Easier PSN specification + tests added for predict()

DESCRIPTION

@@ -17,7 +17,6 @@ Depends:
     R (>= 3.6)
 Suggests: 
   curatedTCGAData,
-	TCGAutils,
 	rmarkdown,
 	testthat,
 	knitr,

NAMESPACE

@@ -15,6 +15,7 @@ export(convertProfileToNetworks)
 export(countIntType)
 export(countIntType_batch)
 export(countPatientsInNet)
+export(createNetFuncFromSimList)
 export(createPSN_MultiData)
 export(dataList2List)
 export(enrichLabelNets)
@@ -64,6 +65,7 @@ export(sparsify2)
 export(sparsify3)
 export(splitTestTrain)
 export(splitTestTrain_resampling)
+export(subsampleValidationData)
 export(tSNEPlotter)
 export(thresholdSmoothedMutations)
 export(updateNets)

R/buildPredictor.R

@@ -29,6 +29,9 @@
 #' So keys(groupList[["rna"]]) would have pathway names, generating one PSN
 #' per pathways, and values(groupList[["rna"]]) would be genes that would be
 #' grouped for the corresponding pathwayList.
+#' @param sims (list) rules to create similarity networks from input data. Keys are names of
+#' data layers and should be identical to names(groupList). Values is either a character
+#' for built-in similarity functions; call allowedSims() to see full list; or a custom function.
 #' @param makeNetFunc (function) user-defined function for creating the set
 #' of input PSN provided to netDx. See createPSN_MultiData()::customFunc.
 #' @param outDir (char) directory where results will be stored. If this
@@ -171,7 +174,8 @@
 #' #   makeNetFunc=makeNets, ### custom network creation function
 #' #   outDir=paste(tempdir(),"pred_output",sep=getFileSep()), ## absolute path
 #' #   numCores=16L,featScoreMax=2L, featSelCutoff=1L,numSplits=2L)
-buildPredictor <- function(dataList,groupList,outDir=tempdir(),makeNetFunc,
+buildPredictor <- function(dataList,groupList,outDir=tempdir(),
+	makeNetFunc=NULL,sims=NULL,
 	featScoreMax=10L,trainProp=0.8,numSplits=10L,numCores,JavaMemory=4L,
 	featSelCutoff=9L,keepAllData=FALSE,startAt=1L, preFilter=FALSE,
 	impute=FALSE,preFilterGroups=NULL, imputeGroups=NULL,logging="default",
@@ -196,7 +200,7 @@ if (logging == "all") {
 	verbose_predict <- FALSE
 }
 
-# Check input
+# Check input - error handling
 if (missing(dataList)) stop("dataList must be supplied.\n")
 if (missing(groupList)) stop("groupList must be supplied.\n")
 if (length(groupList)<1) stop("groupList must be of length 1+\n")
@@ -213,13 +217,18 @@ if (!is(groupList,"list") || not_list || names_nomatch ) {
 	stop(paste(msg,sep=""))
 }
 
+# checks either/or provided, sets missing var to NULL
+x <- checkMakeNetFuncSims(makeNetFunc=makeNetFunc, sims=sims,groupList=groupList)
+
 if (!is(dataList,"MultiAssayExperiment"))
 	stop("dataList must be a MultiAssayExperiment")
 
 if (trainProp <= 0 | trainProp >= 1) 
 		stop("trainProp must be greater than 0 and less than 1")
 if (startAt > numSplits) stop("startAt should be between 1 and numSplits")
 
+# end check input error handling
+
 megaDir <- outDir
 if (file.exists(megaDir)) {
  	stop(paste("outDir seems to already exist!",
@@ -274,7 +283,6 @@ if (verbose_default){
 	}
 }
 
-
 outList <- list()
 
