comparison classification.xml @ 15:f28ad96b76dc draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit d0dc9303d449c63a6ffe8fbfe195951d5db9cb89-dirty"

14:ece627528a78

<tool id="cardinal_classification" name="MSI classification" version="@VERSION@.1">
    <description>spatial classification of mass spectrometry imaging data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">

            merged_response = merge(msidata_coordinates, y_input, by=c("x", "y"), all.x=TRUE)
            merged_response[is.na(merged_response)] = "NA"
            merged_response = merged_response[order(merged_response\$pixel_index),]
            conditions = as.factor(merged_response[,4])
            y_vector = conditions

    ## plot of y vector

    position_df = cbind(coord(msidata)[,1:2], conditions)
    y_plot = ggplot(position_df, aes(x=x, y=y, fill=conditions))+

	       plot.background = element_blank(),
	       panel.grid.major = element_blank(),
	       panel.grid.minor = element_blank())+
           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)~conditions, data=position_df, mean, na.rm=TRUE, na.action="na.pass")
    coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$conditions)
    print(y_plot)

                plot(components, accuracy_vector, ylab = "mean accuracy",type="o", main="Mean 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
                minimumy = min(coord(msidata.cv.pls)[,2])
                maximumy = max(coord(msidata.cv.pls)[,2])
                image(msidata.cv.pls, model = list(ncomp = ncomp_max),ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),layout = c(1, 1))

                ## print table with summary in pdf
                par(opar)
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main="Summary for the different components\n", adj=0.5)

                        }
                    )    

                ### pls analysis and coefficients plot
                msidata.pls <- PLS(msidata, y = y_vector, ncomp = component, scale=$type_cond.method_cond.analysis_cond.pls_scale)
                plot(msidata.pls, main="PLS coefficients per m/z")

                ### summary table of PLS
                summary_table = summary(msidata.pls)\$accuracy[[paste0("ncomp = ",component)]]
                summary_table2 = round(as.numeric(summary_table), digits=2)
                summary_matrix = matrix(summary_table2, nrow=4, ncol=number_groups)

		       plot.background = element_blank(),
		       panel.grid.major = element_blank(),
		       panel.grid.minor = element_blank())+
                       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)~predicted_classes, data=prediction_df, mean, na.rm=TRUE, na.action="na.pass")
                coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$predicted_classes)
                print(prediction_plot)

                ### optional output as .RData

                plot(components, accuracy_vector, ylab = "mean accuracy", type="o", main="Mean 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
                minimumy = min(coord(msidata.cv.opls)[,2])
                maximumy = max(coord(msidata.cv.opls)[,2])
                image(msidata.cv.opls, model = list(ncomp = ncomp_max),ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),layout = c(1, 1))

                ## print table with summary in pdf
                par(opar)
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main="Summary for the different components\n", adj=0.5)

                    )    

                ### opls analysis and coefficients plot
                msidata.opls <- PLS(msidata, y = y_vector, ncomp = component, scale=$type_cond.method_cond.opls_analysis_cond.opls_scale)
                ## to reduce msidata: keep.Xnew = $type_cond.method_cond.opls_analysis_cond.xnew
                plot(msidata.opls, main="OPLS coefficients per m/z")


                ### summary table of OPLS
                summary_table = summary(msidata.opls)\$accuracy[[paste0("ncomp = ",component)]]
                summary_table2 = round(as.numeric(summary_table), digits=2)

		       plot.background = element_blank(),
		       panel.grid.major = element_blank(),
		       panel.grid.minor = element_blank())+
                       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)~predicted_classes, data=prediction_df, mean, na.rm=TRUE, na.action="na.pass")
                coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$predicted_classes)
                print(prediction_plot)

                ## optional output as .RData

                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
                minimumy = min(coord(msidata.cv.ssc)[,2])
                maximumy = max(coord(msidata.cv.ssc)[,2])
                image(msidata.cv.ssc, model = list( r = r_value, s = s_value ), ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),layout=c(1,1))

