| Previous changeset 39:436f03b71cf6 (2019-06-20) Next changeset 41:8acca16f3921 (2020-01-28) |
|
Commit message:
Uploaded |
|
added:
CHM.R heatmap.sh mda_heatmap_gen.py mda_heatmap_gen.xml |
|
removed:
CHM_Advanced.R heatmap_advanced.sh mda_advanced_heatmap_gen.xml |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 CHM.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/CHM.R Thu Jun 20 11:39:46 2019 -0400 |
| [ |
| @@ -0,0 +1,130 @@ +### This method generates a row and column ordering given an input matrix and ordering methods. +### +### matrixData - numeric matrix +### rowOrderMethod - Hierarchical, Original, Random +### rowDistanceMeasure - For clustering, distance measure. May be: euclidean, binary, manhattan, maximum, canberra, minkowski, or correlation. +### rowAgglomerationMethod - For clustering, agglomeration method. May be: 'average' for Average Linkage, 'complete' for Complete Linkage, +### 'single' for Single Linkage, 'ward', 'mcquitty', 'median', or 'centroid'. +### colOrderMethod +### colDistanceMeasure +### colAgglomerationMethod +### rowOrderFile - output file of order of rows +### rowDendroFile - output file of row dendrogram +### colOrderFile - output file of order of cols +### colDendroFile - output file of col dendrogram +### rowCut - For rows the number of classifications to automatically generate based on dendrogram into a classification file. 0 for turned off. +### colCut - For columns the number of classifications to automatically generate based on dendrogram into a classification file. 0 for turned off. + +performDataOrdering<-function(dataFile, rowOrderMethod, rowDistanceMeasure, rowAgglomerationMethod, colOrderMethod, colDistanceMeasure, colAgglomerationMethod,rowOrderFile, colOrderFile, rowDendroFile, colDendroFile, rowCut, colCut) +{ + dataMatrix = read.table(dataFile, header=TRUE, sep = "\t", check.names = FALSE, row.names = 1, as.is=TRUE, na.strings=c("NA","N/A","-","?")) + rowOrder <- createOrdering(dataMatrix, rowOrderMethod, "row", rowDistanceMeasure, rowAgglomerationMethod) + if (rowOrderMethod == "Hierarchical") { + writeHCDataTSVs(rowOrder, rowDendroFile, rowOrderFile) + } + + colOrder <- createOrdering(dataMatrix, colOrderMethod, "col", colDistanceMeasure, colAgglomerationMethod) + if (colOrderMethod == "Hierarchical") { + writeHCDataTSVs(colOrder, colDendroFile, colOrderFile) + writeHCCut(colOrder, colCut, paste(colOrderFile,".cut", sep="")) + } +} + +#creates output files for hclust ordering +writeHCDataTSVs<-function(uDend, outputHCDataFileName, outputHCOrderFileName) +{ + data<-cbind(uDend$merge, uDend$height, deparse.level=0) + colnames(data)<-c("A", "B", "Height") + write.table(data, file = outputHCDataFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE) + + data=matrix(,length(uDend$labels),2); + for (i in 1:length(uDend$labels)) { + print(uDend$labels[i]) + data[i,1] = uDend$labels[i]; + data[i,2] = which(uDend$order==i); + } + colnames(data)<-c("Id", "Order") + write.table(data, file = outputHCOrderFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE) +} + +#creates a classification file based on user specified cut of dendrogram +writeHCCut<-function(uDend, cutNum, outputCutFileName) +{ + if (cutNum < 2) { + return() + } + print (paste("Writing cut file ", outputCutFileName)) + cut <- cutree(uDend, cutNum); + id <- names(cut); + data=matrix(,length(cut),2); + for (i in 1:length(cut)) { + data[i,1] = id[i]; + data[i,2] = sprintf("Cluster %d", cut[i]); + } + + write.table(data, file = outputCutFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE, col.names = FALSE); +} + + +createOrdering<-function(matrixData, orderMethod, direction, distanceMeasure, agglomerationMethod) +{ + ordering <- NULL + + if (orderMethod == "Hierarchical") + { + + # Compute dendrogram for "Distance Metric" + distVals <- NULL + if(direction=="row") { + if (distanceMeasure == "correlation") { + geneGeneCor <- cor(t(matrixData), use="pairwise") + distVals <- as.dist((1-geneGeneCor)/2) + } else { + distVals <- dist(matrixData, method=distanceMeasure) + } + } else { #column + if (distanceMeasure == "correlation") { + geneGeneCor <- cor(matrixData, use="pairwise") + distVals <- as.dist((1-geneGeneCor)/2) + } else { + distVals <- dist(t(matrixData), method=distanceMeasure) + } + } + +# if (agglomerationMethod == "ward") { +# ordering <- hclust(distVals * distVals, method="ward.D2") +# } else { + ordering <- hclust(distVals, method=agglomerationMethod) +# } + } + else if (orderMethod == "Random") + { + if(direction=="row") { + headerList <- rownames(matrixData) + ordering <- sample(headerList, length(headerList)) + } else { + headerList <- colnames(matrixData) + ordering <- sample(headerList, length(headerList)) + } + } + else if (orderMethod == "Original") + { + if(direction=="row") { + ordering <- rownames(matrixData) + } else { + ordering <- colnames(matrixData) + } + } else { + stop("createOrdering -- failed to find ordering method") + } + return(ordering) +} +### Initialize command line arguments and call performDataOrdering + +options(warn=-1) + +args = commandArgs(TRUE) + +performDataOrdering(dataFile=args[1], rowOrderMethod=args[2], rowDistanceMeasure=args[3], rowAgglomerationMethod=args[4], colOrderMethod=args[5], colDistanceMeasure=args[6], colAgglomerationMethod=args[7],rowOrderFile=args[8], colOrderFile=args[9], rowDendroFile=args[10], colDendroFile=args[11], rowCut=args[12], colCut=args[13]) + +#suppressWarnings(performDataOrdering(dataFile=args[1], rowOrderMethod=args[2], rowDistanceMeasure=args[3], rowAgglomerationMethod=args[4], colOrderMethod=args[5], colDistanceMeasure=args[6], colAgglomerationMethod=args[7],rowOrderFile=args[8], colOrderFile=args[9], rowDendroFile=args[10], colDendroFile=args[11])) |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 CHM_Advanced.R --- a/CHM_Advanced.R Thu Jun 20 11:31:24 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,131 +0,0 @@ -### This method generates a row and column ordering given an input matrix and ordering methods. -### -### matrixData - numeric matrix -### rowOrderMethod - Hierarchical, Original, Random -### rowDistanceMeasure - For clustering, distance measure. May be: euclidean, binary, manhattan, maximum, canberra, minkowski, or correlation. -### rowAgglomerationMethod - For clustering, agglomeration method. May be: 'average' for Average Linkage, 'complete' for Complete Linkage, -### 'single' for Single Linkage, 'ward', 'mcquitty', 'median', or 'centroid'. -### colOrderMethod -### colDistanceMeasure -### colAgglomerationMethod -### rowOrderFile - output file of order of rows -### rowDendroFile - output file of row dendrogram -### colOrderFile - output file of order of cols -### colDendroFile - output file of col dendrogram -### rowCut - For rows the number of classifications to automatically generate based on dendrogram into a classification file. 0 for turned off. -### colCut - For columns the number of classifications to automatically generate based on dendrogram into a classification file. 0 for turned off. - -performDataOrdering<-function(dataFile, rowOrderMethod, rowDistanceMeasure, rowAgglomerationMethod, colOrderMethod, colDistanceMeasure, colAgglomerationMethod,rowOrderFile, colOrderFile, rowDendroFile, colDendroFile, rowCut, colCut) -{ - dataMatrix = read.table(dataFile, header=TRUE, sep = "\t", check.names = FALSE, row.names = 1, as.is=TRUE, na.strings=c("NA","N/A","-","?")) - rowOrder <- createOrdering(dataMatrix, rowOrderMethod, "row", rowDistanceMeasure, rowAgglomerationMethod) - if (rowOrderMethod == "Hierarchical") { - writeHCDataTSVs(rowOrder, rowDendroFile, rowOrderFile) - if (rowCut != 0) { - writeHCCut(rowOrder, rowCut, paste(rowOrderFile,".cut", sep="")) - } - } - - colOrder <- createOrdering(dataMatrix, colOrderMethod, "col", colDistanceMeasure, colAgglomerationMethod) - if (colOrderMethod == "Hierarchical") { - writeHCDataTSVs(colOrder, colDendroFile, colOrderFile) - if (colCut != 0) { - writeHCCut(colOrder, colCut, paste(colOrderFile,".cut", sep="")) - } - } -} - -#creates output files for hclust ordering -writeHCDataTSVs<-function(uDend, outputHCDataFileName, outputHCOrderFileName) -{ - data<-cbind(uDend$merge, uDend$height, deparse.level=0) - colnames(data)<-c("A", "B", "Height") - write.table(data, file = outputHCDataFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE) - - data=matrix(,length(uDend$labels),2); - for (i in 1:length(uDend$labels)) { - data[i,1] = uDend$labels[i]; - data[i,2] = which(uDend$order==i); - } - colnames(data)<-c("Id", "Order") - write.table(data, file = outputHCOrderFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE) -} - -#creates a classification file based on user specified cut of dendrogram -writeHCCut<-function(uDend, cutNum, outputCutFileName) -{ - print (paste("Writing cut file ", outputCutFileName)) - cut <- cutree(uDend, cutNum); - id <- names(cut); - data=matrix(,length(cut),2); - for (i in 1:length(cut)) { - data[i,1] = id[i]; - data[i,2] = sprintf("Cluster %d", cut[i]); - } - - write.table(data, file = outputCutFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE, col.names = FALSE); -} - - -createOrdering<-function(matrixData, orderMethod, direction, distanceMeasure, agglomerationMethod) -{ - ordering <- NULL - - if (orderMethod == "Hierarchical") - { - - # Compute dendrogram for "Distance Metric" - distVals <- NULL - if(direction=="row") { - if (distanceMeasure == "correlation") { - geneGeneCor <- cor(t(matrixData), use="pairwise") - distVals <- as.dist((1-geneGeneCor)/2) - } else { - distVals <- dist(matrixData, method=distanceMeasure) - } - } else { #column - if (distanceMeasure == "correlation") { - geneGeneCor <- cor(matrixData, use="pairwise") - distVals <- as.dist((1-geneGeneCor)/2) - } else { - distVals <- dist(t(matrixData), method=distanceMeasure) - } - } - -# if (agglomerationMethod == "ward") { -# ordering <- hclust(distVals * distVals, method="ward.D2") -# } else { - ordering <- hclust(distVals, method=agglomerationMethod) -# } - } - else if (orderMethod == "Random") - { - if(direction=="row") { - headerList <- rownames(matrixData) - ordering <- sample(headerList, length(headerList)) - } else { - headerList <- colnames(matrixData) - ordering <- sample(headerList, length(headerList)) - } - } - else if (orderMethod == "Original") - { - if(direction=="row") { - ordering <- rownames(matrixData) - } else { - ordering <- colnames(matrixData) - } - } else { - stop("createOrdering -- failed to find ordering method") - } - return(ordering) -} -### Initialize command line arguments and call performDataOrdering - -options(warn=-1) - -args = commandArgs(TRUE) - -performDataOrdering(dataFile=args[1], rowOrderMethod=args[2], rowDistanceMeasure=args[3], rowAgglomerationMethod=args[4], colOrderMethod=args[5], colDistanceMeasure=args[6], colAgglomerationMethod=args[7],rowOrderFile=args[8], colOrderFile=args[9], rowDendroFile=args[10], colDendroFile=args[11], rowCut=args[12], colCut=args[13]) - -#suppressWarnings(performDataOrdering(dataFile=args[1], rowOrderMethod=args[2], rowDistanceMeasure=args[3], rowAgglomerationMethod=args[4], colOrderMethod=args[5], colDistanceMeasure=args[6], colAgglomerationMethod=args[7],rowOrderFile=args[8], colOrderFile=args[9], rowDendroFile=args[10], colDendroFile=args[11])) |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 heatmap.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/heatmap.sh Thu Jun 20 11:39:46 2019 -0400 |
| [ |
