Mercurial > repos > md-anderson-bioinformatics > heat_map_creation
changeset 32:16593e40c2cd draft
Version 2.0.5
| author | insilico-bob |
|---|---|
| date | Thu, 20 Jul 2017 15:31:06 -0400 |
| parents | e01b833f5d43 |
| children | 0097750ad7ad |
| files | CHM.R GalaxyMapGen.jar heatmap.sh mda_heatmap_gen.py mda_heatmap_gen.xml mda_heatmap_viz.zip ngchm-matrix-functional-test-data/._.DS_Store ngchm-matrix-functional-test-data/._400x400.txt ngchm-matrix-functional-test-data/400x400.txt |
| diffstat | 8 files changed, 325 insertions(+), 148 deletions(-) [+] |
line wrap: on
line diff
--- a/CHM.R Fri Feb 03 13:20:50 2017 -0500 +++ b/CHM.R Thu Jul 20 15:31:06 2017 -0400 @@ -21,17 +21,12 @@ rowOrder <- createOrdering(dataMatrix, rowOrderMethod, "row", rowDistanceMeasure, rowAgglomerationMethod) if (rowOrderMethod == "Hierarchical") { writeHCDataTSVs(rowOrder, rowDendroFile, rowOrderFile) - writeHCCut(rowOrder, rowCut, paste(rowOrderFile,".cut", sep="")) - } else { - writeOrderTSV(rowOrder, rownames(dataMatrix), rowOrderFile) } colOrder <- createOrdering(dataMatrix, colOrderMethod, "col", colDistanceMeasure, colAgglomerationMethod) if (colOrderMethod == "Hierarchical") { writeHCDataTSVs(colOrder, colDendroFile, colOrderFile) writeHCCut(colOrder, colCut, paste(colOrderFile,".cut", sep="")) - } else { - writeOrderTSV(colOrder, colnames(dataMatrix), colOrderFile) } } @@ -51,18 +46,6 @@ write.table(data, file = outputHCOrderFileName, append = FALSE, quote = FALSE, sep = "\t", row.names=FALSE) } -#creates order file for non-clustering methods -writeOrderTSV<-function(newOrder, originalOrder, outputHCOrderFileName) -{ - data=matrix(,length(originalOrder),2); - for (i in 1:length(originalOrder)) { - data[i,1] = originalOrder[i]; - data[i,2] = which(newOrder==originalOrder[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) {
--- a/heatmap.sh Fri Feb 03 13:20:50 2017 -0500 +++ b/heatmap.sh Thu Jul 20 15:31:06 2017 -0400 @@ -1,8 +1,21 @@ echo $1 $2 $3 $4 $5 $6 $7 $8 $9 ${10} ${11} ${12} ${13} ${14} ${15} ${16} ${17} + +#run python to validate the input matrix and covariate files (if any) +#output="$(python ${11}/mda_heatmap_gen.py $@)" +output=$(python ${11}/mda_heatmap_gen.py "$@") +rc=$?; +echo $output; +if [ $rc != 0 ] +then + exit $rc; +fi + + #create temp directory for row and col order and dendro files. tdir=${11}/$(date +%y%m%d%M%S) echo $tdir mkdir $tdir + #run R to cluster matrix output="$(R --slave --vanilla --file=${11}/CHM.R --args $3 $4 $5 $6 $7 $8 $9 $tdir/ROfile.txt $tdir/COfile.txt $tdir/RDfile.txt $tdir/CDfile.txt ${12} ${13} ${14} ${15} 2>&1)" rc=$?;
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mda_heatmap_gen.py Thu Jul 20 15:31:06 2017 -0400 @@ -0,0 +1,250 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# python shell program to validate ng-chm heat map input matrix file and covariate file formats before calling java shell -- bob brown + +import subprocess #you must import subprocess so that python can talk to the command line +import sys +import os +import re +#import config +import traceback +#import commons + +#ConfigVals = config.Config("../rppaConf.txt") + +def main(): + + try: + print '\nStarting Heat Map file validation ......' + #print "\nheat map sys args len and values = ",len(sys.argv), str(sys.argv) #, '++',argvals + + + error= False + endCovarParam= len(sys.argv)-2 # IF any ending of loc for covar triplet info + startCovarParam= 17 # beginning loc for covar triplet info + inMatrix= sys.argv[3] + + for i in range( endCovarParam, 15, -3): + if len(sys.argv[i]) > 6: + if sys.argv[i][0:4].find('row_') == 0 or sys.argv[i][0:7].find('column_') == 0: # 0 is match start position + startCovarParam= i-2 + #print "\nHeat map arg 3 and start covariate index on = " ,str(sys.argv[3]),' - ', startCovarParam, ' covar name= ',str(sys.argv[startCovarParam:]) + #else: print '\nCovariate param row or column