@@ -2,6 +2,7 @@

 export(plotDotPlot)

 export(plotFemap)

+export(prepInput)

 export(readPathways)

 export(runFedup)

 export(writeFemap)

deleted file mode 100644

@@ -1,17 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/data.R

-\docType{data}

-\name{backgroundGene}

-\alias{backgroundGene}

-\title{Example vector of human genes to use as background set for enrichment.}

-\format{

-a character vector with 10208 elements (gene IDs)

-}

-\usage{

-data(backgroundGene)

-}

-\description{

-Script to generate data

-system.file("data-raw", "genes.R", package = "fedup")

-}

-\keyword{datasets}

new file mode 100644

@@ -0,0 +1,23 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/data.R

+\docType{data}

+\name{geneDouble}

+\alias{geneDouble}

+\title{Example list of a background set and two sets of test genes to use for

+enrichment analysis.}

+\format{

+a named list with three vector elements, one common background

+gene vector and two test gene vectors.

+}

+\usage{

+data(geneDouble)

+}

+\description{

+Raw Excel data file (Sup Tab 2) is available from

+\url{https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7566881/}

+}

+\details{

+Script to prepare data

+system.file("inst", "script", "genes.R", package = "fedup")

+}

+\keyword{datasets}

new file mode 100644

@@ -0,0 +1,23 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/data.R

+\docType{data}

+\name{geneMulti}

+\alias{geneMulti}

+\title{Example list of a background set and multiple sets of test genes

+to use for enrichment analysis.}

+\format{

+a named list with thirteen vector elements, one common background

+gene vector and twelve test gene vectors.

+}

+\usage{

+data(geneMulti)

+}

+\description{

+Raw Excel data file (Sup Tab 2) is available from

+\url{https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7566881/}

+}

+\details{

+Script to prepare data

+system.file("inst", "script", "genes.R", package = "fedup")

+}

+\keyword{datasets}

new file mode 100644

@@ -0,0 +1,23 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/data.R

+\docType{data}

+\name{geneSingle}

+\alias{geneSingle}

+\title{Example list of a background set and single set of test genes to use for

+enrichment analysis.}

+\format{

+a named list with two vector elements, one common background

+gene vector and one test gene vector.

+}

+\usage{

+data(geneSingle)

+}

+\description{

+Raw Excel data file (Sup Tab 2) is available from

+\url{https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7566881/}

+}

+\details{

+Script to prepare data

+system.file("inst", "script", "genes.R", package = "fedup")

+}

+\keyword{datasets}

@@ -11,7 +11,7 @@ a named list of 1437 vectors

 data(pathwaysGMT)

 }

 \description{

-Raw GMT file is available from

+GMT file is available from

 \url{http://download.baderlab.org/EM_Genesets/November_17_2020/Human/symbol}

 }

 \details{

@@ -11,7 +11,7 @@ a named list of 317 vectors

 data(pathwaysTXT)

 }

 \description{

-Raw Excel data file (S5) is available from

+Raw data file (S5) is available from

 \url{https://boonelab.ccbr.utoronto.ca/supplement/costanzo2016/}

 }

 \details{

@@ -11,7 +11,7 @@ a named list of 317 vectors

 data(pathwaysXLSX)

 }

 \description{

-Raw Excel data file (S5) is available from

+Raw data file (S5) is available from

 \url{https://boonelab.ccbr.utoronto.ca/supplement/costanzo2016/}

 }

 \details{

@@ -2,7 +2,7 @@

 % Please edit documentation in R/plot.R

 \name{plotDotPlot}

 \alias{plotDotPlot}

-\title{Visualizes pathway enrichment and depletion using ggplot.}

+\title{Visualizes fedup enrichment and depletion results using ggplot.}

 \usage{

 plotDotPlot(

     df,

@@ -19,49 +19,61 @@ plotDotPlot(

 )

