Mercurial > repos > galaxyp > msi_classification
diff msi_classification.xml @ 0:f0b415eb3bcf draft default tip
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_classification commit 8087490eb4dcaf4ead0f03eae4126780d21e5503
| author | galaxyp |
|---|---|
| date | Fri, 06 Jul 2018 14:12:51 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/msi_classification.xml Fri Jul 06 14:12:51 2018 -0400 @@ -0,0 +1,1079 @@ +<tool id="mass_spectrometry_imaging_classification" name="MSI classification" version="1.10.0.0"> + <description>spatial classification of mass spectrometry imaging data</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="2.2.1">r-ggplot2</requirement> + </requirements> + <command detect_errors="exit_code"> + <![CDATA[ + + #if $infile.ext == 'imzml' + ln -s '${infile.extra_files_path}/imzml' infile.imzML && + ln -s '${infile.extra_files_path}/ibd' infile.ibd && + #elif $infile.ext == 'analyze75' + ln -s '${infile.extra_files_path}/hdr' infile.hdr && + ln -s '${infile.extra_files_path}/img' infile.img && + ln -s '${infile.extra_files_path}/t2m' infile.t2m && + #else + ln -s $infile infile.RData && + #end if + cat '${MSI_segmentation}' && + echo ${MSI_segmentation} && + Rscript '${MSI_segmentation}' + + ]]> + </command> + <configfiles> + <configfile name="MSI_segmentation"><![CDATA[ + + +################################# load libraries and read file ######################### + +library(Cardinal) +library(gridExtra) +library(lattice) +library(ggplot2) + + +#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 + +## function to later read RData reference files in + +loadRData <- function(fileName){ +#loads an RData file, and returns it +load(fileName) +get(ls()[ls() != "fileName"]) +} + +## create full matrix to make processed imzML files compatible with classification +iData(msidata) <- iData(msidata)[] + +###################################### file properties in numbers ############## + +## Number of features (mz) +maxfeatures = length(features(msidata)) +## Range mz +minmz = round(min(mz(msidata)), digits=2) +maxmz = round(max(mz(msidata)), digits=2) +## Number of spectra (pixels) +pixelcount = length(pixels(msidata)) +## Range x coordinates +minimumx = min(coord(msidata)[,1]) +maximumx = max(coord(msidata)[,1]) +## Range y coordinates +minimumy = min(coord(msidata)[,2]) +maximumy = max(coord(msidata)[,2]) +## Range of intensities +minint = round(min(spectra(msidata)[]), digits=2) +maxint = round(max(spectra(msidata)[]), digits=2) +medint = round(median(spectra(msidata)[]), digits=2) +## Number of intensities > 0 +npeaks= sum(spectra(msidata)[]>0) +## Spectra multiplied with mz (potential number of peaks) +numpeaks = ncol(spectra(msidata)[])*nrow(spectra(msidata)[]) +## Percentage of intensities > 0 +percpeaks = round(npeaks/numpeaks*100, digits=2) +## Number of empty TICs +TICs = colSums(spectra(msidata)[]) +NumemptyTIC = sum(TICs == 0) + + +## Processing informations +processinginfo = processingData(msidata) +centroidedinfo = processinginfo@centroided # TRUE or FALSE + +## if TRUE write processinginfo if no write FALSE + +## normalization +if (length(processinginfo@normalization) == 0) { + normalizationinfo='FALSE' +} else { + normalizationinfo=processinginfo@normalization +} +## smoothing +if (length(processinginfo@smoothing) == 0) { + smoothinginfo='FALSE' +} else { + smoothinginfo=processinginfo@smoothing +} +## baseline +if (length(processinginfo@baselineReduction) == 0) { + baselinereductioninfo='FALSE' +} else { + baselinereductioninfo=processinginfo@baselineReduction +} +## peak picking +if (length(processinginfo@peakPicking) == 0) { + peakpickinginfo='FALSE' +} else { + peakpickinginfo=processinginfo@peakPicking +} + +############################################################################# + +properties = c("Number of mz features", + "Range of mz values", + "Number of pixels", + "Range of x coordinates", + "Range of y coordinates", + "Range of intensities", + "Median of intensities", + "Intensities > 0", + "Number of empty spectra", + "Preprocessing", + "Normalization", + "Smoothing", + "Baseline reduction", + "Peak picking", + "Centroided") + +values = c(paste0(maxfeatures), + paste0(minmz, " - ", maxmz), + paste0(pixelcount), + paste0(minimumx, " - ", maximumx), + paste0(minimumy, " - ", maximumy), + paste0(minint, " - ", maxint), + paste0(medint), + paste0(percpeaks, " %"), + paste0(NumemptyTIC), + paste0(" "), + paste0(normalizationinfo), + paste0(smoothinginfo), + paste0(baselinereductioninfo), + paste0(peakpickinginfo), + paste0(centroidedinfo)) + +property_df = data.frame(properties, values) + + +######################################## PDF ################################### +################################################################################ +################################################################################ + +Title = "Prediction" + +#if str( $type_cond.type_method) == "training": + #if str( $type_cond.method_cond.class_method) == "PLS": + Title = "PLS" + #elif str( $type_cond.method_cond.class_method) == "OPLS": + Title = "OPLS" + #elif str( $type_cond.method_cond.class_method) == "spatialShrunkenCentroids": + Title = "SSC" + #end if +#end if + +pdf("classificationpdf.pdf", fonts = "Times", pointsize = 12) +plot(0,type='n',axes=FALSE,ann=FALSE) + + +title(main=paste0(Title," for file: \n\n", "$infile.display_name")) + + + +##################### I) numbers and control plots ############################# +############################################################################### + +## table with values +grid.table(property_df, rows= NULL) + +if (npeaks > 0){ + +opar <- par() + + ######################## II) Training ############################# + ############################################################################# + #if str( $type_cond.type_method) == "training": + print("training") + + + ## load y response (will be needed in every training scenario) + + #if str($type_cond.y_cond.y_vector) == "y_internal": + y_vector = msidata\$$type_cond.y_cond.y_name + #elif str($type_cond.y_cond.y_vector) == "y_external": + y_tabular = read.delim("$type_cond.y_cond.y_data", header = FALSE, stringsAsFactors = FALSE) + y_vector = as.factor(y_tabular[,$type_cond.y_cond.y_column]) + number_pixels = length(y_vector) ## should be same as in data + #end if + + ## plot of y vector + + position_df = cbind(coord(msidata)[,1:2], y_vector) + y_plot = ggplot(position_df, aes(x=x, y=y, fill=y_vector))+ + geom_tile() + + coord_fixed()+ + ggtitle("Distribution of the response variable y")+ + theme_bw()+ + theme(text=element_text(family="ArialMT", face="bold", size=15))+ + theme(legend.position="bottom",legend.direction="vertical")+ + guides(fill=guide_legend(ncol=4,byrow=TRUE)) + coord_labels = aggregate(cbind(x,y)~y_vector, data=position_df, mean, na.rm=TRUE, na.action="na.pass") + coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$y_vector) + print(y_plot) + + + ######################## PLS ############################# + #if str( $type_cond.method_cond.class_method) == "PLS": + print("PLS") + + ######################## PLS - CV ############################# + #if str( $type_cond.method_cond.analysis_cond.PLS_method) == "cvapply": + print("PLS cv") + + ## folds + #if str($type_cond.method_cond.analysis_cond.fold_cond.fold_vector) == "fold_internal": + + fold_vector = msidata\$$type_cond.method_cond.analysis_cond.fold_cond.fold_name + #elif str($type_cond.method_cond.analysis_cond.fold_cond.fold_vector) == "fold_external": + fold_tabular = read.delim("$type_cond.method_cond.analysis_cond.fold_cond.fold_data", header = FALSE, stringsAsFactors = FALSE) + fold_vector = as.factor(fold_tabular[,$type_cond.method_cond.analysis_cond.fold_cond.fold_column]) + number_pixels = length(fold_vector) ## should be same as in data + #end if + + ## plot of folds + + position_df = cbind(coord(msidata)[,1:2], fold_vector) + fold_plot = ggplot(position_df, aes(x=x, y=y, fill=fold_vector))+ + geom_tile() + + coord_fixed()+ + ggtitle("Distribution of the fold variable")+ + theme_bw()+ + theme(text=element_text(family="ArialMT", face="bold", size=15))+ + theme(legend.position="bottom",legend.direction="vertical")+ + guides(fill=guide_legend(ncol=4,byrow=TRUE)) + coord_labels = aggregate(cbind(x,y)~fold_vector, data=position_df, mean, na.rm=TRUE, na.action="na.pass") + coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$fold_vector) + print(fold_plot) + + ## number of components + components = c($type_cond.method_cond.analysis_cond.plscv_comp) + + ## PLS-cvApply: + msidata.cv.pls <- cvApply(msidata, .y = y_vector, .fold = fold_vector, .fun = "PLS", ncomp = components) + + ## create table with summary + count = 1 + summary_plscv = list() + accuracy_vector = numeric() + for (iteration in components){ + + summary_iteration = summary(msidata.cv.pls)\$accuracy[[paste0("ncomp = ", iteration)]] + summary_iteration = cbind(rownames(summary_iteration), summary_iteration) ## include rownames in table + accuracy_vector[count] = summary_iteration[1,2] ## vector with accuracies to find later maximum for plot + empty_row = c(paste0("ncomp = ", iteration), rep( "", length(levels(y_vector)))) ## add line with ncomp for each iteration + ##rownames(labeled_iteration)[1] = paste0("ncomp = ", iteration) + ##labeled_iteration = cbind(rownames(labeled_iteration), labeled_iteration) + labeled_iteration = rbind(empty_row, summary_iteration) + + summary_plscv[[count]] = labeled_iteration + count = count+1} ## create list with summary table for each component + ## create dataframe from list + summary_plscv = do.call(rbind, summary_plscv) + summary_df = as.data.frame(summary_plscv) + rownames(summary_df) = NULL + + ## plots + ## plot to find ncomp with highest accuracy + plot(summary(msidata.cv.pls), main="Accuracy of PLS classification") + ncomp_max = components[which.max(accuracy_vector)] ## find ncomp with max. accuracy + ## one image for each sample/fold, 4 images per page + image(msidata.cv.pls, model = list(ncomp = ncomp_max), layout = c(2, 2)) + + par(opar) + ## print table with summary in pdf + plot(0,type='n',axes=FALSE,ann=FALSE) + title(main="Summary for the different components\n", adj=0.5) + ## summary for 4 components (20 rows) fits in one page: + if (length(components)<5){ + grid.table(summary_df, rows= NULL) + }else{ + grid.table(summary_df[1:20,], rows= NULL) + mincount = 21 + maxcount = 40 + for (count20 in 1:(ceiling(nrow(summary_df)/20)-1)){ + plot(0,type='n',axes=FALSE,ann=FALSE) + if (maxcount <= nrow(summary_df)){ + grid.table(summary_df[mincount:maxcount,], rows= NULL) + mincount = mincount+20 + maxcount = maxcount+20 + }else{### stop last page with last sample otherwise NA in table + grid.table(summary_df[mincount:nrow(summary_df),], rows= NULL)} + } + } + + ## optional output as .RData + #if $output_rdata: + save(msidata.cv.pls, file="$classification_rdata") + #end if + ######################## PLS - analysis ########################### + #elif str( $type_cond.method_cond.analysis_cond.PLS_method) == "PLS_analysis": + print("PLS analysis") + + ## number of components + component = c($type_cond.method_cond.analysis_cond.pls_comp) + + ### pls analysis + msidata.pls <- PLS(msidata, y = y_vector, ncomp = component, scale=$type_cond.method_cond.analysis_cond.pls_scale) + + ### plot of PLS coefficients + plot(msidata.pls, main="PLS coefficients per m/z") + + ### summary table of PLS + summary_table = summary(msidata.pls)\$accuracy[[paste0("ncomp = ",component)]] + summary_table = cbind(rownames(summary_table), data.frame(summary_table)) + rownames(summary_table) = NULL +print(summary_table) + ###plot(0,type='n',axes=FALSE,ann=FALSE) + ###grid.table(test, rows= TRUE) + + ### image of the best m/z + print(image(msidata, mz = topLabels(msidata.pls)[1,1], normalize.image = "linear", contrast.enhance = "histogram",smooth.image="gaussian", main="best m/z heatmap")) + + ## m/z and pixel information output + pls_classes = data.frame(msidata.pls\$classes[[1]]) + rownames(pls_classes) = names(pixels(msidata)) + colnames(pls_classes) = "predicted diagnosis" + pls_toplabels = topLabels(msidata.pls, n=$type_cond.method_cond.analysis_cond.pls_toplabels) + + write.table(pls_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") + write.table(pls_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") + + ## optional output as .RData + #if $output_rdata: + save(msidata.pls, file="$classification_rdata") + #end if + + #end if + + + ######################## OPLS ############################# + #elif str( $type_cond.method_cond.class_method) == "OPLS": + print("OPLS") + + ######################## OPLS -CV ############################# + #if str( $type_cond.method_cond.opls_analysis_cond.opls_method) == "opls_cvapply": + print("OPLS cv") + + ## folds + #if str($type_cond.method_cond.opls_analysis_cond.opls_fold_cond.opls_fold_vector) == "opls_fold_internal": + fold_vector = msidata\$$type_cond.method_cond.opls_analysis_cond.opls_fold_cond.opls_fold_name + #elif str($type_cond.method_cond.opls_analysis_cond.opls_fold_cond.opls_fold_vector) == "opls_fold_external": + fold_tabular = read.delim("$type_cond.method_cond.opls_analysis_cond.opls_fold_cond.opls_fold_data", header = FALSE, stringsAsFactors = FALSE) + fold_vector = as.factor(fold_tabular[,$type_cond.method_cond.opls_analysis_cond.opls_fold_cond.opls_fold_column]) + number_pixels = length(fold_vector) ## should be same as in data + #end if + + ## plot of folds + + position_df = cbind(coord(msidata)[,1:2], fold_vector) + fold_plot = ggplot(position_df, aes(x=x, y=y, fill=fold_vector))+ + geom_tile() + + coord_fixed()+ + ggtitle("Distribution of the fold variable")+ + theme_bw()+ + theme(text=element_text(family="ArialMT", face="bold", size=15))+ + theme(legend.position="bottom",legend.direction="vertical")+ + guides(fill=guide_legend(ncol=4,byrow=TRUE)) + coord_labels = aggregate(cbind(x,y)~fold_vector, data=position_df, mean, na.rm=TRUE, na.action="na.pass") + coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$fold_vector) + print(fold_plot) + + ## number of components + components = c($type_cond.method_cond.opls_analysis_cond.opls_cvcomp) + + ## OPLS-cvApply: + msidata.cv.opls <- cvApply(msidata, .y = y_vector, .fold = fold_vector, .fun = "OPLS", ncomp = components, keep.Xnew = $type_cond.method_cond.opls_analysis_cond.xnew_cv) + + ## create table with summary + count = 1 + summary_oplscv = list() + accuracy_vector = numeric() + for (iteration in components){ + summary_iteration = summary(msidata.cv.opls)\$accuracy[[paste0("ncomp = ", iteration)]] + summary_iteration = cbind(rownames(summary_iteration), summary_iteration) ## include rownames in table + accuracy_vector[count] = summary_iteration[1,2] ## vector with accuracies to find later maximum for plot + empty_row = c(paste0("ncomp = ", iteration), rep( "", length(levels(y_vector)))) ## add line with ncomp for each iteration + ##rownames(labeled_iteration)[1] = paste0("ncomp = ", iteration) + ##labeled_iteration = cbind(rownames(labeled_iteration), labeled_iteration) + labeled_iteration = rbind(empty_row, summary_iteration) + summary_oplscv[[count]] = labeled_iteration ## create list with summary table for each component + count = count+1} + ## create dataframe from list + summary_oplscv = do.call(rbind, summary_oplscv) + summary_df = as.data.frame(summary_oplscv) + rownames(summary_df) = NULL + + ## plots + ## plot to find ncomp with highest accuracy + plot(summary(msidata.cv.opls), main="Accuracy of OPLS classification") + ncomp_max = components[which.max(accuracy_vector)] ## find ncomp with max. accuracy + ## one image for each sample/fold, 4 images per page + image(msidata.cv.opls, model = list(ncomp = ncomp_max), layout = c(2, 2)) + + par(opar) + ## print table with summary in pdf + plot(0,type='n',axes=FALSE,ann=FALSE) + title(main="Summary for the different components\n", adj=0.5) + ## summary for 4 components (20 rows) fits in one page: + if (length(components)<5){ + grid.table(summary_df, rows= NULL) + }else{ + grid.table(summary_df[1:20,], rows= NULL) + mincount = 21 + maxcount = 40 + for (count20 in 1:(ceiling(nrow(summary_df)/20)-1)){ + plot(0,type='n',axes=FALSE,ann=FALSE) + if (maxcount <= nrow(summary_df)){ + grid.table(summary_df[mincount:maxcount,], rows= NULL) + mincount = mincount+20 + maxcount = maxcount+20 + }else{### stop last page with last sample otherwise NA in table + grid.table(summary_df[mincount:nrow(summary_df),], rows= NULL)} + } + } + + ## optional output as .RData + #if $output_rdata: + save(msidata.cv.opls, file="$classification_rdata") + #end if + + ######################## OPLS -analysis ########################### + #elif str( $type_cond.method_cond.opls_analysis_cond.opls_method) == "opls_analysis": + print("OPLS analysis") + + ## number of components + component = c($type_cond.method_cond.opls_analysis_cond.opls_comp) + + ### opls analysis + msidata.opls <- PLS(msidata, y = y_vector, ncomp = component, scale=$type_cond.method_cond.opls_analysis_cond.opls_scale, keep.Xnew = $type_cond.method_cond.opls_analysis_cond.xnew) + + ### plot of OPLS coefficients + plot(msidata.opls, main="OPLS coefficients per m/z") + + ### summary table of OPLS + summary_table = summary(msidata.opls)\$accuracy[[paste0("ncomp = ",component)]] + summary_table = cbind(rownames(summary_table), summary_table) + rownames(summary_table) = NULL + summary_table = data.frame(summary_table) + print(summary_table) + ###plot(0,type='n',axes=FALSE,ann=FALSE) + ###grid.table(test, rows= TRUE) + + ### image of the best m/z + print(image(msidata, mz = topLabels(msidata.opls)[1,1], normalize.image = "linear", contrast.enhance = "histogram",smooth.image="gaussian", main="best m/z heatmap")) + + ## m/z and pixel information output + opls_classes = data.frame(msidata.opls\$classes[[1]]) + rownames(opls_classes) = names(pixels(msidata)) + colnames(opls_classes) = "predicted diagnosis" + opls_toplabels = topLabels(msidata.opls, n=$type_cond.method_cond.opls_analysis_cond.opls_toplabels) + + write.table(opls_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") + write.table(opls_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") + + ## optional output as .RData + #if $output_rdata: + save(msidata.opls, file="$classification_rdata") + #end if + + #end if + + ######################## SSC ############################# + #elif str( $type_cond.method_cond.class_method) == "spatialShrunkenCentroids": + print("SSC") + + ######################## SSC - CV ############################# + #if str( $type_cond.method_cond.ssc_analysis_cond.ssc_method) == "ssc_cvapply": + print("SSC cv") + + ## folds + #if str($type_cond.method_cond.ssc_analysis_cond.ssc_fold_cond.ssc_fold_vector) == "ssc_fold_internal": + fold_vector = msidata\$$type_cond.method_cond.ssc_analysis_cond.ssc_fold_cond.ssc_fold_name + + #elif str($type_cond.method_cond.ssc_analysis_cond.ssc_fold_cond.ssc_fold_vector) == "ssc_fold_external": + fold_tabular = read.delim("$type_cond.method_cond.ssc_analysis_cond.ssc_fold_cond.ssc_fold_data", header = FALSE, stringsAsFactors = FALSE) + fold_vector = as.factor(fold_tabular[,$type_cond.method_cond.ssc_analysis_cond.ssc_fold_cond.ssc_fold_column]) + number_pixels = length(fold_vector) ## should be same as in data + #end if + + ## plot of folds + position_df = cbind(coord(msidata)[,1:2], fold_vector) + fold_plot = ggplot(position_df, aes(x=x, y=y, fill=fold_vector))+ + geom_tile() + + coord_fixed()+ + ggtitle("Distribution of the fold variable")+ + theme_bw()+ + theme(text=element_text(family="ArialMT", face="bold", size=15))+ + theme(legend.position="bottom",legend.direction="vertical")+ + guides(fill=guide_legend(ncol=4,byrow=TRUE)) + coord_labels = aggregate(cbind(x,y)~fold_vector, data=position_df, mean, na.rm=TRUE, na.action="na.pass") + coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$fold_vector) + print(fold_plot) + + ## SSC-cvApply: + msidata.cv.ssc <- cvApply(msidata, .y = y_vector,.fold = fold_vector,.fun = "spatialShrunkenCentroids", r = c($type_cond.method_cond.ssc_r), s = c($type_cond.method_cond.ssc_s), method = "$type_cond.method_cond.ssc_kernel_method") + + ## create table with summary + count = 1 + summary_ssccv = list() + accuracy_vector = numeric() + + for (iteration in names(msidata.cv.ssc@resultData[[1]][,1])){ + summary_iteration = summary(msidata.cv.ssc)\$accuracy[[iteration]] + summary_iteration = cbind(rownames(summary_iteration), summary_iteration) ## include rownames in table + accuracy_vector[count] = summary_iteration[1,2] ## vector with accuracies to find later maximum for plot + empty_row = c(iteration, rep( "", length(levels(y_vector)))) ## add line with ncomp for each iteration + labeled_iteration = rbind(empty_row, summary_iteration) + summary_ssccv[[count]] = labeled_iteration ## create list with summary table for each component + count = count+1 + } + + ##create dataframe from list + summary_ssccv = do.call(rbind, summary_ssccv) + summary_df = as.data.frame(summary_ssccv) + rownames(summary_df) = NULL + + ## plot to find parameters with highest accuracy + plot(summary(msidata.cv.ssc), main="Accuracy of SSC classification") + best_params = names(msidata.cv.ssc@resultData[[1]][,1])[which.max(accuracy_vector)] ## find parameters with max. accuracy + r_value = as.numeric(substring(unlist(strsplit(best_params, ","))[1], 4)) + s_value = as.numeric(substring(unlist(strsplit(best_params, ","))[3], 