filtered to have just the mapped
reads). You could then show the different mappings (and their overlaps)
as a Venn Diagram, and the outside count would be the unmapped reads.

**Citations**

The Venn Diagrams are drawn using Gordon Smyth's limma package from
R/Bioconductor, http://www.bioconductor.org/

The R library is called from Python via rpy, http://rpy.sourceforge.net/

If you use this Galaxy tool in work leading to a scientific publication please
cite:

Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
Galaxy tools and workflows for sequence analysis with applications
in molecular plant pathology. PeerJ 1:e167
http://dx.doi.org/10.7717/peerj.167

This tool uses Biopython to read and write SFF files, so you may also wish to
cite the Biopython application note (and Galaxy too of course):

Cock et al 2009. Biopython: freely available Python tools for computational
molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.

    </help>
    <citations>
        <citation type="doi">10.7717/peerj.167</citation>
        <citation type="doi">10.1093/bioinformatics/15.5.356</citation>
    </citations>
</tool>