 }

 \arguments{

-\item{df}{(data.frame) table with fedup enrichment results to plot.}

+\item{df}{(data.frame) table with fedup results generated via

+\link[fedup]{runFedup}}

-\item{xVar}{(char) x-axis variable (must be a column value in \code{df}).}

+\item{xVar}{(char) x-axis variable (must be a column value in \code{df})}

-\item{yVar}{(char) y-axis variable (must be a column value in \code{df}).}

+\item{yVar}{(char) y-axis variable (must be a column value in \code{df})}

-\item{xLab}{(char) x-axis label (default \code{xVar} value).}

+\item{xLab}{(char) x-axis label (default \code{xVar} value)}

-\item{yLab}{(char) y-axis label (default NULL).}

+\item{yLab}{(char) y-axis label (default NULL)}

-\item{pTitle}{(char) plot title (default NULL).}

+\item{pTitle}{(char) plot title (default NULL)}

-\item{fillVar}{(char) point fill variable (default NULL).}

+\item{fillVar}{(char) point fill variable (default NULL)}

-\item{fillCol}{(char) point fill colours (default NULL).}

+\item{fillCol}{(char) point fill colours (default NULL)}

-\item{fillLab}{(char) point fill label (default \code{fillVar} value).}

+\item{fillLab}{(char) point fill label (default \code{fillVar} value)}

-\item{sizeVar}{(char) point size variable (default NULL).}

+\item{sizeVar}{(char) point size variable (default NULL)}

-\item{sizeLab}{(char) point size label (default \code{sizeVar} value).}

+\item{sizeLab}{(char) point size label (default \code{sizeVar} value)}

 }

 \value{

-object returned from ggplot with the enrichment dot plot.

+Object returned from ggplot with the enrichment dot plot.

 }

 \description{

-Visualizes pathway enrichment and depletion using ggplot.

+This function supports any combination of numeric x-y variables

+to plot from fedup results. The list outputted by \link[fedup]{runFedup}

+must first be converted to a data.frame before plotting (see examples for

+sample use).

 }

 \examples{

-data(testGene)

-data(backgroundGene)

+data(geneDouble)

 data(pathwaysGMT)

-fedup_res <- runFedup(testGene, backgroundGene, pathwaysGMT)

-fedup_plot <- fedup_res[which(fedup_res$qvalue < 0.05), ]

-fedup_plot$log10qvalue <- -log10(fedup_plot$qvalue + 1e-10)

-fedup_plot$pathway <- gsub("\\\\\%.*", "", fedup_plot$pathway)

-plotDotPlot(

-    df = fedup_plot,

+suppressMessages(library(dplyr))

+suppressMessages(library(tidyr))

+fedupRes <- runFedup(geneDouble, pathwaysGMT)

+# Prepare dataframe from fedup results

+fedupPlot <- fedupRes \%>\%

+    bind_rows(.id = "set") \%>\%

+    separate(col = "set", into = c("set", "sign"), sep = "_") \%>\%

+    subset(qvalue < 0.01) \%>\%

+    mutate(log10qvalue = -log10(qvalue)) \%>\%

+    mutate(pathway = gsub("\\\\\%.*", "", pathway)) \%>\%

+    as.data.frame()

+# Plot

+p <- plotDotPlot(

+    df = fedupPlot,

     xVar = "log10qvalue",

     yVar = "pathway",

-    xLab = "-log10(Qvalue)",

-    fillVar = "status",

-    fillLab = "Enrichment\nstatus",

+    xLab = "-log10(qvalue)",

+    fillVar = "sign",

+    fillLab = "Genetic interaction",

+    fillCol = c("#0077f1", "#fcde24"),

     sizeVar = "fold_enrichment",

     sizeLab = "Fold enrichment"

 )

