annotate NmrNormalization_xml.xml @ 0:a5e6499f1b4d draft default tip

planemo upload for repository https://github.com/workflow4metabolomics/spectral_normalization commit 559844c168f0450b9657346ba890d9c028d7537a

<tool id="spectral_normalization" name="Spectral Normalization" version="1.0.2">

    <description> Normalization of (preprocessed) spectra </description>

    <requirements>
	      <requirement type="package" version="1.1_4">r-batch</requirement>
    </requirements>

	  <stdio>
        <exit_code range="1:" level="fatal" />
    </stdio>

    <command>
        Rscript $__tool_directory__/NmrNormalization_wrapper.R

		    ## Data matrix of bucketed and integrated spectra
		    dataMatrix $dataMatrix

		    ## Normalization method
		    scalingMethod $scalingMethod.method
		    #if $scalingMethod.method == "PQN":
			    ## Sample metadata matrix
			    sampleMetadata $scalingMethod.sampleMetadata

			    ## Biological factor of interest (column number in samplemetadata)
			    factor $scalingMethod.factor

			    ## Reference class
			    controlGroup $scalingMethod.controlGroup
		    #end if
		    #if $scalingMethod.method == "QuantitativeVariable":
			    ## Sample metadata matrix
			    sampleMetadata $scalingMethod.sampleMetadata

			    ## Biological factor of interest (column number in samplemetadata)
			    factor $scalingMethod.factor
		    #end if

		    ## Spectra representation
		    graphType $graphType

		    ## Outputs
		    logOut $logOut
		    dataMatrixOut $dataMatrixOut
		    sampleMetadataOut $sampleMetadataOut
		    variableMetadataOut $variableMetadataOut
		    graphOut $graphOut


	</command>

	<inputs>
		<param name="dataMatrix" type="data" label="Data matrix of spectral data" help="" format="tabular" />

		<conditional name="scalingMethod" >
			<param name="method" label="Normalization method" type="select" help="Default method is total intensity" >
				<option value="None">None normalization</option>
				<option value="Total">Total intensity</option>
				<option value="PQN">Probabilistic Quotient Normalization</option>
				<option value="QuantitativeVariable">Quantitative variable</option>
			</param>
      <when value="None" />
      <when value="Total" />
			<when value="PQN">
				<param name="sampleMetadata" type="data" label="Sample metadata matrix" help="" format="tabular" />
				<param name="factor" label="Name of the column of the biological factor of interest (for PQN method)" type="text" />
				<param name="controlGroup" label="Name of reference level for PQN normalization" type="text" help=""/>
			</when>
			<when value="QuantitativeVariable">
				<param name="sampleMetadata" type="data" label="Sample metadata matrix" help="" format="tabular" />
				<param name="factor" label="Name of the column of the numerical variable for normalization (weight, osmolality, ...)" type="text" />
			</when>
		</conditional>

		<param name="graphType" label="Spectra representation" type="select" help="Select 'None' for no representation,'Overlay' to overlay all spectra on a unique chart and 'One per individual' to generate an individual chart for each observation">
			<option value="None"> none </option>
			<option value="Overlay"> Overlay </option>
			<option value="One_per_individual"> One_per_individual </option>
		</param>
	</inputs>


	<outputs>
		<data format="txt" name="logOut" label="${tool.name}_log" />
		<data format="tabular" name="sampleMetadataOut" label="${tool.name}_sampleMetadata" />
		<data format="tabular" name="variableMetadataOut" label="${tool.name}_variableMetadata" />
    <data format="tabular" name="dataMatrixOut" label="${tool.name}_dataMatrix" />
		<data format="pdf" name="graphOut" label="${tool.name}_spectra" >
			<filter> graphType != "None" </filter>
		</data>
	</outputs>

  <tests>
        <test>
            <param name="dataMatrix" value="MTBLS1_bucketedData.tabular" ftype="tabular" />
            <param name="scalingMethod|method" value="Total" />
            <param name="graphType" value="Overlay" />
            <output name="dataMatrixOut" file="MTBLS1_bucketedData_normalized.tabular" />
            <output name="sampleMetadataOut" file="MTBLS1_sampleMetadata_normalized.tabular" />
            <output name="variableMetadataOut" file="MTBLS1_variableMetadata_normalized.tabular" />
        </test>
    </tests>

	<help>

.. class:: infomark

**Authors** Marie Tremblay-Franco ([e-mail]) and Marion Landi ([e-mail])
  MetaboHUB: The French National Infrastructure for Metabolomics and Fluxomics (http://www.metabohub.fr/en)

---------------------------------------------------

.. class:: infomark

**Please cite**

F. Dieterle, A. Ross, G. Schlotterbeck, and H. Senn (2006). Probabilistic Quotient Normalization as Robust Method to Account for Dilution of Complex Biological Mixtures. Application in 1H NMR Metabonomics.
Analytical Chemistry 78(13): 4281-4290.

