Package 'ribiosGSEA'

Description

Subset an AnnoBroadGseaRes object

Usage

## S4 method for signature 'AnnoBroadGseaRes,ANY,ANY,ANY'
x[i, j, ..., drop = FALSE]

Arguments

Value

A subset of the original data as an AnnoBroadGseaRes object

Description

Subset a FisherResultList object by indexing

Usage

## S4 method for signature 'FisherResultList,ANY,missing,missing'
x[i, j, ..., drop = FALSE]

Arguments

Value

A subset of the original data as an FisherResultList object

Description

Subset a FisherResultList object by namespace and name

Usage

## S4 method for signature 'FisherResultList,character,character,missing'
x[i, j, ..., drop = TRUE]

Arguments

Description

Convert a list of AnnoBroadGseaResItem objects to a list

Usage

AnnoBroadGseaRes(object)

Arguments

Value

An AnnoBroadGseaRes object

Description

Annotated BROAD GSEA Results for one contrast

Value

An object of class AnnoBroadGseaRes.

Description

Convert a BroadGseaResItem object to an AnnoBroadGseaResItem object

Usage

AnnoBroadGseaResItem(object, genes, geneValues)

Arguments

Value

An annoBroadGseaResItem object

Description

Annotated BROAD GSEA result item

Value

An object of class AnnoBroadGseaResItem.

Slots

gsGenes

Vector of character strings, gene-set genes

gsGeneValues

Vector of numeric values, statistics of gene-set genes

Description

A list of AnnoBroadGseaRes objects

Value

An object of class AnnoBroadGseaResList.

Description

Convert an FisherResultList object into a data.frame

Usage

## S4 method for signature 'FisherResultList'
as.data.frame(x, row.names = NULL)

Arguments

Value

A data.frame

Description

An adapted and enhanced version of limma::camera

Usage

biosCamera(
  y,
  index,
  design = NULL,
  contrast = ncol(design),
  weights = NULL,
  geneLabels = NULL,
  use.ranks = FALSE,
  allow.neg.cor = FALSE,
  trend.var = FALSE,
  sort = FALSE,
  .fixed.inter.gene.cor = NULL,
  .approx.zscoreT = FALSE
)

Arguments

Value

A data.frame with one row per set and the following columns:

GeneSet

Gene set name

NGenes

Number of genes in the set

Correlation

Estimated correlation

EffectSize

Estimated difference between the mean values of genes in the geneset and the background genes

Direction

Direction of set-wise regulation, Up or Down

Score

Gene-set enrichment score, defined as log10(pValue)*I(directionality), where I(directionality) equals 1 if the directionality is Up and -1 if the directionality is Down

ContribuingGenes

A character string, containing all genes labels of genes that are in the set and regulated in the same direction as the set-wise direction, and the respective statistic

Note

Since limma 3.29.6, the default setting of allow.neg.cor changes from TRUE to FALSE, and a new parameter, inter.gene.cor, is added with the default value of 0.01, namely a prior inter-gene correlation is set for all gene sets. Currently, biosCamera does not have the parameter inter.gene.cor, but allow.neg.cor is set by default to FALSE to be consistent with the latest camera function.

Examples

y <- matrix(rnorm(1000*6),1000,6)
design <- cbind(Intercept=1,Group=c(0,0,0,1,1,1))
# First set of 20 genes are genuinely deferentially expressed 
index1 <- 1:20
y[index1,4:6] <- y[index1,4:6]+1
# The second set of 20 genes are not
index2 <- 21:40
biosCamera(y, index1, design) 
biosCamera(y, index2, design)
biosCamera(y, list(index1, index2), design)

# compare with the output of camera: columns 'GeneSet', 'Score',
# 'ContributingGenes' are missing, and in case \code{inter.gene.cor} is (as
# default) set to a numeric value, the column 'Correlation' is also missing

limmaDefOut <- limma::camera(y, index1, design)
limmaCorDefOut <-
    limma::camera(y, index1, design, inter.gene.cor=NA)

## Not run:  
  # when \code{.approx.zscoreT=TRUE},  PValue reported by
  # \code{limma::camera(inter.gene.cor=NA)} and \code{ribiosGSEA::biosCamera}
  # should equal 
  biosCorOut <- biosCamera(y, index1, design, .approx.zscoreT=TRUE)

  # when \code{.fixed.inter.gene.cor=0.01} and \code{.approx.zscoreT=TRUE},
  # PValue reported by \code{limma::camera} and \code{ribiosGSEA::biosCamera}
  # should equal 
  biosFixCorOut <- biosCamera(y, index1, design,
      .fixed.inter.gene.cor=0.01, .approx.zscoreT=TRUE)
  testthat::expect_equal(biosFixCorOut$PValue, limmaDefOut$PValue)
  testthat::expect_equal(biosCorOut$PValue, limmaCorDefOut$PValue)

## End(Not run)

Description

A S4 class representing the atom structure of results of the BROAD GSEA tool

Value

An object of class BroadGseaResItem.

Slots

geneset

Character, gene-set name

es

Numeric, enrichment score

nes

Numeric, normalised enrichment score

np

Numeric

fdr

Numeric, false discovery rate

fwer

Numeric, family-wise error rate

geneIndices

Integer vector, gene indices

esProfile

Numeric, enrichment score profile

coreEnrichThr

Numeric

Description

Build the command-line command to run BROAD GSEA

Usage

buildBroadGSEAcomm(
  gseaJar,
  javaBin,
  rnkFiles,
  gmtFile,
  chipFile,
  nperm = 1000L,
  collapse = FALSE,
  plotTopX = 25,
  outdir = "./",
  addShebang = TRUE
)

Arguments

Value

A character vector of shell commands to run GSEA.

Description

Run CAMERA method using EdgeResult

Usage

## S3 method for class 'EdgeResult'
camera(y, gmtList, doParallel = FALSE, ...)

Arguments

Value

A data.frame containing CAMERA results.

Examples

exMat <- matrix(rpois(120, 10), nrow=20, ncol=6)
exGroups <- gl(2,3, labels=c("Group1", "Group2"))
exDesign <- model.matrix(~0+exGroups)
colnames(exDesign) <- levels(exGroups)
exContrast <- matrix(c(-1,1,1,-1), ncol=2, dimnames=list(c("Group1", "Group2"), 
  c("Group2.vs.Group1", "Group1.vs.Group2")))
exDescon <- DesignContrast(exDesign, exContrast, groups=exGroups)
exFdata <- data.frame(GeneSymbol=sprintf("GeneSymbol%d", 1:nrow(exMat)))
exPdata <- data.frame(Name=sprintf("Sample%d", 1:ncol(exMat)),
                     Group=exGroups)
exDgeList <- DGEList(exMat, genes=exFdata, samples=exPdata)
exDgeList <- edgeR::estimateDisp(exDgeList, exDesign)
exEdgeObject <- EdgeObject(exDgeList, exDescon)
exEdgeRes <- ribiosNGS::dgeWithEdgeR(exEdgeObject)
exGmt <- BioQC::GmtList(list(GeneSet1=sprintf("GeneSymbol%d", 1:5),
  GeneSet2=sprintf("GeneSymbol%d", 6:10)))
  
exCameraRes <- camera(exEdgeRes, exGmt)

Description

Run the CAMERA method using LimmaVoomResult

Usage

## S3 method for class 'LimmaVoomResult'
camera(y, gmtList, doParallel = FALSE, ...)

Arguments

Value

A data.frame containing CAMERA results.