| @@ -0,0 +1,147 @@ +#echo "1: " $1" 2: " $2" 3: " $3" 4: "$4" 5: "$5 " 6: "$6 "7: "$7" 8: "$8 " 9: "$9" 10: "${10}" 11: "${11} "12: "${12} +#echo " 13: "${13}" 14: "${14}" 15: "${15}" 16: "${16} "17: "${17}" 18: "${18}" 19: "${19}" 20: "${20}" 21: "${21} " 22: "${22}" 23:" ${23} + +#Count total number of parameters and classification parameters +parmSize=0 +classSize=0 +matrixSize=0 +for i in "$@"; do + currParm=$(cut -d'|' -f1 <<< $i) + parmSize=$((parmSize+1)) + if [ $currParm = "classification" ] + then + classSize=$((classSize+1)) + fi +done + +#Get tool data and tool install directories +tooldir=$1 +tooldata=$2 +#create temp directory for row and col order and dendro files. +tdir=$tooldata/$(date +%y%m%d%M%S) +mkdir $tdir +#echo "tdir: "$tdir + +#Extract parameters for row and column order and dendro files +rowOrderFile=$tdir/ROfile.txt +rowDendroFile=$tdir/RDfile.txt +colOrderFile=$tdir/COfile.txt +colDendroFile=$tdir/CDfile.txt +rowOrderJson='"order_file": "'$rowOrderFile'",' +rowDendroJson='"dendro_file": "'$rowDendroFile'",' +colOrderJson='"order_file": "'$colOrderFile'",' +colDendroJson='"dendro_file": "'$colDendroFile'",' + +#BEGIN: Construct JSON for all non-repeating parameters +parmJson='{' +rowConfigJson='"row_configuration": {' +colConfigJson='"col_configuration": {' + +ctr=0 +for i in "$@"; do + if [ $ctr -gt 1 ] + then + currParm=$(cut -d'|' -f1 <<< $i) + if [ $currParm != "matrix_files" ] && [ $currParm != "row_configuration" ] && [ $currParm != "col_configuration" ] && [ $currParm != "classification" ] + then + #Parse pipe-delimited parameter parameter + parmJson=$parmJson' "'$(cut -d'|' -f1 <<< $i)'":"'$(cut -d'|' -f2 <<< $i)'",' + fi + if [ $currParm = "row_configuration" ] + then + rowOrder=$(cut -d'|' -f3 <<< $i) + rowDistance=$(cut -d'|' -f5 <<< $i) + rowAgglomeration=$(cut -d'|' -f7 <<< $i) + rowCuts=$(cut -d'|' -f9 <<< $i) + rowLabels=$(cut -d'|' -f11 <<< $i) + dataTypeJson='"'$(cut -d'|' -f10 <<< $i)'":["'$rowLabels'"]' + if [ $rowOrder = 'Hierarchical' ] + then + rowConfigJson=$rowConfigJson$rowOrderJson$rowDendroJson + fi + rowConfigJson=$rowConfigJson'"'$(cut -d'|' -f2 <<< $i)'":"'$(cut -d'|' -f3 <<< $i)'","'$(cut -d'|' -f4 <<< $i)'":"'$(cut -d'|' -f5 <<< $i)'","'$(cut -d'|' -f6 <<< $i)'":"'$(cut -d'|' -f7 <<< $i)'",'$dataTypeJson'},' + fi + if [ $currParm = "col_configuration" ] + then + colOrder=$(cut -d'|' -f3 <<< $i) + colDistance=$(cut -d'|' -f5 <<< $i) + colAgglomeration=$(cut -d'|' -f7 <<< $i) + colCuts=$(cut -d'|' -f9 <<< $i) + colLabels=$(cut -d'|' -f11 <<< $i) + dataTypeJson='"'$(cut -d'|' -f10 <<< $i)'":["'$colLabels'"]' + if [ $colOrder = 'Hierarchical' ] + then + colConfigJson=$colConfigJson$colOrderJson$colDendroJson + fi + colConfigJson=$colConfigJson'"'$(cut -d'|' -f2 <<< $i)'":"'$(cut -d'|' -f3 <<< $i)'","'$(cut -d'|' -f4 <<< $i)'":"'$(cut -d'|' -f5 <<< $i)'","'$(cut -d'|' -f6 <<< $i)'":"'$(cut -d'|' -f7 <<< $i)'",'$dataTypeJson'},' + fi + fi + ctr=$((ctr+1)) +done +#END: Construct JSON for all non-repeating parameters +#echo "rowCuts: "$rowCuts +#echo "colCuts: "$colCuts +#echo "ROW CONFIG JSON: "$rowConfigJson +#echo "COL CONFIG JSON: "$colConfigJson + +#BEGIN: Construct JSON for data layers +matrixJson='"matrix_files": [ ' +inputMatrix='' +for i in "$@"; do + currParm=$(cut -d'|' -f1 <<< $i) + if [ $currParm = "matrix_files" ] + then + #Parse pipe-delimited parameter parameter + matrixJson=$matrixJson' {"'$(cut -d'|' -f2 <<< $i)'":"'$(cut -d'|' -f3 <<< $i)'","'$(cut -d'|' -f4 <<< $i)'":"'$(cut -d'|' -f5 <<< $i)'","'$(cut -d'|' -f6 <<< $i)'":"'$(cut -d'|' -f7 <<< $i)'"}' + inputMatrix=$(cut -d'|' -f3 <<< $i) + fi +done +matrixJson=$matrixJson"]," +#END: Construct JSON for data layers + +#BEGIN: Construct JSON for classification files +classJson='"classification_files": [ ' +classIter=0 +for i in "$@"; do + currParm=$(cut -d'|' -f1 <<< $i) + if [ $currParm = "classification" ] + then + classIter=$((classIter+1)) + #Parse pipe-delimited 3-part classification bar parameter + classJson=$classJson' {"'$(cut -d'|' -f2 <<< $i)'":"'$(cut -d'|' -f3 <<< $i)'","'$(cut -d'|' -f4 <<< $i)'":"'$(cut -d'|' -f5 <<< $i)'"' + classCat=$(cut -d'|' -f7 <<< $i) + classColorType=$(cut -d'_' -f2 <<< $classCat) + classJson=$classJson',' + classJson=$classJson' "position":"'$(cut -d'_' -f1 <<< $classCat)'","color_map": {"type":"'$classColorType'"}}' + if [ $classIter -lt $classSize ] + then + classJson=$classJson',' + fi + fi +done +classJson=$classJson']' +#END: Construct JSON for classification files + +parmJson=$parmJson$matrixJson$rowConfigJson$colConfigJson$classJson +parmJson=$parmJson'}' +#echo "HEATMAP PARAMETERS JSON: "$parmJson + +#run R to cluster matrix +output="$(R --slave --vanilla --file=$tooldir/CHM.R --args $inputMatrix $rowOrder $rowDistance $rowAgglomeration $colOrder $colDistance $colAgglomeration $rowOrderFile $colOrderFile $rowDendroFile $colDendroFile $rowCuts $colCuts $rowLabels $colLabels 2>&1)" +rc=$?; +if [ $rc != 0 ] +then + echo $output; + if [ `echo "$output" | grep -c "Inf in foreign function call"` -gt 0 ] + then + echo ""; + echo "Note: This error can occur when there is no variation in a row or column. Try a different distance measure or remove rows/columns without variation."; + echo "This error may also be caused when a covariate file has inadvertently been selected as an Input Matrix. Check your Input Matrix entry."; + fi + exit $rc; +fi + +#call java program to generate NGCHM viewer files. +java -jar $tooldir/GalaxyMapGen.jar "$parmJson" +#clean up tempdir +rm -rf $tdir |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 heatmap_advanced.sh --- a/heatmap_advanced.sh Thu Jun 20 11:31:24 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,369 +0,0 @@\n-#echo "1: " $1 " 2: " $2 " 3: " $3 " 4: " $4 " 5: " $5 " 6: " $6 " 7: " $7 " 8: " $8 " 9: " $9 " 10: " ${10} \n-#echo "11: " ${11} " 12: " ${12} 13: " ${13} 14: " ${14} " 15: " ${15} " 16: " ${16} " 17: " ${17} " 18: " ${18} " 19: " ${19} " 20: " ${20} \n-#echo "21: "${21}" 22: "${22}" 23: "${23}" 24: "${24}" 25: "${25}" 26: "${26}" 27: "${27}" 28: "${28}" 29: "${29}" 30: "${30}\n-\n-#Count total number of parameters, dataLayer parameters, and classification parameters\n-parmSize=0\n-classSize=0\n-dataLayerSize=0\n-attribSize=0\n-for i in "$@"; do\n-\tcurrParm=$(cut -d\'|\' -f1 <<< $i)\n-\tparmSize=$((parmSize+1))\n-\tif [ $currParm = "classification" ]\n-\tthen\n-\t\tclassSize=$((classSize+1))\n- \tfi\n-\tif [ $currParm = "matrix_files" ]\n-\tthen\n-\t\tdataLayerSize=$((dataLayerSize+1))\n- \tfi\n-\tif [ $currParm = "attribute" ]\n-\tthen\n-\t\tattribSize=$((attribSize+1))\n- \tfi\n-done\n-\n-if [ $dataLayerSize -lt 1 ]\n-then\n-\tnoDataLayer="ERROR: No Heat Map Matrices provided. Please add at least one Heat Map Matrix to your request and try again."