netZooR 1.0.11 (#249)

* add bioc information * update website * add crane and docs * update crane * update worflow * update crane * update workflows * update workflows * update workfolw * update workfolw * update workfolw * update workfolw * Update main.yml * Update main.yml * Update main.yml * fix lioness py * udpate lioness in R * include calculations python * update panda rm missing * update panda * update lioness joblib * revert commits * ALPACA fix to NAs in community assignement * version bump * revert lioness * update crane with alpaca changes * update lioness * update lioness python * fix test * update workflows * put back github actions * Fixed typo * Added LIONESS-pearson option + unit test * changed param labels in LIONESS example * updated docs for lioness() function * Update main.yml * Update main.yml * Update DESCRIPTION * fix crane issue #240 * expanded PANDA and LIONESS description * update crane fix * added ALPACA, EGRET, and OTTER descriptions * Update README.md * typo in na.rm * update workflow * update workflow2 * fix-actions-3 * add r lib v2 * add r lib v2 * update condor test * update condor test * update condor test * update condor test * show testthat output * add pandoc and use cache * use built in check * use built in check * update actions with built in check * bump version * use built in coverage * use built in coverage * remove sudo * update actions * update actions * removed sudo from actions * ugrade to R42 * remove virtualenv * remove virtualenv * remove virtualenv * modify condor test * update condor test * update condor test * adding retiucualte to covr * adding retiucualte to covr * add panda test to coverignore * update actions * remove lioness tests from coverage * remove lioness tests from coverage * added MONSTER and SAMBAR * remove lionessR test * Added CONDOR and YARN * Update README.md * put back otter in rbuild * remove condor test * remove condor test * remove lioness docs * add lioness to buildingore * donttest lionesss * remove coverage from ubuntu test * remove rbuilignore * update rbuildignore * update rbuildignore * update rbuildignore * update rbuildignore * update rbuildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * add back buildignore * put back tests * add padanedge diff test * add back egeret test * add monster test * fix monster test * tolerance in expect equal * tolerance in expect equal * tolerance in expect equal * tolerance in expect equal * add sourceppi * fixed PANDA tests * modify panda test * update lioness test * fix expect message * update tests * update tests * update tests * update tests * update tests * update tests * reduced lioness test data * reduced lioness test data * reduced lioness test data * reduced lioness test data * reduce test size Co-authored-by: Kate Hoff Shutta <kshutta@umass.edu> Co-authored-by: katehoffshutta <43797774+katehoffshutta@users.noreply.github.com>
netZoo · Jul 7, 2022 · 417c16c · 417c16c
1 parent 57a24ca
commit 417c16c
Show file tree

Hide file tree

Showing 146 changed files with 7,138 additions and 19,287 deletions.
diff --git a/.Rbuildignore b/.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
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -29,59 +29,52 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest]
-        r-version: [4.1]
+        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
-        run: |
-            La_library()
-            extSoftVersion()["BLAS"]
-            install.packages('reticulate', repos = "http://cran.us.r-project.org")
-            library('reticulate')
-        shell: Rscript {0}
-      - name: Install reticulate 2
+
+      - 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 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")
-        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')
-            use_condaenv("r-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
+        if: matrix.os == 'macos-latest'
         run: |
-            library('reticulate')
-            use_condaenv("r-reticulate")
-            py_config()            
             covr::codecov()
-        shell: sudo -E Rscript {0}
-
+        shell: Rscript {0}
diff --git a/.gitignore b/.gitignore
@@ -1,7 +1,6 @@
 .DS_Store
 .Rhistory
 Untitled.R
-.Rbuildignore
 inst/doc/
 doc
 Meta
@@ -32,3 +31,6 @@ tests/testthat/*.txt
 tests/testthat/*.vcf
 /doc/
 /Meta/
+vignettes/*.npy
+docs/*.npy
+docs/reference/*.npy
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,22 +1,22 @@
 Package: netZooR
-Title: Integrate methods: PANDA, LIONESS, CONDOR, ALPACA, SAMBAR, MONSTER, OTTER, EGRET, and YARN into one workflow
-Version: 0.99.85
-Date: 2021-09-20
-Authors@R: c(person("Tian", "Wang",
+Title: netZooR integrates tools for the inference and analysis of gene regulatory networks
+Version: 1.0.11
+Date: 2022-06-20
+Authors@R: c(person("Marouen", "Ben Guebila",
+			email = "benguebila@hsph.harvard.edu", role = c("aut","cre")),
+	     person("Tian", "Wang", 
 			email = "tian.wang@bc.edu", role = c("aut")),
-	     person("Marouen", "Ben Guebila", 
-			email = "marouen.b.guebila@gmail.com", role = c("aut","cre")),
 	     person("John", "Platig",
 			email="john.platig@channing.harvard.edu",role="aut"),
 	     person("Marieke", "Kuijjer",
 			email = "marieke.kuijjer@ncmm.uio.no", role = "aut"),
-	     person("Magha", "Padi",
+	     person("Megha", "Padi",
 			email = "mpadi@email.arizona.edu", role = "aut"),
 	     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 model to reconstruction 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. 
+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. 
 Depends: R (>= 4.1.0),
    	 igraph,
 	 reticulate,

