Merge branch 'devel' into BLOBFISH

.github/workflows/main.yml

@@ -30,7 +30,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest]
-        r-version: [4.2]
+        r-version: [4.3]
 
     steps:
 

.gitignore

@@ -34,3 +34,5 @@ tests/testthat/*.vcf
 vignettes/*.npy
 docs/*.npy
 docs/reference/*.npy
+bladder.rdata
+skin.rdata

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: netZooR
 Type: Package
 Title: Unified methods for the inference and analysis of gene regulatory networks
-Version: 1.5.4
-Date: 2023-09-25
+Version: 1.5.17
+Date: 2024-02-29
 Authors@R: c(person("Marouen", "Ben Guebila",
 			email = "benguebila@hsph.harvard.edu", role = c("aut","cre"), comment = c(ORCID = "0000-0001-5934-966X")),
 	     person("Tian", "Wang", 
@@ -22,11 +22,11 @@ Authors@R: c(person("Marouen", "Ben Guebila",
 Maintainer: Marouen Ben Guebila <marouen.b.guebila@gmail.com>
 Description: netZooR unifies the implementations of several Network Zoo methods (netzoo, netzoo.github.io) into a single package by creating interfaces between network inference and network analysis methods. Currently, the package has 3 methods for network inference including PANDA and its optimized implementation OTTER (network reconstruction using mutliple lines of biological evidence), LIONESS (single-sample network inference), and EGRET (genotype-specific networks). Network analysis methods include CONDOR (community detection), ALPACA (differential community detection), CRANE (significance estimation of differential modules), MONSTER (estimation of network transition states). In addition, YARN allows to process gene expresssion data for tissue-specific analyses and SAMBAR infers missing mutation data based on pathway information.
 Depends: R (>= 4.2.0),
-   	 igraph,
+   igraph,
 	 reticulate,
-         yarn,
 	 pandaR,
-         matrixcalc
+   matrixcalc,
+   Biobase
 Remotes: 
 	 stan-dev/cmdstanr,
 	 jnpaulson/pandaR, 
@@ -77,6 +77,14 @@ Imports:
     loo,
     rARPACK,
     corpcor,
+    biomaRt,
+    downloader,
+    edgeR,
+    limma,
+    preprocessCore,
+    readr,
+    RColorBrewer,
+    quantro
 License: GPL-3
 Encoding: UTF-8
 LazyData: false

NAMESPACE

@@ -9,6 +9,9 @@ export(adj2regulon)
 export(alpaca)
 export(alpacaCrane)
 export(alpacaExtractTopGenes)
+export(annotateFromBiomart)
+export(checkMisAnnotation)
+export(checkTissuesToMerge)
 export(cobra)
 export(condorCluster)
 export(condorCoreEnrich)
@@ -21,10 +24,15 @@ export(craneBipartite)
 export(craneUnipartite)
 export(createCondorObject)
 export(createPandaStyle)
+export(downloadGTEx)
 export(dragon)
 export(el2adj)
 export(el2regulon)
 export(elistToAdjMat)
+export(filterGenes)
+export(filterLowGenes)
+export(filterMissingGenes)
+export(filterSamples)
 export(lioness)
 export(lionessPy)
 export(monster)
@@ -40,11 +48,15 @@ export(monsterTransformationMatrix)
 export(monsterTransitionNetworkPlot)
 export(monsterTransitionPCAPlot)
 export(monsterdTFIPlot)
+export(normalizeTissueAware)
 export(otter)
 export(pandaDiffEdges)
 export(pandaPy)
 export(pandaToAlpaca)
 export(pandaToCondorObject)
+export(plotCMDS)
+export(plotDensity)
+export(plotHeatmap)
 export(priorPp)
 export(puma)
 export(runEgret)
@@ -77,12 +89,33 @@ import(reticulate)
 import(stats, except= c(cov2cor,decompose,toeplitz,lowess,update,spectrum))
 import(vegan, except=diversity)
 import(viridisLite)
-import(yarn)
+importClassesFrom(Biobase,ExpressionSet)
+importClassesFrom(Biobase,eSet)
+importFrom(Biobase,"assayData<-")
+importFrom(Biobase,"fData<-")
+importFrom(Biobase,"pData<-")
+importFrom(Biobase,"phenoData<-")
+importFrom(Biobase,"storageMode<-")
+importFrom(Biobase,AnnotatedDataFrame)
+importFrom(Biobase,ExpressionSet)
 importFrom(Biobase,assayData)
+importFrom(Biobase,exprs)
+importFrom(Biobase,fData)
+importFrom(Biobase,featureNames)
+importFrom(Biobase,pData)
+importFrom(Biobase,storageMode)
+importFrom(RColorBrewer,brewer.pal)
 importFrom(assertthat,assert_that)
+importFrom(biomaRt,getBM)
+importFrom(biomaRt,useMart)
+importFrom(downloader,download)
+importFrom(edgeR,cpm)
+importFrom(gplots,heatmap.2)
+importFrom(graphics,abline)
 importFrom(graphics,axis)
 importFrom(graphics,box)
 importFrom(graphics,hist)
+importFrom(graphics,legend)
 importFrom(graphics,mtext)
 importFrom(graphics,par)
 importFrom(graphics,plot)
@@ -94,6 +127,7 @@ importFrom(igraph,E)
 importFrom(igraph,V)
 importFrom(igraph,graph.data.frame)
 importFrom(igraph,plot.igraph)
+importFrom(limma,normalizeQuantiles)
 importFrom(matrixStats,colSds)
 importFrom(matrixStats,rowSds)
 importFrom(methods,is)
@@ -103,8 +137,18 @@ importFrom(parallel,mclapply)
 importFrom(penalized,optL1)
 importFrom(penalized,penalized)
 importFrom(penalized,predict)
+importFrom(preprocessCore,normalize.quantiles)
+importFrom(quantro,matdensity)
+importFrom(readr,problems)
+importFrom(readr,read_tsv)
 importFrom(reshape,melt.array)
 importFrom(reshape2,dcast)
 importFrom(reshape2,melt)
+importFrom(stats,ave)
+importFrom(stats,cmdscale)
+importFrom(stats,dist)
+importFrom(stats,model.matrix)
+importFrom(stats,runmed)
+importFrom(stats,sd)
 importFrom(tidyr,spread)
 importFrom(utils,write.table)

