Devel

.Rbuildignore

@@ -16,17 +16,6 @@ CONDUCT\.md$
 .Rhistory
 coverZoo.r
 .github
-tests/testthat/test-panda.R
-tests/testthat/test-lioness.R
-tests/testthat/test-egret.R
-tests/testthat/test-monster.R
-tests/testthat/test-alpaca.R
-tests/testthat/test.source.PPI.R
-tests/testthat/test-pandatoalpaca.R
-tests/testthat/test-pandatocondorobject.R
-tests/testthat/test-pandadiffedges.R
-tests/testthat/test-sambar.R
-tests/testthat/test-otter.R
 LICENSE
 netZooR.Rcheck/
 vignettes/ApplicationwithTBdataset.Rmd
@@ -41,6 +30,5 @@ vignettes/pandaR.Rmd
 vignettes/pandaRApplicationinGTExData.Rmd
 vignettes/yarn.Rmd
 notes.md
-R/pandaDiffEdges.R
 R/createDiffPandaStyle.R
 R/visDiffPandaInCytoscape.R

.github/workflows/main.yml

@@ -26,70 +26,61 @@ on:
 jobs:
   build:
     runs-on: ${{ matrix.os }}
+    timeout-minutes: 300
     strategy:
       matrix:
-        os: [macos-latest, ubuntu-latest]
-        r-version: [4.1]
+        os: [ubuntu-latest, macos-latest]
+        r-version: [4.2]
 
     steps:
+
       - uses: actions/checkout@v2
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
       - name: Set up R ${{ matrix.r-version }} 
-        uses: r-lib/actions/setup-r@v1
+        uses: r-lib/actions/setup-r@v2
         with:
           r-version: ${{ matrix.r-version }}
-      - name: Install bash dependencies 1
-        if: matrix.os == 'ubuntu-latest'
-        run: |
-            sudo apt-get install libcurl4-openssl-dev libharfbuzz-dev libfribidi-dev libopenblas-base libatlas3-base
-      - name: Install reticulate 1
+
+      - name: install dependencies
+        uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          cache-version: 1
+          extra-packages: |
+             any::reticulate
+             any::rcmdcheck
+             any::covr
+          needs: |
+             website
+             coverage
+
+      - name: Install blas/lapack
         run: |
             La_library()
             extSoftVersion()["BLAS"]
-            install.packages('reticulate', repos = "http://cran.us.r-project.org")
-            library('reticulate')
         shell: Rscript {0}
-      - name: Install reticulate 2-1
-        if: matrix.os == 'macos-latest'
-        run: |
-            library('reticulate')
-            py_config()
-            use_python("/usr/local/bin/python3")
-            virtualenv_create("r-reticulate")
-        shell: sudo -E Rscript {0}
-      - name: Install reticulate 2-2
-        if: matrix.os == 'ubuntu-latest'
+
+      - name: Install reticulate
         run: |
-            library('reticulate')
+            library("reticulate")
             py_config()
-            use_python("/usr/bin/python3")
-            virtualenv_create("r-reticulate")
-        shell: sudo -E Rscript {0}
-      - name: Install reticulate 3
-        run: |
-            library('reticulate')
-            virtualenv_install("r-reticulate","numpy")
-            virtualenv_install("r-reticulate","scipy")
-            virtualenv_install("r-reticulate","pandas")
-            virtualenv_install("r-reticulate","joblib")
-        shell: sudo -E Rscript {0}
-      - name: Install dependencies 2
-        run: |
-            install.packages(c("remotes", "rcmdcheck"), repos = "http://cran.us.r-project.org")
-            remotes::install_cran("covr") 
-            remotes::install_deps(dep = T)
+            py_install("numpy")
+            py_install("scipy")
+            py_install("pandas")
+            py_install("joblib")
         shell: Rscript {0}
+
       - name: Check
-        run: |
-            library('reticulate')
-            py_config()
-            rcmdcheck::rcmdcheck(args = c("--no-manual","--ignore-vignettes"), error_on = "error", build_args="--no-build-vignettes")
-        shell: sudo -E Rscript {0}
+        uses: r-lib/actions/check-r-package@v2
+        with:
+            args: 'c("--no-manual", "--ignore-vignettes")'
+            build_args: 'c("--no-build-vignettes")'
+            error-on: '"error"'
+
       - name: Report coverage
         run: |
-            library('reticulate')
-            py_config()            
             covr::codecov()
-        shell: sudo -E Rscript {0}
-
+        shell: Rscript {0}