@@ -2,58 +2,66 @@

 % Please edit documentation in R/femap.R

 \name{plotFemap}

 \alias{plotFemap}

-\title{Draws a network representation of overlaps among enriched and depleted

-pathways using EnrichmentMap (EM) in Cytoscape.}

+\title{Draws a network representation of overlaps among pathway enrichment

+results using EnrichmentMap (EM) in Cytoscape.}

 \usage{

 plotFemap(

     gmtFile,

-    resultsFile,

+    resultsFolder,

     pvalue = 1,

     qvalue = 1,

+    chartData = "NES_VALUE",

+    hideNodeLabels = FALSE,

     netName = "generic",

     netFile = "png"

 )

 }

 \arguments{

-\item{gmtFile}{(char) path to GMT file (must be an absolute path).}

+\item{gmtFile}{(char) absolute path to GMT file (generated via

+\link[fedup]{writePathways})}

-\item{resultsFile}{(char) path to file with fedup results

-(must be an absolute path).}

+\item{resultsFolder}{(char) absolute path to folder with fedup results

+(generated via \link[fedup]{writeFemap})}

-\item{pvalue}{(numeric) pvalue cutoff. Pathways with a higher pvalue

-will not be included in the EM (value between 0 and 1; default 1).}

+\item{pvalue}{(numeric) pvalue cutoff (value between 0 and 1; default 1)}

-\item{qvalue}{(numeric) qvalue cutoff. Pathways with a higher qvalue

-will not be included in the EM (value between 0 and 1; default 1).}

+\item{qvalue}{(numeric) qvalue cutoff (value between 0 and 1; default 1)}

-\item{netName}{(char) name for EM in Cytoscape (default generic).}

+\item{chartData}{(char) node chart data (one of NES_VALUE, P_VALUE,

+FDR_VALUE, PHENOTYPES, DATA_SET, EXPRESSION_SET, or NONE;

+default = NES_VALUE)}

-\item{netFile}{(char) name of output image. Supports png, pdf, svg,

-jpeg image formats.}

+\item{hideNodeLabels}{(logical) if TRUE hides the node label in the EM;

+cluster labels generated via AutoAnnotate remain visible}

+

+\item{netName}{(char) name for EM in Cytoscape (default generic)}

+

+\item{netFile}{(char) name of output image (supports png, pdf, svg,

+jpeg image formats)}

 }

 \value{

-file name of image to which the network is exported and an open

+File name of image to which the network is exported and an open

 session of Cytoscape (side effect of plotting EM). NULL if Cytoscape

 is not running locally.

 }

 \description{

-Draws a network representation of overlaps among enriched and depleted

-pathways using EnrichmentMap (EM) in Cytoscape.

+Draws a network representation of overlaps among pathway enrichment

+results using EnrichmentMap (EM) in Cytoscape.

 }

 \examples{

-data(testGene)

-data(backgroundGene)

+data(geneDouble)

 data(pathwaysGMT)

+fedupRes <- runFedup(geneDouble, pathwaysGMT)

+resultsFolder <- tempdir()

+writeFemap(fedupRes, resultsFolder)

 gmtFile <- tempfile("pathwaysGMT", fileext = ".gmt")

-fedupRes <- runFedup(testGene, backgroundGene, pathwaysGMT)

-resultsFile <- tempfile("fedupRes", fileext = ".txt")

-netFile <- tempfile("fedup_EM", fileext = ".png")

 writePathways(pathwaysGMT, gmtFile)

-writeFemap(fedupRes, resultsFile)

+netFile <- tempfile("fedup_EM", fileext = ".png")

 plotFemap(

     gmtFile = gmtFile,

-    resultsFile = resultsFile,

+    resultsFolder = resultsFolder,

     qvalue = 0.05,

+    hideNodeLabels = TRUE,

     netName = "fedup_EM",

     netFile = netFile

 )

new file mode 100644

@@ -0,0 +1,36 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/genes.R

+\name{prepInput}

+\alias{prepInput}

+\title{Prepares input gene list for \link[fedup]{runFedup}.}

+\usage{

+prepInput(setName, ...)