Examples

exMat <- matrix(rpois(120, 10), nrow=20, ncol=6)
exGroups <- gl(2,3, labels=c("Group1", "Group2"))
exDesign <- model.matrix(~0+exGroups)
colnames(exDesign) <- levels(exGroups)
exContrast <- matrix(c(-1,1), ncol=1, dimnames=list(c("Group1", "Group2"), c("Group2.vs.Group1")))
exDescon <- DesignContrast(exDesign, exContrast, groups=exGroups)
exFdata <- data.frame(GeneSymbol=sprintf("Gene%d", 1:nrow(exMat)))
exPdata <- data.frame(Name=sprintf("Sample%d", 1:ncol(exMat)),
                     Group=exGroups)
exDgeList <- DGEList(exMat, genes=exFdata, samples=exPdata)
exDgeList <- edgeR::estimateDisp(exDgeList, exDesign)
edgeObj <- EdgeObject(exDgeList, exDescon)
limmaVoomRes <- ribiosNGS::dgeWithLimmaVoom(edgeObj)
exGmt <- BioQC::GmtList(list(GeneSet1=sprintf("GeneSymbol%d", 1:5),
  GeneSet2=sprintf("GeneSymbol%d", 6:10)))
  
camera(limmaVoomRes, exGmt)

Description

Apply the CAMERA method to a DGEList object and a contrast

Usage

cameraDGEListByContrast(dgeList, index, design, contrasts, doParallel = FALSE)

Arguments

Value

A data.frame containing CAMERA results across contrasts.

Examples

exMat <- matrix(rpois(120, 10), nrow=20, ncol=6)
exGroups <- gl(2,3, labels=c("Group1", "Group2"))
exDesign <- model.matrix(~0+exGroups)
colnames(exDesign) <- levels(exGroups)
exContrast <- matrix(c(-1,1), ncol=1, dimnames=list(c("Group1", "Group2"), c("Group2.vs.Group1")))
exDescon <- DesignContrast(exDesign, exContrast, groups=exGroups)
exFdata <- data.frame(GeneSymbol=sprintf("Gene%d", 1:nrow(exMat)))
exPdata <- data.frame(Name=sprintf("Sample%d", 1:ncol(exMat)),
                     Group=exGroups)
exDgeList <- DGEList(exMat, genes=exFdata, samples=exPdata)
exDgeList <- edgeR::estimateDisp(exDgeList, exDesign)
cameraDGEListByContrast(exDgeList, index=1:5, design=exDesign, contrasts=exContrast)
cameraDGEListByContrast(exDgeList,
  index=list(1:5, 6:10),
  design=exDesign, contrasts=exContrast)

Description

Apply the CAMERA method to a DGEList object

Usage

cameraLimmaVoomResultsByContrast(
  limmaVoomResults,
  index,
  doParallel = FALSE,
  ...
)

Arguments

Value

A data.frame containing CAMERA results.

A data.frame containing CAMERA results across contrasts.

Examples

exMat <- matrix(rpois(120, 10), nrow=20, ncol=6)
exGroups <- gl(2,3, labels=c("Group1", "Group2"))
exDesign <- model.matrix(~0+exGroups)
colnames(exDesign) <- levels(exGroups)
exContrast <- matrix(c(-1,1), ncol=1, dimnames=list(c("Group1", "Group2"), c("Group2.vs.Group1")))
exDescon <- DesignContrast(exDesign, exContrast, groups=exGroups)
exFdata <- data.frame(GeneSymbol=sprintf("Gene%d", 1:nrow(exMat)))
exPdata <- data.frame(Name=sprintf("Sample%d", 1:ncol(exMat)),
                     Group=exGroups)
exDgeList <- DGEList(exMat, genes=exFdata, samples=exPdata)
exDgeList <- edgeR::estimateDisp(exDgeList, exDesign)
edgeObj <- EdgeObject(exDgeList, exDescon)
limmaVoomRes <- ribiosNGS::dgeWithLimmaVoom(edgeObj)
cameraLimmaVoomResultsByContrast(limmaVoomRes, index=c(1:5))
cameraLimmaVoomResultsByContrast(limmaVoomRes, index=list(GS1=1:5, GS2=6:10))

Description

Convert a CAMERA table into a graph

Usage

cameraTable2graph(df, jacThr = 0.25, plot = TRUE, ...)

Arguments

Value

A list with two elements: graph (an igraph object) and resTbl (a data.frame with columns Namespace, GeneSet, Score).

Description

Perform gene-set enrichment (GSE) analysis

Usage

doGse(edgeResult, gmtList, doParallel = FALSE)

Arguments

Value

A data.frame containing results of the gene-set enrichment analysis.

See Also

gseWithLogFCgage and gseWithCamera are wrapped by this function to perform analysis with GAGE and CAMERA, respectively. logFCgage, camera.EdgeResult, and camera.LimmaVoomResult implement the logic, and return the enrichment table.

Examples

exMat <- matrix(rpois(120, 10), nrow=20, ncol=6)
exGroups <- gl(2,3, labels=c("Group1", "Group2"))
exDesign <- model.matrix(~0+exGroups)
exContrast <- matrix(c(-1,1), ncol=1, dimnames=list(c("Group1", "Group2"), c("Group2.vs.Group1")))
exDescon <- DesignContrast(exDesign, exContrast, groups=exGroups)
exFdata <- data.frame(GeneSymbol=sprintf("Gene%d", 1:nrow(exMat)))
exPdata <- data.frame(Name=sprintf("Sample%d", 1:ncol(exMat)),
                     Group=exGroups)
exObj <- EdgeObject(exMat, exDescon, 
                     fData=exFdata, pData=exPdata)
exDgeRes <- ribiosNGS::dgeWithEdgeR(exObj)

exGeneSets <- BioQC::GmtList(list(
    list(name="Set1", desc="set 1", genes=c("Gene1", "Gene2", "Gene3"), namespace="default"),
    list(name="Set2", desc="set 2", genes=c("Gene18", "Gene6", "Gene4"), namespace="default")
))
exGse <- doGse(exDgeRes, exGeneSets)

## Not run: 
  exMat <- matrix(rpois(120000, 10), nrow=20000, ncol=12)
  exGroups <- gl(4,3, labels=c("Group1", "Group2", "Group3", "Group4"))
  exDesign <- model.matrix(~0+exGroups)
  exContrast <- matrix(c(-1,1,0,0, 0,0,-1,1),
     ncol=2, byrow=FALSE,
     dimnames=list(c("Group1", "Group2", "Group3", "Group4"), 
       c("Group2.vs.Group1", "Group4.vs.Group3")))
  exDescon <- DesignContrast(exDesign, exContrast, groups=exGroups)
  exFdata <- data.frame(GeneSymbol=sprintf("Gene%d", 1:nrow(exMat)))
  exPdata <- data.frame(Name=sprintf("Sample%d", 1:ncol(exMat)),
                       Group=exGroups)
  exObj <- EdgeObject(exMat, exDescon, 
                       fData=exFdata, pData=exPdata)
  exDgeRes <- ribiosNGS::dgeWithEdgeR(exObj)
  
  ngeneset <- 1000
  genesetSizes <- round(runif(ngeneset)*100)+1
  exGeneSets <- BioQC::GmtList(lapply(seq(1:ngeneset), function(i) {
    name <- paste0("GeneSet", i)
    desc <- paste0("GeneSet", i)
    genes <- sample(exFdata$GeneSymbol, genesetSizes[i])
    res <- list(name=name, desc=desc, genes=genes, namespace="default")
  }))
  exGse <- doGse(exDgeRes, exGeneSets)

## End(Not run)

Description

Expand genes in the CAMERA result table

Usage

expandCameraTableGenes(tbl)

Arguments

Value

A longer data.frame, with each row one gene.

Description

Make a factor vector from a character vector by the order of the parsed numbers

Usage

factorByNumberInStr(str, decreasing = TRUE)

Arguments

Value

A factor with levels ordered by the parsed numbers.

See Also

orderByNumberInStr, which returns the order of strings by numbers in them

Examples

factorByNumberInStr(c("D1", "D10", "D15", "D3.5"))
factorByNumberInStr(c("D1", "D10", "D15", "D3.5"), decreasing=FALSE)

Description

Return FDR values

Usage

fdrValue(object, ...)

Arguments

Value

A numeric vector of FDR values.

Description

Filter by size

Usage

filterBySize(object, min, max)

Arguments

Value

The filtered object.

Description

Result of Fisher's exact test

Value

An object of class FisherResult.

Description

A list of results of Fisher's exact test

Value

An object of class FisherResultList.