not found at i', i, str(sys.argv[i]) + + #test inMatrix= "/Users/bobbrown/Desktop/NGCHM-Galaxy-Test-Files/400x400firstRowShift.txt" + #test covarFN= '/Users/bobbrown/Desktop/400x400-column-covariate-continuous-TestingErrors.txt' + #test row_col_cat_contin= 'column_continuous' + #test row_col_cat_contin= 'column_categorical' + #test covarLabel = 'bob test' + #test numCovariates= 1 + + errorInMatrix,inMatrixRowLabels,inMatrixColLabels= ValidateHMInputMatrix(inMatrix) # verify input matrix + + print "\nFirst & last Row labels ", inMatrixRowLabels[0],inMatrixRowLabels[-1]," and Columns ", inMatrixColLabels[0],inMatrixColLabels[-1], " number Rows= ",len(inMatrixRowLabels)," number Columns= ",len(inMatrixColLabels) + + # continue reviewing covariates to catch any errors in any of the input info + if len(inMatrixRowLabels) < 5 or len(inMatrixColLabels) < 5: + errorInMatrix = True + print '\n----ERROR Input matrix has too few columns and rows need to ignore validating covariate files for now' + + elif not errorInMatrix: + print "\n++++ SUCCESS the Input Matrix looks good\n\n" + + i= startCovarParam + while i < (len(sys.argv)-2): # todo verify this works with advances tool is one other 0->n param after this + covarLabel= sys.argv[i] + covarLabel= covarLabel.replace(' ','') + covarFN= sys.argv[i+1] + covarFN= covarFN.replace(' ','') + row_col_cat_contin= sys.argv[i+2] + row_col_cat_contin= row_col_cat_contin.replace(' ','') + i +=3 + + print "\nSTART Validating covariate file with label= ", covarLabel, " and type= ",row_col_cat_contin + + error= ValidateHMCorvarFile(covarLabel, covarFN, row_col_cat_contin,inMatrixRowLabels,inMatrixColLabels) # check covariate files + + if error or errorInMatrix: + print"\n---ERROR issues found in input or covariate files\n " + sys.stderr.write( "\nERROR issues found in input or covariate files see errors in Standard Output\n\n ") + sys.exit(3) + + + print"\n FINISHED -- Validation of the Input Matrix and Covariate files (if any)\n\n" + + #print" next running the clustered heat map generator \n",str(sys.argv[11])+"/heatmap.sh "+ str(sys.argv[1:]) + # p = subprocess.Popen([str(sys.argv[1])+"/heatmap.sh "+ argvals], shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) + #p = subprocess.Popen([str(sys.argv[11])+"/heatmap.sh "+ str(sys.argv[1:])], shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) + + #retval = p.wait() + #print ' Cluster and Viewer returned\n' + #for line in p.stdout.readlines(): + # print line + +# else: +# sys.stderr.write("\nERROR -- The Heat Map Generator encountered the above errors with the input file(s)\n\n") +# sys.exit(3) # this will error it out :) +# except: +# sys.stderr.write(str(traceback.format_exc())) +# sys.exit(3) # this will error it out :) + except Exception, err: + sys.stderr.write('ERROR: %sn' % str(err)) + + return + +#+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+- + +def ValidateHMInputMatrix(inputMatrixPath): # This sub routine ensures that the slide design input by the user matches a slide design on record + + try: + error= True + + inputMatrixPath= inputMatrixPath.replace(' ','') + + inMatrixFH= open( inputMatrixPath, 'rU') + + #print "\nInput matrix path and name ", inputMatrixPath,"\n" + error= False + + countRow= 0 + lenRow1= 0 + lenAllRows= 0 + inMatrixRowLabels= [] + inMatrixColLabels= [] + + for rawRow in inMatrixFH: + countRow +=1 + + rawRow= rawRow.replace('\n','') + eachRow= rawRow.split('\t') + if countRow < 2: print 'Input Matrix start 1 to 10= ',eachRow[:10], '\n' + + if countRow == 1: + lenRow1= len(eachRow) + inMatrixColLabels= eachRow + for j in range(1,lenRow1): + tmp= re.search('[abcdefghijklmnopqrstuvwxyz]',eachRow[j].lower()) + try: + if tmp.group(0) == '': # if doesn't exist then error + tmp= tmp + except Exception as e: + print("\n--+-+- ERROR Column Headers at position "+str(j+1)+" value appears to be non-alphanumeric --"+str(eachRow[j])+"--") + sys.stderr.write("\n--+-+- ERROR Column Headers at position "+str(j+1)+" value appears to be non-alphanumeric --"+str(eachRow[j])+"--") + error= True + + if lenRow1 < 3: # likely is covariate file not input matrix + print"----WARNING Input number of columns= " , str(lenRow1)," is too few likely input matrix is really a covariate file" + SystemError ("----WARNING Input number of columns= " + str(lenRow1)+" is too few likely input matrix is really a covariate file") + #error= True + #sys.err= 2 + elif countRow == 2: + lenAllRows= len(eachRow) + if (lenAllRows == lenRow1) or (lenAllRows == lenRow1+1): #or (lenAllRows- lenRow1 == 0 or 1): + print"Validating Input matrix, number of Labeled Columns = ", str(lenAllRows) + inMatrixRowLabels.append(eachRow[0]) + +# allow other error to occur first +# tmp= re.search('[abcdefghijklmnopqrstuvwxyz]',eachRow[0].lower()) +# try: +# if tmp.group(0) == '': # if doesn't exist then error +# tmp= tmp +# except Exception as e: +# print("\n--+-+- WARNING Row Label at row 2 value appears to be non-alphanumeric --"+str(eachRow[j])+"--") +# sys.stderr.write("\n--+-+- WARNING Row Label at row 2 value appears to be non-alphanumeric --"+str(eachRow[j])+"--") +# #error= True + if (lenAllRows == lenRow1) and (inMatrixColLabels[0]==''): inMatrixColLabels.pop(0) #remove blank first cell + + else: + print( "\n--ERROR Input matrix number columns= "+str(lenRow1)+" in first row and the second row= "+str(lenAllRows)+" mismatch ") + sys.stderr.write( "\n--ERROR Input matrix number columns= "+str(lenRow1)+" in first row and the second row= "+str(lenAllRows)+" mismatch ") + error= True + sys.err= 6 + elif (lenRow1 != len(eachRow) and lenRow1+1 != len(eachRow)): + print ("\n--ERROR Input Row "+ str(countRow)+" number of columns= "+str(len(eachRow))+" is a length mismatch with row 2 length "+str( lenAllRows)) + sys.stderr.write ("\n--ERROR Input Row "+ str(countRow)+" number of columns= "+str(len(eachRow))+" is a length mismatch with row 2 length "+str( lenAllRows)) + error= True + sys.err= 7 + else: + inMatrixRowLabels.append(eachRow[0]) + tmp= re.search('[abcdefghijklmnopqrstuvwxyz]',eachRow[0].lower()) + try: + if tmp.group(0) == '': # if doesn't exist then error + tmp= tmp + except Exception as e: + print"-+-+- WARNING Row Label at row "+str(countRow)+" value appears to be non-alphanumeric --"+str(eachRow[j]) + sys.stderr.write("\n--+-+- WARNING Row Label at row "+str(countRow)+" value appears to be non-alphanumeric "+str(eachRow[j])) + + + if len(inMatrixColLabels) > 0: + if (inMatrixColLabels[-1] =='') or (inMatrixColLabels[-1] =='\n'): inMatrixColLabels.pop() + + inMatrixFH.close() + + #print error, lenAllRows, len(eachRow), eachRow[0] + except: + #inMatrixFH.close() + sys.stderr.write(str(traceback.format_exc())) + error= True + + return error,inMatrixRowLabels,inMatrixColLabels + + #+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+- + +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 + +# verify +# 1 That covar file labels match the col or row labels 1 to 1 +# 2 That if a continuous covar file that the 2nd field is not all text hard to tell if '-' or 'e exponent' +# 3 That the length of the covar file matches the row or col length of the input matrix + + error= True + try: + + covFH= open( covariateFilePath, 'rU') + countRow= 0 + + error= False + + for rawRow in covFH: + countRow +=1 + rawRow= rawRow.replace('\n','') + eachRow= rawRow.split('\t') + if countRow== 0: print "\nCovariance file info - label ",str(covarLabel)," row/col categorical or continous",row_col_cat_contin," first row ",str(eachrow) + + if len(eachRow) < 2 and countRow > 1: + print("----ERROR Input Row "+str(countRow)+" does not have a label and/or value ") + sys.stderr.write("----ERROR Input Row "+str(countRow)+" does not have a label/or and value") + error= True + sys.err= 8 + #return