+}

+\arguments{

+\item{setName}{(char) character vector naming gene vectors passed to

+\code{...} (must include "background" (case sensitive)).}

+

+\item{...}{(char) \code{n} vectors with at least one background set of genes

+and any number of test genes.}

+}

+\value{

+List of length \code{n} with gene vectors corresponding to those

+passed to \code{...}.

+}

+\description{

+This function takes any number of test genes and a common

+background set of genes and properly formats them for to pass to

+\link[fedup]{runFedup} \code{gene} argument.

+}

+\examples{

+# Raw gene data file

+genesFile <- system.file("extdata",

+    "NIHMS1587165-supplement-1587165_Sup_Tab_2.txt", package = "fedup")

+genes <- read.delim(genesFile, h = TRUE, as.is = TRUE)

+# Prepare gene vectors

+b <- unique(genes[, "gene"])

+set1 <- unique(genes[which(genes$FASN_merge < -0.4), "gene"])

+set2 <- unique(genes[which(genes$FASN_merge > 0.4), "gene"])

+setName <- c("background", "negative", "positive")

+geneDouble <- prepInput(setName, b, set1, set2)

+}

@@ -2,8 +2,7 @@

 % Please edit documentation in R/pathways.R

 \name{readPathways}

 \alias{readPathways}

-\title{Returns a list of pathways from various file formats.

-Currently supports the following file format: gmt, txt, xlsx.}

+\title{Returns a list of pathways from various file formats.}

 \usage{

 readPathways(

     pathwayFile,

@@ -15,29 +14,30 @@ readPathways(

 )

 }

 \arguments{

-\item{pathwayFile}{(char) path to file with pathway annotations.}

+\item{pathwayFile}{(char) path to file with pathway annotations}

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

-(default FALSE).}

+(default FALSE)}

-\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{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 or int) column name or number with gene identifiers.

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

+in a pathway (default 1)}

 \item{maxGene}{(integer) maximum number of genes to be considered

-in a pathway (default Inf).}

+in a pathway (default Inf)}

 }

 \value{

-a list of vectors with pathway annotations.

+A list of vectors with pathway annotations.

 }

 \description{

-Returns a list of pathways from various file formats.

-Currently supports the following file format: gmt, txt, xlsx.

+This function supports custom pathway annotations to use

+for fedup pathway enrichment analysis. Current file formats supported are

+gmt, txt, and xlsx.

 }

 \examples{

 pathways <- readPathways(

@@ -2,43 +2,51 @@

 % Please edit documentation in R/fedup.R

 \name{runFedup}

 \alias{runFedup}

-\title{Runs gene enrichment and depletion analysis for a list of pathways.}

+\title{Runs pathway enrichment and depletion analysis using a Fisher's

+exact test.}

 \usage{

-runFedup(testGene, backgroundGene, pathways)

+runFedup(genes, pathways)

 }

 \arguments{

-\item{testGene}{(char) vector of genes to use as test set.}

+\item{genes}{(list) named list of vectors with background genes and \code{n}

+test genes.}

-\item{backgroundGene}{(char) vector of genes to use as background set.}

-

-\item{pathways}{(list) list of vectors with pathway annotations.}

+\item{pathways}{(list) named list of vectors with pathway annotations.}

 }

 \value{

-table of pathway enrichment and depletion results. Rows represent

-tested pathways. Columns represent:

+List of length \code{n} with table(s) of pathway enrichment and

+depletion results. Rows represent tested pathways. Columns represent:

 \itemize{

     \item pathway -- name of the pathway, corresponds to

         names(\code{pathways});

     \item size -- size of the pathway;

-    \item real_frac -- fraction of \code{testGene} members in pathway;

-    \item expected_frac -- fraction of \code{backgroundGene} members in

+    \item real_frac -- fraction of test gene members in pathway;

+    \item expected_frac -- fraction of background gene members in

         pathway;

     \item fold_enrichment -- fold enrichment measure,

         evaluates as \code{real_frac} / \code{expected_frac};

     \item status -- indicator that pathway is enriched or depleted for

-        \code{testGene} members;

-    \item real_gene -- vector of \code{testGene} gene members annotated

+        test gene members;

+    \item real_gene -- vector of test gene members annotated

         to \code{pathways};

     \item pvalue -- enrichment p-value calculated via Fisher's exact test;

     \item qvalue -- BH-adjusted p-value

 }

 }

 \description{

-Runs gene enrichment and depletion analysis for a list of pathways.

