[med-svn] [r-bioc-ebseq] 01/02: Imported Upstream version 1.6.0
Michael Crusoe
misterc-guest at moszumanska.debian.org
Tue Feb 17 02:11:03 UTC 2015
This is an automated email from the git hooks/post-receive script.
misterc-guest pushed a commit to branch master
in repository r-bioc-ebseq.
commit c84595bcd7f721a6b4d9026947388f6221dafd3e
Author: Michael R. Crusoe <mcrusoe at msu.edu>
Date: Mon Feb 16 19:43:03 2015 -0500
Imported Upstream version 1.6.0
---
DESCRIPTION | 23 +
NAMESPACE | 5 +
NEWS | 40 ++
R/DenNHist.R | 51 ++
R/EBMultiTest.R | 425 +++++++++++++
R/EBTest.R | 592 ++++++++++++++++++
R/GetMultiFC.R | 65 ++
R/GetMultiPP.R | 14 +
R/GetNg.R | 12 +
R/GetNormalizedMat.R | 6 +
R/GetPP.R | 5 +
R/GetPPMat.R | 5 +
R/GetPatterns.R | 12 +
R/Likefun.R | 26 +
R/LikefunMulti.R | 28 +
R/LogN.R | 64 ++
R/LogNMulti.R | 79 +++
R/MedianNorm.R | 5 +
R/PlotPattern.R | 7 +
R/PlotPostVsRawFC.R | 21 +
R/PolyFitPlot.R | 44 ++
R/PostFC.R | 38 ++
R/QQP.R | 45 ++
R/QuantileNorm.R | 10 +
R/RankNorm.R | 13 +
R/beta.mom.R | 10 +
R/crit_fun.R | 15 +
R/f0.R | 27 +
R/f1.R | 10 +
build/vignette.rds | Bin 0 -> 199 bytes
data/GeneMat.rda | Bin 0 -> 26786 bytes
data/IsoList.rda | Bin 0 -> 32361 bytes
data/IsoMultiList.rda | Bin 0 -> 7739 bytes
data/MultiGeneMat.rda | Bin 0 -> 9221 bytes
demo/00Index | 1 +
demo/EBSeq.R | 250 ++++++++
inst/doc/EBSeq_Vignette.R | 497 +++++++++++++++
inst/doc/EBSeq_Vignette.Rnw | 1054 ++++++++++++++++++++++++++++++++
inst/doc/EBSeq_Vignette.pdf | Bin 0 -> 958612 bytes
man/DenNHist.Rd | 46 ++
man/EBMultiTest.Rd | 97 +++
man/EBSeq_NingLeng-package.Rd | 40 ++
man/EBTest.Rd | 103 ++++
man/GeneMat.Rd | 20 +
man/GetMultiFC.Rd | 64 ++
man/GetMultiPP.Rd | 46 ++
man/GetNg.Rd | 52 ++
man/GetNormalizedMat.Rd | 33 +
man/GetPP.Rd | 42 ++
man/GetPPMat.Rd | 39 ++
man/GetPatterns.Rd | 29 +
man/IsoList.Rd | 19 +
man/IsoMultiList.Rd | 19 +
man/Likefun.Rd | 36 ++
man/LikefunMulti.Rd | 40 ++
man/LogN.Rd | 39 ++
man/LogNMulti.Rd | 44 ++
man/MedianNorm.Rd | 38 ++
man/MultiGeneMat.Rd | 20 +
man/PlotPattern.Rd | 36 ++
man/PlotPostVsRawFC.Rd | 45 ++
man/PolyFitPlot.Rd | 101 ++++
man/PostFC.Rd | 58 ++
man/QQP.Rd | 43 ++
man/QuantileNorm.Rd | 47 ++
man/RankNorm.Rd | 40 ++
man/beta.mom.Rd | 39 ++
man/crit_fun.Rd | 51 ++
man/f0.Rd | 37 ++
man/f1.Rd | 42 ++
vignettes/EBSeq_Vignette.Rnw | 1054 ++++++++++++++++++++++++++++++++
vignettes/PlotExample.png | Bin 0 -> 122287 bytes
vignettes/lengetal.bib | 1342 +++++++++++++++++++++++++++++++++++++++++
73 files changed, 7300 insertions(+)
diff --git a/DESCRIPTION b/DESCRIPTION
new file mode 100644
index 0000000..a05a01d
--- /dev/null
+++ b/DESCRIPTION
@@ -0,0 +1,23 @@
+Package: EBSeq
+Type: Package
+Title: An R package for gene and isoform differential expression
+ analysis of RNA-seq data
+Version: 1.6.0
+Date: 2014-9-17
+Author: Ning Leng, Christina Kendziorski
+Maintainer: Ning Leng <nleng at wisc.edu>
+Depends: blockmodeling, gplots, R (>= 3.0.0)
+Description: Differential Expression analysis at both gene and isoform
+ level using RNA-seq data
+License: Artistic-2.0
+LazyLoad: yes
+Collate: 'MedianNorm.R' 'GetNg.R' 'beta.mom.R' 'f0.R' 'f1.R'
+ 'Likefun.R' 'LogN.R' 'LogNMulti.R' 'LikefunMulti.R' 'EBTest.R'
+ 'GetPatterns.R' 'EBMultiTest.R' 'GetPP.R' 'PostFC.R'
+ 'GetPPMat.R' 'GetMultiPP.R' 'GetMultiFC.R' 'PlotPostVsRawFC.R'
+ 'crit_fun.R' 'DenNHist.R' 'GetNormalizedMat.R' 'PlotPattern.R'
+ 'PolyFitPlot.R' 'QQP.R' 'QuantileNorm.R' 'RankNorm.R'
+BuildVignettes: yes
+biocViews: StatisticalMethod, DifferentialExpression,
+ MultipleComparison, RNASeq, Sequencing
+Packaged: 2014-10-14 03:22:48 UTC; biocbuild
diff --git a/NAMESPACE b/NAMESPACE
new file mode 100644
index 0000000..9b63076
--- /dev/null
+++ b/NAMESPACE
@@ -0,0 +1,5 @@
+export(crit_fun, DenNHist, EBTest, GetNg, GetPP, MedianNorm,
+PolyFitPlot, PostFC, QQP, QuantileNorm, RankNorm, EBMultiTest,
+GetMultiPP, GetPatterns, PlotPattern, GetPPMat, GetMultiFC, PlotPostVsRawFC,
+GetNormalizedMat,f0,f1,LogN,LogNMulti)
+
diff --git a/NEWS b/NEWS
new file mode 100644
index 0000000..0424f32
--- /dev/null
+++ b/NEWS
@@ -0,0 +1,40 @@
+CHANGES IN VERSION 1.5.4
+------------------------
+
+
+ o An extra numerical approximation step is implemented
+ in EBMultiTest() function to avoid
+ underflow. The underflow is likely due to large number of samples.
+ A bug in EBMultiTest() is fixed. The bug will cause error when there is
+ exactly 1 gene/isoform that needs numerical approximation.
+
+CHANGES IN VERSION 1.5.3
+-------------------------
+
+BUG FIXES
+
+ o Fixed a bug that may generate NA FC estimates when there are no replicates.
+
+CHANGES IN VERSION 1.5.2
+------------------------
+
+NEW FEATURES
+
+ o An extra numerical approximation step is
+ implemented in EBTest() function to avoid
+ underflow. The underflow is likely due to large number of samples.
+
+
+CHANGES IN VERSION 1.3.3
+------------------------
+
+NEW FEATURES
+
+ o In EBSeq 1.3.3, the default setting of EBTest function will remove
+ low expressed genes (genes whose 75th quantile of normalized counts is less
+ than 10) before identifying DE genes.
+ These two thresholds can be changed in EBTest function.
+ We found that low expressed genes are more easily to be affected by noises.
+ Removing these genes prior to downstream analyses can improve the
+ model fitting and reduce impacts of noisy genes (e.g. genes with outliers).
+
diff --git a/R/DenNHist.R b/R/DenNHist.R
new file mode 100644
index 0000000..6c36a00
--- /dev/null
+++ b/R/DenNHist.R
@@ -0,0 +1,51 @@
+DenNHist <-
+function(EBOut, GeneLevel=F)
+{
+ if(!"Alpha"%in%names(EBOut))stop("The input doesn't seem like an output from EBTest/EBMultiTest")
+ maxround=nrow(EBOut$Alpha)
+ Alpha=EBOut$Alpha[maxround,]
+ Beta=EBOut$Beta[maxround,]
+ # Multi
+ if(!is.null(EBOut$PPpattern)){
+ QList=EBOut$QList
+ for(i in 1:length(EBOut$QList)){
+ for(j in 1:length(EBOut$QList[[i]])){
+ if(GeneLevel==F)Main=paste("Ig",i,"C",j)
+ if(GeneLevel==T)Main=paste("Gene","C",j)
+ hist(QList[[i]][[j]][QList[[i]][[j]]<.98&QList[[i]][[j]]>0],
+ prob=T,col="blue",breaks=100,
+ main=Main,
+ xlim=c(0,1),xlab=paste("Q alpha=",round(Alpha,2),
+ " beta=",round(Beta[i],2),sep=""))
+ tmpSize=length(QList[[i]][[j]][QList[[i]][[j]]<.98])
+ tmpseq=seq(0.001,1,length=1000)
+ ll=tmpseq
+ lines(ll,dbeta(ll,Alpha,Beta[i]),col="green",lwd=2)
+ legend("topright",c("Data","Fitted density"),col=c("blue","green"),lwd=2)
+ }
+ }
+ }
+
+ if(is.null(EBOut$PPpattern)){
+ for(con in 1:2){
+ if(con==1)QList=EBOut$QList1
+ if(con==2)QList=EBOut$QList2
+ if(!is.list(QList)) QList=list(QList)
+ for (i in 1:length(QList)){
+ if(GeneLevel==F)Main=paste("Ig",i,"C",con)
+ if(GeneLevel==T)Main=paste("Gene","C",con)
+ hist(QList[[i]][QList[[i]]<.98&QList[[i]]>0],
+ prob=T,col="blue",breaks=100,
+ main=Main,
+ xlim=c(0,1),xlab=paste("Q alpha=",round(Alpha,2),
+ " beta=",round(Beta[i],2),sep=""))
+ tmpSize=length(QList[[i]][QList[[i]]<.98])
+ tmpseq=seq(0.001,1,length=1000)
+ ll=tmpseq
+ lines(ll,dbeta(ll,Alpha,Beta[i]),col="green",lwd=2)
+ legend("topright",c("Data","Fitted density"),col=c("blue","green"),lwd=2)
+ }}
+ }
+
+ }
+
diff --git a/R/EBMultiTest.R b/R/EBMultiTest.R
new file mode 100644
index 0000000..ce2dd7e
--- /dev/null
+++ b/R/EBMultiTest.R
@@ -0,0 +1,425 @@
+EBMultiTest <-
+function(Data,NgVector=NULL,Conditions,AllParti=NULL, sizeFactors, maxround, Pool=F, NumBin=1000, ApproxVal=10^-10,PoolLower=.25, PoolUpper=.75,Print=T,Qtrm=.75,QtrmCut=10)
+{
+ if(!is.factor(Conditions))Conditions=as.factor(Conditions)
+ if(is.null(rownames(Data)))stop("Please add gene/isoform names to the data matrix")
+ if(!is.matrix(Data))stop("The input Data is not a matrix")
+ if(length(Conditions)!=ncol(Data))stop("The number of conditions is not the same as the number of samples! ")
+ if(nlevels(Conditions)==2)stop("Only 2 conditions - Please use EBTest() function")
+ if(nlevels(Conditions)<2)stop("Less than 2 conditions - Please check your input")
+ if(length(sizeFactors)!=length(Data) & length(sizeFactors)!=ncol(Data))
+ stop("The number of library size factors is not the same as the number of samples!")
+
+
+ tau=CI=CIthre=NULL
+ Dataraw=Data
+
+
+ #Normalized
+ DataNorm=GetNormalizedMat(Data, sizeFactors)
+
+
+
+ QuantileFor0=apply(DataNorm,1,function(i)quantile(i,Qtrm))
+ AllZeroNames=which(QuantileFor0<=QtrmCut)
+ NotAllZeroNames=which(QuantileFor0>QtrmCut)
+ if(length(AllZeroNames)>0 & Print==T)
+ cat(paste0("Removing transcripts with ",Qtrm*100,
+ " th quantile < = ",QtrmCut," \n",
+ length(NotAllZeroNames)," transcripts will be tested \n"))
+ if(length(NotAllZeroNames)==0)stop("0 transcript passed")
+ Data=Data[NotAllZeroNames,]
+
+ if(!is.null(NgVector))NgVector=NgVector[NotAllZeroNames]
+ if(is.null(NgVector))NgVector=rep(1,nrow(Data))
+
+
+ #ReNameThem
+ IsoNamesIn=rownames(Data)
+ Names=paste("I",c(1:dim(Data)[1]),sep="")
+ names(IsoNamesIn)=Names
+ rownames(Data)=paste("I",c(1:dim(Data)[1]),sep="")
+ names(NgVector)=paste("I",c(1:dim(Data)[1]),sep="")
+
+ # If PossibleCond==NULL, use all combinations
+ NumCond=nlevels(Conditions)
+ CondLevels=levels(Conditions)
+ #library(blockmodeling)
+ if(is.null(AllParti)){
+ AllPartiList=sapply(1:NumCond,function(i)nkpartitions(NumCond,i))
+ AllParti=do.call(rbind,AllPartiList)
+ colnames(AllParti)=CondLevels
+ rownames(AllParti)=paste("Pattern",1:nrow(AllParti),sep="")
+ }
+ if(length(sizeFactors)==length(Data)){
+ rownames(sizeFactors)=rownames(Data)
+ colnames(sizeFactors)=Conditions
+ }
+
+
+ NoneZeroLength=nlevels(as.factor(NgVector))
+ NameList=sapply(1:NoneZeroLength,function(i)names(NgVector)[NgVector==i],simplify=F)
+ DataList=sapply(1:NoneZeroLength , function(i) Data[NameList[[i]],],simplify=F)
+ names(DataList)=names(NameList)
+
+ NumEachGroup=sapply(1:NoneZeroLength , function(i)dim(DataList)[i])
+ # Unlist
+ DataList.unlist=do.call(rbind, DataList)
+
+ # Divide by SampleSize factor
+
+ if(length(sizeFactors)==ncol(Data))
+ DataList.unlist.dvd=t(t( DataList.unlist)/sizeFactors)
+
+ if(length(sizeFactors)==length(Data))
+ DataList.unlist.dvd=DataList.unlist/sizeFactors
+
+ # Pool or Not
+ if(Pool==T){
+ DataforPoolSP.dvd=MeanforPoolSP.dvd=vector("list",NumCond)
+ for(lv in 1:NumCond){
+ DataforPoolSP.dvd[[lv]]=matrix(DataList.unlist.dvd[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist)[1])
+ MeanforPoolSP.dvd[[lv]]=rowMeans(DataforPoolSP.dvd[[lv]])
+ }
+ MeanforPool.dvd=rowMeans(DataList.unlist.dvd)
+ NumInBin=floor(dim(DataList.unlist)[1]/NumBin)
+ StartSeq=c(0:(NumBin-1))*NumInBin+1
+ EndSeq=c(StartSeq[-1]-1,dim(DataList.unlist)[1])
+ MeanforPool.dvd.Sort=sort(MeanforPool.dvd,decreasing=T)
+ MeanforPool.dvd.Order=order(MeanforPool.dvd,decreasing=T)
+ PoolGroups=sapply(1:NumBin,function(i)(names(MeanforPool.dvd.Sort)[StartSeq[i]:EndSeq[i]]),simplify=F)
+ #FCforPool=MeanforPoolSP.dvd1/MeanforPoolSP.dvd2
+ # Use GeoMean of every two-group partition
+ Parti2=nkpartitions(NumCond,2)
+ FCForPoolList=sapply(1:nrow(Parti2),function(i)rowMeans(do.call(cbind,
+ MeanforPoolSP.dvd[Parti2[i,]==1]))/
+ rowMeans(do.call(cbind,MeanforPoolSP.dvd[Parti2[i,]==2])),
+ simplify=F)
+ FCForPoolMat=do.call(cbind,FCForPoolList)
+ FCforPool=apply(FCForPoolMat,1,function(i)exp(mean(log(i))))
+ names(FCforPool)=names(MeanforPool.dvd)
+ FC_Use=names(FCforPool)[which(FCforPool>=quantile(FCforPool[!is.na(FCforPool)],PoolLower) & FCforPool<=quantile(FCforPool[!is.na(FCforPool)],PoolUpper))]
+ PoolGroupVar=sapply(1:NumBin,function(i)(mean(apply(matrix(DataList.unlist[PoolGroups[[i]][PoolGroups[[i]]%in%FC_Use],],ncol=ncol(DataList.unlist)),1,var))))
+ PoolGroupVarInList=sapply(1:NumBin,function(i)(rep(PoolGroupVar[i],length(PoolGroups[[i]]))),simplify=F)
+ PoolGroupVarVector=unlist(PoolGroupVarInList)
+ VarPool=PoolGroupVarVector[MeanforPool.dvd.Order]
+ names(VarPool)=names(MeanforPool.dvd)
+ }
+
+ DataListSP=vector("list",nlevels(Conditions))
+ DataListSP.dvd=vector("list",nlevels(Conditions))
+ SizeFSP=DataListSP
+ MeanSP=DataListSP
+ VarSP=DataListSP
+ GetPSP=DataListSP
+ RSP=DataListSP
+ CISP=DataListSP
+ tauSP=DataListSP
+
+ NumEachCondLevel=summary(Conditions)
+ if(Pool==F & is.null(CI)) CondLevelsUse=CondLevels[NumEachCondLevel>1]
+ if(Pool==T | !is.null(CI)) CondLevelsUse=CondLevels
+ NumCondUse=length(CondLevelsUse)
+
+ for (lv in 1:nlevels(Conditions)){
+ DataListSP[[lv]]= matrix(DataList.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist)[1])
+ rownames(DataListSP[[lv]])=rownames(DataList.unlist)
+ DataListSP.dvd[[lv]]= matrix(DataList.unlist.dvd[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist.dvd)[1])
+ if(ncol(DataListSP[[lv]])==1 & Pool==F & !is.null(CI)){
+ CISP[[lv]]=matrix(CI[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist.dvd)[1])
+ tauSP[[lv]]=matrix(tau[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist.dvd)[1])
+ }
+ # no matter sizeFactors is a vector or a matrix. Matrix should be columns are the normalization factors
+ # may input one for each
+ if(length(sizeFactors)==ncol(Data))SizeFSP[[lv]]=sizeFactors[Conditions==levels(Conditions)[lv]]
+ if(length(sizeFactors)==length(Data))SizeFSP[[lv]]=sizeFactors[,Conditions==levels(Conditions)[lv]]
+
+ MeanSP[[lv]]=rowMeans(DataListSP.dvd[[lv]])
+ names(MeanSP[[lv]])=rownames(DataListSP[[lv]])
+
+ if(length(sizeFactors)==ncol(Data))PrePareVar=sapply(1:ncol( DataListSP[[lv]]),function(i)( DataListSP[[lv]][,i]- SizeFSP[[lv]][i]*MeanSP[[lv]])^2 /SizeFSP[[lv]][i])
+ if(length(sizeFactors)==length(Data))PrePareVar=sapply(1:ncol( DataListSP[[lv]]),function(i)( DataListSP[[lv]][,i]- SizeFSP[[lv]][,i]*MeanSP[[lv]])^2 /SizeFSP[[lv]][,i])
+
+ if(ncol(DataListSP[[lv]])==1 & Pool==F & !is.null(CI))
+ VarSP[[lv]]=as.vector(((DataListSP[[lv]]/tauSP[[lv]]) * CISP[[lv]]/(CIthre*2))^2)
+ if( Pool==T){
+ VarSP[[lv]]=VarPool
+ }
+ if(ncol(DataListSP[[lv]])!=1){
+ VarSP[[lv]]=rowSums(PrePareVar)/ncol( DataListSP[[lv]])
+ names(VarSP[[lv]])=rownames(DataList.unlist)
+ GetPSP[[lv]]=MeanSP[[lv]]/VarSP[[lv]]
+ RSP[[lv]]=MeanSP[[lv]]*GetPSP[[lv]]/(1-GetPSP[[lv]])
+ }
+ names(MeanSP[[lv]])=rownames(DataList.unlist)
+ }
+
+ # Get Empirical R
+ # POOL R???