\n- \techo $noDataLayer\n- \texit $noDataLayer\n-fi\n-\n-#Get tool data and tool install directories\n-tooldir=$1\n-tooldata=$2\n-#create temp directory for row and col order and dendro files.\n-tdir=$tooldata/$(date +%y%m%d%M%S)\n-mkdir $tdir\n-#echo "tdir: "$tdir\n-\n-#Extract parameters for row and column order and dendro files\n-rowOrderFile=$tdir/ROfile.txt\n-rowDendroFile=$tdir/RDfile.txt\n-colOrderFile=$tdir/COfile.txt\n-colDendroFile=$tdir/CDfile.txt\n-rowOrderJson=\'"order_file": "\'$rowOrderFile\'",\'\n-rowDendroJson=\'"dendro_file": "\'$rowDendroFile\'",\'\n-colOrderJson=\'"order_file": "\'$colOrderFile\'",\'\n-colDendroJson=\'"dendro_file": "\'$colDendroFile\'",\'\n-\n-#BEGIN: Construct JSON for all non-repeating parameters\n-parmJson=\'{\'\n-rowConfigJson=\'"row_configuration": {\'\n-colConfigJson=\'"col_configuration": {\'\n-\n-ctr=0\n-for i in "$@"; do\n-\tif [ $ctr -gt 1 ]\n-\tthen\n-\t\tcurrParm=$(cut -d\'|\' -f1 <<< $i)\n-\t\tif [ $currParm != "matrix_files" ] && [ $currParm != "row_configuration" ] && [ $currParm != "col_configuration" ] && [ $currParm != "classification" ] && [ $currParm != "attribute" ]\n-\t\tthen\n-\t\t\t#Parse pipe-delimited parameter parameter\n-\t\t\tparmJson=$parmJson\' "\'$(cut -d\'|\' -f1 <<< $i)\'":"\'$(cut -d\'|\' -f2 <<< $i)\'",\'\n-\t \tfi\n-\t\tif [ $currParm = "row_configuration" ]\n-\t\tthen\n-\t\t\trowOrder=$(cut -d\'|\' -f3 <<< $i)\n-\t\t\trowDistance=$(cut -d\'|\' -f5 <<< $i)\n-\t\t\trowAgglomeration=$(cut -d\'|\' -f7 <<< $i)\n-\t\t\trowCuts=$(cut -d\'|\' -f9 <<< $i)\n-\t\t\trowLabels=$(cut -d\'|\' -f11 <<< $i)\n-\t\t\trowDataTypeJson=\'"\'$(cut -d\'|\' -f10 <<< $i)\'":["\'$rowLabels\'"],\'\n-\t\t\trowCutType=$(cut -d\'|\' -f16 <<< $i)\n-\t\t\trowTopItemsJson=\'\'\n-\t\t\trowTopItems=$(cut -d\'|\' -f13 <<< $i)\n-\t\t\tif [ $rowTopItems != "None" ] && [ $rowTopItems != "" ]\n-\t\t\tthen\n-\t\t\t\trowTopItemsJson=\'"\'$(cut -d\'|\' -f12 <<< $i)\'": [\'\n-\t\t\t\trowTopItems=${rowTopItems//,/\'","\'}\n-\t\t\t\trowTopItemsJson=$rowTopItemsJson\'"\'$rowTopItems\'"],\'\n-\t\t\tfi\n-\t\t\trowCutsJson=\'\'\n-\t\t\tif [ $rowCutType != "none" ]\n-\t\t\tthen\n-\t\t\t\tcutValues=$(cut -d\'|\' -f15 <<< $i) \n-\t\t\t\tif [ $cutValues != "None" ] && [ $cutValues != "0" ]\n-\t\t\t\tthen\n-\t\t\t\t\tif [ $rowCutType = "treecuts" ]\n-\t\t\t\t\tthen\n-\t\t\t\t\t\trowCutsJson=$rowCutsJson\'"tree_cuts": "\'$cutValues\'",\' \n-\t\t\t\t\t\trowCutsJson=$rowCutsJson\'"cut_width": "5",\' \n-\t\t\t\t\tfi\n-\t\t\t\t\tif [ $rowCutType = "positional" ]\n-\t\t\t\t\tthen\n-\t\t\t\t\t\trowCutErrorVal=0\n-\t\t\t\t\t\t[[ $cutValues != ?(-)+([0-9,]) ]] && rowCutErrorVal=$((rowCutErrorVal+1))\n-\t\t\t\t\t\tif [ $rowCutErrorVal -gt 0 ]\n-\t\t\t\t\t\tthen\n-\t \t\t\t\t\t\techo "GALAXY PARAMETER WARNING: Non-numeric values found for Row Fixed Gap Locations. Ignoring parameter value: "$cutValues\n-\t\t\t\t\t\telse\n-\t\t\t\t\t\t\trowCutsJson=$rowCutsJson\'"cut_locations": [\'$cutValues\'],\' \n-\t\t\t\t\t\t\trowCutsJson=$rowCutsJson\'"cut_width": "5",\' \n-\t\t\t\t\t\tfi\n-\t\t\t\t\tfi\n-\t\t\t\tfi\n-\t\t\tfi\n-\t\t\trowConfigJson=$rowConfigJson$rowDataTypeJson$rowCutsJson$rowTopItemsJson\n-\t\t\tif [ $rowOrder = \'Hierarchical\' ]\n-\t\t\tthen\n-\t\t\t\trowConfigJson=$rowConfigJson$rowOrderJson$rowDendroJson\n-\t\t\tfi\n-\t\t\trowConfigJson=$rowConfigJson\' "\'$('..b'N for attributes\n-attribJson=\'"chm_attributes": [ \'\n-attribIter=0\n-for i in "$@"; do\n-\tcurrParm=$(cut -d\'|\' -f1 <<< $i)\n-\tif [ $currParm = "attribute" ]\n-\tthen\n-\t\tattribIter=$((attribIter+1))\n-\t\tattribParam=$(cut -d\'|\' -f2 <<< $i)\n-\t\t#Parse pipe-delimited 2-part data layer parameter\n-\t\tattribJson=$attribJson\' {"\'$(cut -d\':\' -f1 <<< $attribParam)\'":"\'$(cut -d\':\' -f2 <<< $attribParam)\'"}\'\n-\t\tif [ $attribIter -lt $attribSize ]\t\t\n-\t\tthen\n-\t\t\tattribJson=$attribJson\',\'\n-\t\tfi\n- \tfi\n-done\n-attribJson=$attribJson\'],\'\n-#END: Construct JSON for attributes\n-#echo "ATTRIB JSON: "$attribJson\n-\n-#BEGIN: Construct JSON for classification files\n-classJson=\'"classification_files": [ \'\n-colCutClass=\'\'\n-rowCutClass=\'\'\n-if [ $rowCuts -gt 1 ]\n-then\n-\trowCutClass=\'{"name": "Class", "path": "\'$tdir\'/ROfile.txt.cut","position": "row", "color_map": {"type": "discrete"}, "bar_type": "color_plot"}\'\n-fi\n-\n-if [ $colCuts -gt 1 ]\n-then\n-\tif [ $rowCuts -gt 1 ] \n-\tthen\n-\t\trowCutClass=$rowCutClass\',\'\n-\tfi\n-\tcolCutClass=\'{"name": "Class", "path": "\'$tdir\'/COfile.txt.cut","position": "column", "color_map": {"type": "discrete"}, "bar_type": "color_plot"}\'\n-\tif [ $classSize -gt 0 ] \n-\tthen\n-\t\tcolCutClass=$colCutClass\',\'\n-\tfi\n-else\n-\tif [ $rowCuts -gt 1 ] && [ $classSize -gt 0 ] \n-\tthen\n-\t\trowCutClass=$rowCutClass\',\'\n-\tfi\n-fi\n-\n-classJson=$classJson$rowCutClass$colCutClass\n-classIter=0\n-for i in "$@"; do\n-\tcurrParm=$(cut -d\'|\' -f1 <<< $i)\n-\tif [ $currParm = "classification" ]\n-\tthen\n-\t\tclassIter=$((classIter+1))\n-\t\tclassName=$(cut -d\'|\' -f3 <<< $i)\n-\t\t#Parse pipe-delimited 3-part classification bar parameter\n-\t\tclassJson=$classJson\' {"\'$(cut -d\'|\' -f2 <<< $i)\'":"\'$(cut -d\'|\' -f3 <<< $i)\'","\'$(cut -d\'|\' -f4 <<< $i)\'":"\'$(cut -d\'|\' -f5 <<< $i)\'","\'$(cut -d\'|\' -f8 <<< $i)\'":"\'$(cut -d\'|\' -f9 <<< $i)\'","\'$(cut -d\'|\' -f12 <<< $i)\'":"\'$(cut -d\'|\' -f13 <<< $i)\'","\'$(cut -d\'|\' -f14 <<< $i)\'":"\'$(cut -d\'|\' -f15 <<< $i)\'"\'\n-\t\tclassCat=$(cut -d\'|\' -f7 <<< $i)\n-\t\tclassColorType=$(cut -d\'_\' -f2 <<< $classCat)\n-\t\tclassJson=$classJson\',\'\n-\t\tclassHeight=$(cut -d\'|\' -f11 <<< $i)\n-\t\theightErrorVal=0\n-\t\t[[ $classHeight != ?