error + elif len(eachRow) > 1: + tmp= re.search('[abcdefghijklmnopqrstuvwxyz]',eachRow[0].lower()) + try: + if tmp.group(0) == '': # if doesn't exist then error + tmp= tmp + except Exception as e: + print"\n-+-+- WARNING Covariate Label at row "+str(countRow)+" value appears to be non-alphanumeric --", eachRow[0],"--" + sys.stderr.write("\n--+-+- WARNING Row Headers at row "+str(countRow)+" value appears to be non-alphanumeric --"+str(eachRow[0])+"--") + + if not error: + if row_col_cat_contin[-4:] == 'uous': # verify continuous is number-ish + tmp= re.search('[+-.0123456789eE]',eachRow[1]) + try: + if tmp.group(0) == '': + tmp= tmp + except Exception as e: + print("\n-+-+-WARNING Input Row "+str(countRow)+" covariance continuous value appears to be non-numeric --"+ str(eachRow[1])+"--") + sys.stderr.write("\n-+-+-WARNING Input Row "+str(countRow)+" covariance continuous value appears to be non-numeric --"+ str(eachRow[1])+"--") + #error= True + except: + sys.stderr.write(str(traceback.format_exc())) + + covFH.close() + + return error + + +if __name__ == "__main__": + main() + +
--- a/mda_heatmap_gen.xml Fri Feb 03 13:20:50 2017 -0500 +++ b/mda_heatmap_gen.xml Thu Jul 20 15:31:06 2017 -0400 @@ -1,7 +1,8 @@ <?xml version="1.0" encoding="UTF-8" ?> -<tool id="mda_heatmap_gen" name="NG-CHM Generator" version="2.0.2"> +<tool id="mda_heatmap_gen" name="NG-CHM Generator" version="2.0.5"> <description>Create Clustered Heat Maps</description> -<command interpreter="bash" detect_errors="aggressive">$__tool_directory__/heatmap.sh '$hmname' '$hmdesc' '$inputmatrix' ${d_rows.rowOrderMethod} ${d_rows.rowDistanceMeasure} ${d_rows.rowAgglomerationMethod} ${d_cols.columnOrderMethod} ${d_cols.columnDistanceMeasure} ${d_cols.columnAgglomerationMethod} $summarymethod '$__tool_directory__' ${d_rows.rowDendroCut} ${d_cols.colDendroCut} $rowDataType $colDataType +<!-- <command interpreter="python" detect_errors="aggressive">$__tool_directory__/mda_heatmap_gen.py 'Heat_Map_$hmname' '$hmdesc' '$inputmatrix' ${d_rows.rowOrderMethod} ${d_rows.rowDistanceMeasure} ${d_rows.rowAgglomerationMethod} ${d_cols.columnOrderMethod} ${d_cols.columnDistanceMeasure} ${d_cols.columnAgglomerationMethod} $summarymethod '$__tool_directory__' 0 0 labels labels 'None'--> + <command interpreter="bash" detect_errors="aggressive">$__tool_directory__/heatmap.sh "Heat_Map_$hmname" "$hmdesc" '$inputmatrix' ${d_rows.rowOrderMethod} ${d_rows.rowDistanceMeasure} ${d_rows.rowAgglomerationMethod} ${d_cols.columnOrderMethod} ${d_cols.columnDistanceMeasure} ${d_cols.columnAgglomerationMethod} $summarymethod '$__tool_directory__/' 0 0 labels labels 'None' #for $op in $operations ${op.class_name} ${op.repeatinput.file_name} @@ -13,13 +14,13 @@ <exit_code range="1:" level="fatal" /> </stdio> <inputs> - <param name="inputmatrix" type="data" format="text" label="Input Matrix" /> - <param name="hmname" size="20" type="text" value="Heat_Map_name" label="User Defined Heat Map Name"/> + <param name="inputmatrix" type="data" format="Tabular" label="Input Matrix" /> + <param name="hmname" size="20" type="text" value="Heat_Map_name" label="User Defined Heat Map Name"/> <param name="hmdesc" size="100" optional="true" type="text" value="Heat_Map_description" label="User Defined Heat Map Description"/> <param name="summarymethod" type="select" label="Data Summarization Method"> - <option value="average">average</option> - <option value="sample">sample</option> - <option value="mode">mode</option> + <option value="average">Average</option> + <option value="sample">Sample</option> + <option value="mode">Mode</option> </param> <conditional name="d_rows"> <param name="rowOrderMethod" type="select" label="Row ordering method" help="Choices -- Hierarchical Clustering, Original Order, Random"> @@ -28,69 +29,34 @@ <option value="Random">Random</option> </param> <when value="Hierarchical"> - <param