cardinal_preprocessing: preprocessing.xml comparison

comparison preprocessing.xml @ 6:cbd9e4df377d draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit 15e24b1f0143679647906bc427654f66b417a45c"

author	galaxyp
date	Wed, 25 Mar 2020 09:25:47 +0000
parents	84f422579d39
children	173070dafe95

comparison

equal deleted inserted replaced

-:84f422579d39
+:cbd9e4df377d
-<tool id="cardinal_preprocessing" name="MSI preprocessing" version="@VERSION@.3">
+<tool id="cardinal_preprocessing" name="MSI preprocessing" version="2.4.0.0">
 <description>
 mass spectrometry imaging preprocessing
 </description>
 <macros>
 <import>macros.xml</import>
 </macros>
-<expand macro="requirements">
+<requirements>
+<requirement type="package" version="2.4.0">bioconductor-cardinal</requirement>
+<requirement type="package" version="3.6.1">r-base</requirement>
 <requirement type="package" version="2.3">r-gridextra</requirement>
-<requirement type="package" version="3.0">r-ggplot2</requirement>
+<requirement type="package" version="3.2.1">r-ggplot2</requirement>
-<requirement type="package" version="0.20_35">r-lattice</requirement>
+<requirement type="package" version="0.20_38">r-lattice</requirement>
-</expand>
+</requirements>
 <command detect_errors="exit_code">
 <![CDATA[
 @INPUT_LINKING@
 cat '${cardinal_preprocessing}' &&
 Rscript '${cardinal_preprocessing}' &&
-#if str($imzml_output) == "imzml_format":
 mkdir $outfile_imzml.files_path &&
 mv ./out.imzML "${os.path.join($outfile_imzml.files_path, 'imzml')}" | true &&
 mv ./out.ibd "${os.path.join($outfile_imzml.files_path, 'ibd')}" | true &&
-#end if
 echo "imzML file:" > $outfile_imzml &&
 ls -l "$outfile_imzml.files_path" >> $outfile_imzml
 ]]>
 </command>
 library(Cardinal)
 library(gridExtra)
 library(lattice)
 library(ggplot2)
-@READING_MSIDATA@
+## function to read RData files independent of filename
-@READING_MSIDATA_INRAM@  ###change out
+loadRData <- function(fileName){
+load(fileName)
+get(ls()[ls() != "fileName"])
+}
+#if $infile.ext == 'imzml'
+#if str($processed_cond.processed_file) == "processed":
+msidata <- readImzML('infile', resolution=$processed_cond.accuracy, units = "$processed_cond.units")
+centroided(msidata) = $centroids
+#else
+msidata <- readImzML('infile')
+centroided(msidata) = $centroids
+#end if
+#elif $infile.ext == 'analyze75'
+msidata = readAnalyze('infile')
+centroided(msidata) = $centroids
+#else
+msidata = loadRData('infile.RData')
+msidata = as(msidata, "MSImagingExperiment")
+#end if
 ## remove duplicated coordinates, otherwise peak picking and log2 transformation will fail
 msidata <- msidata[,!duplicated(coord(msidata)[,1:2])]
+## set variable to False
+#set $used_peak_picking = False
+#set $used_peak_alignment = False
+#set $continuous_format = False
 if (ncol(msidata)>0 & nrow(msidata) >0){
 ## start QC report
 maxmz = round(max(mz(msidata)), digits=2)
 QC_numbers= data.frame(inputdata = c(minmz, maxmz,maxfeatures, pixelcount))
 vectorofactions = "inputdata"
 ## Choose random spectra for QC plots
 random_spectra = sample(pixels(msidata), 4, replace=FALSE)
-par(mfrow = c(2, 2), oma=c(0,0,2,0))
+par(oma=c(0,0,2,0))
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Input spectra", outer=TRUE, line=0)
 ############################### Preprocessing steps ###########################
 ###############################################################################
 #for $method in $methods:
 #if str( $method.methods_conditional.preprocessing_method ) == 'Normalization':
 print('Normalization')
 ##normalization
+if (class(msidata) == "MSProcessedImagingExperiment"){
+msidata = as(msidata, "MSContinuousImagingExperiment")
+}
 msidata = normalize(msidata, method="tic")
+msidata <- process(msidata, BPPARAM=MulticoreParam())
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 normalized = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, normalized)
 vectorofactions = append(vectorofactions, "normalized")
-par(mfrow = c(2, 2), oma=c(0,0,2,0))
+print(plot(msidata, pixel=random_spectra))
-for (random_sample in 1:length(random_spectra)){
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after normalization", outer=TRUE, line=0)
 ############################### Baseline reduction ###########################
 #elif str( $method.methods_conditional.preprocessing_method ) == 'Baseline_reduction':
 print('Baseline_reduction')
 ##baseline reduction
+if (class(msidata) == "MSProcessedImagingExperiment"){