.gitignore

@@ -1,7 +1,6 @@
 .DS_Store
 .Rhistory
 Untitled.R
-.Rbuildignore
 inst/doc/
 doc
 Meta

DESCRIPTION

@@ -1,22 +1,26 @@
 Package: netZooR
-Title: netZooR integrates tools for the inference and analysis of gene regulatory networks.
-Version: 1.0.4
-Date: 2021-09-20
+Type: Package
+Title: Unified methods for the inference and analysis of gene regulatory networks
+Version: 1.1.16
+Date: 2022-07-07
 Authors@R: c(person("Marouen", "Ben Guebila",
-			email = "benguebila@hsph.harvard.edu", role = c("aut","cre")),
+			email = "benguebila@hsph.harvard.edu", role = c("aut","cre"), comment = c(ORCID = "0000-0001-5934-966X")),
 	     person("Tian", "Wang", 
-			email = "tian.wang@bc.edu", role = c("aut")),
+			email = "tian.wang@bc.edu", role = c("aut"), comment = c(ORCID = "0000-0002-2767-3243")),
 	     person("John", "Platig",
-			email="john.platig@channing.harvard.edu",role="aut"),
+			email="john.platig@channing.harvard.edu", role="aut"),
 	     person("Marieke", "Kuijjer",
-			email = "marieke.kuijjer@ncmm.uio.no", role = "aut"),
+			email = "marieke.kuijjer@ncmm.uio.no", role = "aut", comment = c(ORCID = "0000-0001-6280-3130")),
 	     person("Megha", "Padi",
-			email = "mpadi@email.arizona.edu", role = "aut"),
+			email = "mpadi@email.arizona.edu", role = "aut", comment = c(ORCID = "0000-0002-3446-4562")),
 	     person("Rebekka", "Burkholz",
 			email = "rburkholz@hsph.harvard.edu",role = "aut"),
-             person("Deborah", "Weighill",
-                        email = "",role = "aut"))
-Description: PANDA (Passing Attributes between Networks for Data Assimilation) is a message-passing algorithm to reconstruct gene regulatory network. It integrates multiple sources of biological data, including protein-protein interaction data, gene expression data, and sequence motif information to reconstruct genome-wide, condition-specific regulatory networks.[(Glass et al. 2013)]. LIONESS(Linear Interpolation to Obtain Network Estimates for Single Samples) is a method to estimate sample-specific regulatory networks by applying linear interpolation to the predictions made by existing aggregate network inference approaches. CONDOR(COmplex Network Description Of Regulators)is a bipartite community structure analysis tool of biological networks, especially eQTL networks, including a method for scoring nodes based on their modularity contribution.[(Platig et al. 2016). ALPACA(ALtered Partitions Across Community Architectures) is a method for comparing two genome-scale networks derived from different phenotypic states to identify condition-specific modules.[(Padi and Quackenbush 2018)]. This package integrates pypanda--the Python implementation of PANDA and LIONESS(https://github.com/davidvi/pypanda),the R implementation of CONDOR(https://github.com/jplatig/condor) and the R implementation of ALPACA (https://github.com/meghapadi/ALPACA) into one workflow. Each tool can be call in this package by one function, and the relevant output could be accessible in current R session for downstream analysis. 
+         person("Des", "Weighill",
+                        email = "",role = "aut", comment = c(ORCID = "0000-0003-4979-5871")),
+		 person("Kate", "Shutta",
+                        email = "",role = "ctb", comment = c(ORCID = "0000-0003-0402-3771")))
+Maintainer: Marouen Ben Guebila <benguebila@hsph.harvard.edu>
+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 (>= 4.1.0),
    	 igraph,
 	 reticulate,
@@ -73,3 +77,4 @@ VignetteEngine: knitr
 VignetteBuilder: knitr
 RoxygenNote: 7.1.2
 BugReports: https://github.com/netZoo/netZooR/issues
+URL: https://github.com/netZoo/netZooR, https://netzoo.github.io/

