@@ -4,10 +4,10 @@

 #' @param pathwayFile (char) path to file with pathway annotations.

 #' @param header (logical) whether \code{pathwayFile} has a header

 #'     (default FALSE).

-#' @param pathwayCol (char) column name with pathway identifiers.

-#'     For use with non-GMT input files (eg "Pathway.ID"; default NULL).

-#' @param geneCol (char) column name with gene identifiers.

-#'     For use with non-GMT input files (eg "Gene.ID"; default NULL).

+#' @param pathCol (char or int) column name or number with pathway identifiers.

+#'     For use with non-GMT input files (eg "Pathway.ID" or 2; default NULL).

+#' @param geneCol (char or int) column name or number with gene identifiers.

+#'     For use with non-GMT input files (eg "Gene.ID" or 5; default NULL).

 #' @param minGene (integer) minimum number of genes to be considered

 #'     in a pathway (default 1).

 #' @param maxGene (integer) maximum number of genes to be considered

@@ -22,7 +22,7 @@

 #' )

 #' pathways <- readPathways(

 #'     system.file("extdata", "SAFE_terms.xlsx", package = "FEDUP"),

-#'     header = TRUE, pathwayCol = "Enriched.GO.names", geneCol = "Gene.ID"

+#'     header = TRUE, pathCol = "Enriched.GO.names", geneCol = "Gene.ID"

 #' )

 #' @importFrom openxlsx read.xlsx

 #' @importFrom tibble deframe

@@ -30,8 +30,7 @@

 #' @importFrom utils head read.delim tail

 #' @export

 readPathways <- function(pathwayFile, header = FALSE,

-    pathwayCol = NULL, geneCol = NULL,

-    minGene = 1L, maxGene = Inf) {

+    pathCol = NULL, geneCol = NULL, minGene = 1L, maxGene = Inf) {

     s <- c("gmt", "txt", "xlsx")

     f <- sub(".*\\.", "", pathwayFile)

     if (!f %in% s) {

@@ -41,31 +40,32 @@ readPathways <- function(pathwayFile, header = FALSE,

         ))

     }

     if (f == "gmt") {

-        pathway_in <- strsplit(readLines(pathwayFile), "\t")

+        path_in <- strsplit(readLines(pathwayFile), "\t")

         if (header) {

-            pathway_in <- pathway_in[-1]

+            path_in <- path_in[-1]

         }

-        pathways <- lapply(pathway_in, tail, -2)

-        names(pathways) <- vapply(pathway_in, head, n = 1, character(1))

+        pathways <- lapply(path_in, tail, -2)

+        names(pathways) <- vapply(path_in, head, n = 1, character(1))

     } else {

         if (f == "xlsx") {

-            pathway_in <- read.xlsx(pathwayFile)

-        } else if (f == "txt") {

-            pathway_in <- read.delim(pathwayFile, header = header)

+            path_in <- read.xlsx(pathwayFile)

         }

-        if (missing(pathwayCol) || !pathwayCol %in% colnames(pathway_in)) {

-            stop("Pathway ID column (", pathwayCol, ") not in file")

-        } else if (missing(geneCol) || !geneCol %in% colnames(pathway_in)) {

+        if (f == "txt") {

+            path_in <- read.delim(pathwayFile, header = header)

+        }

+        if (!pathCol %in% names(path_in) && !pathCol %in% seq_along(path_in)) {

+            stop("Pathway ID column (", pathCol, ") not in file")

+        }

+        if (!geneCol %in% names(path_in) && !geneCol %in% seq_along(path_in)) {

             stop("Gene ID column (", geneCol, ") not in file")

-        } else {

-            pathway_df <- data.frame(

-                pathway = pathway_in[, pathwayCol], gene = pathway_in[, geneCol]

-            )

-            pathway_df[which(pathway_df$gene == ""), "gene"] <- NA

-            pathway_df <- na.omit(pathway_df)

-            pathway_df <- aggregate(gene ~ pathway, pathway_df, paste)

-            pathways <- deframe(pathway_df)

         }

+        pathway_df <- data.frame(

+            pathway = path_in[, pathCol], gene = path_in[, geneCol]

+        )

+        pathway_df[which(pathway_df$gene == ""), "gene"] <- NA

+        pathway_df <- na.omit(pathway_df)

+        pathway_df <- aggregate(gene ~ pathway, pathway_df, paste)

+        pathways <- deframe(pathway_df)

     }

     size <- lapply(pathways, length)

     pathways_s <- pathways[which(size >= minGene & size <= maxGene)]

@@ -1,6 +1,6 @@

 ## code to prepare `testGene` and `backgroundGene` datasets goes here

-pathway_file <- system.file("extdata", "Human_Reactome_November_17_2020_symbol.gmt", package = "FEDUP")

-pathwaysGMT <- readPathways(pathway_file, MIN_GENE = 10, MAX_GENE = 500)

+pathwayFile <- system.file("extdata", "Human_Reactome_November_17_2020_symbol.gmt", package = "FEDUP")

+pathwaysGMT <- readPathways(pathwayFile, minGene = 10, maxGene = 500)

 testGene <- pathwaysGMT[[grep("397014", names(pathwaysGMT))]] # Reactome muscle contraction pathway

 backgroundGene <- unique(unlist(pathwaysGMT))