+msidata = as(msidata, "MSContinuousImagingExperiment")
+}
 msidata = reduceBaseline(msidata, method="median", blocks=$method.methods_conditional.blocks_baseline, spar=$method.methods_conditional.spar_baseline)
+msidata <- process(msidata, BPPARAM=MulticoreParam())
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 baseline = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, baseline)
 vectorofactions = append(vectorofactions, "baseline red.")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after baseline reduction", outer=TRUE, line=0)
 ############################### Smoothing ###########################
 #elif str( $method.methods_conditional.preprocessing_method ) == 'Smoothing':
 print('Smoothing')
 ## Smoothing
+if (class(msidata) == "MSProcessedImagingExperiment"){
+msidata = as(msidata, "MSContinuousImagingExperiment")
+}
 #if str( $method.methods_conditional.methods_for_smoothing.smoothing_method) == 'gaussian':
 print('gaussian smoothing')
 msidata = smoothSignal(msidata, method="$method.methods_conditional.methods_for_smoothing.smoothing_method", window=$method.methods_conditional.window_smoothing, sd = $method.methods_conditional.methods_for_smoothing.sd_gaussian)
 print('moving average smoothing')
 msidata = smoothSignal(msidata, method="$method.methods_conditional.methods_for_smoothing.smoothing_method", window=$method.methods_conditional.window_smoothing, coef = $method.methods_conditional.methods_for_smoothing.coefficients_ma_filter)
 #end if
+msidata <- process(msidata, BPPARAM=MulticoreParam())
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 smoothed = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, smoothed)
 vectorofactions = append(vectorofactions, "smoothed")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after smoothing", outer=TRUE, line=0)
 ############################### Peak picking ###########################
 #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_picking':
+#set $used_peak_picking = True
 print('Peak_picking')
 ## Peakpicking
 #if str( $method.methods_conditional.methods_for_picking.picking_method) == 'adaptive':
 print('adaptive peakpicking')
 msidata = peakPick(msidata, window = $method.methods_conditional.window_picking, blocks = $method.methods_conditional.blocks_picking, method='$method.methods_conditional.methods_for_picking.picking_method', SNR=$method.methods_conditional.SNR_picking_method, spar=$method.methods_conditional.methods_for_picking.spar_picking)
-#elif str( $method.methods_conditional.methods_for_picking.picking_method) == 'limpic':
+#elif str( $method.methods_conditional.methods_for_picking.picking_method) == 'mad':
-print('limpic peakpicking')
+print('mad peakpicking')
-msidata = peakPick(msidata, window = $method.methods_conditional.window_picking, blocks = $method.methods_conditional.blocks_picking, method='$method.methods_conditional.methods_for_picking.picking_method', SNR=$method.methods_conditional.SNR_picking_method, thresh=$method.methods_conditional.methods_for_picking.tresh_picking)
+msidata = peakPick(msidata, window = $method.methods_conditional.window_picking, blocks = $method.methods_conditional.blocks_picking, method='$method.methods_conditional.methods_for_picking.picking_method', SNR=$method.methods_conditional.SNR_picking_method)
 #elif str( $method.methods_conditional.methods_for_picking.picking_method) == 'simple':
 print('simple peakpicking')
 msidata = peakPick(msidata, window = $method.methods_conditional.window_picking, blocks = $method.methods_conditional.blocks_picking, method='$method.methods_conditional.methods_for_picking.picking_method', SNR=$method.methods_conditional.SNR_picking_method)
 #end if
+msidata <- process(msidata, BPPARAM=MulticoreParam())
+#if str($method.methods_conditional.imzml_output) == "cont_format":
+#set $continuous_format = True
+#end if
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 picked = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, picked)
 vectorofactions = append(vectorofactions, "picked")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after peak picking", outer=TRUE, line=0)
 ############################### Peak alignment ###########################
 #elif str( $method.methods_conditional.preprocessing_method ) == 'Peak_alignment':
+#set $used_peak_alignment = True
 print('Peak_alignment')
 ## Peakalignment
-#if str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_noref':
+#if str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_table':