		#if $type_cond.method_cond.ssc_analysis_cond.write_best_params:
                	write.table(r_value, file="$best_r", quote = FALSE, row.names = FALSE, col.names=FALSE, sep = "\t")
                	write.table(s_value, file="$best_s", quote = FALSE, row.names = FALSE, col.names=FALSE, sep = "\t")
                #end if

                ## SSC analysis and plot
                msidata.ssc <- spatialShrunkenCentroids(msidata, y = y_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)), 
			col=hue_pal()(length(levels(msidata.ssc\$classes[[1]]))), lwd=2)
                


                ### summary table SSC
                ##############summary_table = summary(msidata.ssc)

                ### stop if multiple values for r and s were used as input

                ssc_toplabels = topFeatures(msidata.ssc, n=Inf)
                ssc_toplabels[,6:9] <-round(ssc_toplabels[,6:9],6)
                write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
                write.table(ssc_classes2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
     
                image(msidata.ssc, model=list(r = c($type_cond.method_cond.ssc_r), s = c($type_cond.method_cond.ssc_s)), 
			col=hue_pal()(length(levels(msidata.ssc\$classes[[1]]))), mode="classes", layout=c(1,1), main="Class Prediction")
                image(msidata.ssc, model=list(r = c($type_cond.method_cond.ssc_r), s = c($type_cond.method_cond.ssc_s)), 
			col=hue_pal()(length(levels(msidata.ssc\$classes[[1]]))), mode="probabilities", layout=c(1,1), main="Class probabilities")

                
               ## image with right and wrong classes: 
               prediction_df = cbind(coord(msidata.ssc)[,1:2], ssc_classes)
               colnames(prediction_df) = c("x", "y", "predicted_classes")

            merged_response[is.na(merged_response)] = "NA"
            merged_response = merged_response[order(merged_response\$pixel_index),]
            new_y_vector = as.factor(merged_response[,4])
            prediction = predict(training_data,msidata, newy = new_y_vector)
            
	    ## Summary table prediction
	    summary_table = summary(prediction)\$accuracy[[names(prediction@resultData)]]
	    summary_table2 = round(as.numeric(summary_table), digits=2)
	    summary_matrix = matrix(summary_table2, nrow=4, ncol=ncol(summary_table))
	    summary_table3 = cbind(rownames(summary_table), summary_matrix) ## include rownames in table

	    plot(0,type='n',axes=FALSE,ann=FALSE)
	   grid.table(summary_table5, rows= NULL)

        #else
            prediction = predict(training_data,msidata)
        #end if

        ## m/z and pixel information output
        predicted_classes = data.frame(prediction\$classes[[1]])
        pixel_names = gsub(", y = ", "_", names(pixels(msidata)))
        pixel_names = gsub(" = ", "y_", pixel_names)

            ## this seems to work only for SSC, therefore overwrite tables
            predicted_probabilities = data.frame(prediction\$probabilities[[1]])
            predicted_classes2 = data.frame(pixel_names, x_coordinates, y_coordinates, predicted_classes, predicted_probabilities)
            colnames(predicted_classes2) = c("pixel names", "x", "y","predicted condition", levels(prediction\$classes[[1]]))
            ## also image modes are specific to SSC
            image(prediction, mode="classes", layout=c(1,1), main="Class", col=hue_pal()(length(unique(prediction\$classes[[1]]))))
            image(prediction, mode="probabilities", layout=c(1,1), main="Class probabilities", col=hue_pal()(length(unique(prediction\$classes[[1]]))))

	#else
        
                prediction_plot = ggplot(prediction_df, aes(x=x, y=y, fill=predicted_classes))+
        	geom_tile()+

        	plot.background = element_blank(),
        	panel.grid.major = element_blank(),
        	panel.grid.minor = element_blank())+
        	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)~predicted_classes, data=prediction_df, mean, na.rm=TRUE, na.action="na.pass")
        	coord_labels\$file_number = gsub( "_.*§", "", coord_labels\$predicted_classes)
        	print(prediction_plot)
        #end if
        