+ MeanList=rowMeans(DataList.unlist.dvd)
+ VarList=apply(DataList.unlist.dvd, 1, var)
+
+ if(NumCondUse!=0){
+ Varcbind=do.call(cbind,VarSP[CondLevels%in%CondLevelsUse])
+ PoolVarSpeedUp_MDFPoi_NoNormVarList=rowMeans(Varcbind)
+ VarrowMin=apply(Varcbind,1,min)
+
+ }
+ if(NumCondUse==0)
+ {
+ NumFCgp=choose(NumCond,2)
+ FC_Use_tmp=vector("list",NumFCgp)
+ aa=1
+ for(k1 in 1:(NumCond-1)){
+ for(k2 in (k1+1):NumCond){
+ FCforPool=DataList.unlist.dvd[,k1]/DataList.unlist.dvd[,k2]
+ names(FCforPool)=rownames(DataList.unlist.dvd)
+ FC_Use_tmp[[aa]]=names(FCforPool)[which(FCforPool>=quantile(FCforPool[!is.na(FCforPool)],.25) &
+ FCforPool<=quantile(FCforPool[!is.na(FCforPool)],.75))]
+ aa=aa+1
+ }}
+ FC_Use=Reduce(intersect,FC_Use_tmp)
+ if(length(FC_Use)==0){
+ All_candi=unlist(FC_Use_tmp)
+ FC_Use=names(table(All_candi))[1:3]
+
+ }
+ Var_FC_Use=apply( DataList.unlist.dvd[FC_Use,],1,var )
+ MeanforPool=apply( DataList.unlist.dvd,1,mean )
+ Mean_FC_Use=apply( DataList.unlist.dvd[FC_Use,],1,mean )
+ FC_Use2=which(Var_FC_Use>=Mean_FC_Use)
+ Var_FC_Use2=Var_FC_Use[FC_Use2]
+ Mean_FC_Use2=Mean_FC_Use[FC_Use2]
+ Phi=mean((Var_FC_Use2-Mean_FC_Use2)/Mean_FC_Use2^2)
+ VarEst= MeanforPool*(1+MeanforPool*Phi)
+ if(Print==T)message(paste("No Replicate - estimate phi",round(Phi,5), "\n"))
+ Varcbind=VarEst
+ PoolVarSpeedUp_MDFPoi_NoNormVarList=VarEst
+ VarrowMin=VarEst
+
+ }
+
+
+
+ GetP=MeanList/PoolVarSpeedUp_MDFPoi_NoNormVarList
+
+ EmpiricalRList=MeanList*GetP/(1-GetP)
+ # sep
+ #Rcb=cbind(RSP[[1]],RSP[[2]])
+ #Rbest=apply(Rcb,1,function(i)max(i[!is.na(i) & i!=Inf]))
+ EmpiricalRList[EmpiricalRList==Inf] =max(EmpiricalRList[EmpiricalRList!=Inf])
+ # fine
+ #
+ GoodData=names(MeanList)[EmpiricalRList>0 & VarrowMin!=0 & EmpiricalRList!=Inf & !is.na(VarrowMin) & !is.na(EmpiricalRList)]
+ NotIn=names(MeanList)[EmpiricalRList<=0 | VarrowMin==0 | EmpiricalRList==Inf | is.na(VarrowMin) | is.na(EmpiricalRList)]
+ #NotIn.BestR=Rbest[NotIn.raw]
+ #NotIn.fix=NotIn.BestR[which(NotIn.BestR>0)]
+ #EmpiricalRList[names(NotIn.fix)]=NotIn.fix
+ #print(paste("ZeroVar",sum(VarrowMin==0), "InfR", length(which(EmpiricalRList==Inf)), "Poi", length(which(EmpiricalRList<0)), ""))
+ #GoodData=c(GoodData.raw,names(NotIn.fix))
+ #NotIn=NotIn.raw[!NotIn.raw%in%names(NotIn.fix)]
+ EmpiricalRList.NotIn=EmpiricalRList[NotIn]
+ EmpiricalRList.Good=EmpiricalRList[GoodData]
+ EmpiricalRList.Good[EmpiricalRList.Good<1]=1+EmpiricalRList.Good[EmpiricalRList.Good<1]
+ if(length(sizeFactors)==ncol(Data))
+ EmpiricalRList.Good.mat= outer(EmpiricalRList.Good, sizeFactors)
+ if(length(sizeFactors)==length(Data))
+ EmpiricalRList.Good.mat=EmpiricalRList.Good* sizeFactors[GoodData,]
+
+
+ # Only Use Data has Good q's
+ DataList.In=sapply(1:NoneZeroLength, function(i)DataList[[i]][GoodData[GoodData%in%rownames(DataList[[i]])],],simplify=F)
+ DataList.NotIn=sapply(1:NoneZeroLength, function(i)DataList[[i]][NotIn[NotIn%in%rownames(DataList[[i]])],],simplify=F)
+ DataListIn.unlist=do.call(rbind, DataList.In)
+ DataListNotIn.unlist=do.call(rbind, DataList.NotIn)
+
+ DataListSPIn=vector("list",nlevels(Conditions))
+ DataListSPNotIn=vector("list",nlevels(Conditions))
+ EmpiricalRList.Good.mat.SP=vector("list",nlevels(Conditions))
+ for (lv in 1:nlevels(Conditions)){
+ DataListSPIn[[lv]]= matrix(DataListIn.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataListIn.unlist)[1])
+ if(length(NotIn)>0) DataListSPNotIn[[lv]]= matrix(DataListNotIn.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataListNotIn.unlist)[1])
+ rownames(DataListSPIn[[lv]])=rownames(DataListIn.unlist)
+ if(length(NotIn)>0)rownames(DataListSPNotIn[[lv]])=rownames(DataListNotIn.unlist)
+ EmpiricalRList.Good.mat.SP[[lv]]=matrix(EmpiricalRList.Good.mat[,Conditions==levels(Conditions)[lv]],nrow=dim(EmpiricalRList.Good.mat)[1])
+ }
+
+ NumOfEachGroupIn=sapply(1:NoneZeroLength, function(i)max(0,dim(DataList.In[[i]])[1]))
+ NumOfEachGroupNotIn=sapply(1:NoneZeroLength, function(i)max(0,dim(DataList.NotIn[[i]])[1]))
+
+ #Initialize SigIn & ...
+ AlphaIn=0.5
+ BetaIn=rep(0.5,NoneZeroLength)
+ PIn=rep(1/nrow(AllParti),nrow(AllParti))
+
+ ####use while to make an infinity round?
+ UpdateAlpha=NULL
+ UpdateBeta=NULL
+ UpdateP=NULL
+ UpdatePFromZ=NULL
+ Timeperround=NULL
+ for (times in 1:maxround){
+ temptime1=proc.time()
+ UpdateOutput=suppressWarnings(LogNMulti(DataListIn.unlist,DataListSPIn, EmpiricalRList.Good.mat ,EmpiricalRList.Good.mat.SP,
+ NumOfEachGroupIn, AlphaIn, BetaIn, PIn, NoneZeroLength, AllParti,Conditions))
+ message(paste("iteration", times, "done \n",sep=" "))
+ AlphaIn=UpdateOutput$AlphaNew
+ BetaIn=UpdateOutput$BetaNew
+ PIn=UpdateOutput$PNew
+ PFromZ=UpdateOutput$PFromZ
+ FOut=UpdateOutput$FGood
+ UpdateAlpha=rbind(UpdateAlpha,AlphaIn)
+ UpdateBeta=rbind(UpdateBeta,BetaIn)
+ UpdateP=rbind(UpdateP,PIn)
+ UpdatePFromZ=rbind(UpdatePFromZ,PFromZ)
+ temptime2=proc.time()
+ Timeperround=c(Timeperround,temptime2[3]-temptime1[3])
+ message(paste("time" ,round(Timeperround[times],2),"\n",sep=" "))
+ Z.output=UpdateOutput$ZEachGood
+ Z.NA.Names=UpdateOutput$zNaNName
+ }
+ #Remove this } after testing!!
+
+# if (times!=1){
+# if((UpdateAlpha[times]-UpdateAlpha[times-1])^2+UpdateBeta[times]-UpdateBeta[times-1])^2+UpdateR[times]-UpdateR[times-1])^2+UpdateP[times]-UpdateP[times-1])^2<=10^(-6)){
+# Result=list(Sig=SigIn, Miu=MiuIn, Tau=TauIn)
+# break
+# }
+# }
+#}
+
+##########Change Names############
+## Only z are for Good Ones
+## Others are for ALL Data
+GoodData=GoodData[!GoodData%in%Z.NA.Names]
+IsoNamesIn.Good=as.vector(IsoNamesIn[GoodData])
+RealName.Z.output=Z.output
+RealName.F=FOut
+rownames(RealName.Z.output)=IsoNamesIn.Good
+rownames(RealName.F)=IsoNamesIn.Good
+
+RealName.EmpiricalRList=sapply(1:NoneZeroLength,function(i)EmpiricalRList[names(EmpiricalRList)%in%NameList[[i]]], simplify=F)
+RealName.MeanList=sapply(1:NoneZeroLength,function(i)MeanList[names(MeanList)%in%NameList[[i]]], simplify=F)
+RealName.SPMeanList=sapply(1:NoneZeroLength,function(i)sapply(1:length(MeanSP), function(j)MeanSP[[j]][names(MeanSP[[j]])%in%NameList[[i]]],simplify=F), simplify=F)
+RealName.SPVarList=sapply(1:NoneZeroLength,function(i)sapply(1:length(VarSP), function(j)VarSP[[j]][names(VarSP[[j]])%in%NameList[[i]]],simplify=F), simplify=F)
+RealName.DataList=sapply(1:NoneZeroLength,function(i)DataList[[i]][rownames(DataList[[i]])%in%NameList[[i]],], simplify=F)
+
+RealName.VarList=sapply(1:NoneZeroLength,function(i)VarList[names(VarList)%in%NameList[[i]]], simplify=F)
+RealName.PoolVarList=sapply(1:NoneZeroLength,function(i)PoolVarSpeedUp_MDFPoi_NoNormVarList[names(PoolVarSpeedUp_MDFPoi_NoNormVarList)%in%NameList[[i]]], simplify=F)
+RealName.QList=sapply(1:NoneZeroLength,function(i)sapply(1:length(GetPSP), function(j)GetPSP[[j]][names(GetPSP[[j]])%in%NameList[[i]]],simplify=F), simplify=F)
+
+
+for (i in 1:NoneZeroLength){
+tmp=NameList[[i]]
+Names=IsoNamesIn[tmp]
+RealName.MeanList[[i]]=RealName.MeanList[[i]][NameList[[i]]]
+RealName.VarList[[i]]=RealName.VarList[[i]][NameList[[i]]]
+ for(j in 1:NumCond){
+ RealName.SPMeanList[[i]][[j]]=RealName.SPMeanList[[i]][[j]][NameList[[i]]]
+ if(!is.null(RealName.QList[[i]][[j]])){
+ RealName.QList[[i]][[j]]=RealName.QList[[i]][[j]][NameList[[i]]]
+ RealName.SPVarList[[i]][[j]]=RealName.SPVarList[[i]][[j]][NameList[[i]]]
+ names(RealName.QList[[i]][[j]])=Names
+ names(RealName.SPVarList[[i]][[j]])=Names
+ }
+ names(RealName.SPMeanList[[i]][[j]])=Names
+ }
+RealName.EmpiricalRList[[i]]=RealName.EmpiricalRList[[i]][NameList[[i]]]
+RealName.PoolVarList[[i]]=RealName.PoolVarList[[i]][NameList[[i]]]
+RealName.DataList[[i]]=RealName.DataList[[i]][NameList[[i]],]
+
+names(RealName.MeanList[[i]])=Names
+names(RealName.VarList[[i]])=Names
+
+names(RealName.EmpiricalRList[[i]])=Names
+names(RealName.PoolVarList[[i]])=Names
+rownames(RealName.DataList[[i]])=Names
+
+}
+
+
+#########posterior part for other data set here later############
+AllNA=unique(c(Z.NA.Names,NotIn))
+AllZ=NULL
+AllF=NULL
+if(length(AllNA)==0){
+ AllZ=RealName.Z.output[IsoNamesIn,]
+ AllF=RealName.F[IsoNamesIn,]
+}
+ZEachNA=NULL
+if (length(AllNA)>0){
+ Ng.NA=NgVector[AllNA]
+ AllNA.Ngorder=AllNA[order(Ng.NA)]
+ NumOfEachGroupNA=rep(0,NoneZeroLength)
+ NumOfEachGroupNA.tmp=tapply(Ng.NA,Ng.NA,length)
+ names(NumOfEachGroupNA)=c(1:NoneZeroLength)
+ NumOfEachGroupNA[names(NumOfEachGroupNA.tmp)]=NumOfEachGroupNA.tmp
+ PNotIn=rep(1-ApproxVal,length(AllNA.Ngorder))
+ MeanList.NotIn=MeanList[AllNA.Ngorder]
+ R.NotIn.raw=MeanList.NotIn*PNotIn/(1-PNotIn)
+ if(length(sizeFactors)==ncol(Data))
+ R.NotIn=matrix(outer(R.NotIn.raw,sizeFactors),nrow=length(AllNA.Ngorder))
+ if(length(sizeFactors)==length(Data))
+ R.NotIn=matrix(R.NotIn.raw*sizeFactors[NotIn,],nrow=length(AllNA.Ngorder))
+
+ DataListNotIn.unlistWithZ=matrix(DataList.unlist[AllNA.Ngorder,],
+ nrow=length(AllNA.Ngorder))
+ rownames(DataListNotIn.unlistWithZ)=AllNA.Ngorder
+ DataListSPNotInWithZ=vector("list",nlevels(Conditions))
+ RListSPNotInWithZ=vector("list",nlevels(Conditions))
+ for (lv in 1:nlevels(Conditions)) {
+ DataListSPNotInWithZ[[lv]] = matrix(DataListSP[[lv]][AllNA.Ngorder,],nrow=length(AllNA.Ngorder))
+ RListSPNotInWithZ[[lv]]=matrix(R.NotIn[,Conditions==levels(Conditions)[lv]],nrow=length(AllNA.Ngorder))
+ }
+
+ FListNA=sapply(1:nrow(AllParti),function(i)sapply(1:nlevels(as.factor(AllParti[i,])),
+ function(j)f0(do.call(cbind, DataListSPNotInWithZ[AllParti[i,]==j]),AlphaIn, BetaIn,
+ do.call(cbind,RListSPNotInWithZ[AllParti[i,]==j]), NumOfEachGroupNA, log=T)),
+ simplify=F)
+ for(ii in 1:length(FListNA))
+ FListNA[[ii]]=matrix(FListNA[[ii]],nrow=length(AllNA.Ngorder))
+ FPartiLogNA=matrix(sapply(FListNA,rowSums),nrow=length(AllNA.Ngorder))
+ FMatNA=exp(FPartiLogNA+600)
+
+ rownames(FMatNA)=rownames(DataListNotIn.unlistWithZ)
+ PMatNA=matrix(rep(1,nrow(DataListNotIn.unlistWithZ)),ncol=1)%*%matrix(PIn,nrow=1)
+ FmultiPNA=matrix(FMatNA*PMatNA,nrow=length(AllNA.Ngorder))
+ DenomNA=rowSums(FmultiPNA)
+ ZEachNA=matrix(apply(FmultiPNA,2,function(i)i/DenomNA),nrow=length(AllNA.Ngorder))
+
+ rownames(ZEachNA)=IsoNamesIn[AllNA.Ngorder]
+
+ AllZ=rbind(RealName.Z.output,ZEachNA)
+ AllZ=AllZ[IsoNamesIn,]
+
+ F.NotIn=FPartiLogNA
+ rownames(F.NotIn)=IsoNamesIn[rownames(FMatNA)]
+ AllF=rbind(RealName.F,F.NotIn)
+ AllF=AllF[IsoNamesIn,]
+
+}
+colnames(AllZ)=rownames(AllParti)
+colnames(AllF)=rownames(AllParti)
+rownames(UpdateAlpha)=paste("iter",1:nrow(UpdateAlpha),sep="")
+rownames(UpdateBeta)=paste("iter",1:nrow(UpdateBeta),sep="")
+rownames(UpdateP)=paste("iter",1:nrow(UpdateP),sep="")
+rownames(UpdatePFromZ)=paste("iter",1:nrow(UpdatePFromZ),sep="")
+colnames(UpdateBeta)=paste("Ng",1:ncol(UpdateBeta),sep="")
+
+CondOut=levels(Conditions)
+names(CondOut)=paste("Condition",c(1:length(CondOut)),sep="")
+
+AllZWith0=matrix(NA,ncol=ncol(AllZ),nrow=nrow(Dataraw))
+rownames(AllZWith0)=rownames(Dataraw)
+colnames(AllZWith0)=colnames(AllZ)
+if(is.null(AllZeroNames))AllZWith0=AllZ
+if(!is.null(AllZeroNames))AllZWith0[names(NotAllZeroNames),]=AllZ[names(NotAllZeroNames),]
+
+#############Result############################
+Result=list(Alpha=UpdateAlpha,Beta=UpdateBeta,P=UpdateP,PFromZ=UpdatePFromZ,
+ Z=RealName.Z.output,PoissonZ=ZEachNA, RList=RealName.EmpiricalRList, MeanList=RealName.MeanList,
+ VarList=RealName.VarList, QList=RealName.QList, SPMean=RealName.SPMeanList, SPEstVar=RealName.SPVarList,
+ PoolVar=RealName.PoolVarList , DataList=RealName.DataList,PPpattern=AllZ,f=AllF, AllParti=AllParti,
+ PPMat=AllZ,PPMatWith0=AllZWith0, ConditionOrder=CondOut)
+}
+
diff --git a/R/EBTest.R b/R/EBTest.R
new file mode 100644
index 0000000..4453909
--- /dev/null
+++ b/R/EBTest.R
@@ -0,0 +1,592 @@
+EBTest <-
+function(Data,NgVector=NULL,Conditions, sizeFactors, maxround, Pool=F, NumBin=1000,ApproxVal=10^-10, Alpha=NULL, Beta=NULL,PInput=NULL,RInput=NULL,PoolLower=.25, PoolUpper=.75,Print=T, Qtrm=.75,QtrmCut=10)
+{
+ if(!is.factor(Conditions))Conditions=as.factor(Conditions)
+ if(is.null(rownames(Data)))stop("Please add gene/isoform names to the data matrix")
+
+ if(!is.matrix(Data))stop("The input Data is not a matrix")
+ if(length(Conditions)!=ncol(Data))stop("The number of conditions is not the same as the number of samples! ")
+ if(nlevels(Conditions)>2)stop("More than 2 conditions! Please use EBMultiTest() function")
+ if(nlevels(Conditions)<2)stop("Less than 2 conditions - Please check your input")
+ if(length(sizeFactors)!=length(Data) & length(sizeFactors)!=ncol(Data))
+ stop("The number of library size factors is not the same as the number of samples!")
