annotate macros.xml @ 4:050cfef6ba65 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/ramclustr commit 981ab05cdced6cbcbb1f13aa492e127365a4e9ed

<macros>
    <token name="@TOOL_VERSION@">1.3.0</token>

    <xml name="creator">
        <creator>
            <person
                givenName="Helge"
                familyName="Hecht"
                url="https://github.com/hechth"
                identifier="0000-0001-6744-996X" />
            <person
                givenName="Maksym"
                familyName="Skoryk"
                url="https://github.com/maximskorik"
                identifier="0000-0003-2056-8018" />
            <person
                givenName="Matej"
                familyName="Troják"
                url="https://github.com/xtrojak"
                identifier="0000-0003-0841-2707" />
            <person
                givenName="Martin"
                familyName="Čech"
                url="https://github.com/martenson"
                identifier="0000-0002-9318-1781" />
            <person
                givenName="Zargham"
                familyName="Ahmad"
                url="https://github.com/zargham-ahmad"
                identifier="0000-0002-6096-224X" />
            <organization
                url="https://www.recetox.muni.cz/"
                email="[e-mail]"
                name="RECETOX MUNI"/>
        </creator>
    </xml>

    <xml name="parameters_csv">
        <section name="ms_csv" title="Input MS Data as CSV" expanded="true">
            <param label="Input CSV" name="ms" type="data" format="csv"
                   help="Features as columns, rows as samples. Column header in format mz_rt."/>
            <param label="idMSMS" name="idmsms" type="data" format="csv" optional="true"
                   help="Optional idMSMS / MSe csv data. Same dimension and names as in input CSV are required."/>
            <param label="phenoData" name="csv_phenoData" type="data" format="csv" optional="true"
                   help="Optional csv containing phenoData."/>
        </section>
    </xml>

    <xml name="parameters_xcms">
        <section name="xcms" title="Input MS Data as XCMS" expanded="true">
            <param name="input_xcms" label="Input XCMS" type="data" format="rdata.xcms.fillpeaks"
                   help="Grouped feature data for clustering." />
        </section>
    </xml>

    <xml name="parameters_recetox_aplcms">
        <section name="ms_dataframe" title="Input MS Data as parquet (output from recetox-aplcms)" expanded="true">
            <param label="Input MS1 featureDefinitions" name="ms1_featureDefinitions" type="data" format="parquet"
                   help="Metadata with columns: mz, rt, feature names containing MS data."/>
            <param label="Input MS1 featureValues" name="ms1_featureValues" type="data" format="parquet"
                   help="data with rownames = sample names, colnames = feature names containing MS data."/>
            <param label="phenoData" name="df_phenoData" type="data" format="tsv,csv" optional="true"
                   help="CSV/TSV file containing phenoData (optional)."/>
        </section>
    </xml>

    <xml name="parameters_required">
        <param label="Sigma r" name="sr" type="float" value="0.5" help="Correlational similarity between features."/>
        <param label="Correlation method" name="cor_method" type="select" display="radio"
               help="Choose correlational method to be used - see [1] for details.">
            <option value="pearson" selected="true">pearson</option>
            <option value="spearman">spearman</option>
            <option value="kendall">kendall</option>
        </param>
        <param label="Maximum RT difference" name="maxt" value="60" type="float"
               help="Maximum difference to calculate RT similarity - values beyond this are assigned zero similarity."/>
    </xml>

    <xml name="main_parameters">
        <section name="clustering" title="Clustering" expanded="true">
            <param label="Clustering linkage method" name="linkage" type="select" display="radio"
                   help="Choose hierarchical clustering linkage method - see [2] for details.">
                <option value="average" selected="true">average</option>
                <option value="ward.D">ward.D</option>
                <option value="ward.D2">ward.D2</option>
                <option value="single">single</option>
                <option value="complete">complete</option>
                <option value="mcquitty">mcquitty</option>
                <option value="median">median</option>
                <option value="centroid">centroid</option>
            </param>
            <param label="Minimal cluster size" name="minModuleSize" type="integer" value="2"
                   help="Minimal size (number of features) of a cluster."/>
            <param label="Maximal tree height" name="hmax" type="float" value="0.3"
                   help="Cut the Hierarchical Cluster Analysis tree at this height, see [3] for details."/>
            <param label="Use deepSplit" name="deepSplit" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
                   help="Check to produce more smaller clusters, uncheck for fewer bigger clusters, see [3] for details."/>
        </section>

        <section name="normalisation" title="Normalisation" expanded="true">
            <conditional name="normalisation_method">
                <param label="Normalisation method" name="normalize" type="select" display="radio"
                       help="Choose method for normalization of feature intensities.">
                    <option value="none" selected="true">none</option>
                    <option value="TIC">TIC</option>
                    <option value="quantile">quantile</option>
                    <option value="batch.qc">batch.qc</option>
                    <option value="qc">qc</option>
                </param>
                <when value="batch.qc">
                    <param label="Metadata details" name="batch_order_qc" type="data" format="csv"
                           help="CSV with sample names (or indices, currently not handled) on rows and columns with:
                           batch number ('batch'), position in sequence ('order'), and whether it is a QC sample or not
                           ('qc' with true/false OR 'sampleType' with 'sample/qc/blank')."/>
                    <param label="QC injection range" name="qc_inj_range" type="integer" value="20"
                             help="How many injections around each injection are to be scanned for presence of QC samples?
                             A good rule of thumb is between 1 and 3 times the typical
                             injection span between QC injections. i.e. if you inject QC ever 7 samples, set this to
                             between 7 and 21. Smaller values provide more local precision but make normalization sensitive
                             to individual poor outliers (though these are first removed using the boxplot function outlier
                             detection), while wider values provide less local precision in normalization but better
                             stability to individual peak areas."/>
                </when>
                <when value="qc">
                    <param label="Metadata details" name="batch_order_qc" type="data" format="csv" optional="true"
                           help="CSV with sample names (or indices, currently not handled) on rows and columns with:
                           batch number ('batch'), position in sequence ('order'), and whether it is a QC sample or not
                           ('qc' with true/false OR 'sampleType' with 'sample/qc/blank')."/>
                    <param label="p.cut" name="p_cut" type="float" value="0.05" 
                            help="Numeric when run order correction is applied, only features showing a run order vs 
                            signal with a linear p-value (after FDR correction) &lt; p.cut will be adjusted.  also requires 
                            r-squared &lt; rsq.cut."/>
                    <param label="rsq.cut" name="rsq_cut" type="float" value="0.1" 
                            help="Numeric when run order correction is applied, only features showing a run order vs signal 
                            with a linear r-squared &gt; rsq.cut will be adjusted. also requires p values &lt; p.cut."/>
                    <param label="p.adjust" name="p_adjust" type="text" value="none" 
                            help="Which p-value adjustment should be used? one of ['holm', 'hochberg', 'hommel', 'bonferroni', 'BH', 
                            'BY', 'fdr', 'none']"/>
                </when>
                <when value="none"/>
                <when value="TIC"/>
                <when value="quantile"/>
            </conditional>
        </section>

        <section name="performance" title="Performance">
            <param label="Blocksize" name="blocksize" type="integer" value="2000"
                   help="Number of features processed in one block."/>
            <param label="Blocksize factor" name="mult" type="integer" value="5"
                   help="Factor to scale blocksize to influence processing speed."/>
        </section>

        <section name="msp_output_details" title="MSP output">
            <param label="Merge MSP Files" name="merge_msp" type="boolean" truevalue="TRUE" falsevalue="FALSE"
                   checked="true" help="Merge all MSP in one file or export one MSP per spectra."/>
            <param label="m/z decimal places" name="mzdec" type="integer" value="6"
                   help="Number of decimal places used in printing m/z values."/>
            <!--
            Currently not forwarded because the MSP is exported always manually afterwards
            <param label="mspout" name="mspout" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" help="write msp formatted spectra to file?" />
            -->
        </section>

        <section name="extras" title="Extras">
            <param label="RT only low n" name="rt_only_low_n" type="boolean" truevalue="TRUE" falsevalue="FALSE"
                   checked="true"
                   help="At low injection numbers, correlational relationships of peak intensities may be unreliable.
                   By default, RAMClustR will simply ignore the correlational Sigma r value and cluster on retention time alone.
                   If you wish to use correlation with at n less than 5, set this value to FALSE."/>
            <param label="Replace zeros" name="replace_zeros" type="boolean" truevalue="TRUE" falsevalue="FALSE"
                   checked="true"
                   help="NA, NaN, and Inf values are replaced with zero, and zero values are sometimes returned from
                   peak peaking. When TRUE, zero values will be replaced with a small amount of noise, with noise level
                   set based on the detected signal intensities for that feature."/>
            <param label="Experimental design metadata" name="ExpDes" type="data" format="csv" optional="true"
                   help="Definition of experimental design in CSV format." />
        </section>
    </xml>

