comparison msi_preprocessing.xml @ 6:d3fd539f477e draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_preprocessing commit 6d877681b6188999b4f5abb1843b420078b71b92

5:2fccfd11360d

<tool id="mass_spectrometry_imaging_preprocessing" name="MSI preprocessing" version="1.10.0.2">
    <description>
        mass spectrometry imaging preprocessing
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</requirement>
        <requirement type="package" version="0.20-35">r-lattice</requirement>
        <!--requirement type="package" version="3.34.9">bioconductor-limma</requirement-->
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[

        #if $infile.ext == 'imzml'

################################# load libraries and read file #################

library(Cardinal)
library(gridExtra)
library(lattice)
###library(limma)

#if $infile.ext == 'imzml'
    msidata <- readImzML('infile', mass.accuracy=$accuracy, units.accuracy = "$units")
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    load('infile.RData')
#end if

    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,rdata,danalyze75"
            label="MSI data as imzml, analyze7.5 or Cardinal MSImageSet saved as RData"
            help="load imzml and ibd file by uploading composite datatype imzml"/>
        <param name="accuracy" type="float" value="50" label="Only for processed imzML files: enter mass accuracy to which the m/z values will be binned" help="This should be set to the native accuracy of the mass spectrometer, if known"/>
        <param name="units" display="radio" type="select" label="Only for processed imzML files: unit of the mass accuracy" help="either m/z or ppm">
            <option value="mz" >mz</option>
            <option value="ppm" selected="True" >ppm</option>
        </param>
        <repeat name="methods" title="Preprocessing" min="1" max="50">
            <conditional name="methods_conditional">
                <param name="preprocessing_method" type="select" label="Select the preprocessing methods you want to apply">
                    <option value="Normalization" selected="True">Normalization to TIC</option>
                    <option value="Baseline_reduction">Baseline Reduction</option>

                            <param name="value_diffalignment" type="integer" value="200"
                                   label="diff.max" help="Peaks that differ less than this value will be aligned together"/>
                            <param name="units_diffalignment" type="select" display = "radio" optional = "False"
                                   label="units">
                                    <option value="ppm" selected="True">ppm</option>
                                    <option value="Da">Da</option>
                            </param>
                        </when>
                        <when value="DP">
                            <param name="gap_DPalignment" type="integer" value="0"
                                   label="Gap" help="The gap penalty for the dynamic programming sequence alignment"/>

- Smoothening: Smoothing of the peaks reduces noise and improves peak detection
- Peak picking: relevant peaks are picked while noise-peaks are removed (needs peak alignment afterwards)
- Peak alignment: only possible after peak picking, m/z inaccuracies are removed by alignment of same peaks to a common m/z value
- Peak filtering: works only on centroided data (after peak picking and alignment or data reduction with peak filtering), removes peaks that occur only in a small proportion of pixels. If not sure which cutoff to chose run qualitycontrol first and decide according to the zero value plot.
- Data reduction: binning, resampling or peak filtering to reduce data


Output: 

- imzML file, preprocessed

6:d3fd539f477e

<tool id="mass_spectrometry_imaging_preprocessing" name="MSI preprocessing" version="1.10.0.3">
    <description>
        mass spectrometry imaging preprocessing
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</requirement>
        <requirement type="package" version="0.20-35">r-lattice</requirement>
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[

        #if $infile.ext == 'imzml'

################################# load libraries and read file #################

library(Cardinal)
library(gridExtra)
library(lattice)

#if $infile.ext == 'imzml'
    #if str($processed_cond.processed_file) == "processed":
        msidata <- readImzML('infile', mass.accuracy=$processed_cond.accuracy, units.accuracy = "$processed_cond.units")
    #else
        msidata <- readImzML('infile')
    #end if
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    load('infile.RData')
#end if

    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,rdata,danalyze75"
            label="MSI data as imzml, analyze7.5 or Cardinal MSImageSet saved as RData"
            help="load imzml and ibd file by uploading composite datatype imzml"/>
        <conditional name="processed_cond">
            <param name="processed_file" type="select" label="Is the input file a processed imzML file ">
                <option value="no_processed" selected="True">not a processed imzML</option>
                <option value="processed">processed imzML</option>
            </param>
            <when value="no_processed"/>
            <when value="processed">
                <param name="accuracy" type="float" value="50" label="Mass accuracy to which the m/z values will be binned" help="This should be set to the native accuracy of the mass spectrometer, if known"/>
                <param name="units" display="radio" type="select" label="Unit of the mass accuracy" help="either m/z or ppm">
                    <option value="mz" >mz</option>
                    <option value="ppm" selected="True" >ppm</option>
                </param>
            </when>
        </conditional>
        <repeat name="methods" title="Preprocessing" min="1" max="50">
            <conditional name="methods_conditional">
                <param name="preprocessing_method" type="select" label="Select the preprocessing methods you want to apply">
                    <option value="Normalization" selected="True">Normalization to TIC</option>
                    <option value="Baseline_reduction">Baseline Reduction</option>

                            <param name="value_diffalignment" type="integer" value="200"
                                   label="diff.max" help="Peaks that differ less than this value will be aligned together"/>
                            <param name="units_diffalignment" type="select" display = "radio" optional = "False"
                                   label="units">
                                    <option value="ppm" selected="True">ppm</option>
                                    <option value="Da">m/z</option>
                            </param>
                        </when>
                        <when value="DP">
                            <param name="gap_DPalignment" type="integer" value="0"
                                   label="Gap" help="The gap penalty for the dynamic programming sequence alignment"/>

- Smoothening: Smoothing of the peaks reduces noise and improves peak detection
- Peak picking: relevant peaks are picked while noise-peaks are removed (needs peak alignment afterwards)
- Peak alignment: only possible after peak picking, m/z inaccuracies are removed by alignment of same peaks to a common m/z value
- Peak filtering: works only on centroided data (after peak picking and alignment or data reduction with peak filtering), removes peaks that occur only in a small proportion of pixels. If not sure which cutoff to chose run qualitycontrol first and decide according to the zero value plot.
- Data reduction: binning, resampling or peak filtering to reduce data
- Transformation: log2 or squareroot transformation of all intensities; when using log2 transformation zero intensities will become NA, this can lead to compatibility problems. 


Output: 

- imzML file, preprocessed