+
+ Conditions=as.factor(Conditions)
+ Vect5End=Vect3End=CI=CIthre=tau=NULL
+ Dataraw=Data
+
+ #Normalized
+ DataNorm=GetNormalizedMat(Data, sizeFactors)
+ Levels=levels(as.factor(Conditions))
+
+ # Dixon Statistics
+# library(outliers)
+# normalized matrix for each condition
+# matC=sapply(1:length(Levels),function(i)DataNorm[,which(Conditions==Levels[i])])
+# run dixon test for each isoform within condition
+# DixonP=sapply(1:length(matC),function(j)
+# apply(DataNorm,1,function(i){
+# if(mean(i)==0)out=NA
+# else out=dixon.test(i)$p.value
+# out}))
+
+
+ QuantileFor0=apply(DataNorm,1,function(i)quantile(i,Qtrm))
+ AllZeroNames=which(QuantileFor0<=QtrmCut)
+ NotAllZeroNames=which(QuantileFor0>QtrmCut)
+ if(length(AllZeroNames)>0 & Print==T)
+ cat(paste0("Removing transcripts with ",Qtrm*100,
+ " th quantile < = ",QtrmCut," \n",
+ length(NotAllZeroNames)," transcripts will be tested\n"))
+ if(length(NotAllZeroNames)==0)stop("0 transcript passed")
+ Data=Data[NotAllZeroNames,]
+ if(!is.null(NgVector))NgVector=NgVector[NotAllZeroNames]
+ if(length(sizeFactors)==length(Data))sizeFactors=sizeFactors[NotAllZeroNames,]
+ if(is.null(NgVector))NgVector=rep(1,nrow(Data))
+
+ #Rename Them
+ IsoNamesIn=rownames(Data)
+ Names=paste("I",c(1:dim(Data)[1]),sep="")
+ names(IsoNamesIn)=Names
+ rownames(Data)=paste("I",c(1:dim(Data)[1]),sep="")
+ names(NgVector)=paste("I",c(1:dim(Data)[1]),sep="")
+
+
+ if(length(sizeFactors)==length(Data)){
+ rownames(sizeFactors)=rownames(Data)
+ colnames(sizeFactors)=Conditions
+ }
+
+ NumOfNg=nlevels(as.factor(NgVector))
+ NameList=sapply(1:NumOfNg,function(i)Names[NgVector==i],simplify=F)
+ names(NameList)=paste("Ng",c(1:NumOfNg),sep="")
+ NotNone=NULL
+ for (i in 1:NumOfNg) {
+ if (length(NameList[[i]])!=0)
+ NotNone=c(NotNone,names(NameList)[i])
+ }
+ NameList=NameList[NotNone]
+
+ NoneZeroLength=length(NameList)
+ DataList=vector("list",NoneZeroLength)
+ DataList=sapply(1:NoneZeroLength , function(i) Data[NameList[[i]],],simplify=F)
+ names(DataList)=names(NameList)
+
+ NumEachGroup=sapply(1:NoneZeroLength , function(i)dim(DataList[[i]])[1])
+ # Unlist
+ DataList.unlist=do.call(rbind, DataList)
+
+ # Divide by SampleSize factor
+
+ if(length(sizeFactors)==ncol(Data))
+ DataList.unlist.dvd=t(t( DataList.unlist)/sizeFactors)
+
+ if(length(sizeFactors)==length(Data))
+ DataList.unlist.dvd=DataList.unlist/sizeFactors
+
+ MeanList=rowMeans(DataList.unlist.dvd)
+
+###############
+# Input R
+###############
+ if (!is.null(RInput)){
+
+ RNoZero=RInput[NotAllZeroNames]
+ names(RNoZero)=rownames(Data)
+ RNoZero.order=RNoZero[rownames(DataList.unlist)]
+ if(length(sizeFactors)==ncol(Data)){
+ RMat= outer(RNoZero.order, sizeFactors)
+ }
+ if(length(sizeFactors)==length(Data)){
+ RMat= RNoZero.order* sizeFactors
+ }
+
+ DataListSP=vector("list",nlevels(Conditions))
+ RMatSP=vector("list",nlevels(Conditions))
+
+ for (lv in 1:nlevels(Conditions)){
+ DataListSP[[lv]]= matrix(DataList.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist)[1])
+ rownames(DataListSP[[lv]])=rownames(DataList.unlist)
+ RMatSP[[lv]]= matrix(RMat[,Conditions==levels(Conditions)[lv]],nrow=dim(RMat)[1])
+ rownames(RMatSP[[lv]])=rownames(RMat)
+
+ }
+
+ F0Log=f0(Input=DataList.unlist, AlphaIn=Alpha, BetaIn=Beta,
+ EmpiricalR=RMat, NumOfGroups=NumEachGroup, log=T)
+ F1Log=f1(Input1=DataListSP[[1]], Input2=DataListSP[[2]],
+ AlphaIn=Alpha, BetaIn=Beta, EmpiricalRSP1=RMatSP[[1]],
+ EmpiricalRSP2=RMatSP[[2]], NumOfGroup=NumEachGroup, log=T)
+ F0LogMdf=F0Log+600
+ F1LogMdf=F1Log+600
+ F0Mdf=exp(F0LogMdf)
+ F1Mdf=exp(F1LogMdf)
+ if(!is.null(PInput)){
+ z.list=PInput*F1Mdf/(PInput*F1Mdf+(1-PInput)*F0Mdf)
+ PIn=PInput
+ }
+ if(is.null(PInput)){
+ PIn=.5
+ PInput=rep(NULL,maxround)
+ for(i in 1:maxround){
+ z.list=PIn*F1Mdf/(PIn*F1Mdf+(1-PIn)*F0Mdf)
+ zNaNName=names(z.list)[is.na(z.list)]
+ zGood=which(!is.na(z.list))
+ PIn=sum(z.list[zGood])/length(z.list[zGood])
+ PInput[i]=PIn
+ }
+
+ zNaNName=names(z.list)[is.na(z.list)]
+ if(length(zNaNName)!=0){
+ PNotIn=rep(1-ApproxVal,length(zNaNName))
+ MeanList.NotIn=MeanList[zNaNName]
+ R.NotIn.raw=MeanList.NotIn*PNotIn/(1-PNotIn)
+ if(length(sizeFactors)==ncol(Data))
+ R.NotIn=outer(R.NotIn.raw,sizeFactors)
+ if(length(sizeFactors)==length(Data))
+ R.NotIn=R.NotIn.raw*sizeFactors[zNaNName,]
+ R.NotIn1=matrix(R.NotIn[,Conditions==levels(Conditions)[1]],nrow=nrow(R.NotIn))
+ R.NotIn2=matrix(R.NotIn[,Conditions==levels(Conditions)[2]],nrow=nrow(R.NotIn))
+ NumOfEachGroupNA=sapply(1:NoneZeroLength, function(i)sum(zNaNName%in%rownames(DataList[[i]])))
+ F0LogNA=f0(matrix(DataList.unlist[zNaNName,],ncol=ncol(DataList.unlist)), Alpha, Beta, R.NotIn, NumOfEachGroupNA, log=T)
+ F1LogNA=f1(matrix(DataListSP[[1]][zNaNName,],ncol=ncol(DataListSP[[1]])),
+ matrix(DataListSP[[2]][zNaNName,],ncol=ncol(DataListSP[[2]])),
+ Alpha, Beta, R.NotIn1,R.NotIn2, NumOfEachGroupNA, log=T)
+ F0LogMdfNA=F0LogNA+600
+ F1LogMdfNA=F1LogNA+600
+ F0MdfNA=exp(F0LogMdfNA)
+ F1MdfNA=exp(F1LogMdfNA)
+ z.list.NotIn=PIn*F1MdfNA/(PIn*F1MdfNA+(1-PIn)*F0MdfNA)
+ z.list[zNaNName]=z.list.NotIn
+ F0Log[zNaNName]=F0LogNA
+ F1Log[zNaNName]=F1LogNA
+ }
+ }
+ RealName.Z.output=z.list
+ RealName.F0=F0Log
+ RealName.F1=F1Log
+ names(RealName.Z.output)=IsoNamesIn
+ names(RealName.F0)=IsoNamesIn
+ names(RealName.F1)=IsoNamesIn
+
+
+ output=list(Alpha=Alpha,Beta=Beta,P=PInput, Z=RealName.Z.output,
+ PPDE=RealName.Z.output,f0=RealName.F0, f1=RealName.F1)
+ return(output)
+
+ }
+
+
+ # Get FC and VarPool for pooling - Only works on 2 conditions
+ if(ncol(Data)==2){
+ DataforPoolSP.dvd1=matrix(DataList.unlist.dvd[,Conditions==levels(Conditions)[1]],nrow=dim(DataList.unlist)[1])
+ DataforPoolSP.dvd2=matrix(DataList.unlist.dvd[,Conditions==levels(Conditions)[2]],nrow=dim(DataList.unlist)[1])
+ MeanforPoolSP.dvd1=rowMeans(DataforPoolSP.dvd1)
+ MeanforPoolSP.dvd2=rowMeans(DataforPoolSP.dvd2)
+ FCforPool=MeanforPoolSP.dvd1/MeanforPoolSP.dvd2
+ names(FCforPool)=rownames(Data)
+ FC_Use=which(FCforPool>=quantile(FCforPool[!is.na(FCforPool)],PoolLower) &
+ FCforPool<=quantile(FCforPool[!is.na(FCforPool)],PoolUpper))
+
+ Var_FC_Use=apply( DataList.unlist.dvd[FC_Use,],1,var )
+ Mean_FC_Use=(MeanforPoolSP.dvd1[FC_Use]+MeanforPoolSP.dvd2[FC_Use])/2
+ MeanforPool=(MeanforPoolSP.dvd1+MeanforPoolSP.dvd2)/2
+ FC_Use2=which(Var_FC_Use>=Mean_FC_Use)
+ Var_FC_Use2=Var_FC_Use[FC_Use2]
+ Mean_FC_Use2=Mean_FC_Use[FC_Use2]
+ Phi=mean((Var_FC_Use2-Mean_FC_Use2)/Mean_FC_Use2^2)
+ VarEst= MeanforPool*(1+MeanforPool*Phi)
+ if(Print==T)message(paste("No Replicate - estimate phi",round(Phi,5), "\n"))
+ names(VarEst)=names(MeanforPoolSP.dvd1)=
+ names(MeanforPoolSP.dvd2)=rownames(DataList.unlist.dvd)
+ }
+
+ #DataListSP Here also unlist.. Only two lists
+ DataListSP=vector("list",nlevels(Conditions))
+ DataListSP.dvd=vector("list",nlevels(Conditions))
+ SizeFSP=DataListSP
+ MeanSP=DataListSP
+ VarSP=DataListSP
+ GetPSP=DataListSP
+ RSP=DataListSP
+ CISP=DataListSP
+ tauSP=DataListSP
+ NumSampleEachCon=rep(NULL,nlevels(Conditions))
+
+ for (lv in 1:nlevels(Conditions)){
+ DataListSP[[lv]]= matrix(DataList.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist)[1])
+ rownames(DataListSP[[lv]])=rownames(DataList.unlist)
+ DataListSP.dvd[[lv]]= matrix(DataList.unlist.dvd[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist.dvd)[1])
+ NumSampleEachCon[lv]=ncol(DataListSP[[lv]])
+
+ if(ncol(DataListSP[[lv]])==1 & !is.null(CI)){
+ CISP[[lv]]=matrix(CI[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist.dvd)[1])
+ tauSP[[lv]]=matrix(tau[,Conditions==levels(Conditions)[lv]],nrow=dim(DataList.unlist.dvd)[1])
+ }
+ # no matter sizeFactors is a vector or a matrix. Matrix should be columns are the normalization factors
+ # may input one for each
+ if(length(sizeFactors)==ncol(Data))SizeFSP[[lv]]=sizeFactors[Conditions==levels(Conditions)[lv]]
+ if(length(sizeFactors)==length(Data))SizeFSP[[lv]]=sizeFactors[,Conditions==levels(Conditions)[lv]]
+
+
+ MeanSP[[lv]]=rowMeans(DataListSP.dvd[[lv]])
+ names(MeanSP[[lv]])=rownames(DataListSP[[lv]])
+
+ if(length(sizeFactors)==ncol(Data))PrePareVar=sapply(1:ncol( DataListSP[[lv]]),function(i)( DataListSP[[lv]][,i]- SizeFSP[[lv]][i]*MeanSP[[lv]])^2 /SizeFSP[[lv]][i])
+ if(length(sizeFactors)==length(Data))PrePareVar=sapply(1:ncol( DataListSP[[lv]]),function(i)( DataListSP[[lv]][,i]- SizeFSP[[lv]][,i]*MeanSP[[lv]])^2 /SizeFSP[[lv]][,i])
+
+ if(ncol(DataListSP[[lv]])==1 & !is.null(CI))
+ VarSP[[lv]]=as.vector(((DataListSP[[lv]]/tauSP[[lv]]) * CISP[[lv]]/(CIthre*2))^2)
+ if(ncol(DataListSP[[lv]])!=1){
+ VarSP[[lv]]=rowSums(PrePareVar)/ncol( DataListSP[[lv]])
+ names(MeanSP[[lv]])=rownames(DataList.unlist)
+ names(VarSP[[lv]])=rownames(DataList.unlist)
+ GetPSP[[lv]]=MeanSP[[lv]]/VarSP[[lv]]
+ RSP[[lv]]=MeanSP[[lv]]*GetPSP[[lv]]/(1-GetPSP[[lv]])
+ }
+}
+
+
+ VarList=apply(DataList.unlist.dvd, 1, var)
+ if(ncol(Data)==2){
+ PoolVar=VarEst
+ VarSP[[1]]=VarSP[[2]]=VarEst
+ GetPSP[[1]]=MeanSP[[1]]/VarEst
+ GetPSP[[2]]=MeanSP[[2]]/VarEst
+
+ }
+ if(!ncol(Data)==2){
+ CondWithRep=which(NumSampleEachCon>1)
+ VarCondWithRep=do.call(cbind,VarSP[CondWithRep])
+ PoolVar=rowMeans(VarCondWithRep)
+
+ }
+ GetP=MeanList/PoolVar
+
+ EmpiricalRList=MeanList*GetP/(1-GetP)
+ EmpiricalRList[EmpiricalRList==Inf] =max(EmpiricalRList[EmpiricalRList!=Inf])
+#####################
+ if(ncol(Data)!=2){
+ Varcbind=do.call(cbind,VarSP)
+ VarrowMin=apply(Varcbind,1,min)
+ }
+
+ if(ncol(Data)==2){
+ Varcbind=VarEst
+ VarrowMin=VarEst
+ VarSP[[1]]=VarSP[[2]]=VarEst
+ names(MeanSP[[1]])=names(VarSP[[1]])
+ names(MeanSP[[2]])=names(VarSP[[2]])
+ }
+ #
+ #
+ GoodData=names(MeanList)[EmpiricalRList>0 & VarrowMin!=0 & EmpiricalRList!=Inf & !is.na(VarrowMin) & !is.na(EmpiricalRList)]
+ NotIn=names(MeanList)[EmpiricalRList<=0 | VarrowMin==0 | EmpiricalRList==Inf | is.na(VarrowMin) | is.na(EmpiricalRList)]
+ #print(paste("ZeroVar",sum(VarrowMin==0), "InfR", length(which(EmpiricalRList==Inf)), "Poi", length(which(EmpiricalRList<0)), ""))
+ EmpiricalRList.NotIn=EmpiricalRList[NotIn]
+ EmpiricalRList.Good=EmpiricalRList[GoodData]
+ EmpiricalRList.Good[EmpiricalRList.Good<1]=1+EmpiricalRList.Good[EmpiricalRList.Good<1]
+ if(length(sizeFactors)==ncol(Data)){
+ EmpiricalRList.Good.mat= outer(EmpiricalRList.Good, sizeFactors)
+ EmpiricalRList.mat= outer(EmpiricalRList, sizeFactors)
+ }
+ if(length(sizeFactors)==length(Data)){
+ EmpiricalRList.Good.mat=EmpiricalRList.Good* sizeFactors[GoodData,]
+ EmpiricalRList.mat=EmpiricalRList* sizeFactors
+ }
+
+ # Only Use Data has Good q's
+ DataList.In=sapply(1:NoneZeroLength, function(i)DataList[[i]][GoodData[GoodData%in%rownames(DataList[[i]])],],simplify=F)
+ DataList.NotIn=sapply(1:NoneZeroLength, function(i)DataList[[i]][NotIn[NotIn%in%rownames(DataList[[i]])],],simplify=F)
+ DataListIn.unlist=do.call(rbind, DataList.In)
+ DataListNotIn.unlist=do.call(rbind, DataList.NotIn)
+
+ DataListSPIn=vector("list",nlevels(Conditions))
+ DataListSPNotIn=vector("list",nlevels(Conditions))
+ EmpiricalRList.Good.mat.SP=EmpiricalRList.mat.SP=vector("list",nlevels(Conditions))
+ for (lv in 1:nlevels(Conditions)){
+ DataListSPIn[[lv]]= matrix(DataListIn.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataListIn.unlist)[1])
+ if(length(NotIn)>0){
+ DataListSPNotIn[[lv]]= matrix(DataListNotIn.unlist[,Conditions==levels(Conditions)[lv]],nrow=dim(DataListNotIn.unlist)[1])
+ rownames(DataListSPNotIn[[lv]])=rownames(DataListNotIn.unlist)
+ }
+ rownames(DataListSPIn[[lv]])=rownames(DataListIn.unlist)
+ EmpiricalRList.Good.mat.SP[[lv]]=matrix(EmpiricalRList.Good.mat[,Conditions==levels(Conditions)[lv]],nrow=dim(EmpiricalRList.Good.mat)[1])
+ EmpiricalRList.mat.SP[[lv]]=matrix(EmpiricalRList.mat[,Conditions==levels(Conditions)[lv]],nrow=dim(EmpiricalRList.mat)[1])
+ }
+
+ NumOfEachGroupIn=sapply(1:NoneZeroLength, function(i)max(0,dim(DataList.In[[i]])[1]))
+ NumOfEachGroupNotIn=sapply(1:NoneZeroLength, function(i)max(0,dim(DataList.NotIn[[i]])[1]))
+
+
+#################
+# For output
+#################
+RealName.EmpiricalRList=sapply(1:NoneZeroLength,function(i)EmpiricalRList[names(EmpiricalRList)%in%NameList[[i]]], simplify=F)
+RealName.MeanList=sapply(1:NoneZeroLength,function(i)MeanList[names(MeanList)%in%NameList[[i]]], simplify=F)
+RealName.C1MeanList=sapply(1:NoneZeroLength,function(i)MeanSP[[1]][names(MeanSP[[1]])%in%NameList[[i]]], simplify=F)
+RealName.C2MeanList=sapply(1:NoneZeroLength,function(i)MeanSP[[2]][names(MeanSP[[2]])%in%NameList[[i]]], simplify=F)
+RealName.C1VarList=sapply(1:NoneZeroLength,function(i)VarSP[[1]][names(VarSP[[1]])%in%NameList[[i]]], simplify=F)
+RealName.C2VarList=sapply(1:NoneZeroLength,function(i)VarSP[[2]][names(VarSP[[2]])%in%NameList[[i]]], simplify=F)
+RealName.DataList=sapply(1:NoneZeroLength,function(i)DataList[[i]][rownames(DataList[[i]])%in%NameList[[i]],], simplify=F)
+
+
+
+RealName.VarList=sapply(1:NoneZeroLength,function(i)VarList[names(VarList)%in%NameList[[i]]], simplify=F)
+RealName.PoolVarList=sapply(1:NoneZeroLength,function(i)PoolVar[names(PoolVar)%in%NameList[[i]]], simplify=F)
+
+
+RealName.QList1=sapply(1:NoneZeroLength,function(i)GetPSP[[1]][names(GetPSP[[1]])%in%NameList[[i]]], simplify=F)
+RealName.QList2=sapply(1:NoneZeroLength,function(i)GetPSP[[2]][names(GetPSP[[2]])%in%NameList[[i]]], simplify=F)