+This function takes a list of test genes and a common background

+set to calculate enrichment and depletion for a list of pathways. The method

+allows for fast and efficient testing of multiple gene sets of interest.

 }

 \examples{

-data(testGene)

-data(backgroundGene)

 data(pathwaysGMT)

-fedup_res <- runFedup(testGene, backgroundGene, pathwaysGMT)

+# Run analysis with a single test set

+data(geneSingle)

+fedupRes <- runFedup(geneSingle, pathwaysGMT)

+# Run analysis with two test sets

+data(geneDouble)

+fedupRes <- runFedup(geneDouble, pathwaysGMT)

+# Run analysis with multiple test sets

+data(geneMulti)

+fedupRes <- runFedup(geneMulti, pathwaysGMT)

 }

deleted file mode 100644

@@ -1,17 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/data.R

-\docType{data}

-\name{testGene}

-\alias{testGene}

-\title{Example vector of human genes to use as test set for enrichment.}

-\format{

-a character vector with 190 elements (gene IDs)

-}

-\usage{

-data(testGene)

-}

-\description{

-Script to prepare data

-system.file("inst", "script", "genes.R", package = "fedup")

-}

-\keyword{datasets}

@@ -4,20 +4,19 @@

 \alias{writeFemap}

 \title{Writes an enrichment dataset file for use in Cytoscape EnrichmentMap.}

 \usage{

-writeFemap(df, resultsFile)

+writeFemap(results, resultsFolder)

 }

 \arguments{

-\item{df}{(data.frame) table with fedup enrichment results.

-(see runFedup() for column descriptions)}

+\item{results}{(list) list with ouput results from \link[fedup]{runFedup}}

-\item{resultsFile}{(char) name of output results file.}

+\item{resultsFolder}{(char) name of folder to store result file(s)}

 }

 \value{

-table of gene enrichment and depletion results formatted as a

+Table of pathway enrichment and depletion results formatted as a

 'Generic results file'. Rows represent tested pathways. Columns represent:

 \itemize{

     \item pathway -- pathway ID (must match pathway IDs in the GMT file

-        provided to plotFemap());

+        provided to \link[fedup]{plotFemap};

     \item description -- pathway name or description;

     \item pvalue -- enrichment pvalue;

     \item qvalue -- BH-corrected pvalue;

@@ -29,10 +28,9 @@ table of gene enrichment and depletion results formatted as a

 Writes an enrichment dataset file for use in Cytoscape EnrichmentMap.

 }

 \examples{

-data(testGene)

-data(backgroundGene)

+data(geneDouble)

 data(pathwaysGMT)

-fedupRes <- runFedup(testGene, backgroundGene, pathwaysGMT)

-resultsFile <- tempfile("fedupRes", fileext = ".txt")

-writeFemap(fedupRes, resultsFile)

+fedupRes <- runFedup(geneDouble, pathwaysGMT)

+resultsFolder <- tempdir()

+writeFemap(fedupRes, resultsFolder)

 }

@@ -7,9 +7,9 @@

 writePathways(pathways, gmtFile)

 }

 \arguments{

-\item{pathways}{(list) named list of vectors.}

+\item{pathways}{(list) named list of vectors}

-\item{gmtFile}{(char) name of output GMT file.}

+\item{gmtFile}{(char) name of output GMT file}

 }

 \value{

 GMT-formatted file. Rows represent pathways. Columns represent: