annotate sleuth.xml @ 3:2c3d294dbe42 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sleuth commit 4adb19064a6973121680119529444286c24c1ac1

<tool id="sleuth" name="Sleuth" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="@PROFILE@">
    <description>Differential expression analysis</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro='xrefs'/>
    <expand macro='requirements'/>
    <stdio>
        <regex match="Execution halted"
           source="both"
           level="fatal"
           description="Execution halted."/>
        <regex match="Error in"
           source="both"
           level="fatal"
           description="An undefined error occurred, please check your input carefully and contact your administrator."/>
        <regex match="Fatal error"
           source="both"
           level="fatal"
           description="An undefined error occurred, please check your input carefully and contact your administrator."/>
    </stdio>
    <version_command><![CDATA[echo $(R --version | grep version | grep -v GNU)", sleuth version" $(R --vanilla --slave -e "library(sleuth); cat(sessionInfo()\$otherPkgs\$sleuth\$Version)" 2> /dev/null | grep -v -i "WARNING: ")]]></version_command>
    <command><![CDATA[
        #import os
        mkdir -p './kallisto_outputs' &&
        #set $cond_files = list()
        #if $experiment_design.selector == "single"
            #set $factor_levels = list()
            #set $cond_n_files = list()
            #for $level in $experiment_design.rep_factorLevel
                $factor_levels.append(str($level.factorLevel))
                $cond_n_files.append(len(str($level.countsFile).split(",")))
                #for $i, $count in enumerate(str($level.countsFile).split(","))
                    #set $fname = str($level.factorLevel) + "_"  + str($i) + '.h5'
                    #set $output_path =  "/".join(['./kallisto_outputs',$fname])
                    ln -s '${count}' $output_path &&
                    $cond_files.append($output_path)
                #end for
            #end for
        #else
            #for $count in $experiment_design.countsFile
                #set $output_path =  "/".join(['./kallisto_outputs',$count.element_identifier])
                ln -s '${count}' $output_path &&
                $cond_files.append($output_path)
            #end for
        #end if
        Rscript '${__tool_directory__}/sleuth.R'
            #if $experiment_design.selector == "single"
                #for $i, $factor in enumerate($factor_levels)
                    --factorLevel $factor
                    --factorLevel_n $cond_n_files[$i]
                #end for
            #else
                --metadata_file $experiment_design.metadata_file
            #end if
            #for $file in $cond_files
                --factorLevel_counts $file
            #end for
            --cores  \${GALAXY_SLOTS:-4}
            $advanced_options.normalization
            --nbins $advanced_options.nbins
            --lwr $advanced_options.lwr
            --upr $advanced_options.upr
            --experiment_design $experiment_design.selector
    ]]></command>
    <inputs>
        <conditional name="experiment_design">
            <param name="selector" type="select" label="Experiment design" help="If you have multiple experimental conditions, you should use propably the complex design mode. In the help section you can find more information.">
                <option value="single">Simple design mode (one experimental factor)</option>
                <option value="complex">Complex design mode (two or more experimental factors)</option>
            </param>
            <when value="single">
                <repeat name="rep_factorLevel" title="Factor level" min="2" default="2">
                    <param name="factorLevel" type="text" value="FactorLevel" label="Specify a factor level, typical values could be 'tumor', 'normal', 'treated' or 'control'"
                        help="Only letters, numbers and underscores will be retained in this field">
                        <sanitizer>
                            <valid initial="string.letters,string.digits"><add value="_"/></valid>
                        </sanitizer>
                    </param>
                    <param name="countsFile" type="data" format="h5" multiple="true" label="Counts file(s)"/>
                </repeat>
            </when>
            <when value="complex">
                <param name="countsFile" type="data_collection" format="h5" multiple="true" label="Counts file(s)"/>
                <param argument="--metadata_file" type="data" format="txt" label="Input metadata file" help="You can find more details about the format of the design table in the help section."/>
            </when>
        </conditional>
        <section name="advanced_options" title="Advanced options" expanded="true">
            <param argument="normalization" type="boolean" truevalue="--normalize" falsevalue="" checked="true" label="Normalize data" 
                help="If this is set to false, bootstraps will not be read and transformation of the data will not be done. This should 
                    only be set to false if one desires to do a quick check of the raw data. "/>
            <param argument="nbins" type="integer" min="0" value="100" label="NBins" help="The number of bins that the data should be 
                split for the sliding window shrinkage using the mean-variance curve."/>
            <param argument="lwr" type="float" min="0" max="1" value="0.25" label="LWR" help="The lower range of variances within each 
                bin that should be included for the shrinkage procedure. "/>
            <param argument="upr" type="float" min="0" max="1" value="0.75" label="UPR" help="The upper range of variances within each 
                bin that should be included for the shrinkage procedure."/>
        </section>