name="rowDistanceMeasure" type="select" label="Row Distance Metric" help="euclidean, binary, manhattan, maximum, canberra, minkowski, or correlation"> - <option value="euclidean">Euclidean</option> - <option value="binary">Binary</option> - <option value="manhattan">Manhattan</option> - <option value="maximum">Maximum</option> - <option value="canberra">Canberra</option> - <option value="minkowski">Minkowski</option> - <option value="correlation">Correlation</option> - </param> - <param name="rowAgglomerationMethod" type="select" label="Row Clustering Method" help="Choices: 'average' for Average Linkage, 'complete' for Complete Linkage, 'single' for Single Linkage, 'ward', 'mcquitty', 'median', or 'centroid'."> - <option value="average">Average Linkage</option> - <option value="complete">Complete Linkage</option> - <option value="single">Single Linkage</option> - <option value="ward" selected="true">Ward</option> - <option value="mcquitty">Mcquitty</option> - <option value="median">Median</option> - <option value="centroid">Centroid</option> - </param> - <param name="rowDendroCut" type="select" label="Create row categorical covariate bar based on number of top-level dendrogram clusters" > - <option value="0" selected="true" >None</option> - <option value="2" >2</option> - <option value="3" >3</option> - <option value="4" >4</option> - <option value="5" >5</option> - <option value="6" >6</option> - <option value="7" >7</option> - <option value="8" >8</option> - <option value="9" >9</option> - <option value="10" >10</option> - </param> + <param name="rowDistanceMeasure" type="select" label="Row Distance Metric" help="Euclidean, Binary, Manhattan, Maximum, Canberra, Minkowski, or Correlation"> + <option value="euclidean">Euclidean</option> + <option value="binary">Binary</option> + <option value="manhattan">Manhattan</option> + <option value="maximum">Maximum</option> + <option value="canberra">Canberra</option> + <option value="minkowski">Minkowski</option> + <option value="correlation">Correlation</option> + </param> + <param name="rowAgglomerationMethod" type="select" label="Row Clustering Method" help="Choices: Average Linkage, Complete Linkage, Single Linkage, 'Ward', 'Mcquitty', 'Median', or 'Centroid'."> + <option value="average">Average Linkage</option> + <option value="complete">Complete Linkage</option> + <option value="single">Single Linkage</option> + <option value="ward" selected="true">Ward</option> + <option value="mcquitty">Mcquitty</option> + <option value="median">Median</option> + <option value="centroid">Centroid</option> + </param> </when> <when value="Original"> - <param name="rowDistanceMeasure" type="text" size="0" value="n/a"/> - <param name="rowAgglomerationMethod" type="text" size="0" value="n/a"/> - <param name="rowDendroCut" size="0" type="text" value="0"/> + <param name="rowDistanceMeasure" type="text" size="0" hidden="true" value="n/a"/> + <param name="rowAgglomerationMethod" type="text" size="0" hidden="true" value="n/a"/> </when> <when value="Random"> - <param name="rowDistanceMeasure" type="text" size="0" value="n/a"/> - <param name="rowAgglomerationMethod" type="text" size="0" value="n/a"/> - <param name="rowDendroCut" type="text" size="0" value="0"/> + <param name="rowDistanceMeasure" type="text" size="0" hidden="true" value="n/a"/> + <param name="rowAgglomerationMethod" type="text" size="0" hidden="true" value="n/a"/> </when> </conditional> - <param name="rowDataType" type="select" label="Linkouts to row data type info" > - <option value="labels" selected="true" >None</option> - <option value="bio.probe.affymetrix" >Affymetrix Probe Id</option> - <option value="bio.feature.agilent" >Agilent Id</option> - <option value="bio.sample.cbioportal" >cBioPortal sample Id</option> - <option value="bio.transcript.ensemble" >Ensemble transcript Id</option> - <option value="bio.gene.entrez" >Gene