R/ALPACA.R

@@ -16,7 +16,6 @@
 #' @importFrom utils write.table
 #' @rawNamespace import(GOstats, except= makeGOGraph)
 #' @import org.Hs.eg.db
-#' @import yarn 
 #' @export
 #' 
 

R/MONSTER.R

@@ -90,7 +90,8 @@ monsterPrintMonsterAnalysis <- function(x, ...){
 #' to give to indirect compared to direct evidence. The default is 0.5 to give an 
 #' equal weight to direct and indirect evidence.
 #' @param mode A parameter telling whether to build the regulatory networks ('buildNet') or to use provided regulatory networks
-#' ('regNet'). If set to 'regNet', then the parameters motif, ni_method, ni.coefficient.cutoff, and alphaw will be set to NA.
+#' ('regNet'). If set to 'regNet', then the parameters motif, ni_method, ni.coefficient.cutoff, and alphaw will be set to NA. Gene regulatory
+#' networks are supplied in the 'expr' variable as a TF-by-Gene matrix, by concatenating the TF-by-Gene matrices of case and control, expr has size nTFs x 2nGenes.
 #' @export
 #' @import doParallel
 #' @import parallel

R/PUMA.R

@@ -89,7 +89,11 @@ puma <- function(motif,expr=NULL,ppi=NULL,alpha=0.1,mir_file,hamming=0.001,
       expr <- expr[order(rownames(expr)),]
     }else if(mode=='union'){
       gene.names=unique(union(rownames(expr),unique(motif[,2])))
-      tf.names  =unique(union(unique(ppi[,1]),unique(motif[,1])))
+      if(is.null(ppi)){
+        tf.names  = unique(motif[,1])        
+      }else{
+        tf.names  =unique(union(unique(ppi[,1]),unique(motif[,1])))
+      }
       num.TFs    <- length(tf.names)
       num.genes  <- length(gene.names)
       # gene expression matrix
@@ -117,7 +121,11 @@ puma <- function(motif,expr=NULL,ppi=NULL,alpha=0.1,mir_file,hamming=0.001,
       regulatoryNetwork[Idx]=motif[,3]
     }else if(mode=='intersection'){
       gene.names=unique(intersect(rownames(expr),unique(motif[,2])))
-      tf.names  =unique(intersect(unique(ppi[,1]),unique(motif[,1])))
+      if(is.null(ppi)){
+        tf.names  =unique(motif[,1])       
+      }else{
+        tf.names  =unique(intersect(unique(ppi[,1]),unique(motif[,1])))
+      }
       num.TFs    <- length(tf.names)
       num.genes  <- length(gene.names)
       # gene expression matrix
@@ -241,6 +249,7 @@ puma <- function(motif,expr=NULL,ppi=NULL,alpha=0.1,mir_file,hamming=0.001,
 
   if(!is.null(mir_file)){
     mirIndex = match(mir_file,tf.names)
+    mirIndex <- mirIndex[!is.na(mirIndex)]
     tfCoopNetwork[mirIndex,] = 0
     tfCoopNetwork[,mirIndex] = 0
     seqs = seq(1, num.TFs*num.TFs, num.TFs+1)