    <xml name="output_msp">
       <collection label="Mass spectra from ${tool.name} on ${on_string} list" name="mass_spectra_collection" type="list">
           <discover_datasets pattern="__name_and_ext__" directory="spectra" recurse="true" ext="msp"/>
           <filter>not msp_output_details['merge_msp']</filter>
       </collection>
       <data label="Mass spectra from ${tool.name} on ${on_string}" name="mass_spectra_merged" format="msp">
           <filter>msp_output_details['merge_msp']</filter>
       </data>
    </xml>

    <xml name="citations">
        <citations>
            <!-- Example of annotating a citation using a BibTex entry. -->
            <citation type="bibtex">
                @article{Broeckling2014e,
                abstract = {Metabolomic data are frequently acquired using chromatographically coupled mass spectrometry
                (MS) platforms. For such datasets, the first step in data analysis relies on feature detection, where a
                feature is defined by a mass and retention time. While a feature typically is derived from a single
                compound, a spectrum of mass signals is more a more-accurate representation of the mass spectrometric
                signal for a given metabolite. Here, we report a novel feature grouping method that operates in an
                unsupervised manner to group signals from MS data into spectra without relying on predictability of the
                in-source phenomenon. We additionally address a fundamental bottleneck in metabolomics, annotation of MS
                level signals, by incorporating indiscriminant MS/MS (idMS/MS) data implicitly: feature detection is
                performed on both MS and idMS/MS data, and feature-feature relationships are determined simultaneously
                from the MS and idMS/MS data. This approach facilitates identification of metabolites using in-source MS
                and/or idMS/MS spectra from a single experiment, reduces quantitative analytical variation compared to
                single-feature measures, and decreases false positive annotations of unpredictable phenomenon as novel
                compounds. This tool is released as a freely available R package, called RAMClustR, and is sufficiently
                versatile to group features from any chromatographic-spectrometric platform or feature-finding software.
                {\textcopyright} 2014 American Chemical Society.},
                author = {Broeckling, C. D. and Afsar, F. A. and Neumann, S. and Ben-Hur, A. and Prenni, J. E.},
                doi = {10.1021/ac501530d},
                issn = {15206882},
                journal = {Analytical Chemistry},
                number = {14},
                pages = {6812--6817},
                pmid = {24927477},
                title = {{RAMClust: A novel feature clustering method enables spectral-matching-based annotation for
                metabolomics data}},
                volume = {86},
                year = {2014}
                }
            </citation>
        </citations>
    </xml>

    <token name="@HELP@">
        <![CDATA[
            Documentation
                    For documentation on the tool see https://github.com/cbroeckl/RAMClustR/blob/master/vignettes/RAMClustR.Rmd

                Upstream Tools
                    +------------------------------+-------------------------------+----------------------+---------------------+
                    | Name                         | Output File                   | Format               | Parameter           |
                    +==============================+===============================+======================+=====================+
                    | xcms                         | xset.fillPeaks.RData          | rdata.xcms.fillpeaks | xcmsObj             |
                    +------------------------------+-------------------------------+----------------------+---------------------+
                    | RAMClustR define experiment  | Table with experiment details | csv                  | Experimental design |
                    +------------------------------+-------------------------------+----------------------+---------------------+

                    The tool takes an **xcmsSet** object as input and extracts all relevant information.

                    +-------+------------------------+--------+------------+
                    | Name  | Output File            | Format | Parameter  |
                    +=======+========================+========+============+
                    | ???   | Feature Table with MS1 | csv    | ms         |
                    +-------+------------------------+--------+------------+
                    | ???   | Feature Table with MS2 | csv    | idmsms     |
                    +-------+------------------------+--------+------------+

                    Alternatively, the tool takes a **csv** table as input which has to fulfill the following requirements

                    (1) no more than one sample (or file) name column and one feature name row;
                    (2) feature names that contain the mass and retention times, separated by a constant delimiter; and
                    (3) features in columns and samples in rows.

                    +----------------------+-------------------+-------------------+--------------------+--------------------+
                    | sample               |    100.88_262.464 |    100.01_423.699 |    100.003_128.313 |   100.0057_154.686 |
                    +======================+===================+===================+====================+====================+
                    | 10_qc_16x_dil_milliq |    0              |    195953.6376	   |     0              |   0                |
                    +----------------------+-------------------+-------------------+--------------------+--------------------+
                    | 11_qc_8x_dil_milliq  |    0              |    117742.1828    |    4247300.664     |   0                |
                    +----------------------+-------------------+-------------------+--------------------+--------------------+
                    | 12_qc_32x_dil_milliq |    4470859.38     |    0              |    2206092.112     |   0                |
                    +----------------------+-------------------+-------------------+--------------------+--------------------+
                    | 15_qc_16x_dil_milliq |    0              |    0              |    2767477.481     |   0                |
                    +----------------------+-------------------+-------------------+--------------------+--------------------+


                Downstream Tools
                    The output is a msp file or a collection of msp files, with additional Spec Abundance file.