5)) ## remove space + + image(msidata.cv.ssc, model = list( r = r_value, s = s_value ), layout=c(2,2)) + + par(opar) + ## print table with summary in pdf + plot(0,type='n',axes=FALSE,ann=FALSE) + title(main="Summary for the different parameters\n", adj=0.5) + ## summary for 4 parameters (20 rows) fits in one page: + if (length(names(msidata.cv.ssc@resultData[[1]][,1]))<5){ + grid.table(summary_df, rows= NULL) + }else{ + grid.table(summary_df[1:20,], rows= NULL) + mincount = 21 + maxcount = 40 + for (count20 in 1:(ceiling(nrow(summary_df)/20)-1)){ + plot(0,type='n',axes=FALSE,ann=FALSE) + if (maxcount <= nrow(summary_df)){ + grid.table(summary_df[mincount:maxcount,], rows= NULL) + mincount = mincount+20 + maxcount = maxcount+20 + }else{### stop last page with last sample otherwise NA in table + grid.table(summary_df[mincount:nrow(summary_df),], rows= NULL)} + } + } + + ## optional output as .RData + #if $output_rdata: + save(msidata.cv.opls, file="$classification_rdata") + #end if + + ######################## SSC -analysis ########################### + #elif str( $type_cond.method_cond.ssc_analysis_cond.ssc_method) == "ssc_analysis": + print("SSC analysis") + + ## SSC analysis + msidata.ssc <- spatialShrunkenCentroids(msidata, y = y_vector, .fold = fold_vector, +r = c($type_cond.method_cond.ssc_r), s = c($type_cond.method_cond.ssc_s), method = "$type_cond.method_cond.ssc_kernel_method") + + plot(msidata.ssc, mode = "tstatistics", model = list("r" = c($type_cond.method_cond.ssc_r), "s" = c($type_cond.method_cond.ssc_s))) + + ### summary table SSC + + ##summary(msidata.ssc)\$accuracy[[names(msidata.ssc@resultData)]] + summary_table = summary(msidata.ssc) +print(summary_table) + ##summary_table = cbind(rownames(summary_table), summary_table) + ##rownames(summary_table) = NULL + + ###plot(0,type='n',axes=FALSE,ann=FALSE) + ###grid.table(summary_table, rows= TRUE) + + ### image of the best m/z + print(image(msidata, mz = topLabels(msidata.ssc)[1,1], normalize.image = "linear", contrast.enhance = "histogram",smooth.image="gaussian", main="best m/z heatmap")) + + ## m/z and pixel information output + ssc_classes = data.frame(msidata.ssc\$classes[[1]]) + rownames(ssc_classes) = names(pixels(msidata)) + colnames(ssc_classes) = "predicted diagnosis" + ssc_toplabels = topLabels(msidata.ssc) + + write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") + write.table(ssc_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") + + ## optional output as .RData + #if $output_rdata: + save(msidata.ssc, file="$classification_rdata") + #end if + + #end if + #end if + + + ######################## II) Prediction ############################# + ############################################################################# + #elif str( $type_cond.type_method) == "prediction": + print("prediction") + + #if str($type_cond.new_y.new_y_values) == "no_new_y": + new_y_vector = FALSE + #elif str($type_cond.new_y.new_y_values) == "new_y_internal": + new_y_vector = msidata\$$type_cond.new_y.new_y_name + #elif str($type_cond.new_y.new_y_values) == "new_y_external": + + new_y_tabular = read.delim("$type_cond.new_y.new_y_data", header = FALSE, stringsAsFactors = FALSE) + new_y_vector = new_y_tabular[,$type_cond.new_y.new_y_column] + number_pixels = length(new_y_vector) ## should be same as in data + #end if + + training_data = loadRData("$type_cond.training_result") + prediction = predict(training_data,msidata, newy = new_y_vector) + + ## optional output as .RData + #if $output_rdata: + msidata = prediction + save(msidata, file="$classification_rdata") + #end if + #end if + + dev.off() +}else{ + print("Inputfile has no intensities > 0") + dev.off() +} + + ]]></configfile> + </configfiles> + <inputs> + <param name="infile" type="data" format="imzml, rdata, analyze75" + label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData" + help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/> + <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> + + <conditional name="type_cond"> + <param name="type_method" type="select" label="Analysis step to perform"> + <option value="training" selected="True">training</option> + <option value="prediction">prediction</option> + </param> + <when value="training"> + + <conditional name="method_cond"> + <param name="class_method" type="select" label="Select the method for classification"> + <option value="PLS" selected="True">PLS</option> + <option value="OPLS">OPLS</option> + <option value="spatialShrunkenCentroids">spatial shrunken centroids</option> + </param> + <when value="PLS"> + + <conditional name="analysis_cond"> + <param name="PLS_method" type="select" label="Crossvalidation or analysis"> + <option value="cvapply" selected="True">cvApply</option> + <option value="PLS_analysis">PLS analysis</option> + </param> + <when value="cvapply"> + + <param name="plscv_comp" type="text" value="1:2" + label="The number of PLS components" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/> + <conditional name="fold_cond"> + <param name="fold_vector" type="select" label="Define the fold variable"> + <option value="fold_internal" selected="True">dataset contains already fold</option> + <option value="fold_external">use fold from tabular file</option> + </param> + <when value="fold_internal"> + <param name="fold_name" type="text" value="sample" label="Name