(-)+([0-9]) ]] && heightErrorVal=$((heightErrorVal+1))\n-\t\tif [ $heightErrorVal -gt 0 ]\n-\t\tthen\n-\t\t\techo \'GALAXY PARAMETER WARNING: Non-numeric values found for covariate bar (\'$className\') height. Height value ignored and default of 15 used: \'$classHeight\n-\t\telse\n-\t\t\tclassJson=$classJson\'"height": "\'$classHeight\'",\' \n-\t\tfi\n-\t\tclassJson=$classJson\' "position":"\'$(cut -d\'_\' -f1 <<< $classCat)\'","color_map": {"type":"\'$classColorType\'"}}\'\n-\t\tif [ $classIter -lt $classSize ]\t\t\n-\t\tthen\n-\t\t\tclassJson=$classJson\',\'\n-\t\tfi\n- \tfi\n-done\n-classJson=$classJson\']\'\n-#END: Construct JSON for classification files\n-#echo "CLASSIFICATION JSON: "$classJson\n-\n-#Complete construction of Parameter JSON file by adding all JSON sections created above\n-parmJson=$parmJson$rowConfigJson$colConfigJson$attribJson$matrixJson$classJson\n-parmJson=$parmJson\'}\'\n-#echo "COMPLETED PARAMETER JSON: "$parmJson\n-\n-#run R to cluster matrix\n-output="$(R --slave --vanilla --file=$tooldir/CHM_Advanced.R --args $inputMatrix $rowOrder $rowDistance $rowAgglomeration $colOrder $colDistance $colAgglomeration $rowOrderFile $colOrderFile $rowDendroFile $colDendroFile $rowCuts $colCuts $rowLabels $colLabels 2>&1)"\n-# Check for errors from R step, log them if found, and exit script\n-rc=$?;\n-if [ $rc != 0 ]\n-then\n- echo $output;\n- if [ `echo "$output" | grep -c "Inf in foreign function call"` -gt 0 ]\n- then\n- echo "";\n- echo "NOTE 1: This error can occur when a covariate file has inadvertently been selected as an Input Matrix. Check your Input Matrix entry.";\n- echo "NOTE 2: This error can occur when there is no variation in a data rows or columns in the input matrix. Try a different distance measure or remove rows/columns without variation.";\n- fi\n- exit $rc;\n-fi\n- \n-#Call java program to generate NGCHM viewer files.\n-java -jar $tooldir/GalaxyMapGen.jar "$parmJson"\n-#clean up tempdir\n-rm -rf $tdir\n' |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 mda_advanced_heatmap_gen.xml --- a/mda_advanced_heatmap_gen.xml Thu Jun 20 11:31:24 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| b'@@ -1,503 +0,0 @@\n-<?xml version="1.0" encoding="UTF-8" ?>\r\n-<tool id="mda_advanced_heatmap_gen" name="Advanced NG-CHM Generator" version="2.3">\r\n- <requirements>\r\n- <requirement type="package" version="3.4.1">r-base</requirement> \r\n-\t\t<requirement type="package" version="8.0.144">openjdk</requirement>\r\n- </requirements>\r\n- <description> Create Clustered Heat Maps with Advanced Options</description>\r\n-<command interpreter="bash" detect_errors="aggressive">$__tool_directory__/heatmap_advanced.sh "$__tool_directory__" "$__tool_data_path__/" "chm_name|Heat_Map_$hmname" "chm_description|$hmdesc" "summary_width|$summaryDisplayWidth"\r\n-\t"row_configuration|order_method|${d_rows.rowOrderMethod}|distance_metric|${d_rows.rowDistanceMeasure}|agglomeration_method|${d_rows.rowAgglomerationMethod}|tree_covar_cuts|${d_rows.rowDendroCut}|data_type|$rowDataType|top_items|$rowTopItems|tree_cuts|${d_rows.rcutrows.rowDendroTreeCut}|${d_rows.rcutrows.raddcuts}|dendro_show|${d_rows.rowDendroShow}|dendro_height|${d_rows.rowDendroHeight}" \r\n-\t"col_configuration|order_method|${d_cols.columnOrderMethod}|distance_metric|${d_cols.columnDistanceMeasure}|agglomeration_method|${d_cols.columnAgglomerationMethod}|tree_covar_cuts|${d_cols.colDendroCut}|data_type|$colDataType|top_items|$colTopItems|tree_cuts|${d_cols.ccutrows.colDendroTreeCut}|${d_cols.ccutrows.caddcuts}|dendro_show|${d_cols.columnDendroShow}|dendro_height|${d_cols.columnDendroHeight}" \r\n- #for $attr in $hm_attribute\r\n- \'attribute|${attr.attrbute_key}\':\'${attr.attrbute_value}\'\r\n- #end for\r\n- #for $mx in $matrices\r\n-\t \'matrix_files|path|$mx.dataLayer|name|${mx.dataLayerName}|summary_method|${mx.summarymethod}|selection_color|${mx.dataLayerSelectionColor}|cuts_color|${mx.dataLayerCutsColor}|grid_color|${mx.dataLayerGridColor}|grid_show|${mx.dataLayerGridShow}|${mx.colorsBreaks.setColorsBreaks}|${mx.colorsBreaks.matrixColor1}|${mx.colorsBreaks.matrixColor2}|${mx.colorsBreaks.matrixColor3}|${mx.colorsBreaks.matrixBreak1}|${mx.colorsBreaks.matrixBreak2}|${mx.colorsBreaks.matrixBreak3}|${mx.colorsBreaks.missingColor}\'\r\n- #end for\r\n- #for $op in $operations\r\n- \'classification|name|${op.class_name}|path|${op.repeatinput.file_name}|category|${op.cattype.cat}|bar_type|${op.cattype.scatbar.bartype}|height|${op.classHeight}|fg_color|${op.cattype.scatbar.fg_color}|bg_color|${op.cattype.scatbar.bg_color}\'\r\n- #end for\r\n- \t\'output_location|$output\' \r\n- </command>\r\n-\t<stdio>\r\n- <exit_code range="1:" level="fatal" />\r\n-\t</stdio>\r\n- <inputs>\r\n- <repeat name="matrices" title="Heat Map Matrices">\r\n- \t<param name="dataLayer" type="data" format="Tabular" label="Input Data Matrix" help="Tab delimited text file with row labels, column labels, and data."/>\r\n- \t<param name="dataLayerName" size="40" type="text" value="Data_Layer_name" label="Data Layer Name" help="Name for data layer (no spaces).">\r\n- <sanitizer>\r\n- <valid>\r\n- <add preset="string.printable"/>\r\n- \t<remove value="""/>\r\n- \t<remove value="'"/>\r\n- <remove value=" "/> \r\n- </valid>\r\n- </sanitizer>\r\n- </param> \r\n-\t <param name="summarymethod" type="select" label="Data Summarization Method" help="For large matrices, the selected method is used to aggregate data values in the summary view.">\r\n-\t\t\t<option value="average">Average</option>\r\n-\t\t\t<option value="sample">Sample</option>\r\n-\t\t\t<option value="mode">Mode</option>\r\n-\t </param>\r\n- \t\t<conditional name="colorsBreaks">\r\n-\t\t\t<param name="setColorsBreaks" type="select" label="Colors and Breakpoints" help="Select whether to set your own colors and breakpoints or use default values.">\r\n-\t\t\t\t<option value="none">Use System Generated Colors and Breakpoints</option>\r\n-\t\t\t\t<option value="defined">Define Your Own Colors and Breakpoints</option>\t \r\n-\t\t\t</param>\r\n-\t \t<when value="none">\r\n-\t \t\t \t<param name="matrixColor1" type'..b'-\t\t\t\t\t <option value="color_plot" >Standard</option>\r\n-\t\t\t\t\t <option value="bar_plot" >Bar Plot</option>\r\n-\t\t\t\t\t <option value="scatter_plot" >Scatter Plot</option>\r\n-\t\t\t\t\t</param>\r\n-\t \t\t<when value="color_plot">\r\n- \t\t\t\t\t\t<param name="bg_color" type="text" size="0" hidden="true" value="#ffffff"/>\r\n- \t\t\t\t\t\t<param