+
+
+for (i in 1:NoneZeroLength){
+tmp=NameList[[i]]
+names=IsoNamesIn[tmp]
+
+RealName.MeanList[[i]]=RealName.MeanList[[i]][NameList[[i]]]
+RealName.VarList[[i]]=RealName.VarList[[i]][NameList[[i]]]
+RealName.QList1[[i]]=RealName.QList1[[i]][NameList[[i]]]
+RealName.QList2[[i]]=RealName.QList2[[i]][NameList[[i]]]
+RealName.EmpiricalRList[[i]]=RealName.EmpiricalRList[[i]][NameList[[i]]]
+RealName.C1MeanList[[i]]=RealName.C1MeanList[[i]][NameList[[i]]]
+RealName.C2MeanList[[i]]=RealName.C2MeanList[[i]][NameList[[i]]]
+RealName.PoolVarList[[i]]=RealName.PoolVarList[[i]][NameList[[i]]]
+RealName.C1VarList[[i]]=RealName.C1VarList[[i]][NameList[[i]]]
+RealName.C2VarList[[i]]=RealName.C2VarList[[i]][NameList[[i]]]
+RealName.DataList[[i]]=RealName.DataList[[i]][NameList[[i]],]
+
+names(RealName.MeanList[[i]])=names
+names(RealName.VarList[[i]])=names
+if(ncol(DataListSP[[1]])!=1){
+ names(RealName.QList1[[i]])=names
+ names(RealName.C1VarList[[i]])=names
+}
+if(ncol(DataListSP[[2]])!=1){
+ names(RealName.QList2[[i]])=names
+ names(RealName.C2VarList[[i]])=names
+}
+
+names(RealName.EmpiricalRList[[i]])=names
+names(RealName.C1MeanList[[i]])=names
+names(RealName.C2MeanList[[i]])=names
+names(RealName.PoolVarList[[i]])=names
+rownames(RealName.DataList[[i]])=names
+
+
+}
+
+#####################
+# If Don need EM
+#####################
+ if(!is.null(Alpha)&!is.null(Beta)){
+ F0Log=f0(Input=DataList.unlist, AlphaIn=Alpha, BetaIn=Beta,
+ EmpiricalR=EmpiricalRList.mat, NumOfGroups=NumEachGroup, log=T)
+ F1Log=f1(Input1=DataListSP[[1]], Input2=DataListSP[[2]],
+ AlphaIn=Alpha, BetaIn=Beta, EmpiricalRSP1=EmpiricalRList.mat.SP[[1]],
+ EmpiricalRSP2=EmpiricalRList.mat.SP[[2]], NumOfGroup=NumEachGroup, log=T)
+ F0LogMdf=F0Log+600
+ F1LogMdf=F1Log+600
+ F0Mdf=exp(F0LogMdf)
+ F1Mdf=exp(F1LogMdf)
+ if(!is.null(PInput)){
+ z.list=PInput*F1Mdf/(PInput*F1Mdf+(1-PInput)*F0Mdf)
+ PIn=PInput
+ }
+ if(is.null(PInput)){
+ PIn=.5
+ PInput=rep(NULL,maxround)
+ for(i in 1:maxround){
+ z.list=PIn*F1Mdf/(PIn*F1Mdf+(1-PIn)*F0Mdf)
+ zNaNName=names(z.list)[is.na(z.list)]
+ zGood=which(!is.na(z.list))
+ PIn=sum(z.list[zGood])/length(z.list[zGood])
+ PInput[i]=PIn
+ }
+
+ zNaNName=names(z.list)[is.na(z.list)]
+ if(length(zNaNName)!=0){
+ PNotIn=rep(1-ApproxVal,length(zNaNName))
+ MeanList.NotIn=MeanList[zNaNName]
+ R.NotIn.raw=MeanList.NotIn*PNotIn/(1-PNotIn)
+ if(length(sizeFactors)==ncol(Data))
+ R.NotIn=outer(R.NotIn.raw,sizeFactors)
+ if(length(sizeFactors)==length(Data))
+ R.NotIn=R.NotIn.raw*sizeFactors[zNaNName,]
+ R.NotIn1=matrix(R.NotIn[,Conditions==levels(Conditions)[1]],nrow=nrow(R.NotIn))
+ R.NotIn2=matrix(R.NotIn[,Conditions==levels(Conditions)[2]],nrow=nrow(R.NotIn))
+ NumOfEachGroupNA=sapply(1:NoneZeroLength, function(i)sum(zNaNName%in%rownames(DataList[[i]])))
+ F0LogNA=f0(matrix(DataList.unlist[zNaNName,], ncol=ncol(DataList.unlist)), Alpha, Beta, R.NotIn, NumOfEachGroupNA, log=T)
+ F1LogNA=f1(matrix(DataListSP[[1]][zNaNName,],ncol=ncol(DataListSP[[1]])),
+ matrix(DataListSP[[2]][zNaNName,],ncol=ncol(DataListSP[[2]])),
+ Alpha, Beta, R.NotIn1,R.NotIn2, NumOfEachGroupNA, log=T)
+ F0LogMdfNA=F0LogNA+600
+ F1LogMdfNA=F1LogNA+600
+ F0MdfNA=exp(F0LogMdfNA)
+ F1MdfNA=exp(F1LogMdfNA)
+ z.list.NotIn=PIn*F1MdfNA/(PIn*F1MdfNA+(1-PIn)*F0MdfNA)
+ z.list[zNaNName]=z.list.NotIn
+ F0Log[zNaNName]=F0LogNA
+ F1Log[zNaNName]=F1LogNA
+ }
+ }
+ RealName.Z.output=z.list
+ RealName.F0=F0Log
+ RealName.F1=F1Log
+ names(RealName.Z.output)=IsoNamesIn
+ names(RealName.F0)=IsoNamesIn
+ names(RealName.F1)=IsoNamesIn
+
+
+ output=list(Alpha=Alpha,Beta=Beta,P=PInput, Z=RealName.Z.output,
+ RList=RealName.EmpiricalRList, MeanList=RealName.MeanList,
+ VarList=RealName.VarList, QList1=RealName.QList1, QList2=RealName.QList2,
+ C1Mean=RealName.C1MeanList, C2Mean=RealName.C2MeanList,
+ C1EstVar=RealName.C1VarList, C2EstVar=RealName.C2VarList,
+ PoolVar=RealName.PoolVarList , DataList=RealName.DataList,
+ PPDE=RealName.Z.output,f0=RealName.F0, f1=RealName.F1)
+ return(output)
+ }
+
+
+#####################
+#Initialize SigIn & ...
+#####################
+ AlphaIn=0.5
+ BetaIn=rep(0.5,NoneZeroLength)
+ PIn=0.5
+
+
+#####################
+# EM
+#####################
+ UpdateAlpha=NULL
+ UpdateBeta=NULL
+ UpdateP=NULL
+ UpdatePFromZ=NULL
+ Timeperround=NULL
+ for (times in 1:maxround){
+ temptime1=proc.time()
+ UpdateOutput=suppressWarnings(LogN(DataListIn.unlist,DataListSPIn, EmpiricalRList.Good.mat ,EmpiricalRList.Good.mat.SP, NumOfEachGroupIn, AlphaIn, BetaIn, PIn, NoneZeroLength))
+ message(paste("iteration", times, "done \n",sep=" "))
+ AlphaIn=UpdateOutput$AlphaNew
+ BetaIn=UpdateOutput$BetaNew
+ PIn=UpdateOutput$PNew
+ PFromZ=UpdateOutput$PFromZ
+ F0Out=UpdateOutput$F0Out
+ F1Out=UpdateOutput$F1Out
+ UpdateAlpha=rbind(UpdateAlpha,AlphaIn)
+ UpdateBeta=rbind(UpdateBeta,BetaIn)
+ UpdateP=rbind(UpdateP,PIn)
+ UpdatePFromZ=rbind(UpdatePFromZ,PFromZ)
+ temptime2=proc.time()
+ Timeperround=c(Timeperround,temptime2[3]-temptime1[3])
+ message(paste("time" ,round(Timeperround[times],2),"\n",sep=" "))
+ Z.output=UpdateOutput$ZNew.list[!is.na(UpdateOutput$ZNew.list)]
+ Z.NA.Names=UpdateOutput$zNaNName
+ }
+ #Remove this } after testing!!
+
+# if (times!=1){
+# if((UpdateAlpha[times]-UpdateAlpha[times-1])^2+UpdateBeta[times]-UpdateBeta[times-1])^2+UpdateR[times]-UpdateR[times-1])^2+UpdateP[times]-UpdateP[times-1])^2<=10^(-6)){
+# Result=list(Sig=SigIn, Miu=MiuIn, Tau=TauIn)
+# break
+# }
+# }
+#}
+
+##########Change Names############
+## Only z are for Good Ones
+GoodData=GoodData[!GoodData%in%Z.NA.Names]
+IsoNamesIn.Good=IsoNamesIn[GoodData]
+RealName.Z.output=Z.output
+RealName.F0=F0Out
+RealName.F1=F1Out
+names(RealName.Z.output)=IsoNamesIn.Good
+names(RealName.F0)=IsoNamesIn.Good
+names(RealName.F1)=IsoNamesIn.Good
+
+
+
+#########posterior part for other data set here later############
+AllNA=unique(c(Z.NA.Names,NotIn))
+z.list.NotIn=NULL
+AllF0=c(RealName.F0)
+AllF1=c(RealName.F1)
+AllZ=RealName.Z.output
+
+if (length(AllNA)>0){
+ Ng.NA=NgVector[AllNA]
+ AllNA.Ngorder=AllNA[order(Ng.NA)]
+ NumOfEachGroupNA=rep(0,NoneZeroLength)
+ NumOfEachGroupNA.tmp=tapply(Ng.NA,Ng.NA,length)
+ names(NumOfEachGroupNA)=c(1:NoneZeroLength)
+ NumOfEachGroupNA[names(NumOfEachGroupNA.tmp)]=NumOfEachGroupNA.tmp
+ PNotIn=rep(1-ApproxVal,length(AllNA.Ngorder))
+ MeanList.NotIn=MeanList[AllNA.Ngorder]
+ R.NotIn.raw=MeanList.NotIn*PNotIn/(1-PNotIn)
+ if(length(sizeFactors)==ncol(Data))
+ R.NotIn=outer(R.NotIn.raw,sizeFactors)
+ if(length(sizeFactors)==length(Data))
+ R.NotIn=R.NotIn.raw*sizeFactors[NotIn,]
+ R.NotIn1=matrix(R.NotIn[,Conditions==levels(Conditions)[1]],nrow=nrow(R.NotIn))
+ R.NotIn2=matrix(R.NotIn[,Conditions==levels(Conditions)[2]],nrow=nrow(R.NotIn))
+
+ DataListNotIn.unlistWithZ=matrix(DataList.unlist[AllNA.Ngorder,],nrow=length(AllNA.Ngorder))
+ DataListSPNotInWithZ=vector("list",nlevels(Conditions))
+ for (lv in 1:nlevels(Conditions))
+ DataListSPNotInWithZ[[lv]] = matrix(DataListSP[[lv]][AllNA.Ngorder,],nrow=length(AllNA.Ngorder))
+ F0Log=f0(DataListNotIn.unlistWithZ, AlphaIn, BetaIn, R.NotIn, NumOfEachGroupNA, log=T)
+ F1Log=f1(DataListSPNotInWithZ[[1]], DataListSPNotInWithZ[[2]], AlphaIn, BetaIn, R.NotIn1,R.NotIn2, NumOfEachGroupNA, log=T)
+ F0LogMdf=F0Log+600
+ F1LogMdf=F1Log+600
+ F0Mdf=exp(F0LogMdf)
+ F1Mdf=exp(F1LogMdf)
+ z.list.NotIn=PIn*F1Mdf/(PIn*F1Mdf+(1-PIn)*F0Mdf)
+# names(z.list.NotIn)=IsoNamesIn.Good=IsoNamesIn[which(Names%in%NotIn)]
+ names(z.list.NotIn)=IsoNamesIn[AllNA.Ngorder]
+
+ AllZ=c(RealName.Z.output,z.list.NotIn)
+ AllZ=AllZ[IsoNamesIn]
+ AllZ[is.na(AllZ)]=0
+ F0.NotIn=F0Log
+ F1.NotIn=F1Log
+ names(F0.NotIn)=IsoNamesIn[names(F0Log)]
+ names(F1.NotIn)=IsoNamesIn[names(F1Log)]
+ AllF0=c(RealName.F0,F0.NotIn)
+ AllF1=c(RealName.F1,F1.NotIn)
+ AllF0=AllF0[IsoNamesIn]
+ AllF1=AllF1[IsoNamesIn]
+ AllF0[is.na(AllF0)]=0
+ AllF1[is.na(AllF1)]=0
+}
+PPMatNZ=cbind(1-AllZ,AllZ)
+colnames(PPMatNZ)=c("PPEE","PPDE")
+rownames(UpdateAlpha)=paste("iter",1:nrow(UpdateAlpha),sep="")
+rownames(UpdateBeta)=paste("iter",1:nrow(UpdateBeta),sep="")
+rownames(UpdateP)=paste("iter",1:nrow(UpdateP),sep="")
+rownames(UpdatePFromZ)=paste("iter",1:nrow(UpdatePFromZ),sep="")
+colnames(UpdateBeta)=paste("Ng",1:ncol(UpdateBeta),sep="")
+
+CondOut=levels(Conditions)
+names(CondOut)=paste("Condition",c(1:length(CondOut)),sep="")
+
+PPMat=matrix(NA,ncol=2,nrow=nrow(Dataraw))
+rownames(PPMat)=rownames(Dataraw)
+colnames(PPMat)=c("PPEE","PPDE")
+if(is.null(AllZeroNames))PPMat=PPMatNZ
+if(!is.null(AllZeroNames))PPMat[names(NotAllZeroNames),]=PPMatNZ[names(NotAllZeroNames),]
+
+
+#############Result############################
+Result=list(Alpha=UpdateAlpha,Beta=UpdateBeta,P=UpdateP,
+ PFromZ=UpdatePFromZ, Z=RealName.Z.output,PoissonZ=z.list.NotIn,
+ RList=RealName.EmpiricalRList, MeanList=RealName.MeanList,
+ VarList=RealName.VarList, QList1=RealName.QList1, QList2=RealName.QList2,
+ C1Mean=RealName.C1MeanList, C2Mean=RealName.C2MeanList,C1EstVar=RealName.C1VarList,
+ C2EstVar=RealName.C2VarList, PoolVar=RealName.PoolVarList ,
+ DataList=RealName.DataList,PPDE=AllZ,f0=AllF0, f1=AllF1,
+ AllZeroIndex=AllZeroNames,PPMat=PPMatNZ, PPMatWith0=PPMat,
+ ConditionOrder=CondOut, Conditions=Conditions)
+}
+
diff --git a/R/GetMultiFC.R b/R/GetMultiFC.R
new file mode 100644
index 0000000..02efe8f
--- /dev/null
+++ b/R/GetMultiFC.R
@@ -0,0 +1,65 @@
+GetMultiFC=function(EBMultiOut,SmallNum=.01){
+ if(!"PPpattern"%in%names(EBMultiOut))stop("The input doesn't seem like an output from EBMultiTest")
+
+ NumNgGroup=length(EBMultiOut$DataList)
+ OutNames=rownames(EBMultiOut$PPMat)
+ NumCondition=length(EBMultiOut$SPMean[[1]])
+ ConditionNames=colnames(EBMultiOut$AllParti)
+ CondMeans=sapply(1:NumCondition,
+ function(i){
+ if (NumNgGroup==1)
+ out=EBMultiOut$SPMean[[1]][[i]][OutNames]
+ if(NumNgGroup>1)
+ out=unlist(sapply(1:NumNgGroup,
+ function(j)EBMultiOut$SPMean[[j]][[i]]))[OutNames]
+ out}
+ )
+ colnames(CondMeans)=ConditionNames
+ CondMeansPlus=CondMeans+SmallNum
+
+ GeneRealMean=rowMeans(CondMeans)
+ GeneR=unlist(EBMultiOut$RList)
+ GeneR[GeneR<=0 | is.na(GeneR)]=GeneRealMean[GeneR<=0 | is.na(GeneR)]*.99/.01
+
+ GeneAlpha=EBMultiOut[[1]][nrow(EBMultiOut[[1]]),]
+ GeneBeta=unlist(sapply(1:length(EBMultiOut$DataList),
+ function(i)rep(EBMultiOut[[2]][nrow(EBMultiOut[[1]]),i],
+ nrow(EBMultiOut$DataList[[i]]))))
+ GeneBeta=as.vector(GeneBeta)
+
+
+ FCMat=PostFCMat=matrix(0,ncol=choose(NumCondition,2),nrow=length(OutNames))
+ rownames(FCMat)=rownames(PostFCMat)=OutNames
+ k=1
+ ColNames=rep(NA,choose(NumCondition,2))
+ for(i in 1:(NumCondition-1)){
+ for(j in (i+1):NumCondition)
+ {
+ ColNames[k]=paste(ConditionNames[i],"Over",ConditionNames[j],sep="")
+ FCMat[,k]=CondMeansPlus[,i]/CondMeansPlus[,j]
+
+
+ nC1=sum(EBMultiOut$ConditionOrder==ConditionNames[i])
+ nC2=sum(EBMultiOut$ConditionOrder==ConditionNames[j])
+ GenePostAlphaC1=GeneAlpha+nC1*GeneR
+ GenePostAlphaC2=GeneAlpha+nC2*GeneR
+ GenePostBetaC1=GeneBeta+nC1*CondMeans[,i]
+ GenePostBetaC2=GeneBeta+nC2*CondMeans[,j]
+ GenePostQC1=GenePostAlphaC1/(GenePostAlphaC1+GenePostBetaC1)
+ GenePostQC2=GenePostAlphaC2/(GenePostAlphaC2+GenePostBetaC2)
+
+ GenePostFC=((1-GenePostQC1)/(1-GenePostQC2))*(GenePostQC2/GenePostQC1)
+ PostFCMat[,k]= GenePostFC
+
+ k=k+1
+ }
+ }
+ colnames(FCMat)=colnames(PostFCMat)=ColNames
+ Log2FCMat=log2(FCMat)
+ Log2PostFCMat=log2(PostFCMat)
+ Out=list(FCMat=FCMat,Log2FCMat=Log2FCMat,
+ PostFCMat=PostFCMat, Log2PostFCMat=Log2PostFCMat,
+ CondMeans=CondMeans,
+ ConditionOrder=EBMultiOut$ConditionOrder)
+}
+
diff --git a/R/GetMultiPP.R b/R/GetMultiPP.R
new file mode 100644
index 0000000..133c57e
--- /dev/null
+++ b/R/GetMultiPP.R
@@ -0,0 +1,14 @@
+GetMultiPP <- function(EBout){
+ if(!"PPpattern"%in%names(EBout))stop("The input doesn't seem like an output from EBMultiTest")
+
+ PP=EBout$PPpattern
+ UnderFlow=which(is.na(rowSums(PP)))
+ if(length(UnderFlow)!=0)Good=c(1:nrow(PP))[-UnderFlow]
+ else Good=c(1:nrow(PP))
+ MAP=rep(NA,nrow(PP))
+ names(MAP)=rownames(PP)
+ MAP[Good]=colnames(PP)[apply(PP[Good,],1,which.max)]
+ MAP[UnderFlow]="NoTest"
+ AllParti=EBout$AllParti
+ out=list(PP=PP, MAP=MAP,Patterns=AllParti)
+}
diff --git a/R/GetNg.R b/R/GetNg.R
new file mode 100644
index 0000000..1dcabca
--- /dev/null
+++ b/R/GetNg.R
@@ -0,0 +1,12 @@
+GetNg<- function(IsoformName, GeneName, TrunThre=3){
+ if(length(IsoformName)!=length(GeneName))stop("The length of IsoformName is not the same as the length of GeneName")
+ GeneNg = tapply(IsoformName, GeneName, length)
+ if(max(GeneNg)<TrunThre)stop("The max Ng is less than the TrunThre")
+ IsoformNg = GeneNg[GeneName]
+ names(IsoformNg) = IsoformName
+ GeneNgTrun=GeneNg
+ GeneNgTrun[GeneNgTrun>TrunThre]=TrunThre
+ IsoformNgTrun=IsoformNg
+ IsoformNgTrun[IsoformNgTrun>TrunThre]=TrunThre
+ out=list( GeneNg=GeneNg, GeneNgTrun=GeneNgTrun, IsoformNg=IsoformNg, IsoformNgTrun=IsoformNgTrun)
+ }
diff --git a/R/GetNormalizedMat.R b/R/GetNormalizedMat.R
new file mode 100644
index 0000000..e24d90d
--- /dev/null
+++ b/R/GetNormalizedMat.R
@@ -0,0 +1,6 @@
+GetNormalizedMat<-function(Data, Sizes){
+if(length(Sizes)!=length(Data) & length(Sizes)!=ncol(Data))
+ stop("The number of library size factors is not the same as the number of samples!")