Description

Fisher's method to combine multiple p-values

Usage

fishersMethod(p, returnValiePvalues = FALSE)

Arguments

Value

A FisherMethodResult S3 object, a list of following elements

1. chisq: Chi-square statistic

2. df: Degree of freedom (which is twice the count of the valid p-values used for calculation)

3. p: p-value

4. validp (optional): valid p-values used for the calculation

The function returns the combined p-value using the sum of logs (Fisher's) method

Note

The function was adapted from metap::sumlog

Examples

ps <- c(0.05, 0.75)
fishersMethod(ps)
fishersMethod(ps, returnValiePvalues=TRUE)

Description

Perform Fisher's exact test

Usage

fisherTest(genes, genesets, universe, ...)

Arguments

Value

A FisherResult object or a data.table of results.

Description

Perform Fisher's exact test on a gene set

Usage

## S4 method for signature 'character,character,character'
fisherTest(
  genes,
  genesets,
  universe,
  gsName,
  gsNamespace,
  makeUniqueNonNA = TRUE,
  checkUniverse = TRUE,
  useEASE = FALSE
)

Arguments

Note

Duplicated items in genes, genesets' genes, and the universe are per default removed

References

Hosack et al.

Hosack, Douglas A., Glynn Dennis, Brad T. Sherman, H. Clifford Lane, and Richard A. Lempicki. Identifying Biological Themes within Lists of Genes with EASE. Genome Biology 4 (2003): R70. doi:10.1186/gb-2003-4-10-r70

Examples

myGenes <- LETTERS[1:3]
myGeneSet1 <- LETTERS[1:6]
myGeneSet2 <- LETTERS[4:7]
myUniverse <- LETTERS
fisherTest(genes=myGenes, genesets=myGeneSet1, universe=myUniverse)
fisherTest(genes=myGenes, genesets=myGeneSet2, universe=myUniverse)
fisherTest(genes=myGenes, genesets=myGeneSet1, universe=myUniverse, 
           gsName="My gene set1", gsNamespace="Letters")

## note that duplicated items are removed by default
resWoRp <- fisherTest(genes=rep(myGenes,2), genesets=myGeneSet1, 
                      universe=myUniverse)
resWithRp <- fisherTest(genes=rep(myGenes,2), genesets=myGeneSet1, 
                      universe=rep(myUniverse,2))
identical(resWoRp, resWithRp)

resWithRpNoUnique <- fisherTest(genes=rep(myGenes,2), genesets=myGeneSet1, 
           universe=rep(myUniverse,2), makeUniqueNonNA=FALSE)
identical(resWoRp, resWithRpNoUnique)

Description

Perform Fisher's exact test on a GmtList object

Usage

## S4 method for signature 'character,GmtList,character'
fisherTest(
  genes,
  genesets,
  universe,
  gsNamespace,
  makeUniqueNonNA = TRUE,
  checkUniverse = TRUE,
  useEASE = FALSE
)

Arguments

Value

A data.table containing Fisher's exact test results of all gene-sets, in the same order as the input gene-sets, with following columns:

1. GeneSetNamespace

2. GeneSetName

3. GeneSetEffectiveSize, the count of genes in the gene-set that are found in the universe

4. HitCount, the count of genes in the genes input that are in the gene-set

5. Hits, a vector of character string, representing hits

6. PValue

7. FDR, PValue adjusted by the Benjamini-Hochberg method. If more than one gene-set categories are provided, the FDR correction is performed per namespace

Examples

gs1 <- list(name="GeneSet1", desc="desc", genes=LETTERS[1:4], namespace="A")
gs2 <- list(name="GeneSet2", desc="desc", genes=LETTERS[5:8], namespace="A")
gs3 <- list(name="GeneSet3", desc="desc", genes=LETTERS[seq(2,8,2)], namespace="A")
gs4 <- list(name="GeneSet3", desc="desc", genes=LETTERS[seq(1,7,2)], namespace="B")
gmtList <- BioQC::GmtList(list(gs1, gs2, gs3, gs4))
myInput <- LETTERS[2:6]
myUniverse <- LETTERS
myFisherRes <- fisherTest(myInput, gmtList, myUniverse)

Description

Perform Fisher's exact test on a GeneSet object

Usage

## S4 method for signature 'character,list,character'
fisherTest(
  genes,
  genesets,
  universe,
  makeUniqueNonNA = TRUE,
  checkUniverse = TRUE,
  useEASE = FALSE
)

Arguments

Examples

myGenes <- LETTERS[1:3]
myS4GeneSet1 <- list(name="GeneSet1", desc="GeneSet", 
    genes=LETTERS[1:6], namespace="My namespace 1")
myS4GeneSet2 <- list(name="GeneSet1", desc="GeneSet", 
    genes=LETTERS[2:7], namespace="My namespace 2")
myUniverse <- LETTERS
fisherTest(myGenes, myS4GeneSet1, myUniverse)
fisherTest(myGenes, myS4GeneSet2, myUniverse)

Description

Run Fisher's exact test on an EdgeResult object

Usage

fisherTestEdgeResult(
  edgeResult,
  gmtList,
  contrast,
  thr.abs.logFC = 1,
  thr.FDR = 0.05,
  minGeneSetEffectiveSize = 5,
  maxGeneSetEffectiveSize = 500,
  ...
)

Arguments

Value

A data.table containing Fisher's exact test results for positively and negatively regulated genes.

Description

Append NewHitsProp to the result data.table returned by fisherTest

Usage

fisherTestResultNewHitsProp(fisherTestResults)

Arguments

Value

A new data.table containing all columns of the input and NewHitsProp, a new column including the proportion of new hits in the gene-set

Description

GeMS base URL To set GeMS base URL in your environment, use 'GeMS_BASE_URL=value' in your "~/.Renviron" file

Usage

GeMS_BASE_URL

Format

An object of class character of length 1.

Description

GeMS genesets retrieval URL

Usage

GeMS_GENESETS_URL

Format

An object of class character of length 1.

Description

GeMS insert URL

Usage

GeMS_INSERT_URL

Format

An object of class character of length 1.

Description

GeMS remove URL

Usage

GeMS_REMOVE_URL

Format

An object of class character of length 1.

Description

GeMS geneset retrieval URL for testing

Usage

GeMS_TEST_GENESETS_URL

Format

An object of class character of length 1.

Description

GeMS URL for testing

Usage

GeMS_TEST_URL

Format

An object of class character of length 1.

Description

Test gene set enrichment by permutating gene labels of statistics

Usage

geneSetPerm(stats, indList, Nsim = 9999)

Arguments

Value

A data frame containg mean statistic, gene set size, and p-values

See Also

geneSetTest, a R implementation in the limma package

Examples

set.seed(1887)
stats <- rnorm(1000)
gsList <- list(gs1=c(3,4,5), gs2=c(7,8,9))
geneSetPerm(stats, gsList, Nsim=99)
gsList2 <- list(gs1=c(3,4,5), gs2=c(7,8,9), gs3=integer())
geneSetPerm(stats, gsList2, Nsim=99)
gsList3 <- sample(1:1000, 200)
geneSetPerm(stats, gsList3, Nsim=99)

Description

A generic, virtual S4 class for gene-set analysis result

Value

An object of class GeneSetResult (virtual).

Description

Get the name of the column which store false-discovery rates (adjusted P-values) from topTables

Usage

getFDRCol(colnames)

Arguments

Value

The column name of the FDRs, NA if not found.

Examples

getFDRCol(c("Feature", "logFC", "PValue", "FDR"))
getFDRCol(c("Feature", "logFC", "P.Value", "FDR"))
getFDRCol(c("Feature", "logFC", "p.Value", "adjPvalue"))
getFDRCol(c("Feature", "logFC", "PValue", "adj.PValue"))

Description

Send a list as JSON query to an URL and fetch the response

Usage

getJsonResponse(url, body)

Arguments

Value

The response from the webserver

Examples

## Not run: 
   ## getJsonResponse(GeMS_GENESETS_URL, list(user=ribiosUtils::whoami()))

## End(Not run)

Description

Get the name of the column which store unadjusted P-values from topTables

Usage

getPvalCol(colnames)

Arguments

Value

The column name of the unadjusted p-values, NA if not found.