of the pData slot where fold is stored" help="each fold must contain pixels of all categories"/> + </when> + <when value="fold_external"> + <param name="fold_data" type="data" format="tabular" label="Tabular file with column for folds" help="Number of rows must be number of pixels"/> + <param name="fold_column" data_ref="fold_data" label="Column with folds" type="data_column"/> + </when> + </conditional> + </when> + + <when value="PLS_analysis"> + <param name="pls_comp" type="integer" value="5" + label="The optimal number of PLS components as indicated by cross-validations" help="Run cvApply first to optain optiaml number of PLS components"/> + <param name="pls_scale" type="boolean" display="radio" label="data scaling" truevalue="TRUE" falsevalue="FALSE"/> + <param name="pls_toplabels" type="integer" value="100" + label="Number of toplabels (masses) which should be written in tabular output"/> + </when> + </conditional> + </when> + + <when value="OPLS"> + + <conditional name="opls_analysis_cond"> + <param name="opls_method" type="select" label="Analysis step to perform"> + <option value="opls_cvapply" selected="True">cvApply</option> + <option value="opls_analysis">OPLS analysis</option> + </param> + + <when value="opls_cvapply"> + <param name="opls_cvcomp" type="text" value="1:2" + label="The number of OPLS components" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/> + <param name="xnew_cv" type="boolean" display="radio" truevalue="TRUE" falsevalue="FALSE" label="Keep new matrix"/> + <conditional name="opls_fold_cond"> + <param name="opls_fold_vector" type="select" label="Define the fold variable"> + <option value="opls_fold_internal" selected="True">dataset contains already fold</option> + <option value="opls_fold_external">use fold from tabular file</option> + </param> + <when value="opls_fold_internal"> + <param name="opls_fold_name" type="text" value="sample" label="Name of the pData slot where fold is stored" help="each fold must contain pixels of all categories"/> + </when> + <when value="opls_fold_external"> + <param name="opls_fold_data" type="data" format="tabular" label="Tabular file with column for folds" help="Number of rows must be number of pixels"/> + <param name="opls_fold_column" data_ref="opls_fold_data" label="Column with folds" type="data_column"/> + </when> + </conditional> + </when> + + <when value="opls_analysis"> + <param name="opls_comp" type="integer" value="5" + label="The optimal number of PLS components as indicated by cross-validations" help="Run cvApply first to optain optiaml number of PLS components"/> + <param name="xnew" type="boolean" display="radio" truevalue="TRUE" falsevalue="FALSE" label="Keep new matrix"/> + <param name="opls_scale" type="select" label="data scaling" display="radio" optional="False"> + <option value="TRUE">yes</option> + <option value="FALSE" selected="True">no</option> + </param> + <param name="opls_toplabels" type="integer" value="100" + label="Number of toplabels (features) which should be written in tabular output"/> + </when> + </conditional> + </when> + + <when value="spatialShrunkenCentroids"> + <conditional name="ssc_analysis_cond"> + <param name="ssc_method" type="select" label="Analysis step to perform"> + <option value="ssc_cvapply" selected="True">cvApply</option> + <option value="ssc_analysis">spatial shrunken centroids analysis</option> + </param> + <when value="ssc_cvapply"> + + <conditional name="ssc_fold_cond"> + <param name="ssc_fold_vector" type="select" label="Define the fold variable"> + <option value="ssc_fold_internal" selected="True">dataset contains already fold</option> + <option value="ssc_fold_external">use fold from tabular file</option> + </param> + <when value="ssc_fold_internal"> + <param name="ssc_fold_name" type="text" value="sample" label="Name of the pData slot where fold is stored" help="each fold must contain pixels of all categories"/> + </when> + <when value="ssc_fold_external"> + <param name="ssc_fold_data" type="data" format="tabular" label="Tabular file with column for folds" help="Number of rows must be number of pixels"/> + <param name="ssc_fold_column" data_ref="ssc_fold_data" label="Column with folds" type="data_column"/> + </when> + </conditional> + </when> + + <when value="ssc_analysis"> + + <param name="ssc_toplabels" type="integer" value="100" + label="Number of toplabels (features) which should be written in tabular output"/> + </when> + </conditional> + <param name="ssc_r" type="text" value="2" + label="The spatial neighborhood radius of nearby pixels to consider (r)" help="For cvapply multiple values are allowed (e.g. 1,2,3 or 2:5)"/> + <param name="ssc_s" type="text" value="2" + label="The sparsity thresholding parameter by which to shrink the t-statistics (s)" help="For cvapply multiple values are allowed (e.g. 1,2,3 or 2:5)"/> + <param name="ssc_kernel_method" type="select" display="radio" label = "The method to use to calculate the spatial smoothing kernels for the embedding. The 'gaussian' method refers to spatially-aware (SA) weights, and 'adaptive' refers to spatially-aware structurally-adaptive (SASA) weights"> + <option value="gaussian">gaussian</option> + <option value="adaptive" selected="True">adaptive</option> + </param> + + </when> + </conditional> + <conditional name="y_cond"> + <param name="y_vector" type="select" label="Define