Entrez Id</option> - <option value="bio.gene.hugo" >Gene HUGO symbol</option> - <option value="bio.go" >Gene Ontology (GO) Id</option> - <option value="bio.geo.acc" >GEO Accession Id</option> - <option value="bio.probe.illumina" >Illumina Probe Id</option> - <option value="bio.probe.infinium" >Infinium Probe Id</option> - <option value="bio.pathway.mdanderson" >MD Anderson pathway Id</option> - <option value="bio.mirna" >miRNA Id</option> - <option value="bio.mirna.mimat" >miRNA MIMAT Id</option> - <option value="bio.pubmed" >Pubmed Id</option> - <option value="bio.pubmed.search" >Pubmed Search Term</option> - <option value="scholar" >Scholarly term</option> - <option value="bio.gene.unigene" >Unigene CID</option> - <option value="bio.protein.uniprot" >UniProt Id</option> - </param> <conditional name="d_cols"> <param name="columnOrderMethod" type="select" label="Column ordering method" help="Choices -- Hierarchical Clustering, Original Order, Random"> <option value="Hierarchical">Hierarchical Clustering</option> @@ -98,69 +64,34 @@ <option value="Random">Random</option> </param> <when value="Hierarchical"> - <param name="columnDistanceMeasure" type="select" label="Column Distance Metric" help="euclidean, binary, manhattan, maximum, canberra, minkowski, or correlation"> - <option value="euclidean">Euclidean</option> - <option value="binary">Binary</option> - <option value="manhattan">Manhattan</option> - <option value="maximum">Maximum</option> - <option value="canberra">Canberra</option> - <option value="minkowski">Minkowski</option> - <option value="correlation">Correlation</option> - </param> - <param name="columnAgglomerationMethod" type="select" label="Column Clustering Method" help="Choices: 'average' for Average Linkage, 'complete' for Complete Linkage, 'single' for Single Linkage, 'ward', 'mcquitty', 'median', or 'centroid'."> - <option value="average">Average Linkage</option> - <option value="complete">Complete Linkage</option> - <option value="single">Single Linkage</option> - <option value="ward" selected="true">Ward</option> - <option value="mcquitty">Mcquitty</option> - <option value="median">Median</option> - <option value="centroid">Centroid</option> - </param> - <param name="colDendroCut" type="select" label="Create column categorical covariate bar based on number of top-level dendrogram clusters" > - <option value="0" selected="true" >None</option> - <option value="2" >2</option> - <option value="3" >3</option> - <option value="4" >4</option> - <option value="5" >5</option> - <option value="6" >6</option> - <option value="7" >7</option> - <option value="8" >8</option> - <option value="9" >9</option> - <option value="10" >10</option> - </param> + <param name="columnDistanceMeasure" type="select" label="Column Distance Metric" help="Euclidean, Binary, Manhattan, Maximum, Canberra, Minkowski, or Correlation"> + <option value="euclidean">Euclidean</option> + <option value="binary">Binary</option> + <option value="manhattan">Manhattan</option> + <option value="maximum">Maximum</option> + <option value="canberra">Canberra</option> + <option value="minkowski">Minkowski</option> + <option value="correlation">Correlation</option> + </param> + <param name="columnAgglomerationMethod" type="select" label="Column Clustering Method" help="Choices: Average Linkage, Complete Linkage, Single Linkage, 'Ward', 'Mcquitty', 'Median', or 'Centroid'."