                        <param name="column_new_response" data_ref="new_response_file" label="Column with new response values" type="data_column"/>
                        <param name="new_tabular_header" type="boolean" label="Tabular files contain a header line" truevalue="TRUE" falsevalue="FALSE"/>
                    </when>
                </conditional>
            </when>
        </conditional>
        <param name="output_rdata" type="boolean" label="Results as .RData output" help="Can be used to generate a classification prediction on new data"/>
    </inputs>
    <outputs>
        <data format="pdf" name="classification_images" from_work_dir="classificationpdf.pdf" label = "${tool.name} on ${on_string}: results"/>

15:f28ad96b76dc

<tool id="cardinal_classification" name="MSI classification" version="@VERSION@.2">
    <description>spatial classification of mass spectrometry imaging data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">

            merged_response = merge(msidata_coordinates, y_input, by=c("x", "y"), all.x=TRUE)
            merged_response[is.na(merged_response)] = "NA"
            merged_response = merged_response[order(merged_response\$pixel_index),]
            conditions = as.factor(merged_response[,4])
            y_vector = conditions
            
        ## colours selection:

	#if str($colour_conditional.colour_type) == "manual_colour"
	    #set $color_string = ','.join(['"%s"' % $color.annotation_color for $color in $colour_conditional.colours])
	    colourvector = c($color_string)

	#elif str($colour_conditional.colour_type) == "colourpalette"
	    number_levels = (length(levels(conditions)))
	    colourvector = noquote($colour_conditional.palettes)(number_levels)

	#end if

    ## plot of y vector

    position_df = cbind(coord(msidata)[,1:2], conditions)
    y_plot = ggplot(position_df, aes(x=x, y=y, fill=conditions))+

	       plot.background = element_blank(),
	       panel.grid.major = element_blank(),
	       panel.grid.minor = element_blank())+
           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))+
           scale_discrete_manual(aesthetics = c("colour", "fill"), values = colourvector)
    coord_labels = aggregate(cbind(x,y)~conditions, data=position_df, mean, na.rm=TRUE, na.action="na.pass")
    coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$conditions)
    print(y_plot)

                plot(components, accuracy_vector, ylab = "mean accuracy",type="o", main="Mean 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
                minimumy = min(coord(msidata.cv.pls)[,2])
                maximumy = max(coord(msidata.cv.pls)[,2])
                image(msidata.cv.pls, model = list(ncomp = ncomp_max),ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),layout = c(1, 1), col=colourvector)

                ## print table with summary in pdf
                par(opar)
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main="Summary for the different components\n", adj=0.5)

                        }
                    )    

                ### pls analysis and coefficients plot
                msidata.pls <- PLS(msidata, y = y_vector, ncomp = component, scale=$type_cond.method_cond.analysis_cond.pls_scale)
                plot(msidata.pls, main="PLS coefficients per m/z", col=colourvector)

                ### summary table of PLS
                summary_table = summary(msidata.pls)\$accuracy[[paste0("ncomp = ",component)]]
                summary_table2 = round(as.numeric(summary_table), digits=2)
                summary_matrix = matrix(summary_table2, nrow=4, ncol=number_groups)

		       plot.background = element_blank(),
		       panel.grid.major = element_blank(),
		       panel.grid.minor = element_blank())+
                       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))+
                       scale_discrete_manual(aesthetics = c("colour", "fill"), values = colourvector)
                coord_labels = aggregate(cbind(x,y)~predicted_classes, data=prediction_df, mean, na.rm=TRUE, na.action="na.pass")
                coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$predicted_classes)
                print(prediction_plot)