-align_peak_reference = msidata
-#elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_table':
 align_reference_table = read.delim("$method.methods_conditional.align_ref_type.mz_tabular", header = $method.methods_conditional.align_ref_type.feature_header, stringsAsFactors = FALSE)
 align_reference_column = align_reference_table[,$method.methods_conditional.align_ref_type.feature_column]
-align_peak_reference = align_reference_column[align_reference_column>=min(mz(msidata)) & align_reference_column<=max(mz(msidata))]
+align_peak_reference = as.numeric(align_reference_column[align_reference_column>=min(mz(msidata)) & align_reference_column<=max(mz(msidata))])
 if (length(align_peak_reference) == 0)
 {align_peak_reference = 0}
-#elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_msidata_ref':
+msidata = peakAlign(msidata,tolerance =$method.methods_conditional.value_diffalignment, units = "$method.methods_conditional.units_diffalignment", ref=align_peak_reference)
-align_peak_reference = loadRData('$method.methods_conditional.align_ref_type.align_peaks_msidata')
+#elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_noref':
-#end if
+msidata = peakAlign(msidata,tolerance =$method.methods_conditional.value_diffalignment, units = "$method.methods_conditional.units_diffalignment")
-#if str( $method.methods_conditional.methods_for_alignment.alignment_method) == 'diff':
-print('diff peakalignment')
+#end if
-msidata = peakAlign(msidata, method='$method.methods_conditional.methods_for_alignment.alignment_method',diff.max =$method.methods_conditional.methods_for_alignment.value_diffalignment, units = "$method.methods_conditional.methods_for_alignment.units_diffalignment", ref=align_peak_reference)
+msidata <- process(msidata, BPPARAM=MulticoreParam())
-#elif str( $method.methods_conditional.methods_for_alignment.alignment_method) == 'DP':
+#if str($method.methods_conditional.imzml_output) == "cont_format":
-print('DPpeakalignment')
+#set $continuous_format = True
+#end if
-msidata = peakAlign(msidata, method='$method.methods_conditional.methods_for_alignment.alignment_method',gap = $method.methods_conditional.methods_for_alignment.gap_DPalignment, ref=align_peak_reference)
-#end if
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 aligned = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, aligned)
 vectorofactions = append(vectorofactions, "aligned")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after alignment", outer=TRUE, line=0)
 ############################### Peak filtering ###########################
 #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_filtering':
 print('Peak_filtering')
-msidata = peakFilter(msidata, method='freq', freq.min = $method.methods_conditional.frequ_filtering)
+msidata = peakFilter(msidata, freq.min = $method.methods_conditional.frequ_filtering)
+msidata <- process(msidata, BPPARAM=MulticoreParam())
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 filtered = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, filtered)
 vectorofactions = append(vectorofactions, "filtered")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after filtering", outer=TRUE, line=0)
 ############################### Data reduction ###########################
 #elif str( $method.methods_conditional.preprocessing_method) == 'Data_reduction':
 print('Data_reduction')
+## these functions only work on MSImageSet
+msidata = as(msidata, "MSImageSet")
 #if str( $method.methods_conditional.methods_for_reduction.reduction_method) == 'bin':
 print('bin reduction')
 msidata = reduceDimension(msidata, method="bin", width=$method.methods_conditional.methods_for_reduction.bin_width, units="$method.methods_conditional.methods_for_reduction.bin_units", fun=$method.methods_conditional.methods_for_reduction.bin_fun)
 #end if
 msidata = reduceDimension(msidata, method="peaks", ref=peak_reference, type="$method.methods_conditional.methods_for_reduction.peaks_type")
 #end if
+## coercition into new format
+msidata = as(msidata, "MSImagingExperiment")
 ############################### QC ###########################
 maxfeatures =nrow(msidata)
 pixelcount = ncol(msidata)
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 reduced = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, reduced)
 vectorofactions = append(vectorofactions, "reduced")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after data reduction", outer=TRUE, line=0)