Examples

getPvalCol(c("Feature", "logFC", "PValue", "FDR"))
getPvalCol(c("Feature", "logFC", "P.Value", "FDR"))
getPvalCol(c("Feature", "logFC", "p.Value", "adjPvalue"))
getPvalCol(c("Feature", "logFC", "pval", "adjPvalue"))

Description

Get one or more gene-sets with their names

Usage

getSetsWithNamesFromGeMS(setNames = NULL)

Arguments

Value

A GmtList object

See Also

getSetWithNameFromGeMS

Examples

## Not run: 
getSetsWithNamesFromGeMS(c("Plasma_sc", "Bcell_l_Danaher17"))

## End(Not run)

Description

Get gene-sets for application

Usage

getSetsWithPropertyFromGeMS(property = "meta.application", value = "")

Arguments

Value

A GmtList object

Examples

## Not run: 
getSetsWithPropertyFromGeMS("meta.application", "rtbeda_CIT")

## End(Not run)

Description

Get one gene-set with its name

Usage

getSetWithNameFromGeMS(setName)

Arguments

Value

A list of two elements

1. name

2. genes

See Also

getSetsWithNamesFromGeMS

Examples

## Not run: 
getSetWithNameFromGeMS("Plasma_sc")

## End(Not run)

Description

Get gene sets of a user from GeMS

Usage

getUserSetsFromGeMS(user = ribiosUtils::whoami())

Arguments

Value

A data.frame including following columns:

1. setName

2. desc

3. domain

4. source

5. subtype

Examples

## Not run: 
#### my gene-sets
## getUserSetsFromGeMS()
#### from another user
## getUserSetsFromGeMS("kanga6")

## End(Not run)

Description

Return GSEA core enrichment genes (also known as leading-edge genes)

Usage

gseaCoreEnrichGenes(object)

## S4 method for signature 'AnnoBroadGseaResItem'
gseaCoreEnrichGenes(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaCoreEnrichGenes(object)

Arguments

Value

A character vector of core enrichment genes.

Methods (by class)

• gseaCoreEnrichGenes(AnnoBroadGseaResItem): Return core enriched genes (also known as leading-edge genes) in an AnnoBroadGseaResItem object as a character string vector.

• gseaCoreEnrichGenes(AnnoBroadGseaRes): Return core enriched genes (also known as leading-edge genes) in an AnnoBroadGseaRes object as a list of character string vectors.

Description

Return GSEA core enrichment score threshold

Usage

gseaCoreEnrichThr(object)

## S4 method for signature 'BroadGseaResItem'
gseaCoreEnrichThr(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaCoreEnrichThr(object)

Arguments

Value

A numeric value.

Methods (by class)

• gseaCoreEnrichThr(BroadGseaResItem): Get the threshold value of GSEA core enrichment from a BroadGseaResItem object

• gseaCoreEnrichThr(AnnoBroadGseaRes): Get the threshold value of GSEA core enrichment from an AnnoBroadGseaRes object

Description

Return GSEA enrichment scores

Usage

gseaES(object)

## S4 method for signature 'BroadGseaResItem'
gseaES(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaES(object)

## S4 method for signature 'AnnoBroadGseaResList'
gseaES(object)

Arguments

Value

A numeric vector of enrichment scores.

Methods (by class)

• gseaES(BroadGseaResItem): Get GSEA enrichment score from a BroadGseaResItem object

• gseaES(AnnoBroadGseaRes): Get GSEA enrichment score from an AnnoBroadGseaRes object

• gseaES(AnnoBroadGseaResList): Get GSEA enrichment score from an AnnoBroadGseaResList object

Description

Return GSEA enrichment score profile

Usage

gseaESprofile(object)

## S4 method for signature 'BroadGseaResItem'
gseaESprofile(object)

Arguments

Value

A numeric vector of enrichment score profiles.

Methods (by class)

• gseaESprofile(BroadGseaResItem): Get GSEA enrichment profile from a BroadGseaResItem object

Description

Return GSEA FDR

Usage

gseaFDR(object)

## S4 method for signature 'BroadGseaResItem'
gseaFDR(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaFDR(object)

## S4 method for signature 'AnnoBroadGseaResList'
gseaFDR(object)

Arguments

Value

A numeric vector of FDR values.

Methods (by class)

• gseaFDR(BroadGseaResItem): Get GSEA FDR values from a BroadGseaResItem object

• gseaFDR(AnnoBroadGseaRes): Get GSEA FDR values from an AnnoBroadGseaRes object

• gseaFDR(AnnoBroadGseaResList): Get GSEA FDR values from an AnnoBroadGseaResList object

Description

gseaFingerprint extracts pathway fingerprints from the result of one GSEA result. gseaFingerprintMatrix extracts multiple signatures and organizes into the form of rectangular matrix.

Usage

gseaFingerprint(
  gseaDir,
  value = c("q", "es", "nes"),
  threshold = 1e-04,
  sortByName = TRUE
)

gseaFingerprintMatrix(gseaDirs, value = c("q", "es", "nes"), ...)

Arguments

Details

gseaFingerprint extracts pathway signature from one GSEA output directory. While gseaFingerprintMatrix simultaneously extracts from more than one GSEA output directories, and organizes pathway signatures in a rectangular matrix form.

gseaFingerprintMatrix takes care of signature mapping between different GSEA result sets.

Value

gseaFingerprint returns a data.frame with two columns name and value, recording gene signature (pathway) names and the statistic chosen by the user.

gseaFingerprintMatrix returns a matrix, with the union set of gene signatures from all GSEA output result sets as rows, and GSEA result names as columns.

Author(s)

Jitao David Zhang <[email protected]>

See Also

See gseaQvalue and gseaES for how to choose the statistic to produce pathway signatures.

Examples

gseaDirZip <- system.file(package="ribiosGSEA","extdata/gseaDirs.zip")
tmpDir <- tempdir()
utils::unzip(gseaDirZip, exdir=tmpDir)
gseaDir <- file.path(tmpDir, "gseaDirs")
gseaDirs <- dir(gseaDir, full.names=TRUE)
gseaFp <- gseaFingerprint(gseaDirs[1], value="q")
gseaFps <- gseaFingerprintMatrix(gseaDirs, value="q")

Description

Return GSEA FWER values

Usage

gseaFWER(object)

## S4 method for signature 'BroadGseaResItem'
gseaFWER(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaFWER(object)

## S4 method for signature 'AnnoBroadGseaResList'
gseaFWER(object)

Arguments

Value

A numeric vector of FWER values.

Methods (by class)

• gseaFWER(BroadGseaResItem): Get GSEA FWER values from a BroadGseaResItem object

• gseaFWER(AnnoBroadGseaRes): Get GSEA FWER values from an AnnoBroadGseaRes object

• gseaFWER(AnnoBroadGseaResList): Get GSEA FWER values from an AnnoBroadGseaResList object

Description

Return GSEA normalized enrichment scores

Usage

gseaNES(object)

## S4 method for signature 'BroadGseaResItem'
gseaNES(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaNES(object)

## S4 method for signature 'AnnoBroadGseaResList'
gseaNES(object)

Arguments

Value

A numeric vector of normalized enrichment scores.

Methods (by class)

• gseaNES(BroadGseaResItem): Get GSEA normalized enrichment score from a BroadGseaResItem object

• gseaNES(AnnoBroadGseaRes): Get GSEA normalized enrichment score from an AnnoBroadGseaRes object

• gseaNES(AnnoBroadGseaResList): Get GSEA normalized enrichment score from an AnnoBroadGseaResList object

Description

Return GSEA number of permutation

Usage

gseaNP(object)

## S4 method for signature 'BroadGseaResItem'
gseaNP(object)

## S4 method for signature 'AnnoBroadGseaRes'
gseaNP(object)

## S4 method for signature 'AnnoBroadGseaResList'
gseaNP(object)

Arguments

Value

A numeric vector.

Methods (by class)

• gseaNP(BroadGseaResItem): Get GSEA number of permutations from a BroadGseaResItem object

• gseaNP(AnnoBroadGseaRes): Get GSEA number of permutations from an AnnoBroadGseaRes object

• gseaNP(AnnoBroadGseaResList): Get GSEA number of permutations from an AnnoBroadGseaResList object

Description

Read GSEA statistics (log-transformed q-value [q], Enrichment Score [ES], or normalized Enrichement Score [NES]) to profile pathway activitities.