+if(length(Sizes)==length(Data))Out=Data/Sizes
+if(length(Sizes)==ncol(Data))Out=t(t(Data)/Sizes)
+Out}
diff --git a/R/GetPP.R b/R/GetPP.R
new file mode 100644
index 0000000..3422285
--- /dev/null
+++ b/R/GetPP.R
@@ -0,0 +1,5 @@
+GetPP <- function(EBout){
+ if(!"PPDE"%in%names(EBout))stop("The input doesn't seem like an output from EBTest")
+
+ PP=EBout$PPDE
+}
diff --git a/R/GetPPMat.R b/R/GetPPMat.R
new file mode 100644
index 0000000..310e363
--- /dev/null
+++ b/R/GetPPMat.R
@@ -0,0 +1,5 @@
+GetPPMat <- function(EBout){
+ if(!"PPMat"%in%names(EBout))stop("The input doesn't seem like an output from EBTest")
+
+ PP=EBout$PPMat
+}
diff --git a/R/GetPatterns.R b/R/GetPatterns.R
new file mode 100644
index 0000000..3a0b5b2
--- /dev/null
+++ b/R/GetPatterns.R
@@ -0,0 +1,12 @@
+GetPatterns<-function(Conditions){
+ if(!is.factor(Conditions))Conditions=as.factor(Conditions)
+ NumCond=nlevels(Conditions)
+ if(NumCond<3)stop("Less than 3 conditions!")
+ CondLevels=levels(Conditions)
+ AllPartiList=sapply(1:NumCond,function(i)nkpartitions(NumCond,i))
+ AllParti=do.call(rbind,AllPartiList)
+ colnames(AllParti)=CondLevels
+ rownames(AllParti)=paste("Pattern",1:nrow(AllParti),sep="")
+ AllParti
+
+}
diff --git a/R/Likefun.R b/R/Likefun.R
new file mode 100644
index 0000000..ebe05ab
--- /dev/null
+++ b/R/Likefun.R
@@ -0,0 +1,26 @@
+Likefun <-
+function(ParamPool, InputPool)
+{
+
+NoneZeroLength=InputPool[[5]]
+AlphaIn=ParamPool[1]
+BetaIn=ParamPool[2:(1+NoneZeroLength)]
+PIn=ParamPool[2+NoneZeroLength]
+ZIn=InputPool[[4]]
+Input=InputPool[[3]]
+Input1=matrix(InputPool[[1]],nrow=nrow(Input))
+Input2=matrix(InputPool[[2]],nrow=nrow(Input))
+RIn=InputPool[[6]]
+RInSP1=matrix(InputPool[[7]],nrow=nrow(Input))
+RInSP2=matrix(InputPool[[8]],nrow=nrow(Input))
+NumIn=InputPool[[9]]
+##Function here
+#LikelihoodFunction<- function(NoneZeroLength){
+ F0=f0(Input, AlphaIn, BetaIn, RIn, NumIn, log=T)
+ F1=f1(Input1, Input2, AlphaIn, BetaIn, RInSP1,RInSP2, NumIn, log=T)
+ F0[F0==Inf]=min(!is.na(F0[F0!=Inf]))
+ F1[F1==Inf]=min(!is.na(F1[F1!=Inf]))
+
+ -sum((1-ZIn)*F0+ (1-ZIn)* log(1-PIn) + ZIn*F1 + ZIn*log(PIn))
+}
+
diff --git a/R/LikefunMulti.R b/R/LikefunMulti.R
new file mode 100644
index 0000000..510cb1e
--- /dev/null
+++ b/R/LikefunMulti.R
@@ -0,0 +1,28 @@
+LikefunMulti <-
+function(ParamPool, InputPool)
+{
+
+NoneZeroLength=InputPool[[4]]
+AlphaIn=ParamPool[1]
+BetaIn=ParamPool[2:(1+NoneZeroLength)]
+PIn=ParamPool[(2+NoneZeroLength):length(ParamPool)]
+PInAll=c(1-sum(PIn),PIn)
+ZIn=InputPool[[3]]
+Input=InputPool[[2]]
+InputSP=InputPool[[1]]
+RIn=InputPool[[5]]
+RInSP=InputPool[[6]]
+NumIn=InputPool[[7]]
+AllParti=InputPool[[8]]
+PInMat=matrix(rep(1,nrow(Input)),ncol=1)%*%matrix(PInAll,nrow=1)
+##Function here
+FList=sapply(1:nrow(AllParti),function(i)sapply(1:nlevels(as.factor(AllParti[i,])),
+ function(j)f0(do.call(cbind,InputSP[AllParti[i,]==j]),AlphaIn, BetaIn,
+ do.call(cbind,RInSP[AllParti[i,]==j]), NumIn, log=T)),
+ simplify=F)
+FPartiLog=sapply(FList,rowSums)
+#FMat=exp(FPartiLog)
+FMat=FPartiLog
+-sum(ZIn*(FMat+log(PInMat)))
+}
+
diff --git a/R/LogN.R b/R/LogN.R
new file mode 100644
index 0000000..026dac6
--- /dev/null
+++ b/R/LogN.R
@@ -0,0 +1,64 @@
+LogN <-
+function(Input, InputSP, EmpiricalR, EmpiricalRSP, NumOfEachGroup, AlphaIn, BetaIn, PIn, NoneZeroLength)
+{
+ #2 condition case (skip the loop then maybe run faster? Code multi condition cases later)
+
+ #For each gene (m rows of Input---m genes)
+ #Save each gene's F0, F1 for further likelihood calculation.
+
+ #Get F0 for EE
+ F0Log=f0(Input, AlphaIn, BetaIn, EmpiricalR, NumOfEachGroup, log=T)
+ #Get F1 for DE
+ F1Log=f1(InputSP[[1]], InputSP[[2]], AlphaIn, BetaIn, EmpiricalRSP[[1]],EmpiricalRSP[[2]], NumOfEachGroup, log=T)
+
+ #Get z
+ #Use data.list in logfunction
+ F0LogMdf=F0Log+600
+ F1LogMdf=F1Log+600
+ F0Mdf=exp(F0LogMdf)
+ F1Mdf=exp(F1LogMdf)
+
+ z.list=PIn*F1Mdf/(PIn*F1Mdf+(1-PIn)*F0Mdf)
+ zNaNName=names(z.list)[is.na(z.list)]
+ zGood=which(!is.na(z.list))
+ if(length(zGood)==0){
+ #Min=min(min(F0Log[which(F0Log!=-Inf)]),
+ # min(F1Log[which(F1Log!=-Inf)]))
+ tmpMat=cbind(F0Log,F1Log)
+ tmpMean=apply(tmpMat,1,mean)
+ F0LogMdf=F0Log-tmpMean
+ F1LogMdf=F1Log-tmpMean
+ F0Mdf=exp(F0LogMdf)
+ F1Mdf=exp(F1LogMdf)
+
+ z.list=PIn*F1Mdf/(PIn*F1Mdf+(1-PIn)*F0Mdf)
+ zNaNName=names(z.list)[is.na(z.list)]
+ zGood=which(!is.na(z.list))
+
+ }
+ ###Update P
+ #PFromZ=sapply(1:NoneZeroLength,function(i) sum(z.list[[i]])/length(z.list[[i]]))
+ PFromZ=sum(z.list[zGood])/length(z.list[zGood])
+ F0Good=F0Log[zGood]
+ F1Good=F1Log[zGood]
+ ### MLE Part ####
+ # Since we dont wanna update p and Z in this step
+ # Each Ng for one row
+
+ NumGroupVector=rep(c(1:NoneZeroLength),NumOfEachGroup)
+
+ NumGroupVector.zGood=NumGroupVector[zGood]
+ NumOfEachGroup.zGood=tapply(NumGroupVector.zGood,NumGroupVector.zGood,length)
+
+ StartValue=c(AlphaIn, BetaIn,PIn)
+
+ Result<-optim(StartValue,Likefun,InputPool=list(InputSP[[1]][zGood,],InputSP[[2]][zGood,],Input[zGood,],z.list[zGood], NoneZeroLength,EmpiricalR[zGood, ],EmpiricalRSP[[1]][zGood,], EmpiricalRSP[[2]][zGood,], NumOfEachGroup.zGood))
+ #LikeOutput=Likelihood( StartValue, Input , InputSP , PNEW.list, z.list)
+ AlphaNew= Result$par[1]
+ BetaNew=Result$par[2:(1+NoneZeroLength)]
+ PNew=Result$par[2+NoneZeroLength]
+ ##
+ Output=list(AlphaNew=AlphaNew,BetaNew=BetaNew,PNew=PNew,ZNew.list=z.list,PFromZ=PFromZ, zGood=zGood, zNaNName=zNaNName,F0Out=F0Good, F1Out=F1Good)
+ Output
+ }
+
diff --git a/R/LogNMulti.R b/R/LogNMulti.R
new file mode 100644
index 0000000..e10df33
--- /dev/null
+++ b/R/LogNMulti.R
@@ -0,0 +1,79 @@
+LogNMulti <-
+function(Input, InputSP, EmpiricalR, EmpiricalRSP, NumOfEachGroup, AlphaIn, BetaIn, PIn, NoneZeroLength, AllParti, Conditions)
+{
+
+ #For each gene (m rows of Input---m genes)
+ #Save each gene's F0, F1 for further likelihood calculation.
+ FList=sapply(1:nrow(AllParti),function(i)sapply(1:nlevels(as.factor(AllParti[i,])),
+ function(j)f0(do.call(cbind,InputSP[AllParti[i,]==j]),AlphaIn, BetaIn,
+ do.call(cbind,EmpiricalRSP[AllParti[i,]==j]), NumOfEachGroup, log=T)),
+ simplify=F)
+ FPartiLog=sapply(FList,rowSums)
+ FMat=exp(FPartiLog+600)
+ rownames(FMat)=rownames(FPartiLog)=rownames(Input)
+ #Get z
+ #Use data.list in logfunction
+ PInMat=matrix(rep(1,nrow(Input)),ncol=1)%*%matrix(PIn,nrow=1)
+ FmultiP=FMat*PInMat
+ Denom=rowSums(FmultiP)
+ ZEach=apply(FmultiP,2,function(i)i/Denom)
+ zNaNName1=names(Denom)[is.na(Denom)]
+ # other NAs in LikeFun
+ LF=ZEach*(log(FmultiP))
+ zNaNMore=rownames(LF)[which(is.na(rowSums(LF)))]
+ zNaNName=unique(c(zNaNName1,zNaNMore))
+ zGood=which(!rownames(LF)%in%zNaNName)
+
+
+ if(length(zGood)==0){
+ #Min=min(min(F0Log[which(F0Log!=-Inf)]),
+ # min(F1Log[which(F1Log!=-Inf)]))
+ tmpMat=FPartiLog
+ tmpMean=apply(tmpMat,1,mean)
+ FLogMdf=FPartiLog-tmpMean
+ FMdf=exp(FLogMdf)
+
+ FmultiPMdf=FMdf*PInMat
+ DenomMdf=rowSums(FmultiPMdf)
+ ZEach=apply(FmultiPMdf,2,function(i)i/DenomMdf)
+ zNaNName1Mdf=names(DenomMdf)[is.na(DenomMdf)]
+ # other NAs in LikeFun
+ LFMdf=ZEach*(log(FmultiPMdf))
+ zNaNMoreMdf=rownames(LFMdf)[which(is.na(rowSums(LFMdf)))]
+ zNaNNameMdf=unique(c(zNaNName1Mdf,zNaNMoreMdf))
+ zGood=which(!rownames(LFMdf)%in%zNaNNameMdf)
+
+
+
+
+ }
+
+ ZEachGood=ZEach[zGood,]
+ ###Update P
+ PFromZ=colSums(ZEach[zGood,])/length(zGood)
+ FGood=FPartiLog[zGood,]
+ ### MLE Part ####
+ # Since we dont wanna update p and Z in this step
+ # Each Ng for one row
+
+ NumGroupVector=rep(c(1:NoneZeroLength),NumOfEachGroup)
+
+ NumGroupVector.zGood=NumGroupVector[zGood]
+ NumOfEachGroup.zGood=tapply(NumGroupVector.zGood,NumGroupVector.zGood,length)
+
+ StartValue=c(AlphaIn, BetaIn,PIn[-1])
+ InputSPGood=sapply(1:length(InputSP),function(i)InputSP[[i]][zGood,],simplify=F)
+ EmpiricalRSPGood=sapply(1:length(EmpiricalRSP),function(i)EmpiricalRSP[[i]][zGood,],simplify=F)
+
+ Result<-optim(StartValue,LikefunMulti,InputPool=list(InputSPGood,Input[zGood,],ZEach[zGood,],
+ NoneZeroLength,EmpiricalR[zGood, ],EmpiricalRSPGood, NumOfEachGroup.zGood, AllParti))
+ AlphaNew= Result$par[1]
+ BetaNew=Result$par[2:(1+NoneZeroLength)]
+ PNewNo1=Result$par[(2+NoneZeroLength):length(Result$par)]
+ PNew=c(1-sum(PNewNo1),PNewNo1)
+ ##
+ Output=list(AlphaNew=AlphaNew,BetaNew=BetaNew,PNew=PNew,ZEachNew=ZEach, ZEachGood=ZEachGood,
+ PFromZ=PFromZ, zGood=zGood, zNaNName=zNaNName,FGood=FGood)
+ Output
+ }
+
diff --git a/R/MedianNorm.R b/R/MedianNorm.R
new file mode 100644
index 0000000..afd7b37
--- /dev/null
+++ b/R/MedianNorm.R
@@ -0,0 +1,5 @@
+MedianNorm=function(Data){
+ if(ncol(Data)==1)stop("Only 1 sample!")
