annotate genomic_super_signature.xml @ 0:d0cbe6cc1f04 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/genomic_super_signature commit 1aadd5dce3b254e7714c2fdd39413029fd4b9b7a"

<tool id="genomic_super_signature" name="GenomicSuperSignature" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.01">
    <description>interpretation of RNAseq experiments</description>
    <macros>
        <token name="@TOOL_VERSION@">1.2.0</token>
        <token name="@GALAXY_VERSION@">0</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">bioconductor-genomicsupersignature</requirement>
        <requirement type="package" version="1.7.1">r-optparse</requirement>
        <requirement type="package" version="2.6">r-wordcloud</requirement>
        <requirement type="package" version="2.22.0">bioconductor-biocstyle</requirement>
        <requirement type="package" version="2.7.3">r-magick</requirement>
        <requirement type="package" version="2021d">tzdata</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #set $model = $model.fields.path
        mkdir out &&
        Rscript '$__tool_directory__/gss.R' --input '$input' --model '$model' --method '$method'  --maxFrom '$maxFrom' --level '$level' --scale '$scale' --numOut $numOut --outDir out --toolDir '$__tool_directory__' --validate '$validate' --html '$html'
    ]]></command>
    <inputs>
        <param argument="--input" type="data" format="tabular,tsv" label="Tabular count matrix"/>
        <param argument="--model" type="select" label="Using RAVmodel" help="Select model from the list">
            <options from_data_table="genomic_super_signature_ravmodels">
                <filter type="data_meta" ref="input" key="dbkey" column="dbkey" />
            </options>
            <validator type="no_options" message="A built-in RAVmodel is not available for the build associated with the selected input file"/>
        </param>
        <param argument="--method" type="select" label="Select a correlation coefficient">
            <option value="pearson">Pearson</option>
            <option value="kendall">Kendall</option>
            <option value="spearman">Spearman</option>
        </param>
        <param argument="--maxFrom" type="select" label="Select whether to display the maximum value from dataset's PCs or avgLoadings" help="With Principal Component (PC), the maximum correlation coefficient from top 8 PCs for each avgLoading will be selected as an output. If you choose Average Loading, the Average Loading with the maximum correlation coefficient with each Principal Component will be in the output.">
            <option value="pc">Principal Components</option>
            <option value="avgLoading">Average Loading</option>
        </param>
        <param argument="--level" type="select" label="Output format of validated result" help="max will output the matrix containing only the maximum coefficient. To get the coefficient of all 8 PCs, set this argument to all.">
            <option value="max">Max</option>
            <option value="all">All</option>
        </param>
        <param argument="--scale" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Normalize rows of datasets?"/>
        <param argument="--numOut" type="integer" min="1" value="3" label="The number of top validated RAVs to check"/>
    </inputs>
    <outputs>
        <collection name="genesets" type="list" label="GenomicSuperSignature Genesets">
            <discover_datasets pattern=".*_genesets_(?P&lt;name&gt;.+)\.csv" format="csv" directory="out" />
        </collection>
        <collection name="literatures" type="list" label="GenomicSuperSignature Literatures">
            <discover_datasets pattern=".*_literatures_(?P&lt;name&gt;.+)\.csv" format="csv" directory="out" />
        </collection>
        <data name="validate" format="csv" label="GenomicSuperSignature validate.csv">
        </data>
        <data name="html" format="html" label="GenomicSuperSignature report.html">
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input" value="bcellViperExpr_10C.tsv.gz" dbkey="hg38" ftype="tabular"/>
            <param name="model" value="microRAVmodel" dbkey="hg38"/>
            <param name="method" value="Pearson"/>
            <param name="maxFrom" value="Principal Components"/>
            <param name="level" value="Max"/>
            <param name="numOut" value="1"/>
            <output name="html" ftype="html">
                 <assert_contents>
                    <has_n_lines n="2843"/>
                 </assert_contents>
             </output>
            <output name="validate" ftype="csv">
                 <assert_contents>
                    <has_line line='"","score","PC","sw","cl_size","cl_num"'/>
                    <has_text text='"RAV1076"'/>
                    <has_text text='"RAV725"'/>
                    <has_text text='"RAV884"'/>
                    <has_text text='"RAV1994"'/>
                    <has_n_lines n="5"/>
                 </assert_contents>
             </output>
        </test>
    </tests>
    <help><![CDATA[
GenomicSuperSignature
=====================

What it does
------------

Connect new gene expression profile with the relevant information from
the existing databases, such as previous publications, MeSH terms, and
gene sets.