 ############################### Transformation ###########################
 #elif str( $method.methods_conditional.preprocessing_method) == 'Transformation':
 print('Transformation')
-## convert data into R matrix what brings it automatically into memory and can take some take but next steps need R matrix
+if (class(msidata) == "MSProcessedImagingExperiment"){
-##iData(msidata) <- iData(msidata)[]
+msidata = as(msidata, "MSContinuousImagingExperiment")
+}
 #if str( $method.methods_conditional.transf_conditional.trans_type) == 'log2':
 print('log2 transformation')
 ## replace 0 with NA to prevent Inf
-spectra_df = spectra(msidata)[] ## convert into R matrix
+spectra_df = spectra(msidata) ## convert into R matrix
 spectra_df[spectra_df ==0] = NA
 print(paste0("Number of 0 which were converted into NA:",sum(is.na(spectra_df))))
 spectra(msidata) = spectra_df
 ## log transformation
 spectra(msidata) = log2(spectra(msidata))
 #end if
 #elif str( $method.methods_conditional.transf_conditional.trans_type) == 'sqrt':
 print('squareroot transformation')
-spectra(msidata) = sqrt(spectra(msidata)[])
+spectra(msidata) = sqrt(spectra(msidata))
 #end if
 ############################### QC ###########################
 minmz = round(min(mz(msidata)), digits=2)
 maxmz = round(max(mz(msidata)), digits=2)
 transformed = c(minmz, maxmz,maxfeatures, pixelcount)
 QC_numbers= cbind(QC_numbers, transformed)
 vectorofactions = append(vectorofactions, "transformed")
-for (random_sample in 1:length(random_spectra)){
+print(plot(msidata, pixel=random_spectra))
-plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
 title("Spectra after transformation", outer=TRUE, line=0)
 #end if
 #end for
 ############# Outputs: RData, imzml and QC report #############
 ################################################################################
 ## save msidata as imzML file, will only work if there is at least 1 m/z left
-#if str($imzml_output) == "imzml_format":
 if (nrow(msidata) > 0){
 ## make sure that coordinates are integers
 coord(msidata)\$y = as.integer(coord(msidata)\$y)
 coord(msidata)\$x = as.integer(coord(msidata)\$x)
-writeImzML(msidata, "out")}
+#if $used_peak_picking:
-#elif str($imzml_output) == "rdata_format":
+#if $continuous_format:
-## save as (.RData)
+msidata = as(msidata, "MSContinuousImagingExperiment")
-iData(msidata) = iData(msidata)[]
+#end if
-save(msidata, file="$outfile_rdata")
+#elif $used_peak_alignment
-#end if
+#if $continuous_format:
+msidata = as(msidata, "MSContinuousImagingExperiment")
+#end if
+#end if
+writeImzML(msidata, "out")
+}
 plot(0,type='n',axes=FALSE,ann=FALSE)
 rownames(QC_numbers) = c("min m/z", "max mz", "# features", "# spectra")
 grid.table(t(QC_numbers))
 dev.off()
 }else{
 print("inputfile has no intensities > 0")
 }
 <inputs>
 <expand macro="reading_msidata"/>
 <repeat name="methods" title="Preprocessing" min="1" max="50">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" type="select" label="Preprocessing methods">
-<option value="Normalization" selected="True">Intensity Normalization (TIC)</option>
+<option value="Normalization" selected="True">Intensity Normalization</option>
 <option value="Baseline_reduction">Baseline Reduction</option>
 <option value="Smoothing">Peak smoothing</option>
 <option value="Peak_picking">Peak picking</option>
 <option value="Peak_alignment">Peak alignment</option>
 <option value="Peak_filtering">Peak filtering</option>
 <option value="Data_reduction">Data reduction</option>
 <option value="Transformation">Transformation</option>
 </param>
-<when value="Normalization"/>
+<when value="Normalization">
+<conditional name="methods_for_normalization">
+<param name="normalization_method" type="select" label="Normalization method">
+<option value="tic" selected="True">TIC</option>
+<option value="rms">RMS</option>
+</param>
+<when value="tic"/>
+<when value="rms"/>
+</conditional>
+</when>
 <when value="Baseline_reduction">
 <param name="blocks_baseline" type="integer" value="500"
 label="Blocks"/>
 <param name="spar_baseline" type="float" value="1.0" label="Spar value"
 help = "Smoothing parameter for the spline smoothing
 </conditional>
 <param name="window_smoothing" type="float" value="8"
 label="Window size"/>
 </when>
 <when value="Peak_picking">
-<param name="SNR_picking_method" type="integer" value="6"
+<param name="SNR_picking_method" type="float" value="6"
 label="Signal to noise ratio"