+ geomeans <- exp(rowMeans(log(Data)))
+ apply(Data, 2, function(cnts) median((cnts/geomeans)[geomeans > 0]))
+}
diff --git a/R/PlotPattern.R b/R/PlotPattern.R
new file mode 100644
index 0000000..c954850
--- /dev/null
+++ b/R/PlotPattern.R
@@ -0,0 +1,7 @@
+PlotPattern<-function(Patterns){
+ par(oma=c(3,3,3,3))
+ PatternCol=rev(rainbow(ncol(Patterns)))
+ heatmap(Patterns,col=PatternCol,Colv=NA,Rowv=NA,scale="none")
+
+}
+
diff --git a/R/PlotPostVsRawFC.R b/R/PlotPostVsRawFC.R
new file mode 100644
index 0000000..64ba2b3
--- /dev/null
+++ b/R/PlotPostVsRawFC.R
@@ -0,0 +1,21 @@
+PlotPostVsRawFC<-function(EBOut,FCOut){
+library(gplots)
+
+par(fig=c(0,.8,0,1), new=F)
+RainbowColor=rev(redgreen(length(FCOut$PostFC)))
+par(oma=c(0,1,1,0),cex=1.3)
+plot(FCOut$PostFC,FCOut$RealFC,
+log="xy",col=RainbowColor[rank(unlist(EBOut$MeanList)[names(FCOut$PostFC)])], xlab="Posterior FC",
+ylab="FC",pch=21)
+abline(h=1, v=1, col="gray")
+#legend("topleft",col=c("green","black","red"),legend=c("Low Expression","Median Expression","High Expression"),pch=21)
+
+par(fig=c(.7,1,0,1), new=TRUE)
+Seq=1:ceiling(length(RainbowColor)/100)
+plot(c(0,10), c(1,length(RainbowColor)), type='n', bty='n', xaxt='n', xlab='Rank', ylab='')
+for (i in 1:length(Seq)) {
+rect(0,(i-1)*100,10,i*100, col=RainbowColor[(i-1)*100], border=NA)
+}
+
+
+}
diff --git a/R/PolyFitPlot.R b/R/PolyFitPlot.R
new file mode 100644
index 0000000..59fd29c
--- /dev/null
+++ b/R/PolyFitPlot.R
@@ -0,0 +1,44 @@
+PolyFitPlot <-
+function(X , Y , nterms , xname="Estimated Mean", yname="Estimated Var", pdfname="", xlim=c(-1,5), ylim=c(-1,7), ChangeXY=F,col="red"){
+
+ b=rep(NA,nterms)
+ logX=matrix(rep(X, nterms),ncol=nterms, byrow=T)
+ for (i in 1:nterms)
+ logX[,i]=(log10(X))^i
+ colnames(logX)=paste("logmu^",c(1:nterms))
+ rownames(logX)=names(X)
+ NotUse=c(names(X)[X==0],names(Y)[Y==0],names(X)[rowMeans(logX)==-Inf],names(X)[rowMeans(logX)==Inf])
+ Use=names(X[!names(X)%in%NotUse])
+ Lm=lm(log10(Y[Use])~logX[Use,1:nterms])
+ b=summary(Lm)$coefficients[2:(nterms+1),1]
+ d=summary(Lm)$coefficients[1,1]
+ bvec=matrix(rep(b,length(X)),ncol=nterms,byrow=T)
+ fit=rowSums(logX*bvec)+d
+ main2=NULL
+ if (ChangeXY==T){
+ X.plot=log10(Y)
+ Y.plot=log10(X)
+ fit.X.plot=fit
+ fit.Y.plot=log10(X)
+ }
+ else{
+ X.plot=log10(X)
+ Y.plot=log10(Y)
+ fit.X.plot=log10(X)
+ fit.Y.plot=fit
+ }
+
+ for (i in 1:nterms)
+ main2=paste(main2,round(b[i],2),"*log(",xname,")^",i,"+")
+ main=pdfname
+
+ smoothScatter(X.plot, Y.plot ,main=main,xlim=xlim,ylim=ylim,xlab=xname,ylab=yname,axes=F)
+ axis(1,at=seq(xlim[1],xlim[2],by=1), 10^seq(xlim[1],xlim[2],by=1))
+ axis(2,at=seq(ylim[1],ylim[2],by=2), 10^seq(ylim[1],ylim[2],by=2))
+ Sortit=order(fit.X.plot)
+ lines(fit.X.plot[Sortit],fit.Y.plot[Sortit],col=col,lwd=3)
+ output=list(b=b,d=d,lm=Lm,fit=fit,sort=Sortit)
+ names(output$b)=paste(xname,"^",c(1:length(output$b)))
+ output
+}
+
diff --git a/R/PostFC.R b/R/PostFC.R
new file mode 100644
index 0000000..557086e
--- /dev/null
+++ b/R/PostFC.R
@@ -0,0 +1,38 @@
+PostFC=function(EBoutput, SmallNum=.01) {
+ if(!"C1Mean"%in%names(EBoutput))
+ stop("The input doesn't seem like an output from EBTest")
+ GeneRealMeanC1=unlist(EBoutput$C1Mean)
+ GeneRealMeanC2=unlist(EBoutput$C2Mean)
+ GeneRealMeanC1Plus=GeneRealMeanC1+SmallNum
+ GeneRealMeanC2Plus=GeneRealMeanC2+SmallNum
+ GeneRealMean=(GeneRealMeanC1+GeneRealMeanC2)/2
+
+ GeneRealFC=GeneRealMeanC1Plus/GeneRealMeanC2Plus
+
+ GeneR=unlist(EBoutput$RList)
+ GeneR[GeneR<=0 | is.na(GeneR)]=GeneRealMean[GeneR<=0 | is.na(GeneR)]*.99/.01
+
+ GeneAlpha=EBoutput[[1]][nrow(EBoutput[[1]]),]
+ GeneBeta=unlist(sapply(1:length(EBoutput$C1Mean),function(i)rep(EBoutput[[2]][nrow(EBoutput[[1]]),i],length(EBoutput$C1Mean[[i]]))))
+ GeneBeta=as.vector(GeneBeta)
+
+ # Post alpha P_a_C1= alpha + r_C1 * n_C1
+ # Post beta P_b_C1= beta + Mean_C1 * n_C1
+ # P_q_C1= P_a_C1/ (P_a_C1 + P_b_C1)
+ # Post FC = ((1-P_q_C1)/P_q_c1) /( (1-P_q_c2)/P_q_c2)
+
+ nC1=sum(EBoutput$Conditions==levels(EBoutput$Conditions)[1])
+ nC2=sum(EBoutput$Conditions==levels(EBoutput$Conditions)[2])
+ GenePostAlphaC1=GeneAlpha+nC1*GeneR
+ GenePostAlphaC2=GeneAlpha+nC2*GeneR
+ GenePostBetaC1=GeneBeta+nC1*GeneRealMeanC1
+ GenePostBetaC2=GeneBeta+nC2*GeneRealMeanC2
+ GenePostQC1=GenePostAlphaC1/(GenePostAlphaC1+GenePostBetaC1)
+ GenePostQC2=GenePostAlphaC2/(GenePostAlphaC2+GenePostBetaC2)
+
+ GenePostFC=((1-GenePostQC1)/(1-GenePostQC2))*(GenePostQC2/GenePostQC1)
+ Out=list(PostFC=GenePostFC[rownames(EBoutput$PPMat)], RealFC=GeneRealFC[rownames(EBoutput$PPMat)],
+ Direction=paste(EBoutput$ConditionOrder[[1]],"Over", EBoutput$ConditionOrder[[2]])
+ )
+
+}
diff --git a/R/QQP.R b/R/QQP.R
new file mode 100644
index 0000000..b9e938f
--- /dev/null
+++ b/R/QQP.R
@@ -0,0 +1,45 @@
+QQP <-
+function(EBOut, GeneLevel=F){
+ if(!"Alpha"%in%names(EBOut))stop("The input doesn't seem like an output from EBTest/EBMultiTest")
+ maxround=nrow(EBOut$Alpha)
+ AlphaResult=EBOut$Alpha[maxround,]
+ BetaResult=EBOut$Beta[maxround,]
+
+ # Multi
+ if(!is.null(EBOut$PPpattern)){
+ QList=EBOut$QList
+ for(i in 1:length(EBOut$QList)){
+ for(j in 1:length(EBOut$QList[[i]])){
+ if(GeneLevel==F)Main=paste("Ig",i,"C",j)
+ if(GeneLevel==T)Main=paste("Gene","C",j)
+ tmpSize=length(QList[[i]][[j]][QList[[i]][[j]]<1 & !is.na(QList[[i]][[j]])])
+ rdpts=rbeta(tmpSize,AlphaResult,BetaResult[i])
+ qqplot(QList[[i]][[j]][QList[[i]][[j]]<1],
+ rdpts,xlab="estimated q's", ylab="simulated q's from fitted beta",
+ main=Main,
+ xlim=c(0,1),ylim=c(0,1))
+ fit=lm(sort(rdpts)~sort(QList[[i]][[j]][QList[[i]][[j]]<1 & !is.na(QList[[i]][[j]])]))
+ abline(fit,col="red")
+
+ }
+ }
+ }
+
+ if(is.null(EBOut$PPpattern)){
+ for(con in 1:2){
+ if(con==1)QList=EBOut$QList1
+ if(con==2)QList=EBOut$QList2
+ for (i in 1:length(BetaResult)){
+ if(GeneLevel==F)Main=paste("Ig",i,"C",con)
+ if(GeneLevel==T)Main=paste("Gene","C",con)
+ tmpSize=length(QList[[i]][QList[[i]]<1 & !is.na(QList[[i]])])
+ rdpts=rbeta(tmpSize,AlphaResult,BetaResult[i])
+ qqplot(QList[[i]][QList[[i]]<1],
+ rdpts,xlab="estimated q's", ylab="simulated q's from fitted beta",
+ main=Main,
+ xlim=c(0,1),ylim=c(0,1))
+ fit=lm(sort(rdpts)~sort(QList[[i]][QList[[i]]<1 & !is.na(QList[[i]])]))
+ abline(fit,col="red")
+ } }}
+}
+
diff --git a/R/QuantileNorm.R b/R/QuantileNorm.R
new file mode 100644
index 0000000..c96ea1e
--- /dev/null
+++ b/R/QuantileNorm.R
@@ -0,0 +1,10 @@
+
+QuantileNorm=function(Data, Quantile){
+ if(ncol(Data)==1)stop("Only 1 sample!")
+
+ QtilePt=apply(Data, 2, function(i)quantile(i, Quantile))
+# Size= QtilePt * prod(QtilePt) ^ (-1/ncol(Data))
+ Size=10^(log10(QtilePt)-sum(log10(QtilePt))*(1/ncol(Data)) )
+ Size
+ }
+
diff --git a/R/RankNorm.R b/R/RankNorm.R
new file mode 100644
index 0000000..11215cc
--- /dev/null
+++ b/R/RankNorm.R
@@ -0,0 +1,13 @@
+
+RankNorm=function(Data){
+ if(ncol(Data)==1)stop("Only 1 sample!")
+
+ RankData=apply(Data, 2, rank)
+ SortData=apply(Data, 2, sort)
+ SortMean=rowMeans(SortData)
+ SortMean[SortMean==0]=1
+ NormMatrix=sapply(1:ncol(Data), function(i)Data[,i]/(SortMean[RankData[,i]]))
+ NormMatrix[NormMatrix==0]=1
+ NormMatrix
+ }
+
diff --git a/R/beta.mom.R b/R/beta.mom.R
new file mode 100644
index 0000000..269996d
--- /dev/null
+++ b/R/beta.mom.R
@@ -0,0 +1,10 @@
+beta.mom <-
+function(qs.in){
+ xbar<-mean(qs.in)
+ s2<-var(qs.in)
+ term<-(xbar*(1-xbar))/s2
+ alpha.hat<-xbar*(term-1)
+ beta.hat<-(1-xbar)*(term-1)
+ return(c(alpha.hat,beta.hat))
+}
+
diff --git a/R/crit_fun.R b/R/crit_fun.R
new file mode 100644
index 0000000..e68ed4b
--- /dev/null
+++ b/R/crit_fun.R
@@ -0,0 +1,15 @@
+crit_fun<-function (PPEE, thre)
+{
+ y <- cumsum(sort(PPEE))/(1:length(PPEE))
+ mm <- y < thre
+ index <- sum(mm)
+ if (index > 0) {
+ out <- 1 - sort(PPEE)[index]
+ }
+ if (index == 0) {
+ out <- 1
+ }
+ names(out) <- NULL
+ return(out)
+}
+
diff --git a/R/f0.R b/R/f0.R
new file mode 100644
index 0000000..e5d8901
--- /dev/null
+++ b/R/f0.R
@@ -0,0 +1,27 @@
+f0 <-
+function(Input, AlphaIn, BetaIn, EmpiricalR, NumOfGroups, log)
+{
+ BetaVect=do.call(c,sapply(1:length(BetaIn),function(i)rep(BetaIn[i],NumOfGroups[i]),simplify=F))
+ SampleNum=dim(Input)[2]
+ #Product part
+ ChooseParam1=round(Input+EmpiricalR-1)
+ roundInput=round(Input)
+ EachChoose0=matrix(sapply(1:SampleNum, function(i)lchoose(ChooseParam1[,i], roundInput[,i])),ncol=SampleNum)
+ # numerical approximation to rescue -Inf ones
+ NoNegInfMin=min(EachChoose0[which(EachChoose0!=-Inf)])
+ NoPosInfMax=max(EachChoose0[which(EachChoose0!=Inf)])
+ EachChoose=EachChoose0
+ EachChoose[which(EachChoose0==-Inf, arr.ind=T)]=NoNegInfMin
+ EachChoose[which(EachChoose0==Inf, arr.ind=T)]=NoPosInfMax
+
+ SumEachIso=rowSums(Input)
+ param1=AlphaIn + rowSums(EmpiricalR)
+ param2=BetaVect + SumEachIso
+ LogConst=rowSums(EachChoose)+lbeta(param1, param2)-lbeta(AlphaIn, BetaVect)
+
+
+ if (log==F) FinalResult=exp(LogConst)
+ if (log==T) FinalResult=LogConst
+ FinalResult
+}
+
diff --git a/R/f1.R b/R/f1.R
new file mode 100644
index 0000000..1f160a0
--- /dev/null
+++ b/R/f1.R
@@ -0,0 +1,10 @@
+f1 <-
+function(Input1, Input2, AlphaIn, BetaIn, EmpiricalRSP1,EmpiricalRSP2,NumOfGroup, log){
+ F0.1=f0(Input1, AlphaIn, BetaIn, EmpiricalRSP1, NumOfGroup, log=log)
+ F0.2=f0(Input2, AlphaIn, BetaIn, EmpiricalRSP2, NumOfGroup, log=log)
+
+ if (log==F) Result=F0.1*F0.2
+ if (log==T) Result=F0.1+F0.2
+ Result
+}
+
diff --git a/build/vignette.rds b/build/vignette.rds
new file mode 100644
index 0000000..6c7e94f
Binary files /dev/null and b/build/vignette.rds differ
diff --git a/data/GeneMat.rda b/data/GeneMat.rda
new file mode 100644
index 0000000..91d9e8b
Binary files /dev/null and b/data/GeneMat.rda differ
diff --git a/data/IsoList.rda b/data/IsoList.rda
new file mode 100644
index 0000000..8f22575
Binary files /dev/null and b/data/IsoList.rda differ
diff --git a/data/IsoMultiList.rda b/data/IsoMultiList.rda
new file mode 100644
index 0000000..f9aa5d9
Binary files /dev/null and b/data/IsoMultiList.rda differ
diff --git a/data/MultiGeneMat.rda b/data/MultiGeneMat.rda
new file mode 100644
index 0000000..944abf2
Binary files /dev/null and b/data/MultiGeneMat.rda differ
diff --git a/demo/00Index b/demo/00Index
new file mode 100644
index 0000000..24bc98e
--- /dev/null
+++ b/demo/00Index
@@ -0,0 +1 @@
+EBSeq demo
diff --git a/demo/EBSeq.R b/demo/EBSeq.R
new file mode 100644
index 0000000..3d5024d
--- /dev/null
+++ b/demo/EBSeq.R
@@ -0,0 +1,250 @@
+library(EBSeq)
+# 3.1
+data(GeneMat)
+str(GeneMat)
+Sizes=MedianNorm(GeneMat)
+EBOut=EBTest(Data=GeneMat,
+ Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+PP=GetPPMat(EBOut)
+str(PP)
+head(PP)
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+#3.2
+data(IsoList)
+str(IsoList)
+IsoMat=IsoList$IsoMat
+str(IsoMat)
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+IsoSizes=MedianNorm(IsoMat)
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+ Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+str(IsoPP)
+head(IsoPP)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+str(IsoDE)
+#3.3
+data(MultiGeneMat)
+str(MultiGeneMat)
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+Parti=PosParti[-3,]
+Parti
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,NgVector=NULL,Conditions=Conditions,
+ AllParti=Parti, sizeFactors=MultiSize, maxround=5)
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+
+#3.4
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+IsoMultiOut=EBMultiTest(IsoMultiMat,NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+ AllParti=Parti.4Cond, sizeFactors=IsoMultiSize, maxround=5)
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+
+
+#4.1
+data(GeneMat)
+str(GeneMat)
+Sizes=MedianNorm(GeneMat)
+EBOut=EBTest(Data=GeneMat,
+ Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+PP=GetPPMat(EBOut)
+str(PP)
+head(PP)
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+EBOut$Alpha
+EBOut$Beta
+EBOut$P
+GeneFC=PostFC(EBOut)
+str(GeneFC)
+par(mfrow=c(2,2))
+QQP(EBOut)
+par(mfrow=c(2,2))
+DenNHist(EBOut)
+PlotPostVsRawFC(EBOut,GeneFC)
+
+#4.2
+data(IsoList)
+str(IsoList)
+IsoMat=IsoList$IsoMat
+str(IsoMat)
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+IsoSizes=MedianNorm(IsoMat)
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+ Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+str(IsoPP)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+str(IsoDE)
+IsoEBOut$Alpha
+IsoEBOut$Beta
+IsoEBOut$P
+IsoFC=PostFC(IsoEBOut)
+str(IsoFC)
+PlotPostVsRawFC(IsoEBOut,IsoFC)
+
+par(mfrow=c(2,2))
+PolyFitValue=vector("list",3)
+for(i in 1:3)
+ PolyFitValue[[i]]=PolyFitPlot(IsoEBOut$C1Mean[[i]],
+ IsoEBOut$C1EstVar[[i]],5)
+PolyAll=PolyFitPlot(unlist(IsoEBOut$C1Mean), unlist(IsoEBOut$C1EstVar),5)
+lines(log10(IsoEBOut$C1Mean[[1]][PolyFitValue[[1]]$sort]),
+ PolyFitValue[[1]]$fit[PolyFitValue[[1]]$sort],col="yellow",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[2]][PolyFitValue[[2]]$sort]),
+ PolyFitValue[[2]]$fit[PolyFitValue[[2]]$sort],col="pink",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[3]][PolyFitValue[[3]]$sort]),
+ PolyFitValue[[3]]$fit[PolyFitValue[[3]]$sort],col="green",lwd=2)
+legend("topleft",c("All Isoforms","Ig = 1","Ig = 2","Ig = 3"),
+ col=c("red","yellow","pink","green"),lty=1,lwd=3,box.lwd=2)
+par(mfrow=c(2,3))
+QQP(IsoEBOut)
+par(mfrow=c(2,3))
+DenNHist(IsoEBOut)
+
+
+#4.3
+data(MultiGeneMat)
+str(MultiGeneMat)
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+PlotPattern(PosParti)
+Parti=PosParti[-3,]
+Parti
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,NgVector=NULL,Conditions=Conditions,
+ AllParti=Parti, sizeFactors=MultiSize, maxround=5)
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+MultiFC=GetMultiFC(MultiOut)
+str(MultiFC)
+par(mfrow=c(2,2))
+DenNHist(MultiOut)
+par(mfrow=c(2,2))
+QQP(MultiOut)
+
+#4.4
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+PlotPattern(PosParti.4Cond)
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+IsoMultiOut=EBMultiTest(IsoMultiMat,NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+ AllParti=Parti.4Cond, sizeFactors=IsoMultiSize, maxround=5)
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+IsoMultiFC=GetMultiFC(IsoMultiOut)
+str(IsoMultiFC)
+par(mfrow=c(3,4))
+DenNHist(IsoMultiOut)
+par(mfrow=c(3,4))
+QQP(IsoMultiOut)
+IsoMultiFC=GetMultiFC(IsoMultiOut)
+
+
+
+#4.5
+data(GeneMat)
+GeneMat.norep=GeneMat[,c(1,6)]
+Sizes.norep=MedianNorm(GeneMat.norep)
+EBOut.norep=EBTest(Data=GeneMat.norep,
+ Conditions=as.factor(rep(c("C1","C2"))),sizeFactors=Sizes.norep, maxround=5)
+PP.norep=GetPPMat(EBOut.norep)
+DEfound.norep=rownames(PP.norep)[which(PP.norep[,"PPDE"]>=.95)]
+GeneFC.norep=PostFC(EBOut.norep)
+
+
+#4.6
+data(IsoList)
+IsoMat=IsoList$IsoMat
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoMat.norep=IsoMat[,c(1,6)]
+IsoSizes.norep=MedianNorm(IsoMat.norep)
+IsoEBOut.norep=EBTest(Data=IsoMat.norep, NgVector=IsoNgTrun,
+ Conditions=as.factor(c("C1","C2")),sizeFactors=IsoSizes.norep, maxround=5)
+IsoPP.norep=GetPPMat(IsoEBOut.norep)
+IsoDE.norep=rownames(IsoPP.norep)[which(IsoPP.norep[,"PPDE"]>=.95)]
+IsoFC.norep=PostFC(IsoEBOut.norep)
+
+
+#4.7
+data(MultiGeneMat)
+MultiGeneMat.norep=MultiGeneMat[,c(1,3,5)]
+Conditions=c("C1","C2","C3")
+PosParti=GetPatterns(Conditions)
+Parti=PosParti[-3,]
+MultiSize.norep=MedianNorm(MultiGeneMat.norep)
+MultiOut.norep=EBMultiTest(MultiGeneMat.norep,NgVector=NULL,Conditions=Conditions,
+ AllParti=Parti, sizeFactors=MultiSize.norep, maxround=5)
+MultiPP.norep=GetMultiPP(MultiOut.norep)
+MultiFC.norep=GetMultiFC(MultiOut.norep)
+
+#4.8
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiMat.norep=IsoMultiMat[,c(1,3,5,7)]
+IsoMultiSize.norep=MedianNorm(IsoMultiMat.norep)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C2","C3","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+IsoMultiOut.norep=EBMultiTest(IsoMultiMat.norep,NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+ AllParti=Parti.4Cond, sizeFactors=IsoMultiSize.norep, maxround=5)
+IsoMultiPP.norep=GetMultiPP(IsoMultiOut.norep)
+IsoMultiFC.norep=GetMultiFC(IsoMultiOut.norep)
+
+
+# EOF
diff --git a/inst/doc/EBSeq_Vignette.R b/inst/doc/EBSeq_Vignette.R
new file mode 100644
index 0000000..1595b03
--- /dev/null
+++ b/inst/doc/EBSeq_Vignette.R
@@ -0,0 +1,497 @@
+### R code from vignette source 'EBSeq_Vignette.Rnw'
+
+###################################################
+### code chunk number 1: EBSeq_Vignette.Rnw:172-173
+###################################################
+library(EBSeq)
+
+
+###################################################
+### code chunk number 2: EBSeq_Vignette.Rnw:198-200
+###################################################
+data(GeneMat)
+str(GeneMat)
+
+
+###################################################
+### code chunk number 3: EBSeq_Vignette.Rnw:208-209
+###################################################
+Sizes=MedianNorm(GeneMat)
+
+
+###################################################
+### code chunk number 4: EBSeq_Vignette.Rnw:235-237
+###################################################
+EBOut=EBTest(Data=GeneMat,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+
+
+###################################################
+### code chunk number 5: EBSeq_Vignette.Rnw:241-244
+###################################################
+PP=GetPPMat(EBOut)
+str(PP)
+head(PP)
+
+
+###################################################
+### code chunk number 6: EBSeq_Vignette.Rnw:249-251
+###################################################
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+
+
+###################################################