                    +---------+--------------+----------------------+
                    | Name    | Output File  | Format               |
                    +=========+==============+======================+
                    | matchMS | Mass Spectra | collection (tgz/msp) |
                    +---------+--------------+----------------------+

        @GENERAL_HELP@
        ]]>
    </token>

    <token name="@GENERAL_HELP@">
        Background
            Metabolomics
                Metabolomics is frequently performed using chromatographically coupled mass spectrometry, with gas
                chromatography, liquid chromatography, and capillary electrophoresis being the most frequently utilized
                methods of separation. The coupling of chromatography to mass spectrometry is enabled with an
                appropriate ionization source - electron impact (EI) for gas phase separations and electrospray
                ionization (ESI) for liquid phase separations. XCMS is a commonly used tool to detect all the signals
                from a metabolomics dataset, generating aligned features, where a feature is represented by a mass and
                retention time. Each feature is presumed to derive from a single compound. However, each compound is
                represented by several features. With any ionization method, isotopic peaks will be observed reflective
                of the elemental composition of the analyte. In EI, fragmentation is a byproduct of ionization, and has
                driven the generation of large mass spectral libraries. In ESI, in-source fragmentation frequently
                occurs, the magnitude of which is compound dependent, with more labile compounds being more prone to
                in-source fragmentation. ESI can also product multiple adduct forms (protonated, potassiated, sodiated,
                ammoniated...), and can produce multimers (i.e. [2M+H]+, [3M+K]+, etc) and multiple charged species
                ([M+2H]++). This can become further complicated by considering combinations of these phenomena. For
                example [2M+3H]+++ (triply charged dimer) or an in-source fragment of a dimer.

            RAMClustR approach
                RAMClustR was designed to group features designed from the same compound using an approach which is
                **1.** unsupervised, **2.** platform agnostic, and **3.** devoid of curated rules, as the depth of
                understanding of these processes is insufficient to enable accurate curation/prediction of all phenomenon
                that may occur. We achieve this by making two assumptions. The first is that two features derived
                from the same compound with have (approximately) the same retention time. The second is that two
                features derived from the same compound will have (approximately) the same quantitative trend across
                all samples in the xcms sample set. From these assumptions, we can calculate a retention time
                similarity score and a correlational similarity score for each feature pair. A high similarity score
                for both retention time and correlation indicates a strong probability that two features derive from
                the same compound. Since both conditions must be met, the product of the two similarity scores provides
                the best approximation of the total similarity score - i.e. a feature pair with retention time similarity
                of 1 and correlational similarity of 0 is unlikely to derive from one compound - 1 x 0 = 0, the final
                similarity score is zero, indicating the two features represent two different compounds. Similarly, a
                feature pair with retention time similarity of 0 and correlational similarity of 1 is unlikely to derive
                from one compound - 0 x 1 = 0. Alternatively - a feature pair with retention time similarity of 1 and
                correlational similarity of 1 is likely to derive from one compound - 1 x 1 = 1.

        The RAMClustR algorithm is built on creating similarity scores for all pairs of features, submitting
        this score matrix for hierarchical clustering, and then cutting the resulting dendrogram into neat
        chunks using the dynamicTreeCut package - where each 'chunk' of the dendrogram results in a group of
        features likely to be derived from a single compound. Importantly, this is achieved without looking for
        specific phenomenon (i.e. sodiation), meaning that grouping can be performed on any dataset, whether it
        is positive or negative ionization mode, EI or ESI, LC-MS GC-MS or CE-MS, in-source fragment or complex
        adduction event, and predictable or unpredictable signals.
    </token>

        <token name="@HELP_experiment@">
        <![CDATA[
            Create an Experimental Design specification for RAMClustR experiment.

            Downstream Tools
                +-----------+-----------------------+--------+
                | Name      | Output File           | Format |
                +===========+=======================+========+
                | RAMClustR | Experiment definition | csv    |
                +-----------+-----------------------+--------+

        ]]>
    </token>
</macros>