Usage

gseaResQvalue(file, threshold = 1e-04, log = FALSE, posLog = FALSE)

gseaResES(file, normalized = FALSE)

Arguments

Details

In many cases we want to extract pathway signatures from a set of experiments. Both gseaResQvalue and gseaES can read GSEA output files and extract desired statistic: q-value, ES or NES.

See the GSEA document for definitions of the three values. For comparing a few conditions to another, we recommend using q-value. For large-scale comparisons between pathways (or other gene signatures), we have found ES very useful. It is adviced to choose proper statistic to extract pathway signatures only when you are sure of the aim. Using any statistic without good reasoning may as always lead to wrong intepretations of the data.

These functions are usually not directly called by end-users. See gseaFingerprint and link{gseaFingerprintMatrix} instead.

Value

A data.frame with two columns: name and value. The column name contains gene signatures (e.g. pathways), and value contains the statistic.

Functions

• gseaResQvalue(): The function to extract the Q-value

  Extract Q-values from GSEA result file

Author(s)

Jitao David Zhang <[email protected]>, with input from Martin Ebeling, Laura Badi and Isabelle Wells.

References

GSEA documentation http://www.broadinstitute.org/gsea/doc/GSEAUserGuideFrame.html

See Also

End-users will probably find gseaFingerprint and link{gseaFingerprintMatrix} more useful, since they operate on the level of GSEA result directories, instead of single output tab-delimited files.

Examples

gseaDirZip <- system.file(package="ribiosGSEA","extdata/gseaDirs.zip")
tmpDir <- tempdir()
utils::unzip(gseaDirZip, exdir=tmpDir)
gseaDir <- file.path(tmpDir, "gseaDirs")
gseaFile <- file.path(gseaDir,
   "VitaminA_24h_High",
   "gsea_report_for_na_neg_1336489010730.xls")

gseaQ <- gseaResQvalue(gseaFile)
gseaLogQ <- gseaResQvalue(gseaFile, log=TRUE)
gseaQscore <- gseaResQvalue(gseaFile, log=TRUE, posLog=TRUE)

gseaEs <- gseaResES(gseaFile)
gseaNes <- gseaResES(gseaFile, normalized=TRUE)

Description

One way to score GSEA results is to multiple the absolute value of log10 transformed p-values (nominal p-value, FDR, or FWER) with the sign of the enrichment scores. This score is intuitive since it combines statistical significance and the sign of regulation.

Usage

gseaScore(x, type = c("fdr", "p", "fwer"))

gseaScores(..., names = NULL, type = c("fdr", "p", "fwer"))

Arguments

Details

gseaScores takes care of the situation where some gene sets are missing in one or more conditions.

Value

gseaScore returns a double vector of scores with gene set names.

gseaScores returns a data frame of scores, with gene set names as row names.

Functions

• gseaScores(): gseaScore applied to multiple objects

Author(s)

Jitao David Zhang <[email protected]>

See Also

gseaNP, gseaFDR, gseaFWER to get p-values.

parseGSEAdir.

Description

Return the effective size of gene-set

Usage

gsEffectiveSize(object, ...)

## S4 method for signature 'FisherResult'
gsEffectiveSize(object)

## S4 method for signature 'FisherResultList'
gsEffectiveSize(object)

Arguments

Value

An integer vector of effective sizes.

Methods (by class)

• gsEffectiveSize(FisherResult): Effective sizes of gene-set, returning an integer.

• gsEffectiveSize(FisherResultList): Effective sizes of Gene-sets, returning an integer vector.

Description

The core algorithm to perform Fisher's exact test on a gene set

Usage

gsFisherTestCore(
  genes,
  geneSetGenes,
  universe,
  makeUniqueNonNA = TRUE,
  checkUniverse = TRUE,
  useEASE = FALSE
)

Arguments

Value

A list of three elements

1. p The p-value of one-sided (over-representation of the Fisher's test)

2. gsEffectiveSize Gene-set's effective size, namely number of genes that are in the universe

3. hits Character vector, genes that are found in the gene sets

References

Hosack et al.

Hosack, Douglas A., Glynn Dennis, Brad T. Sherman, H. Clifford Lane, and Richard A. Lempicki. Identifying Biological Themes within Lists of Genes with EASE. Genome Biology 4 (2003): R70. doi:10.1186/gb-2003-4-10-r70

Examples

myGenes <- LETTERS[1:3]
myGeneSet1 <- LETTERS[1:6]
myGeneSet2 <- LETTERS[4:7]
myUniverse <- LETTERS
gsFisherTestCore(myGenes, myGeneSet1, myUniverse)
gsFisherTestCore(myGenes, myGeneSet2, myUniverse)

## use EASE for conservative estimating
gsFisherTestCore(myGenes, myGeneSet1, myUniverse, useEASE=FALSE)
gsFisherTestCore(myGenes, myGeneSet1, myUniverse, useEASE=TRUE)

## checkUniverse will make sure that \code{univese} contains all element in \code{genes}
gsFisherTestCore(c("OutOfUniverse", myGenes), myGeneSet1, myUniverse, checkUniverse=FALSE)
gsFisherTestCore(c("OutOfUniverse", myGenes), myGeneSet1, myUniverse, checkUniverse=TRUE)

Description

Return gene-set gene count

Usage

gsGeneCount(object, ...)

Arguments

Value

An integer vector of gene counts.

Description

Return gene-set gene indices

Usage

gsGeneIndices(object)

## S4 method for signature 'BroadGseaResItem'
gsGeneIndices(object)

Arguments

Value

An integer vector of gene indices.

Methods (by class)

• gsGeneIndices(BroadGseaResItem): Get gene-set gene indices from a BroadGseaResItem object, returning a vector of integers.

Description

Return gene-set genes

Usage

gsGenes(object, ...)

## S4 method for signature 'AnnoBroadGseaResItem'
gsGenes(object)

## S4 method for signature 'AnnoBroadGseaRes'
gsGenes(object)

## S4 method for signature 'GmtList'
gsGenes(object)

Arguments

Value

A character vector or list of character vectors of gene-set genes.

Methods (by class)

• gsGenes(AnnoBroadGseaResItem): Get gene-set genes from a BroadGseaResItem object, returning a character string vector.

• gsGenes(AnnoBroadGseaRes): Get gene-set genes from an AnnoBroadGseaRes object, returning a list of character string vectors.

• gsGenes(GmtList): Get gene-set genes from a GmtList object, returning a list of character string vector. It uses the implementation in BioQC.

Description

Set gene-set genes

Usage

gsGenes(object) <- value

## S4 replacement method for signature 'AnnoBroadGseaResItem,character'
gsGenes(object) <- value

Arguments

Value

The modified object.

Functions

• gsGenes(object = AnnoBroadGseaResItem) <- value: Assign gene-set genes to AnnoBroadGseaResItem

Description

Return gene-set gene values

Usage

gsGeneValues(object)

## S4 method for signature 'AnnoBroadGseaResItem'
gsGeneValues(object)

## S4 method for signature 'AnnoBroadGseaRes'
gsGeneValues(object)

Arguments

Value

A numeric vector or list of numeric vectors of gene values.

Methods (by class)

• gsGeneValues(AnnoBroadGseaResItem): Return values associated with the genes in a gene-set in an AnnoBroadGseaResItem object in a numeric vector.

• gsGeneValues(AnnoBroadGseaRes): Return values associated with the genes in a gene-set in an AnnoBroadGseaRes object in a list of numeric vectors.

Description

Set gene-set gene statistics (values)

Usage

gsGeneValues(object) <- value

## S4 replacement method for signature 'AnnoBroadGseaResItem,numeric'
gsGeneValues(object) <- value

Arguments

Value

The modified object.