Inputs
------

Count Files
~~~~~~~~~~~

GenomicSuperSignature takes a count matrix as an input. Input file
should have row names in gene symbols and column names in sample ID. For
the best result, we recommend a data transformation (e.g. log2) for the
input to follow a normal distribution, while scaling is NOT recommended.
Currently for validation, inputs need at least eight samples.

Example of input format:

===== ======== ========= ======== =========
\     GSM44075 GSM44078  GSM44080 GSM44081
===== ======== ========= ======== =========
ADA   9.571369 10.599436 8.740659 10.104469
CDH2  6.175890 5.312704  5.651928 4.462205
MED6  9.671113 8.773383  9.190276 9.526235
NR2E3 9.847733 9.582061  9.628792 8.820422
===== ======== ========= ======== =========

RAVmodel
~~~~~~~~

*R*\ eplicable *A*\ xes of *V*\ ariation (RAV) consists of principal
components repeatedly observed in an independent analysis of multiple
published datasets. RAVs connect different databases that are both
linked to the originated study or associated with the RAV itself through
the gene rankings of it. RAVmodel contains the collection of RAVs
(RAVindex), metadata from model building process and the additional
annotations. Currently, two RAVmodels are available based on the gene
sets used for annotation.

1) C2 : RAVmodel annotated with Molecular Signatures Database (MSigDB)
   curated gene sets (version 7.1)
2) PLIERpriors : RAVmodel annotated with the three gene sets provided in
   the `PLIER package <https://github.com/wgmao/PLIER>`__ -
   bloodCellMarkersIRISDMAP, svmMarkers, and canonicalPathways

Outputs
-------

There are four categories of outputs from this tool, which is one html
file and three csv tabular files. The actual number of csv files will
vary depending on the parameter, *–numOut*, and the validated RAVs.

validate.csv
~~~~~~~~~~~~

+--------------------------+--------------------------------------------+
| Column                   | Description                                |
+==========================+============================================+
| score                    | the maximum pearson correlation            |
|                          | coefficient between the top 8 PCs of the   |
|                          | input and RAVs                             |
+--------------------------+--------------------------------------------+
| PC                       | one of the top 8 PCs of the input, which   |
|                          | gives the highest *score*                  |
+--------------------------+--------------------------------------------+
| sw                       | the average silhouette width of the RAV    |
+--------------------------+--------------------------------------------+
| cl_size                  | the size of each RAV                       |
+--------------------------+--------------------------------------------+
| cl_num                   | the RAV number                             |
+--------------------------+--------------------------------------------+

Genesets
~~~~~~~~

This is the enriched gene sets for the target RAV, calculated from the
ranked gene list. Gene sets with the adjusted p-value < 0.05 are
included.

=========== ================================
Column      Description
=========== ================================
Description name of the gene sets
NES         normalized enrichment score (ES)
pvalue      statistical significance
qvalues     p-value adjusted for the FDR
=========== ================================

Literatures
~~~~~~~~~~~

========= ======================
Column    Description
========= ======================
studyName study accession
title     the title of the study
========= ======================

report.html
~~~~~~~~~~~

A html file with the summary of the main analyses by
GenomicSuperSignature. It includes MeSH terms in word cloud and an
interactive plot overviewing the validated RAVs, in addition to the
previews of the tabular output files.

Citations
---------

Oh, S., Geistlinger, L., Ramos, M., Taroni, J.N., Carey, V.J., Greene,
C.S., Waldron, L., & Davis, S.R. (2021). GenomicSuperSignature:
interpretation of RNA-seq experiments through robust, efficient
comparison to public databases. bioRxiv.

References
----------

| GenomicSuperSignature package:
  `webpage <https://shbrief.github.io/GenomicSuperSignature/>`__
| GenomicSuperSignature usecases:
  `webpage <https://shbrief.github.io/GenomicSuperSignaturePaper/>`__
    ]]></help>
    <citations>
        <citation type="doi">10.1101/2021.05.26.445900</citation>
    </citations>
</tool>