 help="The minimal signal to noise ratio for peaks to be considered as a valid peak."/>
 <param name="blocks_picking" type="integer" value="100" label = "Number of blocks"
 help="Number of blocks in which to divide mass spectrum to calculate noise"/>
 <param name="window_picking" type="float" value="5" label= "Window size" help="Window width for seeking local maxima"/>
 <conditional name="methods_for_picking">
-<param name="picking_method" type="select" label="Peak picking method" help="only simple works for processed imzML files">
+<param name="picking_method" type="select" label="Peak picking method">
 <option value="adaptive" selected="True">adaptive</option>
-<option value="limpic">limpic</option>
+<option value="mad">mad</option>
 <option value="simple">simple</option>
 </param>
 <when value="adaptive">
 <param name="spar_picking" type="float" value="1.0"
 label="Spar value"
 help = "Smoothing parameter for the spline smoothing
 applied to the spectrum in order to decide the cutoffs
 for throwing away false noise spikes that might occur inside peaks"/>
 </when>
-<when value="limpic">
+<when value="mad"/>
-<param name="tresh_picking" type="float" value="0.75"
-label="thresh value" help="The thresholding quantile to use when comparing slopes in order to throw away peaks that are too flat"/>
-</when>
 <when value="simple"/>
 </conditional>
+<param name="imzml_output" type="boolean" label="imzML output in processed format" truevalue="proc_format" falsevalue="cont_format" help= "Processed imzML works only in MALDIquant tools, not yet in MSI tools (Cardinal)"/>
 </when>
 <when value="Peak_alignment">
-<conditional name="methods_for_alignment">
+<param name="value_diffalignment" type="float" value="200"
-<param name="alignment_method" type="select" label="Alignment method">
+label="tolerance" help="Peaks that differ less than this value will be aligned together"/>
-<option value="diff" selected="True">diff</option>
+<param name="units_diffalignment" type="select" display="radio" optional="False" label="units">
-<option value="DP">DP</option>
+<option value="ppm" selected="True">ppm</option>
-</param>
+<option value="mz">m/z</option>
-<when value="diff">
+</param>
-<param name="value_diffalignment" type="float" 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="mz">m/z</option>
-</param>
-</when>
-<when value="DP">
-<param name="gap_DPalignment" type="float" value="0"
-label="Gap" help="The gap penalty for the dynamic programming sequence alignment"/>
-</when>
-</conditional>
 <conditional name="align_ref_type">
 <param name="align_reference_datatype" type="select" label="Choose reference">
 <option value="align_noref" selected="True">no reference</option>
 <option value="align_table" >tabular file as reference</option>
-<option value="align_msidata_ref">msidata file as reference</option>
 </param>
 <when value="align_noref"/>
 <when value="align_table">
 <expand macro="reading_1_column_mz_tabular" label="Tabular file with m/z features to use for alignment. Only the m/z values from the tabular file will be kept."/>
 </when>
-<when value="align_msidata_ref">
+</conditional>
-<param name="align_peaks_msidata" type="data" format="rdata" label="Picked and aligned Cardinal MSImageSet saved as RData"/>
+<param name="imzml_output" type="boolean" label="imzML output in processed format" truevalue="proc_format" falsevalue="cont_format" help= "Processed imzML works only in MALDIquant tools, not yet in MSI tools (Cardinal)"/>
-</when>
-</conditional>
 </when>
 <when value="Peak_filtering">
-<param name="frequ_filtering" type="integer" value="1000"
+<param name="frequ_filtering" type="float" value="0.01" max="1" min="0" label="Minimum frequency" help="Peaks that occur in the dataset in lesser proportion than this will be dropped (0.01 --> filtering for 1% of spectra)"/>
-label="Freq.min" help="Peaks that occur in the dataset fewer times than this will be removed. Number should be between 1 (no filtering) and number of spectra (pixel)"/>
 </when>
 <when value="Data_reduction">
 <conditional name="methods_for_reduction">
 <param name="reduction_method" type="select" label="Reduction method">
 <option value="bin" selected="True">bin</option>
 <when value="sqrt"/>
 </conditional>
 </when>
 </conditional>
 </repeat>
-<param name="imzml_output" type="select" display = "radio" optional = "False"
-label="Output format" help= "Choose the output format">
-<option value="imzml_format" >imzML</option>