the response variable y"> + <option value="y_internal" selected="True">dataset contains already y</option> + <option value="y_external">use y from tabular file</option> + </param> + <when value="y_internal"> + <param name="y_name" type="text" value="combined_sample" label="Name of the pData slot where y is stored" help="Outputs of MSI_combine tool have 'combined_sample' as name"/> + </when> + <when value="y_external"> + <param name="y_data" type="data" format="tabular" label="Tabular file with column for y response"/> + <param name="y_column" data_ref="y_data" label="Column with y response" type="data_column"/> + </when> + </conditional> + </when> + + <when value="prediction"> + <param name="training_result" type="data" format="rdata" label="Result from previous classification training"/> + <conditional name="new_y"> + <param name="new_y_values" type="select" label="Define the new response y"> + <option value="no_new_y" >no new y response</option> + <option value="new_y_internal" selected="True">dataset contains already y</option> + <option value="new_y_external">use y from tabular file</option> + </param> + <when value="no_new_y"/> + <when value="new_y_internal"> + <param name="new_y_name" type="text" value="combined_sample" label="Name of the pData slot where y is stored" help="data merged with MSI_combine tool has 'combined_sample' as name"/> + </when> + + <when value="new_y_external"> + <param name="new_y_data" type="data" format="tabular" label="Tabular file with column for y response"/> + <param name="new_y_column" data_ref="new_y_data" label="Column with y response" type="data_column"/> + </when> + </conditional> + </when> + </conditional> + <param name="output_rdata" type="boolean" display="radio" label="Results as .RData output"/> + </inputs> + <outputs> + <data format="pdf" name="classification_images" from_work_dir="classificationpdf.pdf" label = "$infile.display_name classification"/> + <data format="tabular" name="mzfeatures" label="$infile.display_name features"/> + <data format="tabular" name="pixeloutput" label="$infile.display_name pixels"/> + <data format="rdata" name="classification_rdata" label="$infile.display_name classification"> + <filter>output_rdata</filter> + </data> + </outputs> + <tests> + <test expect_num_outputs="3"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="training"/> + <conditional name="method_cond"> + <param name="class_method" value="PLS"/> + <conditional name="analysis_cond"> + <param name="PLS_method" value="cvapply"/> + + <param name="plscv_comp" value="2:4"/> + <conditional name="fold_cond"> + <param name="fold_vector" value="fold_external"/> + <param name="fold_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="fold_column" value="1"/> + </conditional> + + </conditional> + </conditional> + <conditional name="y_cond"> + <param name="y_vector" value="y_external"/> + <param name="y_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="y_column" value="2"/> + </conditional> + </conditional> + <output name="mzfeatures" file="features_test1.tabular"/> + <output name="pixeloutput" file="pixels_test1.tabular"/> + <output name="classification_images" file="test1.pdf" compare="sim_size" delta="20000"/> + </test> + + <test expect_num_outputs="4"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="training"/> + <conditional name="method_cond"> + <param name="class_method" value="PLS"/> + <conditional name="analysis_cond"> + <param name="PLS_method" value="PLS_analysis"/> + + <param name="pls_comp" value="2"/> + <param name="pls_scale" value="TRUE"/> + <param name="pls_toplabels" value="100"/> + <conditional name="fold_cond"> + <param name="fold_vector" value="fold_external"/> + <param name="fold_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="fold_column" value="1"/> + </conditional> + + </conditional> + </conditional> + <conditional name="y_cond"> + <param name="y_vector" value="y_external"/> + <param name="y_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="y_column" value="2"/> + </conditional> + </conditional> + <param name="output_rdata" value="True"/> + <output name="mzfeatures" file="features_test2.tabular"/> + <output name="pixeloutput" file="pixels_test2.tabular"/> + <output name="classification_images" file="test2.pdf" compare="sim_size" delta="20000"/> + <output name="classification_rdata" file="test2.rdata" compare="sim_size" /> + </test> + + <test expect_num_outputs="3"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="training"/> + <conditional name="method_cond"> + <param name="class_method" value="OPLS"/> + <conditional name="opls_analysis_cond"> + <param name="opls_method" value="opls_analysis"/> + + <param name="opls_cvcomp" value="1:2"/> + <param name="xnew_cv" value="FALSE"/> + <conditional name="opls_fold_cond"> + <param name="opls_fold_vector" value="opls_fold_external"/> + <param name="opls_fold_data" ftype="tabular" value="random_factors.tabular"/> + <param name="opls_fold_column" value="1"/> + </conditional> + </conditional> + </conditional> + <conditional name="y_cond"> + <param name="y_vector" value="y_external"/> + <param name="y_data" value="random_factors.tabular" ftype="tabular"/> + <param name="y_column" value="2"/> + </conditional> + </conditional> + <output name="mzfeatures" file="features_test3.tabular"/> + <output name="pixeloutput" file="pixels_test3.tabular"/> + <output