                ### optional output as .RData

                plot(components, accuracy_vector, ylab = "mean accuracy", type="o", main="Mean 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
                minimumy = min(coord(msidata.cv.opls)[,2])
                maximumy = max(coord(msidata.cv.opls)[,2])
                image(msidata.cv.opls, model = list(ncomp = ncomp_max),ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),layout = c(1, 1), col=colourvector)

                ## print table with summary in pdf
                par(opar)
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main="Summary for the different components\n", adj=0.5)

                    )    

                ### opls analysis and coefficients plot
                msidata.opls <- PLS(msidata, y = y_vector, ncomp = component, scale=$type_cond.method_cond.opls_analysis_cond.opls_scale)
                ## to reduce msidata: keep.Xnew = $type_cond.method_cond.opls_analysis_cond.xnew
                plot(msidata.opls, main="OPLS coefficients per m/z", col=colourvector)


                ### summary table of OPLS
                summary_table = summary(msidata.opls)\$accuracy[[paste0("ncomp = ",component)]]
                summary_table2 = round(as.numeric(summary_table), digits=2)

		       plot.background = element_blank(),
		       panel.grid.major = element_blank(),
		       panel.grid.minor = element_blank())+
                       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))+
                       scale_discrete_manual(aesthetics = c("colour", "fill"), values = colourvector)
                coord_labels = aggregate(cbind(x,y)~predicted_classes, data=prediction_df, mean, na.rm=TRUE, na.action="na.pass")
                coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$predicted_classes)
                print(prediction_plot)

                ## optional output as .RData

                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
                minimumy = min(coord(msidata.cv.ssc)[,2])
                maximumy = max(coord(msidata.cv.ssc)[,2])
                image(msidata.cv.ssc, model = list( r = r_value, s = s_value ), ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),layout=c(1,1), col=colourvector)

		#if $type_cond.method_cond.ssc_analysis_cond.write_best_params:
                	write.table(r_value, file="$best_r", quote = FALSE, row.names = FALSE, col.names=FALSE, sep = "\t")
                	write.table(s_value, file="$best_s", quote = FALSE, row.names = FALSE, col.names=FALSE, sep = "\t")
                #end if

                ## SSC analysis and plot
                msidata.ssc <- spatialShrunkenCentroids(msidata, y = y_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)), 
			col=colourvector, lwd=2)

                ### summary table SSC
                ##############summary_table = summary(msidata.ssc)

                ### stop if multiple values for r and s were used as input

                ssc_toplabels = topFeatures(msidata.ssc, n=Inf)
                ssc_toplabels[,6:9] <-round(ssc_toplabels[,6:9],6)
                write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
                write.table(ssc_classes2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
     
                image(msidata.ssc, model=list(r = c($type_cond.method_cond.ssc_r), s = c($type_cond.method_cond.ssc_s)), ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),
			col=colourvector, mode="classes", layout=c(1,1), main="Class Prediction")
                image(msidata.ssc, model=list(r = c($type_cond.method_cond.ssc_r), s = c($type_cond.method_cond.ssc_s)), ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),
			col=colourvector, mode="probabilities", layout=c(1,1), main="Class probabilities")

                
               ## image with right and wrong classes: 
               prediction_df = cbind(coord(msidata.ssc)[,1:2], ssc_classes)
               colnames(prediction_df) = c("x", "y", "predicted_classes")

            merged_response[is.na(merged_response)] = "NA"
            merged_response = merged_response[order(merged_response\$pixel_index),]
            new_y_vector = as.factor(merged_response[,4])
            prediction = predict(training_data,msidata, newy = new_y_vector)
            
            ##numbers of levels for colour selection
            number_levels = length(levels(new_y_vector))
            
	    ## Summary table prediction
	    summary_table = summary(prediction)\$accuracy[[names(prediction@resultData)]]
	    summary_table2 = round(as.numeric(summary_table), digits=2)
	    summary_matrix = matrix(summary_table2, nrow=4, ncol=ncol(summary_table))
	    summary_table3 = cbind(rownames(summary_table), summary_matrix) ## include rownames in table

	    plot(0,type='n',axes=FALSE,ann=FALSE)
	   grid.table(summary_table5, rows= NULL)