-<option value="rdata_format" selected="True" >RData</option>
-</param>
 </inputs>
 <outputs>
-<data format="imzml" name="outfile_imzml" label="${tool.name} on ${on_string}: imzML">
+<data format="imzml" name="outfile_imzml" label="${tool.name} on ${on_string}: imzML"/>
-<filter>imzml_output=='imzml_format'</filter>
-</data>
-<data format="rdata" name="outfile_rdata" label="${tool.name} on ${on_string}: RData">
-<filter>imzml_output == 'rdata_format'</filter>
-</data>
 <data format="pdf" name="QC_overview" from_work_dir="Preprocessing.pdf" label = "${tool.name} on ${on_string}: QC"/>
 </outputs>
 <tests>
 <test>
 <expand macro="infile_imzml"/>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Normalization"/>
 <conditional name="methods_for_normalization">
-<param name="normalization_method" value="median"/>
+<param name="normalization_method" value="tic"/>
 </conditional>
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Peak_alignment"/>
-<conditional name="methods_for_alignment">
-<param name="alignment_method" value="diff"/>
-</conditional>
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Peak_filtering"/>
-<param name="frequ_filtering" value="2"/>
+<param name="frequ_filtering" value="0.3"/>
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Transformation"/>
 <conditional name="transf_conditional">
 <param name="trans_type" value="sqrt"/>
 </conditional>
 </conditional>
 </repeat>
-<param name="imzml_output" value="imzml_format"/>
 <output name="QC_overview" file="preprocessing_results1.pdf" compare="sim_size"/>
 <output name="outfile_imzml" ftype="imzml" file="preprocessing_results1.imzml.txt" compare="sim_size">
-<extra_files type="file" file="preprocessing_results1.imzml" name="imzml" lines_diff="4"/>
+<extra_files type="file" file="preprocessing_results1.imzml" name="imzml" lines_diff="6"/>
 <extra_files type="file" file="preprocessing_results1.ibd" name="ibd" compare="sim_size"/>
 </output>
 </test>
 <test>
 <param name="infile" value="3_files_combined.RData" ftype="rdata"/>
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Peak_alignment"/>
-<conditional name="methods_for_alignment">
+</conditional>
-<param name="alignment_method" value="DP"/>
+</repeat>
-</conditional>
-</conditional>
-</repeat>
-<param name="imzml_output" value="imzml_format"/>
 <output name="QC_overview" file="preprocessing_results2.pdf" compare="sim_size"/>
 <output name="outfile_imzml" ftype="imzml" file="preprocessing_results2.imzml.txt" compare="sim_size">
-<extra_files type="file" file="preprocessing_results2.imzml" name="imzml" lines_diff="4"/>
+<extra_files type="file" file="preprocessing_results2.imzml" name="imzml" lines_diff="6"/>
 <extra_files type="file" file="preprocessing_results2.ibd" name="ibd" compare="sim_size"/>
 </output>
 </test>
 <test>
 <expand macro="infile_analyze75"/>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Normalization"/>
 <conditional name="methods_for_normalization">
-<param name="normalization_method" value="median"/>
+<param name="normalization_method" value="rms"/>
 </conditional>
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Peak_picking"/>
 <param name="blocks_picking" value="100"/>
 <param name="window_picking" value="5"/>
 <param name="SNR_picking_method" value="3"/>
-<param name="picking_method" value="limpic"/>
+<conditional name="methods_for_picking">
-</conditional>
+<param name="picking_method" value="mad"/>
+</conditional>
+</conditional>
+<param name="imzml_output" value="proc_format"/>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Peak_alignment"/>
-<conditional name="methods_for_alignment">
+</conditional>
-<param name="alignment_method" value="diff"/>
+<param name="imzml_output" value="proc_format"/>
-</conditional>
+</repeat>
-</conditional>
+<repeat name="methods">
-</repeat>
+<conditional name="methods_conditional">
-<param name="imzml_output" value="imzml_format"/>
+<param name="preprocessing_method" value="Transformation"/>
+<conditional name="transf_conditional">
+<param name="trans_type" value="log2"/>
+</conditional>
+</conditional>
+</repeat>
 <output name="QC_overview" file="preprocessing_results3.pdf" compare="sim_size"/>
 <output name="outfile_imzml" ftype="imzml" file="preprocessing_results3.imzml.txt" compare="sim_size">
-<extra_files type="file" file="preprocessing_results3.imzml" name="imzml" lines_diff="4"/>
+<extra_files type="file" file="preprocessing_results3.imzml" name="imzml" lines_diff="6"/>