diff --git a/NAMESPACE b/NAMESPACE
@@ -1,6 +1,7 @@
 # Generated by roxygen2: do not edit by hand
 
 export(alpaca)
+export(alpacaCrane)
 export(alpacaExtractTopGenes)
 export(condorCluster)
 export(condorCoreEnrich)
@@ -9,8 +10,11 @@ export(condorModularityMax)
 export(condorPlotCommunities)
 export(condorPlotHeatmap)
 export(condorQscore)
+export(craneBipartite)
+export(craneUnipartite)
 export(createCondorObject)
 export(createPandaStyle)
+export(elistToAdjMat)
 export(lioness)
 export(lionessPy)
 export(monster)

diff --git a/R/ALPACA.R b/R/ALPACA.R
@@ -68,32 +68,29 @@ alpaca <- function(net.table,file.stem,verbose=FALSE)
     print("Computing node scores...")
     louv.Ascores <- NULL
     louv.Bscores <- NULL
+    louv.Anames <- NULL
+    louv.Bnames <- NULL
     for (i in seq_len(max(louv.memb)))
     {
-      print(i)
+        print(i)
         this.comm <- names(louv.memb)[louv.memb==i]
         this.tfs <- this.comm[grep("_A$",this.comm)]
         this.genes <- this.comm[grep("_B$",this.comm)]
-    if (length(this.tfs)>=1){
-        if (length(this.tfs)>1){
-            if (length(this.genes)==1){
-                gene.sums <- sum(dwbm[this.tfs,this.genes])
-                tf.sums <- dwbm[this.tfs,this.genes]
-            }else if (length(this.genes)>1){
-                tf.sums <- apply(dwbm[this.tfs,this.genes],1,sum)
-                gene.sums <- apply(dwbm[this.tfs,this.genes],2,sum)
-            }
-        } else if (length(this.tfs)==1) {
-            tf.sums <- sum(dwbm[this.tfs,this.genes])
-            gene.sums <- dwbm[this.tfs,this.genes]
-        }
-      this.denom <- sum(dwbm[this.tfs,this.genes])
-      louv.Ascores <- c(louv.Ascores,tf.sums/this.denom)
-      louv.Bscores <- c(louv.Bscores,gene.sums/this.denom)
+        if (length(this.tfs)>0 && length(this.genes)>0)
+        {
+          dwbm.submat <- array(dwbm[this.tfs,this.genes],dim=c(length(this.tfs),length(this.genes)))
+          tf.sums <- apply(dwbm.submat,1,sum)
+          gene.sums <- apply(dwbm.submat,2,sum)
+          this.denom <- sum(dwbm[this.tfs,this.genes])
+          louv.Ascores <- c(louv.Ascores,tf.sums/this.denom)
+          louv.Bscores <- c(louv.Bscores,gene.sums/this.denom)
+          louv.Anames <- c(louv.Anames,this.tfs)
+          louv.Bnames <- c(louv.Bnames,this.genes)
         }
     }
 
     louv.scores <- c(louv.Ascores,louv.Bscores)
+    names(louv.scores) <- c(louv.Anames,louv.Bnames)
 
     if (!is.null(file.stem)) {
         write.table(cbind(names(louv.memb), as.vector(louv.memb)),paste(c(file.stem,"_ALPACA_final_memb.txt"),collapse=""),col.names=FALSE,row.names=FALSE,quote=FALSE,sep="\t")