NAMESPACE

@@ -31,6 +31,7 @@ export(monsterTransitionNetworkPlot)
 export(monsterTransitionPCAPlot)
 export(monsterdTFIPlot)
 export(otter)
+export(pandaDiffEdges)
 export(pandaPy)
 export(pandaToAlpaca)
 export(pandaToCondorObject)

NEWS.md

@@ -0,0 +1,9 @@
+CHANGES IN VERSION 1.1.12
+--------------------------
+
+    o Reactivated unit tests for Ubuntu GitHub actions.
+    o LIONESS can now build single-sample coexpression networks using @kshutta's implementation
+    o Fix for ALPACA singleton community case (detected by @talkhanz)
+    o Fix for CRANE significance test on constant modularity scores (detected by @talkhanz)
+    o Improved method description by @kshutta
+    o Fix for PANDA edge case when only expression is provided

R/LIONESS.R

@@ -1,7 +1,7 @@
 #' Run python implementation of LIONESS
 #'
 #' \strong{LIONESS}(Linear Interpolation to Obtain Network Estimates for Single Samples) is a method to estimate sample-specific regulatory networks.
-#'  \href{https://arxiv.org/abs/1505.06440}{[(LIONESS arxiv paper)])}.
+#'  \href{https://pubmed.ncbi.nlm.nih.gov/30981959/}{[(LIONESS publication)])}.
 #'
 #' @param expr_file Character string indicating the file path of expression values file, with each gene(in rows) across samples(in columns).
 #' @param motif_file An optional character string indicating the file path of a prior transcription factor binding motifs dataset.
@@ -46,13 +46,17 @@
 lionessPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu", precision="double", save_tmp=TRUE, modeProcess="union", remove_missing=FALSE, start_sample=1, end_sample="None", save_single_network=FALSE, save_dir="lioness_output", save_fmt='npy'){
 
   if(missing(expr_file)){
-    stop("Please provide the gene expression value with option e, e.g. e=\"expression.txt\"") }
-  else{ expr.str <- paste("\'", expr_file, "\'", sep = '') }
+    stop("Please provide the gene expression value with option e, e.g. e=\"expression.txt\"") 
+  }else{ 
+    expr.str <- paste("\'", expr_file, "\'", sep = '') 
+  }
 
   if(is.null(motif_file)){
     motif.str <- 'None'
-    message("Prior motif network is not provided, analysis continues with Pearson correlation matrix.") }
-  else{ motif.str <- paste("\'", motif_file,"\'", sep = '') }
+    message("Prior motif network is not provided, analysis continues with Pearson correlation matrix.") 
+  }else{ 
+    motif.str <- paste("\'", motif_file,"\'", sep = '') 
+  }
 
   if(is.null(ppi_file)){
     ppi.str <- 'None'
@@ -112,7 +116,7 @@ lionessPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu"
    panda_net <- py$panda_network
 
    # re-assign data type of cloumn.
-   panda_net$tf <- as.character(panda_net$tf)
+   panda_net$tf   <- as.character(panda_net$tf)
    panda_net$gene <- as.character(panda_net$gene)
 
    # rename first two columns
@@ -128,8 +132,10 @@ lionessPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu"
    # create an instance named "lioness_obj" of Lioness Class.
    # when save_single_network = TRUE
    if(save_single_network==TRUE){
-   py_run_string(paste("lioness_obj = Lioness(panda_obj", " , " , "computing='", computing, "' , ","start=", start_sample," , ", "end=" ,end_sample, " , " ,'save_single_network= True', " , ", "save_dir='", save_dir, "' , " , "save_fmt='" , save_fmt, "' )",sep = "" ))
-   } else {py_run_string(paste("lioness_obj = Lioness(panda_obj", " , " , "computing='", computing, "' , ","start=", start_sample," , ", "end=" ,end_sample,  ")",sep = "" ))}
+     py_run_string(paste("lioness_obj = Lioness(panda_obj", " , " , "computing='", computing, "' , ","start=", start_sample," , ", "end=" ,end_sample, " , ", "save_dir='", save_dir, "' , " , "save_fmt='" , save_fmt, "' )",sep = "" ))
+   }else{
+     py_run_string(paste("lioness_obj = Lioness(panda_obj", " , " , "computing='", computing, "' , ","start=", start_sample," , ", "end=" ,end_sample,  ")",sep = "" ))
+  }
 