        #else
            prediction = predict(training_data,msidata)
            number_levels = length(levels(training_data\$y[[1]]))
        #end if
        
        ## colours selection:

	#if str($colour_conditional.colour_type) == "manual_colour"
	    #set $color_string = ','.join(['"%s"' % $color.annotation_color for $color in $colour_conditional.colours])
	    colourvector = c($color_string)

	#elif str($colour_conditional.colour_type) == "colourpalette"
	    colourvector = noquote($colour_conditional.palettes)(number_levels)

	#end if

        ## m/z and pixel information output
        predicted_classes = data.frame(prediction\$classes[[1]])
        pixel_names = gsub(", y = ", "_", names(pixels(msidata)))
        pixel_names = gsub(" = ", "y_", pixel_names)

            ## this seems to work only for SSC, therefore overwrite tables
            predicted_probabilities = data.frame(prediction\$probabilities[[1]])
            predicted_classes2 = data.frame(pixel_names, x_coordinates, y_coordinates, predicted_classes, predicted_probabilities)
            colnames(predicted_classes2) = c("pixel names", "x", "y","predicted condition", levels(prediction\$classes[[1]]))
            ## also image modes are specific to SSC
            image(prediction, mode="classes", layout=c(1,1), main="Class", ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy), col=colourvector)
            image(prediction, mode="probabilities", layout=c(1,1), main="Class probabilities",ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy), col=colourvector)

	#else
        
                prediction_plot = ggplot(prediction_df, aes(x=x, y=y, fill=predicted_classes))+
        	geom_tile()+

        	plot.background = element_blank(),
        	panel.grid.major = element_blank(),
        	panel.grid.minor = element_blank())+
        	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))+
        	scale_discrete_manual(aesthetics = c("colour", "fill"), values = colourvector)
        	coord_labels = aggregate(cbind(x,y)~predicted_classes, data=prediction_df, mean, na.rm=TRUE, na.action="na.pass")
        	coord_labels\$file_number = gsub( "_.*§", "", coord_labels\$predicted_classes)
        	print(prediction_plot)
        #end if
        

                        <param name="column_new_response" data_ref="new_response_file" label="Column with new response values" type="data_column"/>
                        <param name="new_tabular_header" type="boolean" label="Tabular files contain a header line" truevalue="TRUE" falsevalue="FALSE"/>
                    </when>
                </conditional>
            </when>
        </conditional>
        <conditional name="colour_conditional">
	    <param name="colour_type" type="select" label="Choose a colour scheme">
	        <option value="colourpalette" selected="True" >Colour palette</option>
	        <option value="manual_colour">Manual selection</option>
	    </param>
	    <when value="manual_colour">
	       <repeat name="colours" title="Colours for the plots" min="1" max="50">
	       <param name="annotation_color" type="color" label="Colours" value="#ff00ff" help="Numbers of colours should be the same as number of components">
	       <sanitizer>
	           <valid initial="string.letters,string.digits">
	           <add value="#" />
	           </valid>
	       </sanitizer>
	       </param>
	       </repeat>
	    </when>
	    <when value="colourpalette">
	        <param name="palettes" type="select" display="radio" label="Select a colourpalette">
		    <option value="hue_pal()" selected="True">hue</option>
		    <option value="rainbow">rainbow</option>
		    <option value="heat.colors">heat colors</option>
		    <option value="terrain.colors">terrain colors</option>
		    <option value="topo.colors">topo colors</option>
		    <option value="cm.colors">cm colors</option>
	        </param>
	    </when>
        </conditional>
        <param name="output_rdata" type="boolean" label="Results as .RData output" help="Can be used to generate a classification prediction on new data"/>
    </inputs>
    <outputs>
        <data format="pdf" name="classification_images" from_work_dir="classificationpdf.pdf" label = "${tool.name} on ${on_string}: results"/>