Functions

• gsGeneValues(object = AnnoBroadGseaResItem) <- value: Assign values associated with gene-set genes to an annoBraoadGseaResItem object

Description

Core algorithm to perform Fisher's exact test on a list of gene set

Usage

gsListFisherTestCore(
  genes,
  geneSetGenesList,
  universe,
  makeUniqueNonNA = TRUE,
  checkUniverse = TRUE,
  useEASE = FALSE
)

Arguments

Value

A list of lists, of the same length as the input geneSetGenesList, each list consisting of three elements

1. p The p-value of one-sided (over-representation of the Fisher's test)

2. gsEffectiveSize Gene-set's effective size, namely number of genes that are in the universe

3. hits Character vector, genes that are found in the gene sets

References

Hosack et al.

Hosack, Douglas A., Glynn Dennis, Brad T. Sherman, H. Clifford Lane, and Richard A. Lempicki. Identifying Biological Themes within Lists of Genes with EASE. Genome Biology 4 (2003): R70. doi:10.1186/gb-2003-4-10-r70

See Also

gsFisherTestCore

Examples

myGenes <- LETTERS[1:3]
myGeneSet1 <- LETTERS[1:6]
myGeneSet2 <- LETTERS[4:7]
myUniverse <- LETTERS
gsListFisherTestCore(myGenes, list(myGeneSet1, myGeneSet2), myUniverse)

Description

Return gene-set name

Usage

gsName(object, ...)

## S4 method for signature 'BroadGseaResItem'
gsName(object)

## S4 method for signature 'AnnoBroadGseaRes'
gsName(object)

## S4 method for signature 'FisherResult'
gsName(object)

## S4 method for signature 'FisherResultList'
gsName(object, ...)

## S4 method for signature 'GmtList'
gsName(object)

## S4 method for signature 'FisherResultList'
gsName(object, ...)

Arguments

Value

A character vector of gene-set names.

Methods (by class)

• gsName(BroadGseaResItem): Get gene-set name from a BroadGseaResItem object

• gsName(AnnoBroadGseaRes): Get gene-set name from an AnnoBroadGseaRes object

• gsName(FisherResult): Get gene-set name from a FisherResult object

• gsName(FisherResultList): Get gene-set name from a FisherResultList object

• gsName(GmtList): Get gene-set name from a GmtList object

• gsName(FisherResultList): Get gene-set name from a FisherResultList object

Description

Return gene-set namespace

Usage

gsNamespace(object, ...)

## S4 method for signature 'GmtList'
gsNamespace(object)

## S4 method for signature 'FisherResult'
gsNamespace(object)

## S4 method for signature 'FisherResultList'
gsNamespace(object)

Arguments

Value

A character vector of gene-set namespaces.

Methods (by class)

• gsNamespace(GmtList): Return gene-set namespace from a GmtList object

• gsNamespace(FisherResult): Return gene-set namespace from a FisherResult object

• gsNamespace(FisherResultList): Return gene-set namespace from a FisherResultList object.

Description

Return the size (unique length) of gene-sets

Usage

gsSize(gmtList)

Arguments

Value

An integer vector

Description

Return hits

Usage

hits(object, ...)

## S4 method for signature 'FisherResult'
hits(object)

## S4 method for signature 'FisherResultList'
hits(object, geneset)

Arguments

Value

A character vector or list of hit genes.

Methods (by class)

• hits(FisherResult): Return hits from a FisherResult object

• hits(FisherResultList): Return hits from a FisherResultList object, returning a list if geneset is missing, or gene-set genes if geneset is present.

Description

Insert a GmtList object to GeMS

Usage

insertGmtListToGeMS(
  gmtList,
  geneFormat = 0,
  source = "PubMed",
  taxID = 9606,
  user = ribiosUtils::whoami(),
  subtype = "",
  domain = ""
)

Arguments

Value

Response code or error message returned by the GeMS API. A value of 200 indicates a successful insertion.

See Also

removeFromGeMS

Examples

## Not run: 
  testList <- list(list(name="GS_A", desc=NULL, genes=c("MAPK14", "JAK1", "EGFR")),
    list(name="GS_B", desc="gene set B", genes=c("ABCA1", "DDR1", "DDR2")),
    list(name="GS_C", desc="gene set C", genes=NULL))
  testGmt <- BioQC::GmtList(testList)
  ## insertGmtListToGeMS(testGmt, geneFormat=0, source="Test")
  ## removeFromGeMS(setName=c("GS_A", "GS_B", "GS_C"), source="Test")

## End(Not run)

Description

Construct message body to insert into GeMS

Usage

insertGmtListToGeMSBody(
  gmtList,
  geneFormat = 0,
  source = "PubMed",
  taxID = 9606,
  user = ribiosUtils::whoami(),
  subtype = "",
  domain = ""
)

Arguments

Value

A list with three items: headers, parsed, and params

Examples

testList <- list(list(name="GS_A", desc=NULL, genes=c("MAPK14", "JAK1", "EGFR")),
  list(name="GS_B", desc="gene set B", genes=c("ABCA1", "DDR1", "DDR2")),
  list(name="GS_C", desc="gene set C", genes=NULL))
testGmt <- BioQC::GmtList(testList)
insertGmtListToGeMSBody(testGmt, geneFormat=0, source="Test")

Description

Test whether GeMS is reachable

Usage

isGeMSReachable()

Value

Logical value

Examples

## Not run: 
  ## isGeMSReachble()

## End(Not run)

Description

Return a vector of logical values, indicating whether genes belong to core enrichment or not

Usage

isGseaCoreEnrich(object)

Arguments

Value

A logical vector

Description

Return a logical vector indicating whether a gene-set is significantly enriched or not, given the FDR threshold

Usage

isSigGeneSet(object, fdr = 0.05)

Arguments

Value

A logical vector

Description

S3 generic for kendallW

Usage

kendallW(object, ...)

Arguments

Value

A matrix with an info attribute, see kendallWmat.

Description

Compute Kendall's W for an eSet object

Usage

## S3 method for class 'eSet'
kendallW(
  object,
  row.factor,
  summary = c("none", "mean", "median", "max.mean.sig", "max.var.sig"),
  na.rm = TRUE,
  alpha = 0.01,
  ...
)

Arguments

Value

An ExpressionSet object with consolidated features.

See Also

kendallWmat

Description

Compute Kendall's W for a matrix

Usage

## S3 method for class 'matrix'
kendallW(
  object,
  row.factor,
  summary = c("none", "mean", "median", "max.mean.sig", "max.var.sig"),
  na.rm = TRUE,
  alpha = 0.01,
  ...
)

Arguments

Value

A matrix with an info attribute, see kendallWmat.

See Also

kendallWmat

Description

S3 generic for kendallW information

Usage

kendallWinfo(object)

## S3 method for class 'matrix'
kendallWinfo(object)

Arguments

Value

A data.frame containing grouping information.

Methods (by class)

• kendallWinfo(matrix): Extract kendallW information from a matrix

Description

S3 method to assign kendallW information to a matrix

Usage

## S3 replacement method for class 'matrix'
kendallWinfo(object) <- value

Arguments

Value

The matrix containing grouping information

Description

Kendall's W, also known as Kendall's coefficient of concordance, is a non-parametric statistic developed to assess agreement among raters used in psychological or similar experimental settings.

Usage

kendallWmat(
  mat,
  row.factor,
  summary = c("none", "mean", "median", "max.mean.sig", "max.var.sig"),
  na.rm = TRUE,
  alpha = 0.01
)

Arguments

Details

In computational biology, the concept of associating features with similar patterns while keeping outliers can be useful in many cases. See the Details section for examples.

This function implements the Kendall's W recursively with graph theory. It split grouped measurements into strongly associated sub-groups. See the Details section.

We take a microarray experiment as an example to demonstrate how the function works. In microarrays, a gene is often represented by more than one probeset, and it is not rare that they do not all resemble the same expression pattern. Usually a one gene-one value relation is desired. Common practices including choosing the probeset with the highest average signal or the highest variance, as well as taking the mean/median value of all probesets mapped to one gene as the representative value.

Kendall's W takes a very different approach. First it tries to judge whether multiple probesets of one gene are concordant. The concordance is determined by a non-parametric statistic closely related to Spearman correlation coefficient as well as Friedman's test. If all probesets are concordant, it means that their expression patterns are closely associated with each other. Any one of them, or the mean value, can be then used to represent the expression level of the gene.