 # create master list of possible networks
@@ -289,8 +297,14 @@ colnames(tmp) <- c("NetType","NetName")
 outList[["inputNets"]] <- tmp
 
 if (verbose_default) {
-	message("\n\nCustom function to generate input nets:")
-	print(makeNetFunc)
+	if (!is.null(makeNetFunc)){
+		message("\n\nCustom function to generate input nets:")
+		print(makeNetFunc)
+
+	} else {
+		message("Similarity metrics provided:")
+		print(sims)
+	}
 	message(sprintf("-------------------------------\n"))
 }
 
@@ -386,8 +400,8 @@ for (rngNum in startAt:numSplits) {
 
 	if (verbose_default) message("** Creating features")
 	createPSN_MultiData(dataList=dats_train,groupList=groupList,
-			pheno=pheno_id,
-			netDir=netDir,customFunc=makeNetFunc,numCores=numCores,
+			pheno=pheno_id, 
+			netDir=netDir,makeNetFunc=makeNetFunc,sims=sims, numCores=numCores,
 			verbose=verbose_makeFeatures)
 	if (verbose_default) message("** Compiling features")
 	dbDir <- compileFeatures(netDir,outDir, numCores=numCores, 
@@ -512,7 +526,8 @@ for (rngNum in startAt:numSplits) {
 		pheno_id <- setupFeatureDB(pheno,netDir)
 		createPSN_MultiData(dataList=dats_tmp,groupList=groupList,
 			pheno=pheno_id,
-			netDir=netDir,customFunc=makeNetFunc,numCores=numCores,
+			netDir=netDir,makeNetFunc=makeNetFunc,sims=sims, 
+			numCores=numCores,
 			filterSet=pTally,verbose=verbose_default)
 		dbDir <- compileFeatures(netDir,outDir=pDir,numCores=numCores,
 			verbose=verbose_compileNets,debugMode=debugMode)

R/compileFeatures.R

@@ -58,7 +58,7 @@
 #' 
 #' pheno_id <- setupFeatureDB(pheno,netDir)
 #' netList <- createPSN_MultiData(dataList=dataList, groupList=groupList,
-#'     pheno=pheno_id,netDir=netDir,customFunc=makeNets,verbose=TRUE)
+#'     pheno=pheno_id,netDir=netDir,makeNetFunc=makeNets,verbose=TRUE)
 #' 
 #' outDir <- paste(tmpDir,'dbdir',sep=getFileSep()); 
 #'	dir.create(outDir)

R/createPSN_MultiData.R

@@ -12,11 +12,15 @@
 #' with internally-generated identifiers.
 #' @param netDir (char) path to directory where networks will be stored
 #' @param filterSet (char) vector of networks to include
-#' @param customFunc (function) custom user-function to create PSN. 
+#' @param makeNetFunc (function) custom user-function to create PSN. 
 #' Must take dataList,groupList,netDir as parameters. Must
 #' check if a given groupList is empty (no networks to create) before 
 #' the makePSN call for it. This is to avoid trying to make nets for datatypes
 #' that did not pass feature selection
+#' @param sims (list) Similarity metric settings for patient data. 
+#' Keys must be identical to those of groupList. 
+#' Values are either of type character, used for built-in similarity functions, 
+#' or are functions, when a custom function is provided.
 #' @param verbose (logical) print messages
 #' @param ... other parameters to makePSN_NamedMatrix() or makePSN_RangedSets()
 #' @return (char) vector of network names. Side effect of creating the nets
@@ -95,33 +99,33 @@
 #' pheno_id <- setupFeatureDB(colData(brca),netDir)
 #' createPSN_MultiData(dataList=datList2,groupList=groupList,
 #'  pheno=pheno_id,
-#'  netDir=netDir,customFunc=makeNets,numCores=1)
+#'  netDir=netDir,makeNetFunc=makeNets,numCores=1)
 #' @export
 createPSN_MultiData <- function(dataList, groupList, pheno, netDir=tempdir(), 
 		filterSet = NULL, 
-    verbose = TRUE, customFunc, ...) {
+    verbose = TRUE, makeNetFunc=NULL, sims=NULL, ...) {
 