+### code chunk number 7: EBSeq_Vignette.Rnw:285-291
+###################################################
+data(IsoList)
+str(IsoList)
+IsoMat=IsoList$IsoMat
+str(IsoMat)
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+
+
+###################################################
+### code chunk number 8: EBSeq_Vignette.Rnw:298-299
+###################################################
+IsoSizes=MedianNorm(IsoMat)
+
+
+###################################################
+### code chunk number 9: EBSeq_Vignette.Rnw:320-323
+###################################################
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+
+
+###################################################
+### code chunk number 10: EBSeq_Vignette.Rnw:335-342
+###################################################
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+str(IsoPP)
+head(IsoPP)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+str(IsoDE)
+
+
+###################################################
+### code chunk number 11: EBSeq_Vignette.Rnw:353-355
+###################################################
+data(MultiGeneMat)
+str(MultiGeneMat)
+
+
+###################################################
+### code chunk number 12: EBSeq_Vignette.Rnw:363-366
+###################################################
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+
+
+###################################################
+### code chunk number 13: EBSeq_Vignette.Rnw:374-376
+###################################################
+Parti=PosParti[-3,]
+Parti
+
+
+###################################################
+### code chunk number 14: EBSeq_Vignette.Rnw:381-384
+###################################################
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize, maxround=5)
+
+
+###################################################
+### code chunk number 15: EBSeq_Vignette.Rnw:388-393
+###################################################
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+
+
+###################################################
+### code chunk number 16: EBSeq_Vignette.Rnw:412-420
+###################################################
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+
+
+###################################################
+### code chunk number 17: EBSeq_Vignette.Rnw:426-428
+###################################################
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+
+
+###################################################
+### code chunk number 18: EBSeq_Vignette.Rnw:433-435
+###################################################
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+
+
+###################################################
+### code chunk number 19: EBSeq_Vignette.Rnw:440-444
+###################################################
+IsoMultiOut=EBMultiTest(IsoMultiMat,
+NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond, sizeFactors=IsoMultiSize,
+maxround=5)
+
+
+###################################################
+### code chunk number 20: EBSeq_Vignette.Rnw:448-453
+###################################################
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+
+
+###################################################
+### code chunk number 21: EBSeq_Vignette.Rnw:470-475 (eval = FALSE)
+###################################################
+## data(GeneMat)
+## Sizes=MedianNorm(GeneMat)
+## EBOut=EBTest(Data=GeneMat,
+## Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+## PP=GetPPMat(EBOut)
+
+
+###################################################
+### code chunk number 22: EBSeq_Vignette.Rnw:477-481
+###################################################
+str(PP)
+head(PP)
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+
+
+###################################################
+### code chunk number 23: EBSeq_Vignette.Rnw:491-494
+###################################################
+GeneFC=PostFC(EBOut)
+str(GeneFC)
+PlotPostVsRawFC(EBOut,GeneFC)
+
+
+###################################################
+### code chunk number 24: EBSeq_Vignette.Rnw:515-518
+###################################################
+EBOut$Alpha
+EBOut$Beta
+EBOut$P
+
+
+###################################################
+### code chunk number 25: EBSeq_Vignette.Rnw:537-539
+###################################################
+par(mfrow=c(1,2))
+QQP(EBOut)
+
+
+###################################################
+### code chunk number 26: EBSeq_Vignette.Rnw:555-557
+###################################################
+par(mfrow=c(1,2))
+DenNHist(EBOut)
+
+
+###################################################
+### code chunk number 27: EBSeq_Vignette.Rnw:578-583 (eval = FALSE)
+###################################################
+## data(IsoList)
+## IsoMat=IsoList$IsoMat
+## IsoNames=IsoList$IsoNames
+## IsosGeneNames=IsoList$IsosGeneNames
+## NgList=GetNg(IsoNames, IsosGeneNames, TrunThre=3)
+
+
+###################################################
+### code chunk number 28: EBSeq_Vignette.Rnw:585-588
+###################################################
+names(NgList)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+
+
+###################################################
+### code chunk number 29: EBSeq_Vignette.Rnw:619-620 (eval = FALSE)
+###################################################
+## IsoNgTrun = scan(file="output_name.ngvec", what=0, sep="\n")
+
+
+###################################################
+### code chunk number 30: EBSeq_Vignette.Rnw:633-638 (eval = FALSE)
+###################################################
+## IsoSizes=MedianNorm(IsoMat)
+## IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+## Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+## IsoPP=GetPPMat(IsoEBOut)
+## IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+
+
+###################################################
+### code chunk number 31: EBSeq_Vignette.Rnw:640-641
+###################################################
+str(IsoDE)
+
+
+###################################################
+### code chunk number 32: EBSeq_Vignette.Rnw:646-648
+###################################################
+IsoFC=PostFC(IsoEBOut)
+str(IsoFC)
+
+
+###################################################
+### code chunk number 33: EBSeq_Vignette.Rnw:659-662
+###################################################
+IsoEBOut$Alpha
+IsoEBOut$Beta
+IsoEBOut$P
+
+
+###################################################
+### code chunk number 34: EBSeq_Vignette.Rnw:681-686
+###################################################
+par(mfrow=c(2,2))
+PolyFitValue=vector("list",3)
+for(i in 1:3)
+ PolyFitValue[[i]]=PolyFitPlot(IsoEBOut$C1Mean[[i]],
+ IsoEBOut$C1EstVar[[i]],5)
+
+
+###################################################
+### code chunk number 35: EBSeq_Vignette.Rnw:699-708
+###################################################
+PolyAll=PolyFitPlot(unlist(IsoEBOut$C1Mean), unlist(IsoEBOut$C1EstVar),5)
+lines(log10(IsoEBOut$C1Mean[[1]][PolyFitValue[[1]]$sort]),
+PolyFitValue[[1]]$fit[PolyFitValue[[1]]$sort],col="yellow",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[2]][PolyFitValue[[2]]$sort]),
+PolyFitValue[[2]]$fit[PolyFitValue[[2]]$sort],col="pink",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[3]][PolyFitValue[[3]]$sort]),
+PolyFitValue[[3]]$fit[PolyFitValue[[3]]$sort],col="green",lwd=2)
+legend("topleft",c("All Isoforms","Ng = 1","Ng = 2","Ng = 3"),
+col=c("red","yellow","pink","green"),lty=1,lwd=3,box.lwd=2)
+
+
+###################################################
+### code chunk number 36: EBSeq_Vignette.Rnw:721-723
+###################################################
+par(mfrow=c(2,3))
+QQP(IsoEBOut)
+
+
+###################################################
+### code chunk number 37: EBSeq_Vignette.Rnw:735-737
+###################################################
+par(mfrow=c(2,3))
+DenNHist(IsoEBOut)
+
+
+###################################################
+### code chunk number 38: EBSeq_Vignette.Rnw:754-758
+###################################################
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+PlotPattern(PosParti)
+
+
+###################################################
+### code chunk number 39: EBSeq_Vignette.Rnw:765-767
+###################################################
+Parti=PosParti[-3,]
+Parti
+
+
+###################################################
+### code chunk number 40: EBSeq_Vignette.Rnw:773-779 (eval = FALSE)
+###################################################
+## data(MultiGeneMat)
+## MultiSize=MedianNorm(MultiGeneMat)
+## MultiOut=EBMultiTest(MultiGeneMat,
+## NgVector=NULL,Conditions=Conditions,
+## AllParti=Parti, sizeFactors=MultiSize,
+## maxround=5)
+
+
+###################################################
+### code chunk number 41: EBSeq_Vignette.Rnw:783-788
+###################################################
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+
+
+###################################################
+### code chunk number 42: EBSeq_Vignette.Rnw:795-797
+###################################################
+MultiFC=GetMultiFC(MultiOut)
+str(MultiFC)
+
+
+###################################################
+### code chunk number 43: EBSeq_Vignette.Rnw:806-808
+###################################################
+par(mfrow=c(2,2))
+QQP(MultiOut)
+
+
+###################################################
+### code chunk number 44: EBSeq_Vignette.Rnw:816-818
+###################################################
+par(mfrow=c(2,2))
+DenNHist(MultiOut)
+
+
+###################################################
+### code chunk number 45: EBSeq_Vignette.Rnw:833-836
+###################################################
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+
+
+###################################################
+### code chunk number 46: EBSeq_Vignette.Rnw:841-844
+###################################################
+PlotPattern(PosParti.4Cond)
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+
+
+###################################################
+### code chunk number 47: EBSeq_Vignette.Rnw:851-862 (eval = FALSE)
+###################################################
+## data(IsoMultiList)
+## IsoMultiMat=IsoMultiList[[1]]
+## IsoNames.Multi=IsoMultiList$IsoNames
+## IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+## IsoMultiSize=MedianNorm(IsoMultiMat)
+## NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+## IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+## IsoMultiOut=EBMultiTest(IsoMultiMat,NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+## AllParti=Parti.4Cond,
+## sizeFactors=IsoMultiSize, maxround=5)
+## IsoMultiPP=GetMultiPP(IsoMultiOut)
+
+
+###################################################
+### code chunk number 48: EBSeq_Vignette.Rnw:864-869
+###################################################
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+IsoMultiFC=GetMultiFC(IsoMultiOut)
+
+
+###################################################
+### code chunk number 49: EBSeq_Vignette.Rnw:880-883
+###################################################
+par(mfrow=c(3,4))
+QQP(IsoMultiOut)
+
+
+
+###################################################
+### code chunk number 50: EBSeq_Vignette.Rnw:893-895
+###################################################
+par(mfrow=c(3,4))
+DenNHist(IsoMultiOut)
+
+
+###################################################
+### code chunk number 51: EBSeq_Vignette.Rnw:927-936
+###################################################
+data(GeneMat)
+GeneMat.norep=GeneMat[,c(1,6)]
+Sizes.norep=MedianNorm(GeneMat.norep)
+EBOut.norep=EBTest(Data=GeneMat.norep,
+Conditions=as.factor(rep(c("C1","C2"))),
+sizeFactors=Sizes.norep, maxround=5)
+PP.norep=GetPPMat(EBOut.norep)
+DEfound.norep=rownames(PP.norep)[which(PP.norep[,"PPDE"]>=.95)]
+GeneFC.norep=PostFC(EBOut.norep)
+
+
+###################################################
+### code chunk number 52: EBSeq_Vignette.Rnw:946-960
+###################################################
+data(IsoList)
+IsoMat=IsoList$IsoMat
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoMat.norep=IsoMat[,c(1,6)]
+IsoSizes.norep=MedianNorm(IsoMat.norep)
+IsoEBOut.norep=EBTest(Data=IsoMat.norep, NgVector=IsoNgTrun,
+Conditions=as.factor(c("C1","C2")),
+sizeFactors=IsoSizes.norep, maxround=5)
+IsoPP.norep=GetPPMat(IsoEBOut.norep)
+IsoDE.norep=rownames(IsoPP.norep)[which(IsoPP.norep[,"PPDE"]>=.95)]
+IsoFC.norep=PostFC(IsoEBOut.norep)
+
+
+###################################################
+### code chunk number 53: EBSeq_Vignette.Rnw:969-981
+###################################################
+data(MultiGeneMat)
+MultiGeneMat.norep=MultiGeneMat[,c(1,3,5)]
+Conditions=c("C1","C2","C3")
+PosParti=GetPatterns(Conditions)
+Parti=PosParti[-3,]
+MultiSize.norep=MedianNorm(MultiGeneMat.norep)
+MultiOut.norep=EBMultiTest(MultiGeneMat.norep,
+NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize.norep,
+maxround=5)
+MultiPP.norep=GetMultiPP(MultiOut.norep)
+MultiFC.norep=GetMultiFC(MultiOut.norep)
+
+
+###################################################
+### code chunk number 54: EBSeq_Vignette.Rnw:993-1012
+###################################################
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiMat.norep=IsoMultiMat[,c(1,3,5,7)]
+IsoMultiSize.norep=MedianNorm(IsoMultiMat.norep)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C2","C3","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+IsoMultiOut.norep=EBMultiTest(IsoMultiMat.norep,
+NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond, sizeFactors=IsoMultiSize.norep,
+maxround=5)
+IsoMultiPP.norep=GetMultiPP(IsoMultiOut.norep)
+IsoMultiFC.norep=GetMultiFC(IsoMultiOut.norep)
+
+
diff --git a/inst/doc/EBSeq_Vignette.Rnw b/inst/doc/EBSeq_Vignette.Rnw
new file mode 100644
index 0000000..b384e0c
--- /dev/null
+++ b/inst/doc/EBSeq_Vignette.Rnw
@@ -0,0 +1,1054 @@
+%\VignetteIndexEntry{EBSeq}
+
+\documentclass{article}
+\usepackage{fullpage}
+\usepackage{graphicx, graphics, epsfig,setspace,amsmath, amsthm}
+\usepackage{hyperref}
+\usepackage{natbib}
+%\usepackage{listings}
+\usepackage{moreverb}
+\begin{document}
+\title{EBSeq: An R package for differential expression analysis using RNA-seq data}
+\author{Ning Leng, John Dawson, and Christina Kendziorski}
+\maketitle
+\tableofcontents
+\setcounter{tocdepth}{2}
+
+\section{Introduction}
+EBSeq may be used to identify differentially expressed (DE)
+genes and isoforms in an RNA-Seq experiment. As detailed in
+Leng {\it et al.}, 2013 \cite{Leng13},
+EBSeq is an empirical Bayesian approach that models a number of features
+observed in RNA-seq data. Importantly, for isoform level inference,
+EBSeq directly accommodates isoform expression estimation uncertainty by
+modeling the differential variability observed in distinct groups of isoforms.
+Consider Figure 1, where we have plotted variance against mean
+for all isoforms using RNA-Seq expression data from Leng {\it et al.}, 2013 \cite{Leng13}.
+Also shown is the fit within three sub-groups of isoforms defined
+by the number of constituent isoforms of the parent gene.
+An isoform of gene $g$ is assigned to the $I_g=k$ group, where $k=1,2,3$,
+if the total number of isoforms from gene $g$ is $k$ (the $I_g=3$ group contains
+all isoforms from genes having 3 or more isoforms).
+As shown in Figure 1, there is decreased variability in the $I_g=1$ group,
+but increased variability in the others, due to the relative increase in
+uncertainty inherent in estimating isoform expression when multiple isoforms of a given gene are
+present. If this structure is not accommodated, there is reduced power for
+identifying isoforms in the $I_g=1$ group (since the true variances in that group are
+lower, on average, than that derived from the full collection of isoforms) as well as increased
+false discoveries in the $I_g=2$ and $I_g=3$ groups (since the true variances are higher, on average,
+than those derived from the full collection). EBSeq directly models differential variability
+as a function of $I_g$ providing a powerful approach for isoform level inference. As shown in Leng {\it et al.}, 2013
+\cite{Leng13}, the model is also useful for identifying DE genes.
+We will briefly detail the model in Section \ref{sec:model} and then describe
+the flow of analysis in Section \ref{sec:quickstart} for both isoform and gene-level inference.
+
+\begin{figure}[t]
+\centering
+\includegraphics[width=0.6\textwidth]{PlotExample.png}
+\label{fig:GouldNg}
+\caption{Empirical variance vs. mean for
+each isoform profiled in the ESCs vs iPSCs experiment detailed in
+the Case Study section of Leng {\it et al.}, 2013 \cite{Leng13}.
+A spline fit to all isoforms is shown in red with splines fit within the $I_g=1$, $I_g=2$, and $I_g=3$ isoform groups
+shown in yellow, pink, and green, respectively.}
+\end{figure}
+
+
+\section{Citing this software}
+\label{sec:cite}
+Please cite the following article when reporting results from the software.
+
+\noindent Leng, N., J.A. Dawson, J.A. Thomson, V. Ruotti, A.I. Rissman,
+B.M.G. Smits, J.D. Haag, M.N. Gould, R.M. Stewart, and C. Kendziorski.
+EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq
+experiments, {\it Bioinformatics}, 2013.
+
+\section{The Model}
+\label{sec:model}
+\subsection{Two conditions}
+\label{sec:twocondmodel}
+We let $X_{g_i}^{C1} = X_{g_i,1} ,X_{g_i,2}, ...,X_{g_i,S_1}$ denote data from condition 1
+and $ X_{g_i}^{C2} = X_{g_i,(S_1+1)},X_{g_i,(S_1+2)},...,X_{g_i,S}$ data from condition 2.
