1.6.2 (#339)

* Modified the LIONESS R code to disallow PANDA inference unless either a PPI or motif are provided * add mode parameter to lioness (#336) * update maintainer * update maintainer * update maintainer * update maintainer (#337) * update maintainer * update maintainer * Update ALPACA.R * update sambar (#338) --------- Co-authored-by: Tara Eicher <[email protected]>
netZoo · Jan 31, 2025 · bab4685 · bab4685
1 parent 9dd9438
commit bab4685
Show file tree

Hide file tree

Showing 7 changed files with 31 additions and 11 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: netZooR
 Type: Package
 Title: Unified methods for the inference and analysis of gene regulatory networks
-Version: 1.6.0
-Date: 2024-07-26
+Version: 1.6.1
+Date: 2024-11-26
 Authors@R: c(person("Tara", "Eicher",
                         email = "[email protected]", role = c("aut","cre"), comment = c(ORCID = "0000-0003-1809-4458")),
              person("Marouen", "Ben Guebila",
@@ -23,7 +23,6 @@ Authors@R: c(person("Tara", "Eicher",
                         email = "",role = "aut", comment = c(ORCID = "0000-0002-8042-7201")),
              person("Kate", "Shutta",
                         email = "",role = "aut", comment = c(ORCID = "0000-0003-0402-3771")))
-Maintainer: Tara Eicher <[email protected]>
 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,

diff --git a/NAMESPACE b/NAMESPACE
@@ -9,6 +9,7 @@ export(adj2regulon)
 export(alpaca)
 export(alpacaCrane)
 export(alpacaExtractTopGenes)
+export(alpacaListToGo)
 export(annotateFromBiomart)
 export(checkMisAnnotation)
 export(checkTissuesToMerge)
@@ -62,11 +63,14 @@ export(priorPp)
 export(puma)
 export(runEgret)
 export(sambar)
+export(sambarConvertgmt)
+export(sambarCorgenelength)
 export(sourcePPI)
 export(spider)
 export(tiger)
 export(visPandaInCytoscape)
 import(AnnotationDbi, except= select)
+import(AnnotationDbi, except= select)
 
 import(GO.db)
 import(GOstats, except= makeGOGraph)

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,10 @@
+CHANGES IN VERSION 1.6.1
+--------------------------
+
+    - Update: MONSTER has a wrapper function to process input
+    - Update: LIONESS can use new data merging strategies ('union','intersection','legacy') as opposed to union by default
+
+
 CHANGES IN VERSION 1.6.0
 --------------------------
 

diff --git a/R/ALPACA.R b/R/ALPACA.R
@@ -476,7 +476,7 @@ alpacaNodeToGene <- function(x){strsplit(x,split="_")[[1]][1]}
 #' @rawNamespace import(GOstats, except= makeGOGraph)
 #' @import org.Hs.eg.db
 #' @rawNamespace import(AnnotationDbi, except= select)
-#' 
+#' @export
 
 alpacaListToGo <- function(gene.list,univ.vec,comm.nums){
 

diff --git a/R/LIONESS.R b/R/LIONESS.R
@@ -164,6 +164,7 @@ lionessPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu"
 #' Options include "pearson". 
 #' @param ncores int specifying the number of cores to be used. Default is 1. 
 #' (Note: constructing panda networks can be memory-intensive, and the number of cores should take into consideration available memory.)
+#' @param union Aggregation mode between three input networks: Union (default), intersection, legacy (maps on motif network).
 #' @param ... additional arguments for panda analysis
 #' @keywords keywords
 #' @importFrom matrixStats rowSds
@@ -186,19 +187,25 @@ lionessPy <- function(expr_file, motif_file=NULL, ppi_file=NULL, computing="cpu"
 #' Kuijjer, M.L., Tung, M., Yuan, G., Quackenbush, J. and Glass, K., 2015. 
 #' Estimating sample-specific regulatory networks. arXiv preprint arXiv:1505.06440.
 #' Kuijjer, M.L., Hsieh, PH., Quackenbush, J. et al. lionessR: single sample network inference in R. BMC Cancer 19, 1003 (2019). https://doi.org/10.1186/s12885-019-6235-7
-lioness = function(expr, motif = NULL, ppi = NULL, network.inference.method = "panda", ncores = 1, ...){
+lioness = function(expr, motif = NULL, ppi = NULL, network.inference.method = "panda", ncores = 1, mode = "union", ...){
+
+  # If both the PPI and motif are NULL, default to Pearson instead of PANDA.
+  if(is.null(motif) && is.null(ppi) && network.inference.method == "panda"){
+    message("Because input has neither a motif nor a PPI, we are defaulting to Pearson inference.")
+    network.inference.method = "pearson"
+  }
   N <- ncol(expr)
   if(ncores < 1){
     print('Setting number of cores to 1.')
     ncores <- 1
   }
   if(network.inference.method == "panda")
   {
-    fullnet <- panda(motif, expr, ppi, ...)
+    fullnet <- panda(motif, expr, ppi, mode = mode, ...)
     return(mclapply(seq_len(N), function(i) {
       print(paste("Computing network for sample ", i))
       N * fullnet@regNet - (N - 1) * panda(motif, expr[, -i], 
-                                           ppi, ...)@regNet
+                                           ppi, mode = mode, ...)@regNet
     }, mc.cores = ncores))
   }
   if(network.inference.method == "pearson")

diff --git a/R/SAMBAR.R b/R/SAMBAR.R
@@ -2,9 +2,8 @@
 #' @param signature A file containing gene sets (signatures) in .gmt format. These gene sets will be used to de-sparsify the gene-level mutation scores.
 #' @param cagenes A vector of genes, for example of cancer-associated genes. This will be used to subset the gene-level mutation data to.
 #' @return A matrix containing gene set mutation scores.
-#
-# OBS! cagenes should be optional
-# dependencies: utils
+#' @export
+#' 
 sambarConvertgmt <- function(signature, cagenes){
 
   # determine the maximum number of genes a signature can have in the .gmt file
@@ -43,7 +42,8 @@ sambarConvertgmt <- function(signature, cagenes){
 #' @param cagenes A vector of genes, for example of cancer-associated genes. This will be used to subset the gene-level mutation data to.
 #' @param exonsize A vector of gene lengths. This will be used to normalize the gene mutation scores.
 #' @return Mutation rate-adjusted gene mutation scores.
-#
+#' @export
+#' 
 sambarCorgenelength <- function(x, cagenes, exonsize){
 
   # subset mutation data to cancer-associated genes

diff --git a/man/lioness.Rd b/man/lioness.Rd