In cases where there is little concordance among probesets, we can take use of graph theory to iteratively search for sub-groups of probesets resemble each other's expression patterns. In the extreme case, each probeset can be different from the rest, and in this case the number of sub-groups will be equal to the number of probesets mapped to the gene. Such cases can appear, for instance, when each probeset was designed to target a different region of a transcript with splice variants. By using Kendall's W statistic with graph theory, the kendallWmat function can detect sub-groups with strongly correlated expression patterns, while keeping outliers on their own, therefore providing help for both conventional expression analysis and post-hoc analysis with the help of sequence analysis. See reference for examples on this application.

We believe this approach is only useful for microarray, but can be also interesting for other applications like next-generation sequencing (NGS) or pathway/network analysis. For instance, in NGS experiments, this method can help to determine which splice variants of a transcript have similar expression patterns, and how different are other variants. In pathway analysis, when rows indicate gene expression values and row.factor indicate pathway membership, the result reveals which sub-networks are regulated associatively.

Value

Currently a matrix with one attribute slot named info.

Author(s)

Jitao David Zhang <[email protected]>

References

The concept of Kendall's W was introduced in the seminal paper The problem of m rankings by M.G. Kendall and B.B. Smith (The Annals of Mathematical Statistics, 1939). Schneider, Smith and Hansen developed the SCOREM algorithm combining this statistic with graph theory (SCOREM: statistical consolidation of redundant expression measures, Nucleic Acids Research, 2011). This implementation is very much based on the SCOREM algorithm. The main changes are (1) the current implementation is more generic, applicable to native R data structures, therefore able to be applied in other scenario than microarray analysis (2) it takes not-annotated features into account as well and (3) it is possible to directly calculate summary statistics from sub-groups.

Examples

## use a mock example
emat <- matrix(c(2,3,5,
                 8,9,2,
                 3,4,7,
                 0,2,1,
                 NA, 3, 1.2,
                 5, -3,4,
                 5,7,11), ncol=3, byrow=TRUE,
               dimnames=list(paste("row", 1:7, sep=""),NULL))
efac <- factor(c("a", "b", "c", NA, "b", "a", "a"),
               levels=letters[1:5])

print(emat)
kendallWmat(emat, efac, summary="none")
kendallWmat(emat, efac, summary="none", na.rm=FALSE)
kendallWmat(emat, efac, summary="mean")
kendallWmat(emat, efac, summary="mean", na.rm=FALSE)
kendallWmat(emat, efac, summary="median")
kendallWmat(emat, efac, summary="median", na.rm=FALSE)
kendallWmat(emat, efac, summary="max.mean.sig")
kendallWmat(emat, efac, summary="max.mean.sig", na.rm=FALSE)
kendallWmat(emat, efac, summary="max.var.sig")
kendallWmat(emat, efac, summary="max.var.sig", na.rm=TRUE)

## kendallW acts as an interface to matrix
kendallW(emat, efac, summary="none")

## kendallW acts as an interface to ExpressionSet
data(ribios.ExpressionSet, package="ribiosExpression")
kendallW(ribios.ExpressionSet, 
  Biobase::fData(ribios.ExpressionSet)$GeneID,
  summary="none")
kendallW(ribios.ExpressionSet, 
  Biobase::fData(ribios.ExpressionSet)$GeneID, 
  summary="mean")

Description

Cluster gene-sets by enrichment profiles with k-means clustering, and select representative gene-sets by gene-set composition

Usage

kmeansGeneset(
  enrichProfMatrix,
  genesetGenes,
  optK = pmin(25, floor(nrow(enrichProfMatrix)/2)),
  iter.max = 15,
  nstart = 50,
  thrCumJaccardIndex = 0.5,
  maxRepPerCluster = 10,
  metaClusterColumns = 1:ncol(enrichProfMatrix)
)

Arguments

Value

A list:

• kmeans Result object returned by kmeans.

• genesetClusterData A data.frame with following columns: GenesetCluster, GenesetInd, GenesetName, JaccardIndex, CumJaccardIndex, IsRepresentative.

• repGenesets Character vector, gene-set names that are selected as representative gene-sets from each gene-set clsuter.

• gsCompOverlapSelInd Factor vector, indicating the gene-set clusters represented by each representative gene-set.

Examples

set.seed(1887)
profMat <- matrix(rnorm(100), nrow=20, 
    dimnames=list(sprintf("geneset%d", 1:20), sprintf("contrast%d", 1:5)))
gsGenes <- lapply(1:nrow(profMat), function(x) 
    unique(sample(LETTERS, 10, replace=TRUE)))
names(gsGenes) <- rownames(profMat)
kmeansGeneset(profMat, gsGenes, optK=5)

Description

First-level list must have vectors of basic data types defined by R such as characater, integer, number, and logical.The function transforms such a list into adjacency matrix, rows of which are vector elements and columns of which are names of the list.

Usage

list2mat(list)

Arguments

Value

An adjacency matrix. Row and column names are defined by unique elements and list names, respectively.

Author(s)

Jitao David Zhang <[email protected]>

Examples

testList <- list(HSV=c("Adler", "Westermann", "Jansen"), FCB=c("Robben",
"Jansen", "Neuer"), S04=c("Westermann", "Neuer"))
list2mat(testList)

testList2 <- list(c("A", "B", "C"), c("B", "C", "D"), c("D", "E", "F"))
list2mat(testList2)

testList3 <- list(Worker1=0:8L, Worker2=5:13L, Worker3=8:16L, Worker4=16:24L)
list2mat(testList3)

Description

Perform the GAGE analysis for EdgeResult and GmtList

Usage

logFCgage(edgeResult, gmtList)

Arguments

Value

A data.frame containing enrichment analysis results.

Description

Merge CAMERA results using limma default parameters and biosCamera parameters

Usage

mergeCameraResults(
  matrix,
  index,
  designMatrix,
  contrast,
  featureLabels,
  weights = NULL,
  use.ranks = FALSE
)

Arguments

Value

A data.frame containing merged CAMERA results.

See Also

camera, biosCamera

Examples

y <- matrix(rnorm(1000*6),1000,6)
features <- sprintf("Feature%d", 1:nrow(y))
design <- cbind(Intercept=1,Group=c(0,0,0,1,1,1))
# First set of 20 genes are genuinely deferentially expressed 
index1 <- 1:20
y[index1,4:6] <- y[index1,4:6]+1
# The second set of 20 genes are not
index2 <- 21:40
index1Res <- mergeCameraResults(y, index=index1, 
  designMatrix=design, contrast=c(0,1), featureLabels=features)
index1ListRes <- mergeCameraResults(y, index=list(index1), 
   designMatrix=design, contrast=c(0,1), featureLabels=features)
index12ListRes <- mergeCameraResults(y, index=list(index1, index2), 
   designMatrix=design, contrast=c(0,1), featureLabels=features)

Description

Return the minimal FDR value from a FisherResultList

Usage

minFDRvalue(object)

Arguments

Value

A numeric value

Description

Return the minimal p-value from a FisherResultList

Usage

minPvalue(object)

Arguments

Value

A numeric value

Description

Wrap the gage::gage method to report consistent results as the CAMERA method

Usage

myGage(logFC, gmtList, ...)

Arguments

Value

A data.frame containing enrichment analysis results.

Description

Order strings by numbers in them

Usage

orderByNumberInStr(str, ...)

Arguments

Value

An integer vector of indices.

See Also

factorByNumberInStr, which makes factors with levels ordered by numbers in the string

Examples

orderByNumberInStr(c("D1", "D10", "D15", "D3.5"))

Description

Parse contributing genes by genesets from the result data.frame of the CAMERA method

Usage

parseCameraContributingGenes(cameraResTbl, genesets)

Arguments

Value

A list of gene symbols, indexed by geneset names that are found in the results.