name="fg_color" type="text" size="0" hidden="true" value="#000000"/>\r\n-\t \t\t</when>\r\n-\t \t\t<when value="bar_plot">\r\n- \t\t\t\t\t\t<param name="bg_color" type="color" label="Color for Bar Plot Background" value="#ffffff"/>\r\n- \t\t\t\t\t\t<param name="fg_color" type="color" label="Color for Bar Plot Foreground" value="#000000"/>\r\n-\t \t\t</when>\r\n-\t \t\t<when value="scatter_plot">\r\n- \t\t\t\t\t\t<param name="bg_color" type="color" label="Color for Scatter Plot Background" value="#ffffff"/>\r\n- \t\t\t\t\t\t<param name="fg_color" type="color" label="Color for Scatter Plot Foreground" value="#000000"/>\r\n-\t \t\t</when>\r\n-\t \t</conditional>\r\n-\t </when>\r\n-\t <when value="column_discrete">\r\n- \t\t<conditional name="scatbar">\r\n-\t\t\t\t\t<param name="bartype" type="select" hidden="true">\r\n-\t\t\t\t\t <option value="color_plot" >Standard</option>\r\n-\t\t\t\t\t</param>\r\n- \t \t\t<when value="color_plot">\r\n-\t\t\t\t\t\t<param name="bg_color" type="text" size="0" hidden="true" value="#ffffff"/>\r\n- \t\t\t\t\t\t<param name="fg_color" type="text" size="0" hidden="true" value="#000000"/>\r\n- \t\t\t\t\t</when>\r\n-\t \t</conditional>\r\n-\t </when>\r\n-\t <when value="row_discrete">\r\n- \t\t<conditional name="scatbar">\r\n-\t\t\t\t\t<param name="bartype" type="select" hidden="true">\r\n-\t\t\t\t\t <option value="color_plot" >Standard</option>\r\n-\t\t\t\t\t</param>\r\n- \t \t\t<when value="color_plot">\r\n-\t\t\t\t\t\t<param name="bg_color" type="text" size="0" hidden="true" value="#ffffff"/>\r\n- \t\t\t\t\t\t<param name="fg_color" type="text" size="0" hidden="true" value="#000000"/>\r\n- \t\t\t\t\t</when>\r\n-\t \t</conditional>\r\n-\t </when>\r\n-\t \t</conditional>\r\n- </repeat> \r\n- <repeat name="hm_attribute" title="Heat Map Attributes">\r\n- <param name="attrbute_key" size="50" type="text" value="" label="Heat Map Attribute Key" help="For map level attributes. Enter the key (no spaces).">\r\n- <sanitizer invalid_char="_">\r\n- <valid initial="">\r\n- <add preset="string.letters"/>\r\n- <add preset="string.digits"/>\r\n- </valid>\r\n- <mapping initial="">\r\n- </mapping>\r\n- </sanitizer>\r\n- </param>\r\n- <param name="attrbute_value" size="50" type="text" label="Heat Map Attributes Value" help="For map level attributes. Enter the value (no spaces).">\r\n- <sanitizer invalid_char="_">\r\n- <valid initial="">\r\n- <add preset="string.letters"/>\r\n- <add preset="string.digits"/>\r\n- </valid>\r\n- <mapping initial="">\r\n- </mapping>\r\n- </sanitizer>\r\n- </param>\r\n- </repeat> \r\n- </inputs>\r\n- <outputs>\r\n- <data name="output" label=\'Heat_Map_$hmname\' format="ngchm"/>\r\n- </outputs>\r\n- <tests>\r\n- <test>\r\n- <param name="inputmatrix" value="400x400.txt" />\r\n- <param name="hmname" value="testRun" />\r\n- <param name="$hmdesc" value="validateTool" />\r\n- <param name="summarymethod" value="Average" />\r\n- <param name="rowOrderMethod" value="Hierarchical" />\r\n- <param name="rowDistanceMeasure" value="Manhattan" />\r\n- <param name="rowAgglomerationMethod" value="Ward" />\r\n- <param name="columnOrderMethod" value="Hierarchical" />\r\n- <param name="columnDistanceMeasure" value="Manhattan" />\r\n- <param name="columnAgglomerationMethod" value="Ward" />\r\n- <output name="output" file="Galaxy400x400-noCovariates.ngchm" lines_diff="10" /> \r\n-\r\n- </test>\r\n-<!-- galaxy/test-data/ dir where the input and output file that should match tool output will be copied -->\r\n- </tests>\r\n- </tool>\r\n' |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 mda_heatmap_gen.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mda_heatmap_gen.py Thu Jun 20 11:39:46 2019 -0400 |
| [ |
| b'@@ -0,0 +1,250 @@\n+#!/usr/bin/env python\n+# -*- coding: utf-8 -*-\n+# python shell program to validate ng-chm heat map input matrix file and covariate file formats before calling java shell -- bob brown\n+\n+import subprocess #you must import subprocess so that python can talk to the command line\n+import sys\n+import os\n+import re\n+#import config\n+import traceback\n+#import commons\n+\n+#ConfigVals = config.Config("../rppaConf.txt")\n+\n+def main():\n+ \n+ try:\n+ print \'\\nStarting Heat Map file validation ......\' \n+ #print "\\nheat map sys args len and values = ",len(sys.argv), str(sys.argv) #, \'++\',argvals\n+\n+ \n+ error= False\n+ endCovarParam= len(sys.argv)-2 # IF any ending of loc for covar triplet info \n+ startCovarParam= 17 # beginning loc for covar triplet info\n+ inMatrix= sys.argv[3]\n+\n+ for i in range( endCovarParam, 15, -3):\n+ if len(sys.argv[i]) > 6:\n+ if sys.argv[i][0:4].find(\'row_\') == 0 or sys.argv[i][0:7].find(\'column_\') == 0: # 0 is match start position\n+ startCovarParam= i-2 \n+ #print "\\nHeat map arg 3 and start covariate index on = " ,str(sys.argv[3]),\' - \', startCovarParam, \' covar name= \',str(sys.argv[startCovarParam:])\n+ #else: print \'\\nCovariate param row or column not found at i\', i, str(sys.argv[i])\n+\n+ #test inMatrix= "/Users/bobbrown/Desktop/NGCHM-Galaxy-Test-Files/400x400firstRowShift.txt"\n+ #test covarFN= \'/Users/bobbrown/Desktop/400x400-column-covariate-continuous-TestingErrors.txt\'\n+ #test row_col_cat_contin= \'column_continuous\'\n+ #test row_col_cat_contin= \'column_categorical\' \n+ #test covarLabel = \'bob test\'\n+ #test numCovariates= 1\n+ \n+ errorInMatrix,inMatrixRowLabels,inMatrixColLabels= ValidateHMInputMatrix(inMatrix) # verify input matrix\n+ \n+ print "\\nFirst & last Row labels ", inMatrixRowLabels[0],inMatrixRowLabels[-1]," and Columns ", inMatrixColLabels[0],inMatrixColLabels[-1], " number Rows= ",len(inMatrixRowLabels)," number Columns= ",len(inMatrixColLabels)\n+ \n+ # continue reviewing covariates to catch any errors in any of the input info\n+ if len(inMatrixRowLabels) < 5 or len(inMatrixColLabels) < 5: \n+ errorInMatrix = True\n+ print \'\\n----ERROR Input matrix has too few columns and rows need to ignore validating covariate files for now\'\n+ \n+ elif not errorInMatrix: \n+ print "\\n++++ SUCCESS the Input Matrix looks good\\n\\n"\n+ \n+ i= startCovarParam\n+ while i < (len(sys.argv)-2): # todo verify this works with advances tool is one other 0->n param after this\n+ covarLabel= sys.argv[i]\n+ covarLabel= covarLabel.replace(\' \',\'\')\n+ covarFN= sys.argv[i+1]\n+ covarFN= covarFN.replace(\' \',\'\')\n+ row_col_cat_contin= sys.argv[i+2]\n+ row_col_cat_contin= row_col_cat_contin.replace(\' \',\'\')\n+ i +=3\n+ \n+ print "\\nSTART Validating covariate file with label= ", covarLabel, " and type= ",row_col_cat_contin\n+ \n+ error= ValidateHMCorvarFile(covarLabel, covarFN, row_col_cat_contin,inMatrixRowLabels,inMatrixColLabels) # check covariate files\n+ \n+ if error or errorInMatrix:\n+ print"\\n---ERROR issues found in input or covariate files\\n "\n+ sys.stderr.write( "\\nERROR issues found in input or covariate files see errors in Standard Output\\n\\n ") \n+ sys.exit(3)\n+ \n+ \n+ print"\\n FINISHED -- Validation of the Input Matrix and Covariate files (if any)\\n\\n"\n+ \n+ #print" next running the clustered heat map generator \\n",str(sys.argv[11])+"/heatmap.'..b'ue\n+ sys.err= 7\n+ else:\n+ inMatrixRowLabels.append(eachRow[0])\n+ tmp= re.search(\'[abcdefghijklmnopqrstuvwxyz]\',eachRow[0].lower())\n+ try:\n+ if tmp.group(0) == \'\': # if doesn\'t exist then error\n+ tmp= tmp\n+ except Exception as e:\n+ print"-+-+- WARNING Row Label at row "+str(countRow)+" value appears to be non-alphanumeric --"+str(eachRow[j])\n+ sys.stderr.write("\\n--+-+- WARNING Row Label at row "+str(countRow)+" value appears to be non-alphanumeric "+str(eachRow[j]))\n+ \n+ \n+ if len(inMatrixColLabels) > 0: \n+ if (inMatrixColLabels[-1] ==\'\') or (inMatrixColLabels[-1] ==\'\\n\'): inMatrixColLabels.pop()\n+ \n+ inMatrixFH.close()\n+\n+ #print error, lenAllRows, len(eachRow), eachRow[0]\n+ except:\n+ #inMatrixFH.close()\n+ sys.stderr.write(str(traceback.format_exc()))\n+ error= True\n+ \n+ return error,inMatrixRowLabels,inMatrixColLabels\n+\n+ #+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-\n+\n+def ValidateHMCorvarFile(covarLabel, covariateFilePath, row_col_cat_contin, inMatrixRowLabels,inMatrixColLabels): # This sub routine ensures that the slide design input by the user matches a slide design on record\n+\n+# verify \n+# 1 That covar file labels match the col or row labels 1 to 1\n+# 2 That if a continuous covar file that the 2nd field is not all text hard to tell if \'-\' or \'e exponent\'\n+# 3 That the length of the covar file matches the row or col length of the input matrix \n+\n+ error= True\n+ try:\n+ \n+ covFH= open( covariateFilePath, \'rU\')\n+ countRow= 0\n+\n+ error= False\n+ \n+ for rawRow in covFH:\n+ countRow +=1\n+ rawRow= rawRow.replace(\'\\n\',\'\')\n+ eachRow= rawRow.split(\'\\t\')\n+ if countRow== 0: print "\\nCovariance file info - label ",str(covarLabel)," row/col categorical or continous",row_col_cat_contin," first row ",str(eachrow)\n+ \n+ if len(eachRow) < 2 and countRow > 1:\n+ print("----ERROR Input Row "+str(countRow)+" does not have a label and/or value ")\n+ sys.stderr.write("----ERROR Input Row "+str(countRow)+" does not have a label/or and value")\n+ error= True\n+ sys.err= 8\n+ #return error\n+ elif len(eachRow) > 1:\n+ tmp= re.search(\'[abcdefghijklmnopqrstuvwxyz]\',eachRow[0].lower())\n+ try:\n+ if tmp.group(0) == \'\': # if doesn\'t exist then error\n+ tmp= tmp\n+ except Exception as e:\n+ print"\\n-+-+- WARNING Covariate Label at row "+str(countRow)+" value appears to be non-alphanumeric --", eachRow[0],"--"\n+ sys.stderr.write("\\n--+-+- WARNING Row Headers at row "+str(countRow)+" value appears to be non-alphanumeric --"+str(eachRow[0])+"--")\n+ \n+ if not error:\n+ if row_col_cat_contin[-4:] == \'uous\': # verify continuous is number-ish\n+ tmp= re.search(\'[+-.0123456789eE]\',eachRow[1])\n+ try:\n+ if tmp.group(0) == \'\':\n+ tmp= tmp\n+ except Exception as e:\n+ print("\\n-+-+-WARNING Input Row "+str(countRow)+" covariance continuous value appears to be non-numeric --"+ str(eachRow[1])+"--")\n+ sys.stderr.write("\\n-+-+-WARNING Input Row "+str(countRow)+" covariance continuous value appears to be non-numeric --"+ str(eachRow[1])+"--")\n+ #error= True\n+ except:\n+ sys.stderr.write(str(traceback.format_exc()))\n+\n+ covFH.close()\n+\n+ return error\n+\n+\n+if __name__ == "__main__":\n+ main()\n+\n+\n' |
| b |
| diff -r 436f03b71cf6 -r 8f8ab332a050 mda_heatmap_gen.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mda_heatmap_gen.xml Thu Jun 20 11:39:46 2019 -0400 |
| b |
| b'@@ -0,0 +1,159 @@\n+<?xml version="1.0" encoding="UTF-8" ?>\n+<tool id="mda_heatmap_gen" name="NG-CHM Generator" version="2.3">\n+ <requirements>\n+ <requirement type="package" version="3.4.1">r-base</requirement> \n+\t\t<requirement type="package" version="8.0.144">openjdk</requirement>\n+ </requirements>\n+ <description>Create Clustered Heat Maps</description>\n+ <command interpreter="bash" detect_errors="aggressive">$__tool_directory__/heatmap.sh "$__tool_directory__" "$__tool_data_path__/" "chm_name|Heat_Map_$hmname" "chm_description|$hmdesc" \n+\t"matrix_files|path|$inputmatrix|name|datalayer|summary_method|$summarymethod"\n+\t"row_configuration|order_method|${d_rows.rowOrderMethod}|distance_metric|${d_rows.rowDistanceMeasure}|agglomeration_method|${d_rows.rowAgglomerationMethod}|tree_covar_cuts|0|data_type|labels" \n+\t"col_configuration|order_method|${d_cols.columnOrderMethod}|distance_metric|${d_cols.columnDistanceMeasure}|agglomeration_method|${d_cols.columnAgglomerationMethod}|tree_covar_cuts|0|data_type|labels" \n+ #for $op in $operations\n+ \'classification|name|${op.class_name}|path|${op.repeatinput.file_name}|category|${op.cat}\'\n+ #end for\n+ \t\'output_location|$output\' \n+ </command>\n+\t<stdio>\n+ <exit_code range="1:" level="fatal" />\n+\t</stdio>\n+ <inputs>\n+ <param name="inputmatrix" type="data" format="Tabular" label="Input Data Matrix" help="Tab delimited text file with row labels, column labels, and data." />\n+ <param name="hmname" size="40" type="text" value="Heat_Map_name" label="Heat Map Name" help="Short Name for heat map (no spaces)."