Mercurial > repos > galaxyp > cardinal_preprocessing
diff preprocessing.xml @ 7:44a4b31fcbf3 draft
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit f986c51abe33c7f622d429a3c4a79ee24b33c1f3"
| author | galaxyp |
|---|---|
| date | Thu, 23 Apr 2020 08:07:20 -0400 |
| parents | 5bf056c0354e |
| children | 87bb011a4ee8 |
line wrap: on
line diff
--- a/preprocessing.xml Wed Mar 25 08:13:17 2020 -0400 +++ b/preprocessing.xml Thu Apr 23 08:07:20 2020 -0400 @@ -1,17 +1,14 @@ -<tool id="cardinal_preprocessing" name="MSI preprocessing" version="2.4.0.0"> +<tool id="cardinal_preprocessing" name="MSI preprocessing" version="@VERSION@.1"> <description> mass spectrometry imaging preprocessing </description> <macros> <import>macros.xml</import> </macros> - <requirements> - <requirement type="package" version="2.4.0">bioconductor-cardinal</requirement> - <requirement type="package" version="3.6.1">r-base</requirement> + <expand macro="requirements"> <requirement type="package" version="2.3">r-gridextra</requirement> <requirement type="package" version="3.2.1">r-ggplot2</requirement> - <requirement type="package" version="0.20_38">r-lattice</requirement> - </requirements> + </expand> <command detect_errors="exit_code"> <![CDATA[ @@ -32,33 +29,21 @@ ################################# load libraries and read file ################# +## set CPU, default = 1 + +if (Sys.getenv("GALAXY_SLOTS")!="") + { + number_cpu = 1 ## default = 1 + }else{ + number_cpu = as.numeric(Sys.getenv("GALAXY_SLOTS")) ##cpu set by Galaxy + } + library(Cardinal) library(gridExtra) -library(lattice) library(ggplot2) - ## function to read RData files independent of filename - 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) = $centroids - #else - msidata = loadRData('infile.RData') - msidata = as(msidata, "MSImagingExperiment") - #end if +@READING_MSIDATA_FULLY_COMPATIBLE@ ## remove duplicated coordinates, otherwise peak picking and log2 transformation will fail @@ -108,7 +93,7 @@ } msidata = normalize(msidata, method="tic") - msidata <- process(msidata, BPPARAM=MulticoreParam()) + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) ############################### QC ########################### @@ -134,7 +119,7 @@ } msidata = reduceBaseline(msidata, method="median", blocks=$method.methods_conditional.blocks_baseline, spar=$method.methods_conditional.spar_baseline) - msidata <- process(msidata, BPPARAM=MulticoreParam()) + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) ############################### QC ########################### @@ -180,7 +165,7 @@ msidata = smoothSignal(msidata, method="$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()) + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) ############################### QC ########################### @@ -217,7 +202,7 @@ 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=$method.methods_conditional.SNR_picking_method) #end if - msidata <- process(msidata, BPPARAM=MulticoreParam()) + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) #if str($method.methods_conditional.imzml_output) == "cont_format": #set $continuous_format = True @@ -262,7 +247,7 @@ #end if - msidata <- process(msidata, BPPARAM=MulticoreParam()) + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) #if str($method.methods_conditional.imzml_output) == "cont_format": #set $continuous_format = True @@ -286,7 +271,7 @@ print('Peak_filtering') msidata = peakFilter(msidata, freq.min = $method.methods_conditional.frequ_filtering) - msidata <- process(msidata, BPPARAM=MulticoreParam()) + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) ############################### QC ########################### @@ -300,6 +285,32 @@ print(plot(msidata, pixel=random_spectra)) title("Spectra after filtering", outer=TRUE, line=0) + ############################### Peak binning ########################### + + #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_binning': + print('Peak_binning') + + ## reading reference file + reference_table = read.delim("$method.methods_conditional.mz_tabular", header = $method.methods_conditional.feature_header, stringsAsFactors = FALSE) + reference_column = reference_table[,$method.methods_conditional.feature_column] + peak_reference = reference_column[reference_column>min(mz(msidata)) & reference_column<max(mz(msidata))] + + msidata = peakBin(msidata, ref = peak_reference, tolerance = $method.methods_conditional.peakbin_tol, units = "$method.methods_conditional.peakbin_units", type="$method.methods_conditional.peaks_type") + msidata <- process(msidata, BPPARAM=MulticoreParam(workers=number_cpu)) + + ############################### QC ########################### + + maxfeatures =nrow(msidata) + pixelcount = ncol(msidata) + minmz = round(min(mz(msidata)), digits=2) + maxmz = round(max(mz(msidata)), digits=2) + peak_binned = c(minmz, maxmz,maxfeatures, pixelcount) + QC_numbers= cbind(QC_numbers, peak_binned) + vectorofactions = append(vectorofactions, "peak binned") + print(plot(msidata, pixel=random_spectra)) + title("Spectra after peak binning", outer=TRUE, line=0) + + ############################### Data reduction ########################### #elif str( $method.methods_conditional.preprocessing_method) == 'Data_reduction': @@ -324,23 +335,6 @@ print('resample reduction') msidata = reduceDimension(msidata, method="resample", step=$method.methods_conditional.methods_for_reduction.resample_step) - - #elif str( $method.methods_conditional.methods_for_reduction.reduction_method) == 'peaks': - print('peaks reduction') - - #if str( $method.methods_conditional.methods_for_reduction.ref_type.reference_datatype) == 'table': - - reference_table = read.delim("$method.methods_conditional.methods_for_reduction.ref_type.mz_tabular", header = $method.methods_conditional.methods_for_reduction.ref_type.feature_header, stringsAsFactors = FALSE) - reference_column = reference_table[,$method.methods_conditional.methods_for_reduction.ref_type.feature_column] - peak_reference = reference_column[reference_column>min(mz(msidata)) & reference_column<max(mz(msidata))] - - #elif str( $method.methods_conditional.methods_for_reduction.ref_type.reference_datatype) == 'msidata_ref': - - peak_reference = loadRData('$method.methods_conditional.methods_for_reduction.ref_type.peaks_msidata') - - #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 @@ -447,6 +441,7 @@ <option value="Peak_picking">Peak picking</option> <option value="Peak_alignment">Peak alignment</option> <option value="Peak_filtering">Peak filtering</option> + <option value="Peak_binning">Peak binning to reference peaks</option> <option value="Data_reduction">Data reduction</option> <option value="Transformation">Transformation</option> </param> @@ -464,7 +459,7 @@ <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 + 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> @@ -515,7 +510,7 @@ <when value="mad"/> <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)"/> + <param name="imzml_output" type="boolean" label="imzML output in processed format" checked="True" truevalue="proc_format" falsevalue="cont_format"/> </when> <when value="Peak_alignment"> <param name="value_diffalignment" type="float" value="200" @@ -534,17 +529,35 @@ <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> </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)"/> + <param name="imzml_output" type="boolean" label="imzML output in processed format" checked="True" truevalue="proc_format" falsevalue="cont_format" help= "Processed imzML works only in MALDIquant tools, not yet in MSI tools (Cardinal)"/> </when> <when value="Peak_filtering"> <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)"/> </when> + <when value="Peak_binning"> + <expand macro="reading_1_column_mz_tabular" label="A reference to which the peaks are binned." help="Tabular file with m/z features to extract from input file"/> + <param name="peakbin_tol" value="NA" type="text" label="The tolerance to be used when matching the m/z features in the dataset to the reference. If this is NA, then automatically guess a resolution from the data." > + <sanitizer invalid_char=""> + <valid initial="string.digits"> + <add value="NA" /> + </valid> + </sanitizer> + </param> + <param name="peakbin_units" display="radio" type="select" label="The units to use for the tolerance."> + <option value="mz" >mz</option> + <option value="ppm" selected="True" >ppm</option> + </param> + <param name="peaks_type" type="select" display="radio" + label="Should the peak height or area under the curve be taken as the intensity value?"