> + <option value="average">Average Linkage</option> + <option value="complete">Complete Linkage</option> + <option value="single">Single Linkage</option> + <option value="ward" selected="true">Ward</option> + <option value="mcquitty">Mcquitty</option> + <option value="median">Median</option> + <option value="centroid">Centroid</option> + </param> </when> <when value="Original"> - <param name="columnDistanceMeasure" type="text" size="0" value="n/a"/> - <param name="columnAgglomerationMethod" type="text" size="0" value="n/a"/> - <param name="colDendroCut" type="text" size="0" value="0"/> + <param name="columnDistanceMeasure" type="text" size="0" hidden="true" value="n/a"/> + <param name="columnAgglomerationMethod" type="text" size="0" hidden="true" value="n/a"/> </when> <when value="Random"> - <param name="columnDistanceMeasure" type="text" size="0" value="n/a"/> - <param name="columnAgglomerationMethod" type="text" size="0" value="n/a"/> - <param name="colDendroCut" type="text" size="0" value="0"/> + <param name="columnDistanceMeasure" type="text" size="0" hidden="true" value="n/a"/> + <param name="columnAgglomerationMethod" type="text" size="0" hidden="true" value="n/a"/> </when> </conditional> - <param name="colDataType" type="select" label="Linkouts to column data type info" > - <option value="labels" selected="true" >None</option> - <option value="bio.probe.affymetrix" >Affymetrix Probe Id</option> - <option value="bio.feature.agilent" >Agilent Id</option> - <option value="bio.sample.cbioportal" >cBioPortal sample Id</option> - <option value="bio.transcript.ensemble" >Ensemble transcript Id</option> - <option value="bio.gene.entrez" >Gene Entrez Id</option> - <option value="bio.gene.hugo" >Gene HUGO symbol</option> - <option value="bio.go" >Gene Ontology (GO) Id</option> - <option value="bio.geo.acc" >GEO Accession Id</option> - <option value="bio.probe.illumina" >Illumina Probe Id</option> - <option value="bio.probe.infinium" >Infinium Probe Id</option> - <option value="bio.pathway.mdanderson" >MD Anderson pathway Id</option> - <option value="bio.mirna" >miRNA Id</option> - <option value="bio.mirna.mimat" >miRNA MIMAT Id</option> - <option value="bio.pubmed" >Pubmed Id</option> - <option value="bio.pubmed.search" >Pubmed Search Term</option> - <option value="scholar" >Scholarly term</option> - <option value="bio.gene.unigene" >Unigene CId</option> - <option value="bio.protein.uniprot" >UniProt Id</option> - </param> <repeat name="operations" title="Covariate Bars"> <param name="class_name" size="20" type="text" value="" label="Axis Covariate Name"> <sanitizer invalid_char="_"> @@ -174,28 +105,28 @@ </param> <param name="repeatinput" type="data" format="text" label="Axis Covariate File"/> <param name="cat" type="select" label="Axis Covariate Type"> - <option value="row_categorical" >row categorical</option> - <option value="row_continuous" >row continuous</option> - <option value="column_categorical" >column categorical</option> - <option value="column_continuous" >column continuous</option> + <option value="row_categorical" >Row Categorical</option> + <option value="row_continuous" >Row Continuous</option> + <option value="column_categorical" >Column Categorical</option> + <option value="column_continuous" >Column Continuous</option> </param> </repeat> </inputs> <outputs> - <data name="output" label='${hmname}' format="ngchm"/> + <data name="output" label='Heat_Map_$hmname' format="ngchm"/> </outputs> <tests> <test> <param name="inputmatrix" value="400x400.txt" /> <param name="hmname" value="testRun" /> <param name="$hmdesc" value="validateTool" /> - <param name="summarymethod" value="average" /> + <param name="summarymethod" value="Average" /> <param name="rowOrderMethod" value="Hierarchical" /> - <param name="rowDistanceMeasure" value="manhattan" /> - <param name="rowAgglomerationMethod" value="ward" /> + <param name="rowDistanceMeasure" value="Manhattan" /> + <param name="rowAgglomerationMethod" value="Ward" /> <param name="columnOrderMethod" value="Hierarchical" /> - <param name="columnDistanceMeasure" value="manhattan" /> - <param name="columnAgglomerationMethod" value="ward" /> + <param name="columnDistanceMeasure" value="Manhattan" /> + <param name="columnAgglomerationMethod" value="Ward" /> <output name="output" file="Galaxy400x400-noCovariates.ngchm" lines_diff="10" /> </test>