Description

Parse contributing genes from the CAMERA output file

Usage

parseContributingGenes(str)

Arguments

Value

A list of data.frames, each containing two columns, Gene and Stat

Examples

parseContributingGenes("AKR1C4(-1.25), AKR1D1(-1.11)")
parseContributingGenes(c("AKR1C4(-1.25), AKR1D1(-1.11)",
                         "AKT1(1.24), AKT2(1.11), AKT3(1.05)"))

Description

Parse contributing genes by genesets

Usage

parseGenesetsContributingGenes(str, genesets)

Arguments

Value

A data.frame containing genesets, genes, and statistics

Examples

parseGenesetsContributingGenes("AKR1C4(-1.25), AKR1D1(-1.11)", "Metabolism")
parseGenesetsContributingGenes(c("AKR1C4(-1.25), AKR1D1(-1.11)",
                         "AKT1(1.24), AKT2(1.11), AKT3(1.05)"),
                         c("Metabolism", "AKTs"))

Description

Parse an output directory of the Broad GSEA tool

Usage

parseGSEAdir(dir)

Arguments

Value

An AnnoBroadGseaRes object

Description

Pretty RONET Gene-set Names

Usage

prettyRonetGenesetNames(x, nchar = 50)

Arguments

Value

Character strings

Examples

strs <- c("ARNT_GeneID405_negativeTargets",
  "Neurophysiological_process_nNOS_signaling_in_neuronal_synapses",
  "NR5A1_GeneID2516_allTargets", 
  "IL4_GeneID3565_negativeTargets",
  "Apoptosis_REACTOME")
prettyRonetGenesetNames(strs)

Description

Print a FisherResult object

Usage

## S3 method for class 'FisherResult'
print(x, ...)

Arguments

Value

x, invisibly.

Description

Print a FisherResultList object

Usage

## S3 method for class 'FisherResultList'
print(x, ...)

Arguments

Value

x, invisibly.

Description

Print S3 object FishersMethodResult

Usage

## S3 method for class 'FishersMethodResult'
print(x, ...)

Arguments

Value

x, invisibly.

Description

Print contributing genes

Usage

printContributingGenes(geneLabels, geneValues)

Arguments

Value

A vector of character strings

Description

Return P-values

Usage

pValue(object, ...)

## S4 method for signature 'FisherResult'
pValue(object)

## S4 method for signature 'FisherResultList'
pValue(object, ind, ...)

## S4 method for signature 'FisherResult'
fdrValue(object)

## S4 method for signature 'FisherResultList'
fdrValue(object, ind, ...)

Arguments

Value

A numeric vector of p-values.

Methods (by class)

• pValue(FisherResult): Return the p-value from a FisherResult

• pValue(FisherResultList): Return the p-values from a FisherResultList. If ind is missing, all p-values are returned; otherwise, the subset indicated by ind is returned.

• fdrValue(FisherResult): Return the FDR-value from a FisherResult

• fdrValue(FisherResultList): Return the FDR-values from a FisherResultList. If ind is missing, all FDR-values are returned; otherwise, the subset indicated by ind is returned.

Description

Read CAMERA results into a tibble object

Usage

readCameraResults(file, minNGenes = 3, maxNGenes = 1000)

Arguments

Value

A tibble containing the CAMERA results.

Description

In Roche Bioinformatics we use a default collection of gene-sets for gene-set enrichment analysis. This function loads this collection.

Usage

readDefaultGenesets(path, mps = FALSE)

Arguments

Details

The default collection includes both publicly available genesets as well as proprietary genesets, and therefore they are not included as part of the ribios package.

Publicly available genesets include

• MSigDB: collections C2, C7 and Hallmark

• RONET: which is a collection of publicly available pathway databases including REACTOME and NCI-Nature

• goslim

Value

A GmtList object containing the default gene-set collections.

Examples

## Not run: 
  ## this cannot be run because the files are not located there
  ## readDefaultGenesets("/tmp/defaultGmts")

## End(Not run)

Description

Read molecular-phenotyping genesets

Usage

readMPSGmt(file)

Arguments

Value

A GmtList object containing molecular-phenotypic screening (MPS) categories and genes

Description

Read RONET GMT files with namespace information

Usage

readRonetGmt(file)

Arguments

Value

A GmtList object with an additional 'namespace' item in each list

Description

Read significant CAMERA results into a tibble

Usage

readSigCameraResults(
  file,
  returnAllContrasts = TRUE,
  maxPValue = 0.01,
  minAbsEffectSize = 0.5,
  minNGenes = 5,
  maxNGenes = 200,
  excludeNamespace = c("goslim", "immunespace", "immunomics", "mbdisease", "mbpathology",
    "mbtoxicity", "msigdbC7", "msigdbC2", "MolecularPhenotyping")
)

Arguments

Value

A tibble containing filtered CAMERA results.

Description

Read significant CAMERA results into a matrix

Usage

readSigCameraScoreMatrix(file, ...)

Arguments

Value

A numeric matrix with gene-sets as rows and contrasts as columns.

Description

Rmove one or gene sets of the same source and user from GeMS

Usage

removeFromGeMS(
  setName = "",
  source = "",
  user = ribiosUtils::whoami(),
  subtype = ""
)

Arguments

Value

Response code or error message returned by the GeMS API. A value of 200 indicates a successful insertion.

See Also

insertGmtListToGeMS

Examples

## Not run: 
  testList <- list(list(name="GS_A", desc=NULL, genes=c("MAPK14", "JAK1", "EGFR")),
    list(name="GS_B", desc="gene set B", genes=c("ABCA1", "DDR1", "DDR2")),
    list(name="GS_C", desc="gene set C", genes=NULL))
  testGmt <- BioQC::GmtList(testList)
  ## insertGmtListToGeMS(testGmt, geneFormat=0, source="Test")
  ## removeFromGeMS(setName=c("GS_A", "GS_B", "GS_C"), source="Test")

## End(Not run)

Description

Message body to remove one or gene sets of the same source and user from GeMS

Usage

removeFromGeMSBody(
  setName = "",
  source = "",
  user = ribiosUtils::whoami(),
  subtype = ""
)

Arguments

Value

A list of genesets to be removed, to be sent as message body

Examples

removeFromGeMSBody(setName=c("GS_A", "GS_B", "GS_C"), source="Test")

Description

Extract gene-set namespace from RONET GMT files

Usage

ronetGeneSetNamespace(gmtList)

Arguments

Value

Character vector of the same length, indicating categorie

Description

Show a anonBroadGseaRes object

Usage

## S4 method for signature 'AnnoBroadGseaRes'
show(object)

Arguments

Description

Show an AnnoBroadGseaResItem object

Usage

## S4 method for signature 'AnnoBroadGseaResItem'
show(object)

Arguments

Description

Show a BroadGseaResItem object

Usage

## S4 method for signature 'BroadGseaResItem'
show(object)

Arguments

Description

Return names of gene-sets that are significantly enriched given the FDR threshold

Usage

sigGeneSet(object, fdr)

Arguments

Value

A character vector

Description

Return a data.frame of significantly enriched gene-sets

Usage

sigGeneSetTable(object, fdr)

Arguments

Value

A data.frame

Description

Return a data.frame of top gene-sets with the lowest p-values

Usage

topGeneSetTable(object, N)

Arguments

Value

A data.frame

Description

Return a data.frame of significantly enriched gene-sets with a minimum number

Usage

topOrSigGeneSetTable(object, fdr = 0.05, N = 10)

Arguments

Value

A data.frame.

Description

Write an GmtList object into a file

Usage

writeGmt(gmtList, file)

Arguments

Value

Invisibly returns NULL. Called for its side effect of writing the GMT file.

Note

The function will be moved to BioQC once the ribiosIO is reposited in CRAN

Examples

gmtFile <- system.file("extdata", "example.gmt", package="ribiosGSEA")
mySet <- BioQC::readGmt(gmtFile)[1:5]
myTempFile <- tempfile()
writeGmt(mySet, file=myTempFile)
readLines(myTempFile)

Description

Calculate mid-p quantile residuals

Usage

zscoreDGE(y, design = NULL, contrast = ncol(design))

Arguments

Value

A numeric matrix of z-scores with the same dimensions as the input count matrix.

Examples

dgeMatrix <- matrix(rpois(1200, 10), nrow=200)
dgeList <- DGEList(dgeMatrix)
dgeList <- edgeR::estimateCommonDisp(dgeList)
dgeDesign <- model.matrix(~gl(2,3))
dgeZscore <- zscoreDGE(dgeList, dgeDesign, contrast=c(0,1))
head(dgeZscore)