name="classification_images" file="test3.pdf" compare="sim_size" delta="20000"/> + </test> + + <test expect_num_outputs="4"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="training"/> + <conditional name="method_cond"> + <param name="class_method" value="OPLS"/> + <conditional name="opls_analysis_cond"> + + <param name="opls_method" value="opls_analysis"/> + <param name="opls_comp" value="3"/> + <param name="xnew" value="FALSE"/> + <param name="opls_scale" value="FALSE"/> + <param name="opls_toplabels" value="100"/> + </conditional> + + </conditional> + <conditional name="y_cond"> + <param name="y_vector" value="y_external"/> + <param name="y_data" value="random_factors.tabular" ftype="tabular"/> + <param name="y_column" value="2"/> + </conditional> + </conditional> + <param name="output_rdata" value="True"/> + <output name="mzfeatures" file="features_test4.tabular"/> + <output name="pixeloutput" file="pixels_test4.tabular"/> + <output name="classification_images" file="test4.pdf" compare="sim_size" delta="20000"/> + <output name="classification_rdata" file="test4.rdata" compare="sim_size" /> + </test> + + <test expect_num_outputs="3"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="training"/> + <conditional name="method_cond"> + <param name="class_method" value="spatialShrunkenCentroids"/> + <conditional name="ssc_analysis_cond"> + <param name="ssc_method" value="ssc_cvapply"/> + <conditional name="ssc_fold_cond"> + <param name="ssc_fold_vector" value="ssc_fold_external"/> + <param name="ssc_fold_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="ssc_fold_column" value="1"/> + </conditional> + <param name="ssc_r" value="1:2"/> + <param name="ssc_s" value="2:3"/> + <param name="ssc_kernel_method" value="adaptive"/> + </conditional> + </conditional> + <conditional name="y_cond"> + <param name="y_vector" value="y_external"/> + <param name="y_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="y_column" value="2"/> + </conditional> + </conditional> + <output name="mzfeatures" file="features_test5.tabular"/> + <output name="pixeloutput" file="pixels_test5.tabular"/> + <output name="classification_images" file="test5.pdf" compare="sim_size" delta="20000"/> + </test> + + <test expect_num_outputs="4"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="training"/> + <conditional name="method_cond"> + <param name="class_method" value="spatialShrunkenCentroids"/> + <conditional name="ssc_analysis_cond"> + <param name="ssc_method" value="ssc_analysis"/> + <param name="ssc_toplabels" value="100"/> + </conditional> + <param name="ssc_r" value="2"/> + <param name="ssc_s" value="2"/> + <param name="ssc_kernel_method" value="adaptive"/> + </conditional> + <conditional name="y_cond"> + <param name="y_vector" value="y_external"/> + <param name="y_data" value="random_factors.tabular" ftype="tabular"/> + <param name="y_column" value="2"/> + </conditional> + </conditional> + <param name="output_rdata" value="True"/> + <output name="mzfeatures" file="features_test6.tabular"/> + <output name="pixeloutput" file="pixels_test6.tabular"/> + <output name="classification_images" file="test6.pdf" compare="sim_size" delta="20000"/> + <output name="classification_rdata" file="test6.rdata" compare="sim_size" /> + </test> + + <test expect_num_outputs="4"> + <param name="infile" value="testfile_squares.rdata" ftype="rdata"/> + <conditional name="type_cond"> + <param name="type_method" value="prediction"/> + <param name="training_result" value="test2.rdata" ftype="rdata"/> + <conditional name="new_y"> + <param name="new_y_values" value="new_y_external"/> + <param name="new_y_data" value="pixel_annotation_file1.tabular" ftype="tabular"/> + <param name="new_y_column" value="2"/> + </conditional> + </conditional> + <param name="output_rdata" value="True"/> + <output name="mzfeatures" file="features_test7.tabular"/> + <output name="pixeloutput" file="pixels_test7.tabular"/> + <output name="classification_images" file="test7.pdf" compare="sim_size" delta="20000"/> + <output name="classification_rdata" file="test7.rdata" compare="sim_size" /> + </test> + + </tests> + <help> + <![CDATA[ + +Cardinal is an R package that implements statistical & computational tools for analyzing mass spectrometry imaging datasets. `More information on Cardinal <http://cardinalmsi.org//>`_ + +This tool provides three different Cardinal functions for supervised classification of mass-spectrometry imaging data. + +Input data: 3 types of input data can be used: + +- imzml file (upload imzml and ibd file via the "composite" function) `Introduction to the imzml format <https://ms-imaging.org/wp/imzml/>`_ +- Analyze7.5 (upload hdr, img and t2m file via the "composite" function) +- Cardinal "MSImageSet" data (with variable name "msidata", saved as .RData) + +Options: + +- PLS(-DA): partial least square (discriminant analysis) +- O-PLS(-DA): Orthogonal partial least squares (discriminant analysis) +- Spatial shrunken centroids + +Output: + +- Pdf with the heatmaps and plots for the classification +- Tabular file with information on masses and pixels: toplabels/classes (PLS, spatial shrunken centroids) +- optional RData output to further explore the results with Cardinal in R + + ]]> + </help> + <citations> + <citation type="doi">10.1093/bioinformatics/btv146</citation> + </citations> +</tool>