    </inputs>
    <outputs>
        <data name="sleuth_table" from_work_dir="sleuth_table.tab" format="tabular" label="${tool.name} on ${on_string}: DE table">
            <actions>
                <action name="column_names" type="metadata" default="target_id,pval,qval,test_stat,rss,degrees_free,mean_obs,var_obs,tech_var,sigma_sq,smooth_sigma_sq,final_sigma_sq"/>
            </actions>
        </data>
        <data name="pca_plot" from_work_dir="pca_plot.pdf" format="pdf" label="${tool.name} on ${on_string}: PCA plot"/>
        <data name="density_plot" from_work_dir="group_density.pdf" format="pdf" label="${tool.name} on ${on_string}: density plot"/>
    </outputs>
    <tests>
        <test expect_num_outputs="3">
            <repeat name="rep_factorLevel">
                <param name="factorLevel" value="Control"/>
                <param name="countsFile" value="kallisto_output_01.h5,kallisto_output_02.h5"/>
            </repeat>
            <repeat name="rep_factorLevel">
                <param name="factorLevel" value="Cancer"/>
                <param name="countsFile" value="kallisto_output_03.h5,kallisto_output_04.h5"/>
            </repeat>
            <section name="advanced_options">
                <param name="normalization" value="true"/>
                <param name="nbins" value="100"/>
                <param name="lwr" value="0.25"/>
                <param name="upr" value="0.75"/>
            </section>
            <output name="sleuth_table" ftype="tabular">
                <assert_contents>
                    <has_size value="689791" delta="100"/>
                    <has_text text="ENST00000281092.9"/>
                    <has_text text="ENST00000700211.1"/>
                </assert_contents>
            </output>
            <output name="pca_plot" file="test01_pca.pdf" ftype="pdf" compare="sim_size"/>
            <output name="density_plot" file="test01_density.pdf" ftype="pdf" compare="sim_size"/>
        </test>
        <test expect_num_outputs="3">
            <conditional name="experiment_design">
                <param name="selector" value="complex"/>
                <param name="countsFile">
                    <collection type="list">
                        <element name="kallisto_output_01.h5" ftype="h5" value="kallisto_output_01.h5"/>
                        <element name="kallisto_output_02.h5" ftype="h5" value="kallisto_output_02.h5"/>
                        <element name="kallisto_output_03.h5" ftype="h5" value="kallisto_output_03.h5"/>
                        <element name="kallisto_output_04.h5" ftype="h5" value="kallisto_output_04.h5"/>
                    </collection>
                </param>
                <param name="metadata_file" value="design_two_factors.tab"/>
            </conditional>
            <section name="advanced_options">
                <param name="normalization" value="true"/>
                <param name="nbins" value="100"/>
                <param name="lwr" value="0.25"/>
                <param name="upr" value="0.75"/>
            </section>
            <output name="sleuth_table" ftype="tabular">
                <assert_contents>
                    <has_size value="756425" delta="100"/>
                    <has_text text="ENST00000394894.8"/>
                    <has_text text="ENST00000524187.1"/>
                </assert_contents>
            </output>
            <output name="pca_plot" file="test02_pca.pdf" ftype="pdf" compare="sim_size"/>
            <output name="density_plot" file="test02_density.pdf" ftype="pdf" compare="sim_size"/>
        </test>
        <test expect_num_outputs="3">
            <conditional name="experiment_design">
                <param name="selector" value="complex"/>
                <param name="countsFile">
                    <collection type="list">
                        <element name="kallisto_output_01.h5" ftype="h5" value="kallisto_output_01.h5"/>
                        <element name="kallisto_output_02.h5" ftype="h5" value="kallisto_output_02.h5"/>
                        <element name="kallisto_output_03.h5" ftype="h5" value="kallisto_output_03.h5"/>
                        <element name="kallisto_output_04.h5" ftype="h5" value="kallisto_output_04.h5"/>
                    </collection>
                </param>
                <param name="metadata_file" value="design_three_factors.tab"/>
            </conditional>
            <section name="advanced_options">
                <param name="normalization" value="true"/>
                <param name="nbins" value="100"/>
                <param name="lwr" value="0.25"/>
                <param name="upr" value="0.75"/>
            </section>
            <output name="sleuth_table" ftype="tabular">
                <assert_contents>
                    <has_size value="756425" delta="100"/>
                    <has_text text="ENST00000394894.8"/>
                    <has_text text="ENST00000524187.1"/>
                </assert_contents>
            </output>
            <output name="pca_plot" file="test03_pca.pdf" ftype="pdf" compare="sim_size"/>
            <output name="density_plot" file="test03_density.pdf" ftype="pdf" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**Purpose**

Sleuth is a tool for the analysis and comparison of multiple related RNA-Seq experiments. Key features include:

- The ability to perform both transcript-level and gene-level analysis.
- Compatibility with kallisto enabling a fast and accurate workflow from reads to results.
- The use of bootstraps to ascertain and correct for technical variation in experiments.
- An interactive app for exploratory data analysis.

To use sleuth, RNA-Seq data must first be quantified with kallisto, which is a program for very fast RNA-Seq quantification based on 
pseudo-alignment. An important feature of kallisto is that it outputs bootstraps along with the estimates of transcript abundances. 
These can serve as proxies for technical replicates, allowing for an ascertainment of the variability in estimates due to the random 
processes underlying RNA-Seq as well as the statistical procedure of read assignment. 

.. class:: infomark

**Experimental design tabular input for complex experimental designs**

The experimental design input should have this format:

        ::
        
            data_filename	condition	sample
            finename_01.fastq.gz	condition1	replicate1
            filename_02.fastq.gz	condition1	replicate2
            filename_03.fastq.gz	condition2	replicate1
            filename_04.fastq.gz	condition2	replicate2


The tabular file **requires to have at least three columns with the same names as the previous example** (path, condition, sample). The path column correspond to original FASTQ filenames uploaded to Galaxy. 
Condition includes the information about the first factor, and sample includes information about the second factor. **Only alphanumeric characters, undescores and dots are allowed**. 
Additional factors can be included in the design table.

    ]]></help>
    <expand macro="citations"/>
</tool>