/>\n+ <sanitizer>\n+ <valid>\n+ <add preset="string.printable"/>\n+ \t<remove value="""/>\n+ \t<remove value="'"/>\n+ <remove value=" "/> \n+ </valid>\n+ </sanitizer>\n+ <param name="hmdesc" size="100" optional="true" type="text" value="Heat_Map_description" label="Heat Map Description" help="Longer description of the heat map contents."/>\n+ <sanitizer>\n+ <valid>\n+ <add preset="string.printable"/>\n+ <add value="string.letters"/>\n+ <add value="string.digits"/>\n+ <add value="-"/>\n+ <add value="_"/>\n+ \t<remove value="""/>\n+ \t<remove value="'"/>\n+ <remove value=" "/> \n+ </valid>\n+ </sanitizer>\n+ <param name="summarymethod" \ttype="select" label="Data Summarization Method" help="For large matrices, the selected method is used to aggregate data values in the summary view.">\n+\t\t<option value="average">Average</option>\n+\t\t<option value="sample">Sample</option>\n+\t\t<option value="mode">Mode</option>\n+ </param>\n+ <conditional name="d_rows">\n+\t<param name="rowOrderMethod" type="select" label="Row ordering method" help="Determine if rows should be clustered, randomized, or remain as is.">\n+\t\t<option value="Hierarchical">Hierarchical Clustering</option>\n+\t\t<option value="Original">Original Order</option>\t \n+\t\t<option value="Random">Random</option>\t \n+\t</param>\n+ <when value="Hierarchical">\n+\t\t\t<param name="rowDistanceMeasure" type="select" label="Row Distance Metric" help="For clustering, select the method of determining distance between rows">\n+\t\t\t\t<option value="euclidean">Euclidean</option>\n+\t\t\t\t<!-- <option value="binary">Binary</option> ** breaks dendrogram -->\n+\t\t\t\t<option value="manhattan">Manhattan</option>\n+\t\t\t\t<option value="maximum">Maximum</option>\n+\t\t\t\t<!-- <option value="canberra">Canberra</option> ** breaks dendrogram -->\n+\t\t\t\t<option value="minkowski">Minkowski</option>\t \n+\t\t\t\t<!-- <option value="correlation">Correlation</option>\t** breaks dendrogram --> \n+\t\t\t</param>\n+\t\t\t<param name="rowAgglomerationMethod" type="select" label="Row Clustering Method" help="For clustering, select algorithm for building clusters.">\n+\t\t\t\t<option value="average">Average Lin'..b'="Hierarchical">Hierarchical Clustering</option>\n+\t\t<option value="Original">Original Order</option>\t \n+\t\t<option value="Random">Random</option>\t \n+\t</param>\n+ <when value="Hierarchical">\n+\t\t\t<param name="columnDistanceMeasure" type="select" label="Column Distance Metric" help="For clustering, select the method of determining distance between columns">\n+\t\t\t\t<option value="euclidean">Euclidean</option>\n+\t\t\t\t<!-- <option value="binary">Binary</option> ** breaks dendrogram -->\n+\t\t\t\t<option value="manhattan">Manhattan</option>\n+\t\t\t\t<option value="maximum">Maximum</option>\n+\t\t\t\t<!-- <option value="canberra">Canberra</option> ** breaks dendrogram -->\t \n+\t\t\t\t<option value="minkowski">Minkowski</option>\t \n+\t\t\t\t<!-- <option value="correlation">Correlation</option>\t** breaks dendrogram -->\n+\t\t\t</param>\n+\t\t\t<param name="columnAgglomerationMethod" type="select" label="Column Clustering Method" help="For clustering, select algorithm for building clusters.">\n+\t\t\t\t<option value="average">Average Linkage</option>\n+\t\t\t\t<option value="complete">Complete Linkage</option>\n+\t\t\t\t<option value="single">Single Linkage</option>\n+\t\t\t\t<option value="ward" selected="true">Ward</option>\n+\t\t\t\t<option value="mcquitty">Mcquitty</option>\t \n+\t\t\t\t<!-- <option value="median">Median</option>\t ** breaks dendrogram \n+\t\t\t\t<option value="centroid">Centroid</option>\t ** breaks dendrogram -->\n+\t\t\t</param>\n+ </when>\n+ <when value="Original">\n+\t\t <param name="columnDistanceMeasure" type="text" size="0" hidden="true" value="n/a"/>\n+\t\t <param name="columnAgglomerationMethod" type="text" size="0" hidden="true" value="n/a"/>\n+ </when>\n+ <when value="Random">\n+\t\t <param name="columnDistanceMeasure" type="text" size="0" hidden="true" value="n/a"/>\n+\t\t <param name="columnAgglomerationMethod" type="text" size="0" hidden="true" value="n/a"/>\n+ </when>\n+ </conditional>\n+ <repeat name="operations" title="Covariate Bars">\n+ <param name="class_name" size="25" type="text" value="" label="Covariate Name" help="Covariate heat map display label.">\n+ <sanitizer>\n+ <valid>\n+ <add preset="string.printable"/>\n+ \t<remove value="""/>\n+ \t<remove value="'"/>\n+ <remove value=" "/> \n+ </valid>\n+ </sanitizer>\n+ </param>\n+ <param name="repeatinput" type="data" format="Tabular" label="Covariate File" help="Tab delimited text file with row or column label and covariate value on each line."/>\n+\t<param name="cat" type="select" label="Axis Covariate Type" help="Identify the covariate as belonging to rows or columns and containing categorical or continuous values.">\n+\t <option value="row_discrete" >Row Categorical</option>\n+\t <option value="row_continuous" >Row Continuous</option>\n+\t <option value="column_discrete" >Column Categorical</option>\n+\t <option value="column_continuous" >Column Continuous</option>\n+\t</param>\n+ </repeat> \n+ </inputs>\n+ <outputs>\n+ <data name="output" label=\'Heat_Map_$hmname\' format="ngchm"/>\n+ </outputs>\n+ <tests>\n+ <test>\n+ <param name="inputmatrix" value="400x400.txt" />\n+ <param name="hmname" value="testRun" />\n+ <param name="$hmdesc" value="validateTool" />\n+ <param name="summarymethod" value="Average" />\n+ <param name="rowOrderMethod" value="Hierarchical" />\n+ <param name="rowDistanceMeasure" value="Manhattan" />\n+ <param name="rowAgglomerationMethod" value="Ward" />\n+ <param name="columnOrderMethod" value="Hierarchical" />\n+ <param name="columnDistanceMeasure" value="Manhattan" />\n+ <param name="columnAgglomerationMethod" value="Ward" />\n+ <output name="output" file="Galaxy400x400-noCovariates.ngchm" lines_diff="10" /> \n+\n+ </test>\n+<!-- galaxy/test-data/ dir where the input and output file that should match tool output will be copied -->\n+ </tests>\n+ </tool>\n' |