@@ -1,5 +1,5 @@

 ## code to prepare `pathwaysGMT` dataset goes here

-pathway_file <- system.file("extdata", "Human_Reactome_November_17_2020_symbol.gmt", package = "FEDUP")

-pathwaysGMT <- readPathways(pathway_file, MIN_GENE = 10, MAX_GENE = 500)

+pathwayFile <- system.file("extdata", "Human_Reactome_November_17_2020_symbol.gmt", package = "FEDUP")

+pathwaysGMT <- readPathways(pathwayFile, minGene = 10, maxGene = 500)

 names(pathwaysGMT) <- stringi::stri_trans_general(names(pathwaysGMT), "latin-ascii")

 usethis::use_data(pathwaysGMT, compress = "xz", version = 2, overwrite = TRUE)

@@ -1,12 +1,12 @@

 ## code to prepare `pathwaysXLSX` dataset goes here

 library(tibble)

-pathway_file <- system.file("extdata", "SAFE_terms.txt", package = "FEDUP")

+pathwayFile <- system.file("extdata", "SAFE_terms.txt", package = "FEDUP")

 pathwaysTXT <- readPathways(

-    pathway_file,

+    pathwayFile,

     header = TRUE,

-    pathway_col = "Enriched.GO.names",

-    gene_col = "Gene.ID"

+    pathCol = "Enriched.GO.names",

+    geneCol = "Gene.ID"

 )

 names(pathwaysTXT) <- stringi::stri_trans_general(names(pathwaysTXT), "latin-ascii")

@@ -2,12 +2,12 @@

 library(openxlsx)

 library(tibble)

-pathway_file <- system.file("extdata", "SAFE_terms.xlsx", package = "FEDUP")

+pathwayFile <- system.file("extdata", "SAFE_terms.xlsx", package = "FEDUP")

 pathwaysXLSX <- readPathways(

-    pathway_file,

+    pathwayFile,

     header = TRUE,

-    pathway_col = "Enriched.GO.names",

-    gene_col = "Gene.ID"

+    pathCol = "Enriched.GO.names",

+    geneCol = "Gene.ID"

 )

 names(pathwaysXLSX) <- stringi::stri_trans_general(names(pathwaysXLSX), "latin-ascii")

@@ -8,7 +8,7 @@ Currently supports the following file format: gmt, txt, xlsx.}

 readPathways(

   pathwayFile,

   header = FALSE,

-  pathwayCol = NULL,

+  pathCol = NULL,

   geneCol = NULL,

   minGene = 1L,

   maxGene = Inf

@@ -20,11 +20,11 @@ readPathways(

 \item{header}{(logical) whether \code{pathwayFile} has a header

 (default FALSE).}

-\item{pathwayCol}{(char) column name with pathway identifiers.

-For use with non-GMT input files (eg "Pathway.ID"; default NULL).}

+\item{pathCol}{(char or int) column name or number with pathway identifiers.

+For use with non-GMT input files (eg "Pathway.ID" or 2; default NULL).}

-\item{geneCol}{(char) column name with gene identifiers.

-For use with non-GMT input files (eg "Gene.ID"; default NULL).}

+\item{geneCol}{(char or int) column name or number with gene identifiers.

+For use with non-GMT input files (eg "Gene.ID" or 5; default NULL).}

 \item{minGene}{(integer) minimum number of genes to be considered

 in a pathway (default 1).}

@@ -48,6 +48,6 @@ pathways <- readPathways(

 )

 pathways <- readPathways(

     system.file("extdata", "SAFE_terms.xlsx", package = "FEDUP"),

-    header = TRUE, pathwayCol = "Enriched.GO.names", geneCol = "Gene.ID"

+    header = TRUE, pathCol = "Enriched.GO.names", geneCol = "Gene.ID"

 )

 }

@@ -8,17 +8,17 @@ test_that("Test that readPathways stops without proper inputs", {

     expect_error(readPathways(

         pathwayFile,

         header = TRUE,

-        pathwayCol = "Enriched.GO.names", geneCol = "oops"

+        pathCol = "Enriched.GO.names", geneCol = "oops"

     ))

     expect_error(readPathways(

         pathwayFile,

         header = TRUE,

-        pathwayCol = "oops", geneCol = "Gene.ID"

+        pathCol = "oops", geneCol = "Gene.ID"

     ))

     expect_error(readPathways(

         pathwayFile,

         header = TRUE, minGene = 500,

-        pathwayCol = "Enriched.GO.names", geneCol = "Gene.ID"

+        pathCol = "Enriched.GO.names", geneCol = "Gene.ID"

     ))

 })

@@ -43,7 +43,7 @@ test_that("Test that readPathways works with XLSX input", {

     pathways <- readPathways(

         pathwayFile,

         header = TRUE,

-        pathwayCol = "Enriched.GO.names", geneCol = "Gene.ID"

+        pathCol = "Enriched.GO.names", geneCol = "Gene.ID"

     )

     expect_true(is.list(pathways))

     expect_equal(length(pathways), 30)

@@ -58,7 +58,7 @@ test_that("Test that readPathways works with TXT input", {

     pathways <- readPathways(

         pathwayFile,

         header = TRUE,

-        pathwayCol = "Enriched.GO.names", geneCol = "Gene.ID"

+        pathCol = "Enriched.GO.names", geneCol = "Gene.ID"

     )

     expect_true(is.list(pathways))

     expect_equal(length(pathways), 30)