     if (missing(dataList)) 
         stop("dataList must be supplied.\n")
     if (missing(groupList)) 
         stop("groupList must be supplied.\n")
-    
+
     # resolve user-provided IDs with internal IDs
     dataList <- lapply(dataList, function(x) {
         midx <- match(colnames(x), pheno$ID)
         colnames(x) <- pheno$INTERNAL_ID[midx]
         x
     })
-    
+
     if (!is.null(filterSet)) {
         if (length(filterSet) < 1) {
           s1 <- "filterSet is empty."
         	s2 <- "It needs to have at least one net to proceed."
         	stop(paste(s1, s2, sep = " "))
 				}
     }
-    if (missing(customFunc)) 
-        stop("customFunc must be suppled.\n")
+
+
 
     # Filter for nets (potentially feature-selected ones)
     if (!is.null(filterSet)) {
@@ -139,12 +143,22 @@ createPSN_MultiData <- function(dataList, groupList, pheno, netDir=tempdir(),
             }
         }
         groupList <- groupList2
+        sims <- sims[which(names(sims) %in% names(groupList))]
         rm(groupList2)
     }
 
+    if (!is.null(makeNetFunc)){
     # call user-defined function for making PSN
-    netList <- customFunc(dataList = dataList, groupList = groupList, 
+        netList <- makeNetFunc(dataList = dataList, groupList = groupList, 
 				netDir = netDir, ...)
+    } else {
+        netList <- createNetFuncFromSimList(dataList=dataList,
+            groupList = groupList, 
+            netDir = netDir,
+            sims = sims, 
+            ...
+            )
+    }
 
     if (length(netList) < 1) 
         stop("\n\nNo features created! Filters may be too stringent.\n")

R/helper.R

@@ -159,8 +159,11 @@ return(list(
 #' @param EMapPctPass (numeric between 0 and 1) percent of splits for which feature must have score in range
 #'  [EMapMinScore,EMapMaxScore] to be included for EnrichmentMap visualization
 #' @param outDir (char) directory where files should be written
-#' @return 
-#' @export
+#' @return (list) 1) GMTfiles (char): GMT files used to create EnrichmentMap in Cytoscape.
+#' 2) NodeStyles (char): .txt files used to assign node attributes in Cytoscape. Importantly, 
+#' attributes include node fill, which indicates the highest consistent score for a given 
+#' feature. 
+#' @export 
 makeInputForEnrichmentMap <- function(model,results,pathwayList,
     EMapMinScore=0L, EMapMaxScore=1L,
     EMapPctPass=0.5,outDir)
@@ -214,8 +217,10 @@ return(list(GMTfiles=gmtFiles,NodeStyles=nodeAttrFiles))
 #' same class, relative to those of other classes, using Dijkstra distance (calcShortestPath flag).  
 #' @param dat (MultiAssayExperiment) input data
 #' @param groupList (list) feature groups, identical to groupList provided for buildPredictor()
-#' @param makeNets (function) Function used to create patient similarity networks. Identical to 
+#' @param makeNetFunc (function) Function used to create patient similarity networks. Identical to 
 #' makeNets provided to buildPredictor()
+#' @param sims (list) rules for creating PSN. Preferred over makeNetFunc. See buildPredictor() 
+#' for details.
 #' @param selectedFeatures (list) selected features for each class (key of list). This object is returned as
 #' part of a call to getResults(), after running buildPredictor().
 #' @param plotCytoscape (logical) If TRUE, plots network in Cytoscape.
@@ -245,9 +250,18 @@ return(list(GMTfiles=gmtFiles,NodeStyles=nodeAttrFiles))
 #' colours (colour)
 #' 6) outDir (char) value of outDir parameter
 #' @export
-getPSN <- function(dat, groupList, makeNets, selectedFeatures, plotCytoscape=FALSE,
-    aggFun="MEAN", prune_pctX=0.30, prune_useTop=TRUE,numCores=1L,calcShortestPath=FALSE
+getPSN <- function(dat, groupList, 
+    makeNetFunc=NULL, sims=NULL, 
+    selectedFeatures, plotCytoscape=FALSE,
+    aggFun="MEAN", prune_pctX=0.30, prune_useTop=TRUE,
+    numCores=1L,calcShortestPath=FALSE
     ){
+
+
+# checks either/or provided, sets missing var to NULL
+x <- checkMakeNetFuncSims(makeNetFunc=makeNetFunc, 
+    sims=sims,groupList=groupList)
+
 topPath <- gsub(".profile","", unique(unlist(selectedFeatures)))
 topPath <- gsub("_cont.txt","",topPath)
 