> + <option value="height" selected="True">height</option> + <option value="area">area</option> + </param> + </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> <option value="resample">resample</option> - <option value="peaks">peaks</option> </param> <when value="bin"> <param name="bin_width" type="float" value="1" @@ -565,25 +578,6 @@ <param name="resample_step" type="float" value="1" label="The step size in m/z" help="Step size must be greater than range of m/z values divided by number of m/z features"/> </when> - <when value="peaks"> - <param name="peaks_type" type="select" display="radio" - label="Should the peak height or area under the curve be taken as the intensity value?"> - <option value="height" selected="True">height</option> - <option value="area">area</option> - </param> - <conditional name="ref_type"> - <param name="reference_datatype" type="select" label="Choose reference datatype"> - <option value="table" selected="True">tabular file</option> - <option value="msidata_ref">msidata file</option> - </param> - <when value="table"> - <expand macro="reading_1_column_mz_tabular" label="Tabular file with m/z features to extract from input file"/> - </when> - <when value="msidata_ref"> - <param name="peaks_msidata" type="data" format="rdata" label="Picked and aligned Cardinal MSImageSet saved as RData"/> - </when> - </conditional> - </when> </conditional> </when> <when value="Transformation"> @@ -635,11 +629,13 @@ <param name="blocks_picking" value="3"/> <param name="window_picking" value="3"/> <param name="SNR_picking_method" value="3"/> + <param name="imzml_output" value="cont_format"/> </conditional> </repeat> <repeat name="methods"> <conditional name="methods_conditional"> <param name="preprocessing_method" value="Peak_alignment"/> + <param name="imzml_output" value="cont_format"/> </conditional> </repeat> <repeat name="methods"> @@ -673,11 +669,13 @@ <conditional name="methods_for_picking"> <param name="picking_method" value="adaptive"/> </conditional> + <param name="imzml_output" value="cont_format"/> </conditional> </repeat> <repeat name="methods"> <conditional name="methods_conditional"> <param name="preprocessing_method" value="Peak_alignment"/> + <param name="imzml_output" value="cont_format"/> </conditional> </repeat> <output name="QC_overview" file="preprocessing_results2.pdf" compare="sim_size"/> @@ -699,27 +697,19 @@ <repeat name="methods"> <conditional name="methods_conditional"> <param name="preprocessing_method" value="Peak_picking"/> - <param name="blocks_picking" value="100"/> + <param name="blocks_picking" value="20"/> <param name="window_picking" value="5"/> - <param name="SNR_picking_method" value="3"/> + <param name="SNR_picking_method" value="2"/> <conditional name="methods_for_picking"> <param name="picking_method" value="mad"/> </conditional> + <param name="imzml_output" value="proc_format"/> </conditional> - <param name="imzml_output" value="proc_format"/> </repeat> <repeat name="methods"> <conditional name="methods_conditional"> <param name="preprocessing_method" value="Peak_alignment"/> - </conditional> - <param name="imzml_output" value="proc_format"/> - </repeat> - <repeat name="methods"> - <conditional name="methods_conditional"> - <param name="preprocessing_method" value="Transformation"/> - <conditional name="transf_conditional"> - <param name="trans_type" value="log2"/> - </conditional> + <param name="imzml_output" value="proc_format"/> </conditional> </repeat> <output name="QC_overview" file="preprocessing_results3.pdf" compare="sim_size"/> @@ -762,7 +752,7 @@ <conditional name="methods_conditional"> <param name="preprocessing_method" value="Transformation"/> <conditional name="transf_conditional"> - <param name="trans_type" value="sqrt"/> + <param name="trans_type" value="log2"/> </conditional> </conditional> </repeat> @@ -799,12 +789,13 @@ - 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 +- Peak binning: extracts peaks intensities (from a profile dataset) for a list of m/z (reference) values +- Data reduction: binning or resampling 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** -- 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) +- MSI data as continuous or processed imzML file - pdf with key values and four random mass spectra after each processing step ]]>