    # retrieve the "total_lioness_network" attribute of instance "lionesss_obj"
    py_run_string("lioness_network = lioness_obj.export_lioness_results",local = FALSE, convert = TRUE)

R/PANDA.R

@@ -65,7 +65,7 @@
 #'
 
 
-pandaPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu", precision="double",save_memory=FALSE, save_tmp=TRUE, keep_expression_matrix=FALSE, modeProcess="union", remove_missing=FALSE){
+pandaPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu", precision="double",save_memory=FALSE, save_tmp=TRUE, keep_expression_matrix=FALSE, modeProcess="union", remove_missing=FALSE, with_header=FALSE){
 
   if(missing(expr_file)){
     stop("Please provide the path of gene expression data file to 'expr_file' variable") }
@@ -106,6 +106,13 @@ pandaPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu",
     keepexpression.str <- "keep_expression_matrix=True"
   } else{ keepexpression.str <- "keep_expression_matrix=False" }
 
+  # with header option
+  if(with_header==FALSE){
+    withheader.str <- "with_header=False"
+  }else if (with_header==TRUE){
+    withheader.str <- "with_header=True"   
+  }
+
   # when pre-processing mode is legacy
   if(modeProcess == "legacy"){
 
@@ -130,7 +137,9 @@ pandaPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu",
   reticulate::source_python(pandapath,convert = TRUE)
 
   # invoke Python script to create a Panda object
-  obj.str <-  paste("panda_obj=Panda(", expr.str, ",", motif.str,",", ppi.str, ",", computing.str, ",", precision.str, ",", savememory.str, ",", savetmp.str, "," , keepexpression.str, ",",  mode.str, ")", sep ='')
+  obj.str <-  paste("panda_obj=Panda(", expr.str, ",", motif.str,",", ppi.str, ",", 
+                    computing.str, ",", precision.str, ",", savememory.str, ",", savetmp.str, "," , 
+                    keepexpression.str, ",",  mode.str, "," , withheader.str, ")", sep ='')
 
   # run Python code
   py_run_string(obj.str)
@@ -144,12 +153,21 @@ pandaPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu",
     # re-assign data type
     panda_net$tf <- as.character(panda_net$tf)
     panda_net$gene <- as.character(panda_net$gene)
-    panda_net$motif <- as.numeric(panda_net$motif)
+    if("motif" %in% names(panda_net)){
+      panda_net$motif <- as.numeric(panda_net$motif)
+    }
     panda_net$force <- as.numeric(panda_net$force)
-    # adjust column order
-    panda_net <- panda_net[,c("tf","gene","motif","force")]
-    # rename the PANDA output colnames
-    colnames(panda_net) <- c("TF","Gene","Motif","Score")
+    if("motif" %in% names(panda_net)){
+      # adjust column order
+      panda_net <- panda_net[,c("tf","gene","motif","force")]
+      # rename the PANDA output colnames
+      colnames(panda_net) <- c("TF","Gene","Motif","Score")
+    }else{
+      # adjust column order
+      panda_net <- panda_net[,c("tf","gene","force")]
+      # rename the PANDA output colnames
+      colnames(panda_net) <- c("TF","Gene","Score")
+    }
 
 
     # in-degree of panda network

R/pandaDiffEdges.R

@@ -1,4 +1,3 @@
-
 #' Identify differential edges in two PANDA networks
 #'
 #'To determine the probability that an edge is "different" between the networks, 
@@ -14,7 +13,6 @@
 #' @return a data.frame with five columns: tf, gene, motif, Score and defined condition name(the row with "T" in this column means this egde belongs to first condition or phenotype,
 #' "F" means this edge belongs to the second condition or phenotype)
 #' @examples 
-#' 
 #' # refer to four input datasets files in inst/extdat
 #' treated_expression_file_path <- system.file("extdata", "expr4_matched.txt", 
 #' package = "netZooR", mustWork = TRUE)
@@ -38,6 +36,7 @@
 #' 
 #' @export
 #'
+
 pandaDiffEdges <- function(panda.net1, panda.net2, threshold=0.8, condition_name="cond.1"){
 
   # reshape two PANDA networks