@@ -262,8 +276,10 @@ for (nm in names(groupList)) {
 
 message("* Making integrated PSN")
 psn <- 
-   plotIntegratedPatientNetwork(dat,
-  groupList=g2, makeNetFunc=makeNets,
+   plotIntegratedPatientNetwork(
+       dataList=dat,
+  groupList=g2, makeNetFunc=makeNetFunc,
+  sims=sims,
   aggFun=aggFun,
   prune_pctX=prune_pctX,
   prune_useTop=prune_useTop,

R/plotEmap.R

@@ -80,14 +80,14 @@ plotEmap <- function(gmtFile, nodeAttrFile, netName = "generic",
     }
 
     ####################################### create EM using given parameters
-    if (netName %in% getNetworkList()) {
+    if (netName %in% RCy3::getNetworkList()) {
         RCy3::deleteNetwork(netName)
     }
     em_command <- paste("enrichmentmap build analysisType=\"generic\"", 
 				"gmtFile=", gmtFile, "pvalue=", 1, "qvalue=", 1, 
 				"similaritycutoff=", 0.05, "coefficients=", "JACCARD")
     response <- RCy3::commandsGET(em_command)
-    renameNetwork(netName, getNetworkSuid())
+    RCy3::renameNetwork(netName, RCy3::getNetworkSuid())
 
     ### #annotate the network using AutoAnnotate app
     aa_command <- paste("autoannotate annotate-clusterBoosted", 

R/plotIntegratedPatientNetwork.R

@@ -19,6 +19,7 @@
 #' list of lists, where the outer list corresponds to assay (e.g. mRNA,
 #' clinical) and inner list to features to generate from that datatype.
 #' @param makeNetFunc (function) function to create features
+#' @param sims (list) rules for creating PSN. Preferred over makeNetFunc
 #' @param setName (char) name to assign the network in Cytoscape
 #' @param numCores (integer) number of cores for parallel processing
 #' @param prune_pctX (numeric between 0 and 1) fraction of most/least 
@@ -59,14 +60,20 @@
 #' @importFrom RColorBrewer brewer.pal
 #' @importFrom stats wilcox.test qexp density
 #' @export
-plotIntegratedPatientNetwork <- function(dataList,groupList,makeNetFunc,
+plotIntegratedPatientNetwork <- function(dataList,groupList,
+	makeNetFunc=NULL,sims=NULL,
 	setName="predictor",prune_pctX=0.05, prune_useTop=TRUE,
 	 aggFun="MAX",calcShortestPath=FALSE,
 	showStats=FALSE,
 	outDir=tempdir(),numCores=1L,nodeSize=50L,edgeTransparency=40L,
 	nodeTransparency=155L,plotCytoscape=FALSE,
 	verbose=FALSE) {
 
+
+# checks either/or provided, sets missing var to NULL
+checkMakeNetFuncSims(makeNetFunc=makeNetFunc, 
+    sims=sims,groupList=groupList)
+
 if (missing(dataList)) stop("dataList is missing.")
 
 dat <- dataList2List(dataList, groupList)
@@ -81,7 +88,9 @@ pheno_id <- setupFeatureDB(pheno,outDir)
 
 createPSN_MultiData(dataList=dat$assays,groupList=groupList,
 			pheno=pheno_id,
-			netDir=outDir,customFunc=makeNetFunc,numCores=numCores,
+			netDir=outDir,
+			makeNetFunc=makeNetFunc,sims=sims,
+			numCores=numCores,
 			verbose=FALSE)
 convertProfileToNetworks(
 		netDir=profDir,