---------------------------------------------------

======================
Spectral Normalization
======================

-----------
Description
-----------

Normalization (operation applied on each (preprocessed) individual spectrum) of spectral data

-----------------
Workflow position
-----------------

**Upstream tools**

+----------------------+------------------------------------+---------+-------------+
| Name                 | output file                        | format  | parameter   |
+======================+====================================+=========+=============+
| NMR_Bucketing        | Normalization_bucketedData.tsv     | tabular | Ions Matrix |
+----------------------+------------------------------------+---------+-------------+




**Downstream tools**

+---------------------------+----------------------+--------+
| Name                      | Output file          | Format |
+===========================+======================+========+
|Univariate                 | variableMetadata.tsv | Tabular|
+---------------------------+----------------------+--------+
|Multivariate               | sampleMetadata.tsv   | Tabular|
+---------------------------+----------------------+--------+
|                           | variableMetadata.tsv | Tabular|
+---------------------------+----------------------+--------+


-----------
Input files
-----------

+---------------------------+------------+
| Parameter : num + label   |   Format   |
+===========================+============+
| DataMatrix                |   Tabular  |
+---------------------------+------------+

**DataMAtrix**

	| variable x sample dataMatrix tabular separated file containing (preprocessed) spectra, with . as decimal, and NA for missing values


----------
Parameters
----------

DataMatrix
	| see "Input files" section above
	|

Normalization method
	| normalization to apply on each spectrum:

+---------------------------+--------------------------------------+
| Name                      | Normalization                        |
+===========================+======================================+
|None                       | No                                   |
+---------------------------+--------------------------------------+
|Total                      | Total intensity                      |
+---------------------------+--------------------------------------+
|PQN                        | Probabilistic Quotient Normalization |
+---------------------------+--------------------------------------+
|QuantitativeVariable       | Weight, osmolality, ...              |
+---------------------------+--------------------------------------+


sampleMetadata
	| sample x metadata **sample** tabular separated file of the numeric and/or character sample metadata, with . as decimal and NA for missing values
	| Mandatory for "PQN" or "Quantitative" normalization method
	| The row names must be identical to the column names of the dataMatrix file
	|


Spectra representation:
	| Graphical chart of bucketed and integrated raw files
	| If "Overlay": the n (sample number) spectra are overlaid on the same figure
	| If "One_per_individual": pdf file includes n pages (1 per sample)
	|


------------
Output files
------------


dataMatrix.tsv
	| tabular output
	| Data matrix with p rows (buckets) and n columns (samples) containing the intensities
	|

sampleMetadata.tsv
	| tabular output
	| sampleMetadata file identical to the file given as argument if "PQN" or "Quantitative" normalization method; file with n rows (samples) and 2 columns containing sample identifier (rownames) and sample order if "None" or "Total" normalization methof
	| Mandatory file in the statistical analysis step of the workflow
	|

variableMetadata.tsv
	| tabular output
	| file with p rows (buckets) and 2 columns containing variable identifier (rownames) and bucket order. Can add columns with numeric and/or character variable metadata.
	| Mandatory file in the statistical analysis step of the workflow
	|

spectra.pdf
	| pdf output
	| Graphical chart of bucketed and integrated data
	|


---------------------------------------------------

---------------
Working example
---------------


.. class:: warningmark

Under construction

.. image:: ./static/images/Mth_Travaux.png
        :width: 100


---------------------------------------------------

--------------
Changelog/News
--------------

**Version 1.0.2 - 22/10/2016**

- NEW: this tool was previously named NMR Normalization. It had been generalize to deal with all kind of spectral data

**Version 1.0.1 - 14/04/2016**

- TEST: refactoring to pass planemo test using conda dependencies


**Version 2015-01-28 - 28/01/2015**

   </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btu813</citation>
    </citations>
</tool>