 <extra_files type="file" file="preprocessing_results3.ibd" name="ibd" compare="sim_size"/>
 </output>
 </test>
 <test>
 <expand macro="infile_analyze75"/>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Normalization"/>
+<param name="normalization_method" value="tic"/>
 </conditional>
 </repeat>
 <repeat name="methods">
 <conditional name="methods_conditional">
 <param name="preprocessing_method" value="Data_reduction"/>
-<param name="bin_width" value="0.1"/>
+<conditional name="methods_for_reduction">
-</conditional>
+<param name="reduction_method" value="bin"/>
-</repeat>
+<param name="bin_width" value="0.1"/>
-<param name="imzml_output" value="imzml_format"/>
+</conditional>
+</conditional>
+</repeat>
 <output name="QC_overview" file="preprocessing_results4.pdf" compare="sim_size"/>
 <output name="outfile_imzml" ftype="imzml" file="preprocessing_results4.imzml.txt" compare="sim_size">
-<extra_files type="file" file="preprocessing_results4.imzml" name="imzml" lines_diff="4"/>
+<extra_files type="file" file="preprocessing_results4.imzml" name="imzml" lines_diff="6"/>
 <extra_files type="file" file="preprocessing_results4.ibd" name="ibd" compare="sim_size"/>
 </output>
 </test>
 <test>
-<expand macro="infile_imzml"/>
+<expand macro="processed_infile_imzml"/>
-<repeat name="methods">
+<conditional name="processed_cond">
-<conditional name="methods_conditional">
+<param name="processed_file" value="processed"/>
-<param name="preprocessing_method" value="Data_reduction"/>
+<param name="accuracy" value="100"/>
-<conditional name="methods_for_reduction">
+<param name="units" value="ppm"/>
-<param name="reduction_method" value="resample"/>
+</conditional>
-<param name="step_width" value="0.1"/>
+<repeat name="methods">
+<conditional name="methods_conditional">
+<param name="preprocessing_method" value="Transformation"/>
+<conditional name="transf_conditional">
+<param name="trans_type" value="sqrt"/>
 </conditional>
 </conditional>
 </repeat>
-<param name="imzml_output" value="rdata_format"/>
+<repeat name="methods">
-<output name="outfile_rdata" file="preprocessing_results5.RData" compare="sim_size"/>
+<conditional name="methods_conditional">
+<param name="preprocessing_method" value="Baseline_reduction"/>
+</conditional>
+</repeat>
 <output name="QC_overview" file="preprocessing_results5.pdf" compare="sim_size"/>
+<output name="outfile_imzml" ftype="imzml" file="preprocessing_results5.imzml.txt" compare="sim_size">
+<extra_files type="file" file="preprocessing_results5.imzml" name="imzml" lines_diff="6"/>
+<extra_files type="file" file="preprocessing_results5.ibd" name="ibd" compare="sim_size"/>
+</output>
 </test>
 </tests>
 <help>
 <![CDATA[
 - Coordinates stored as decimals rather than integers will be rounded to obtain a regular pixel grid. This might lead to duplicated coordinates which will be automatically removed after the data is read by the tool.
 @MZ_TABULAR_INPUT_DESCRIPTION@
 **Options**
-- Normalization: Normalization of intensities to total ion current (TIC)
+- Normalization: Normalization of intensities to total ion current (TIC) or to root-mean-square (RMS)
 - Baseline reduction: Baseline  reduction removes background intensity generated by chemical noise (common in MALDI datasets)
 - Smoothing: 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; if no reference is given the peaks are aligned to the local maxima of the mean spectrum of the current dataset; external reference data can be used from another MSI data file or a tabular file with m/z values, but then only the m/z from the reference will be kept
 - Peak filtering: removes peaks that occur only in a small proportion of pixels. If not sure which cut off to choose run quality control tool first and decide according to the number of peaks per m/z 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.
-**Tips**
-- Peak alignment works only after peak picking
-- Peak filtering works only on centroided data (peak picking and alignment or Data reduction peaks
 **Output**
-- MSI data as imzML file or .RData (can be read with the Cardinal package in R)
+- MSI data as continuous imzML file (option to output processed imzML file only after peak picking/peak alignment; but is not yet compatible with other MSI tools)
 - pdf with key values and four random mass spectra after each processing step
 ]]>
 </help>
 <expand macro="citations"/>

Mercurial > repos > galaxyp > cardinal_preprocessing

comparison preprocessing.xml @ 6:cbd9e4df377d draft