+We assume that counts within condition $C$ are distributed as Negative Binomial:
+$X_{g_i,s}^C|r_{g_i,s}, q_{g_i}^C \sim NB(r_{g_i,s}, q_{g_i}^C)$ where
+\begin{equation}
+P(X_{g_i,s}|r_{g_i,s},q_{g_i}^C) = {X_{g_i,s}+r_{g_i,s}-1\choose X_{g_i,s}}(1-q_{g_i}^C)^{X_{g_i,s}}(q_{g_i}^C)^{r_{g_i,s}}\label{eq:01}
+\end{equation}
+
+\noindent and $\mu_{g_i,s}^C=r_{g_i,s} (1-q_{g_i}^C)/q_{g_i}^C$;
+$(\sigma_{g_i,s}^C)^2=r_{g_i,s} (1-q_{g_i}^C)/(q_{g_i}^C)^2.$
+
+\medskip
+
+We assume a prior distribution on $q_{g_i}^C$: $q_{g_i}^C|\alpha, \beta^{I_g} \sim Beta(\alpha, \beta^{I_g})$.
+The hyperparameter $\alpha$ is shared by all the isoforms and $\beta^{I_g}$ is $I_g$ specific (note this is an index, not a power).
+We further assume that $r_{g_i,s}=r_{g_i,0} l_s$, where $r_{g_i,0}$ is an isoform specific
+parameter common across conditions and $r_{g_i,s}$ depends on it through the sample-specific normalization factor $l_s$.
+Of interest in this two group comparison is distinguishing between two cases, or what we will refer to subsequently as
+two patterns of expression, namely equivalent expression (EE) and differential expression (DE):
+\begin{center}
+$H_0$ (EE) : $q_{g_i}^{C1}=q_{g_i}^{C2}$ vs $H_1$ (DE) : $q_{g_i}^{C1} \neq q_{g_i}^{C2}$.
+\end{center}
+Under the null hypothesis (EE), the data $X_{g_i}^{C1,C2} = X_{g_i}^{C1}, X_{g_i}^{C2}$ arises
+from the prior predictive distribution $f_0^{I_g}(X_{g_i}^{C1,C2})$:
+%\tiny
+\begin{equation}
+f_0^{I_g}(X_{g_i}^{C1,C2})=\Bigg[\prod_{s=1}^S {X_{g_i,s}+r_{g_i,s}-1\choose X_{g_i,s}}\Bigg]
+\frac{Beta(\alpha+\sum_{s=1}^S r_{g_i,s}, \beta^{I_g}+\sum_{s=1}^SX_{g_i,s} )}{Beta(\alpha, \beta^{I_g})}\label{eq:05}
+\end{equation}
+%\normalsize
+
+Alternatively (in a DE scenario), $X_{g_i}^{C1,C2}$ follows the prior predictive distribution $f_1^{I_g}(X_{g_i}^{C1,C2})$:
+\begin{equation}
+f_1^{I_g}(X_{g_i}^{C1,C2})=f_0^{I_g}(X_{g_i}^{C1})f_0^{I_g}(X_{g_i}^{C2}) \label{eq:06}
+\end{equation}
+
+Let the latent variable $Z_{g_i}$ be defined so that $Z_{g_i} = 1$ indicates that
+isoform $g_i$ is DE and $Z_{g_i} = 0$ indicates isoform $g_i$ is EE, and
+$Z_{g_i} \sim Bernoulli(p)$.
+Then, the marginal distribution of $X_{g_i}^{C1,C2}$ and $Z_{g_i}$ is:
+\begin{equation}
+(1-p)f_0^{I_g}(X_{g_i}^{C1,C2}) + pf_1^{I_g}(X_{g_i}^{C1,C2})\label{eq:07}
+\end{equation}
+
+\noindent The posterior probability of being DE at isoform $g_i$ is obtained by Bayes' rule:
+\begin{equation}
+\frac{pf_1^{I_g}(X_{g_i}^{C1,C2})}{(1-p)f_0^{I_g}(X_{g_i}^{C1,C2}) + pf_1^{I_g}(X_{g_i}^{C1,C2})}\label{eq:08}
+\end{equation}
+
+%\newpage
+\subsection{More than two conditions}
+\label{sec:multicondmodel}
+EBSeq naturally accommodates multiple condition comparisons.
+For example, in a study with 3 conditions, there are K=5 possible expression patterns (P1,...,P5), or ways in which
+latent levels of expression may vary across conditions:
+\begin{align}
+\textrm {P1:}& \hspace{0.05in} q_{g_i}^{C1} = q_{g_i}^{C2}=q_{g_i}^{C3} \nonumber \\
+\textrm {P2:}& \hspace{0.05in} q_{g_i}^{C1} = q_{g_i}^{C2} \neq q_{g_i}^{C3} \nonumber \\
+\textrm {P3:}& \hspace{0.05in} q_{g_i}^{C1} = q_{g_i}^{C3} \neq q_{g_i}^{C2} \nonumber \\
+\textrm {P4:}& \hspace{0.05in} q_{g_i}^{C1} \neq q_{g_i}^{C2} = q_{g_i}^{C3} \nonumber \\
+\textrm {P5:}& \hspace{0.05in} q_{g_i}^{C1} \neq q_{g_i}^{C2} \neq
+q_{g_i}^{C3} \textrm{ and } q_{g_i}^{C1} \neq q_{g_i}^{C3} \nonumber
+\end{align}
+
+\noindent The prior predictive distributions for these are given, respectively, by:
+
+\begin{align}
+g_1^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1,C2,C3}) \nonumber \\
+g_2^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1,C2})f_0^{I_g}(X_{g_i}^{C3}) \nonumber \\
+g_3^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1,C3})f_0^{I_g}(X_{g_i}^{C2}) \nonumber \\
+g_4^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1})f_0^{I_g}(X_{g_i}^{C2,C3}) \nonumber \\
+g_5^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1})f_0^{I_g}(X_{g_i}^{C2})f_0^{I_g}(X_{g_i}^{C3}) \nonumber
+\end{align}
+
+\noindent where $f_0^{I_g}$ is the same as in equation \ref{eq:05}. Then the marginal distribution in
+equation \ref{eq:07} becomes:
+
+\begin{equation}
+\sum_{k=1}^5 p_k g_k^{I_g}(X_{g_i}^{C1,C2,C3}) \label{eq:11}
+\end{equation}
+\noindent where $\sum_{k=1}^5 p_k = 1$. Thus, the posterior probability of
+isoform $g_i$ coming from pattern $K$ is readily obtained by:
+
+\begin{equation}
+\frac{p_K g_K^{I_g}(X_{g_i}^{C1,C2,C3})}{\sum_{k=1}^5 p_k g_k^{I_g}(X_{g_i}^{C1,C2,C3})} \label{eq:12}
+\end{equation}
+
+\subsection{Getting a false discovery rate (FDR) controlled list of genes or isoforms}
+\label{sec:fdrlist}
+To obtain a list of DE genes with false discovery rate (FDR) controlled
+at $\alpha$ in an experiment comparing two biological conditions, the genes
+with posterior probability of being DE (PPDE) greater than 1 - $\alpha$ should be used.
+For example, the genes with PPDE>=0.95 make up the list of DE genes with target
+FDR controlled at 5\%. With more than two biological conditions, there are multiple
+DE patterns (see Section \ref{sec:multicondmodel}). To obtain a list of genes in a specific DE pattern with target
+FDR $\alpha$, a user should
+take the genes with posterior probability of being in that pattern greater
+than 1 - $\alpha$. Isoform-based lists are obtained in the same way.
+\newpage
+\section{Quick Start}
+\label{sec:quickstart}
+Before analysis can proceed, the EBSeq package must be loaded into the working space:
+<<>>=
+library(EBSeq)
+@
+\subsection{Gene level DE analysis (two conditions)}
+\label{sec:startgenede}
+\subsubsection{Required input}
+\label{sec:startgenedeinput}
+\begin{flushleft}
+{\bf Data}: The object \verb+Data+ should be a $G-by-S$ matrix containing the expression values for each gene and each sample,
+where $G$ is the number of genes and $S$ is the number of samples. These
+values should exhibit raw counts, without normalization
+across samples. Counts of this nature may be obtained from RSEM \cite{Li11b},
+Cufflinks \cite{Trapnell12}, or a similar approach.
+
+\vspace{5 mm}
+
+{\bf Conditions}: The object \verb+Conditions+ should be a Factor vector of length $S$ that indicates to which condition each sample belongs.
+For example, if there are two conditions and three samples in each,
+$S=6$ and \verb+Conditions+ may be given by
+
+\verb+as.factor(c("C1","C1","C1","C2","C2","C2"))+
+
+\end{flushleft}
+\noindent The object \verb+GeneMat+ is a simulated data matrix containing
+1,000 rows of genes and 10 columns of samples. The genes are named
+\verb+Gene_1, Gene_2 ...+
+<<>>=
+data(GeneMat)
+str(GeneMat)
+@
+
+\subsubsection{Library size factor}
+\label{sec:startgenedesize}
+As detailed in Section \ref{sec:model}, EBSeq requires the library size factor $l_s$ for each sample $s$.
+Here, $l_s$ may be obtained via the function \verb+MedianNorm+, which reproduces the median normalization approach
+in DESeq \citep{Anders10}.
+<<>>=
+Sizes=MedianNorm(GeneMat)
+@
+
+\noindent If quantile normalization is preferred, $l_s$ may be obtained via the function \verb+QuantileNorm+.
+(e.g. \verb+QuantileNorm(GeneMat,.75)+ for Upper-Quantile Normalization in \cite{Bullard10})
+
+\subsubsection{Running EBSeq on gene expression estimates}
+\label{sec:startgenederun}
+The function \verb+EBTest+ is used to detect DE genes.
+For gene-level data, we don't need to specify the parameter
+\verb+NgVector+ since there are no differences in $I_g$ structure among the different genes.
+Here, we simulated the first five samples to be in condition 1 and the other five in condition 2, so define:
+
+\verb+Conditions=as.factor(rep(c("C1","C2"),each=5))+
+
+\noindent \verb+sizeFactors+ is used to define the library size factor of each sample.
+It could be obtained by summing up the total number of reads within each sample,
+Median Normalization \citep{Anders10},
+scaling normalization \citep{Robinson10}, Upper-Quantile Normalization \cite{Bullard10},
+or some other such approach.
+These in hand, we run the EM algorithm, setting the number
+of iterations to five via \verb+maxround=5+ for demonstration purposes.
+However, we note that in practice,
+additional iterations are usually required. Convergence should always be
+checked (see Section \ref{sec:detailedgenedeconverge} for details).
+Please note this may take several minutes:
+<<>>=
+EBOut=EBTest(Data=GeneMat,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+@
+\noindent The posterior probabilities of being DE are obtained as follows, where \verb+PP+ is a matrix containing the posterior probabilities of
+being EE or DE for each of the 1,000 simulated genes:
+<<>>=
+PP=GetPPMat(EBOut)
+str(PP)
+head(PP)
+@
+\noindent The matrix \verb+PP+ contains two columns \verb+PPEE+ and \verb+PPDE+,
+corresponding to the posterior probabilities of being EE or DE for each gene.
+\verb+PP+ may be used to form an FDR-controlled list of DE genes with a target FDR of 0.05 as follows:
+<<>>=
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+@
+\noindent EBSeq found 98 DE genes in total with target FDR 0.05.
+
+\subsection{Isoform level DE analysis (two conditions)}
+\label{sec:startisode}
+\subsubsection{Required inputs}
+\label{sec:startisodeinput}
+
+\begin{flushleft}
+{\bf Data}: The object \verb+Data+ should be a $I-by-S$ matrix containing the expression values for each isoform and each sample,
+where $I$ is the number of isoforms and $S$ is the number of sample. As in the gene-level analysis, these values should exhibit raw data, without normalization
+across samples.
+
+\vspace{5 mm}
+
+{\bf Conditions}: The object \verb+Conditions+ should be a vector with length $S$ to indicate the condition of each sample.
+
+\vspace{5 mm}
+
+{\bf IsoformNames}: The object \verb+IsoformNames+ should be a vector with length $I$ to indicate the isoform names.
+
+\vspace{5 mm}
+
+{\bf IsosGeneNames}: The object \verb+IsosGeneNames+ should be a vector with length $I$ to indicate the gene name of each isoform.
+(in the same order as \verb+IsoformNames+.)
+\end{flushleft}
+
+\noindent \verb+IsoList+ contains 1,200 simulated isoforms.
+In which \verb+IsoList$IsoMat+ is a data matrix containing
+1,200 rows of isoforms and 10 columns of samples;
+\verb+IsoList$IsoNames+ contains the isoform names;
+\verb+IsoList$IsosGeneNames+ contains the names of the genes the isoforms belong to.
+
+<<>>=
+data(IsoList)
+str(IsoList)
+IsoMat=IsoList$IsoMat
+str(IsoMat)
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+@
+
+\subsubsection{Library size factor}
+\label{sec:startisodesize}
+Similar to the gene-level analysis presented above, we may obtain the isoform-level
+library size factors via \verb+MedianNorm+:
+<<>>=
+IsoSizes=MedianNorm(IsoMat)
+@
+
+\subsubsection{The $I_g$ vector}
+\label{sec:startisodeNg}
+
+While working on isoform level data, EBSeq fits different prior
+parameters for different uncertainty groups (defined as $I_g$ groups).
+The default setting to define the uncertainty groups consists of using
+the number of isoforms the host gene contains ($N_g$) for each isoform.
+The default settings will provide three uncertainty groups:
+
+$I_g=1$ group: Isoforms with $N_g=1$;
+
+$I_g=2$ group: Isoforms with $N_g=2$;
+
+$I_g=3$ group: Isoforms with $N_g \geq 3$.
+
+The $N_g$ and $I_g$ group assignment can be obtained using the function \verb+GetNg+.
+The required inputs of \verb+GetNg+ are the isoform names (\verb+IsoformNames+) and
+their corresponding gene names (\verb+IsosGeneNames+).
+<<>>=
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+@
+More details could be found in Section \ref{sec:detailedisode}.
+
+\subsubsection{Running EBSeq on isoform expression estimates}
+\label{sec:startisoderun}
+The \verb+EBTest+ function is also used to run EBSeq for two condition comparisons
+on isoform-level data.
+Below we use 5 iterations to demonstrate. However, as
+in the gene level analysis, we advise that additional iterations will likely be
+required in practice (see Section \ref{sec:detailedisodeconverge} for details).
+
+<<>>=
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+str(IsoPP)
+head(IsoPP)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+str(IsoDE)
+@
+\noindent We see that EBSeq found 105 DE isoforms at the target FDR of 0.05.
+
+\subsection{Gene level DE analysis (more than two conditions)}
+\label{sec:startmulticond}
+\noindent The object \verb+MultiGeneMat+ is a matrix containing
+500 simulated genes with 6 samples:
+the first two samples are from condition 1; the second and the third sample are
+from condition 2; the last two samples are from condition 3.
+
+<<>>=
+data(MultiGeneMat)
+str(MultiGeneMat)
+@
+In analysis where the data are spread over more than two conditions,
+the set of possible patterns for each gene is more complicated
+than simply EE and DE. As noted in Section \ref{sec:model}, when we have 3 conditions, there are 5 expression
+patterns to consider. In the simulated data, we have 6 samples, 2 in each of 3 conditions.
+The function \verb+GetPatterns+ allows the user to generate all possible patterns given the conditions. For example:
+
+<<>>=
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+@
+
+\noindent where the first row means all three conditions have the same latent mean expression level;
+the second row means C1 and C2 have the same latent mean expression level but that of C3 is different;
+and the last row corresponds to the case where the three conditions all have different latent mean expression levels.
+The user may use all or only some of these possible patterns as an input to \verb+EBMultiTest+.
+For example, if we were interested in Patterns 1, 2, 4 and 5 only, we'd define:
+<<>>=
+Parti=PosParti[-3,]
+Parti
+@
+
+Moving on to the analysis, \verb+MedianNorm+ or one of its competitors should be used to determine the normalization factors.
+Once this is done, the formal test is performed by \verb+EBMultiTest+.
+<<>>=
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize, maxround=5)
+@
+\noindent The posterior probability of being in each pattern for every gene is obtained by using the
+function \verb+GetMultiPP+:
+<<>>=
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+@
+\noindent where \verb+MultiPP$PP+ provides the posterior probability of being in each pattern for every gene.
+\verb+MultiPP$MAP+ provides the most likely pattern of each gene based on the posterior
+probabilities. \verb+MultiPP$Patterns+ provides the details of the patterns.
+
+
+
+\subsection{Isoform level DE analysis (more than two conditions)}
+\label{sec:startisomulticond}
+\noindent Similar to \verb+IsoList+,
+the object \verb+IsoMultiList+ is an object containing the isoform expression estimates matrix, the isoform
+names, and the gene names of the isoforms' host genes.
+\verb+IsoMultiList$IsoMultiMat+ contains 300 simulated isoforms with 8 samples.
+The first two samples are from condition 1; the second and the third sample are
+from condition 2; the fifth and sixth sample are from condition 3;
+the last two samples are from condition 4.
+Similar to Section \ref{sec:startisode}, the function \verb+MedianNorm+ and \verb+GetNg+ could be used for normalization
+and calculating the $N_g$'s.
+<<>>=
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+@
+Here we have 4 conditions, there are 15 expression
+patterns to consider.
+The function \verb+GetPatterns+ allows the user to generate all possible patterns given the conditions. For example:
+
+<<>>=
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+@
+
+\noindent
+If we were interested in Patterns 1, 2, 3, 8 and 15 only, we'd define:
+<<>>=
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+@
+
+\noindent
+Moving on to the analysis, \verb+EBMultiTest+ could be used to perform the test:
+<<>>=
+IsoMultiOut=EBMultiTest(IsoMultiMat,
+NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond, sizeFactors=IsoMultiSize,
+maxround=5)
+@
+\noindent The posterior probability of being in each pattern for every gene is obtained by using the
+function \verb+GetMultiPP+:
+<<>>=
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+@
+\noindent where \verb+MultiPP$PP+ provides the posterior probability of being in each pattern for every gene.
+\verb+MultiPP$MAP+ provides the most likely pattern of each gene based on the posterior
+probabilities. \verb+MultiPP$Patterns+ provides the details of the patterns.
+
+
+
+\newpage
+\section{More detailed examples}
+\label{sec:detailed}
+\subsection{Gene level DE analysis (two conditions)}
+\label{sec:detailedgenede}
+
+\subsubsection{Running EBSeq on simulated gene expression estimates}
+\label{sec:detailedgenederun}
+EBSeq is applied as described in Section \ref{sec:startgenederun}.
+<<eval=FALSE>>=
+data(GeneMat)
+Sizes=MedianNorm(GeneMat)
+EBOut=EBTest(Data=GeneMat,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+PP=GetPPMat(EBOut)
+@
+<<>>=
+str(PP)
+head(PP)
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+@
+\noindent EBSeq found 98 DE genes at a target FDR of 0.05.\\
+
+\subsubsection{Calculating FC}
+\label{sec:detailedgenedefc}
+The function \verb+PostFC+ may be used to calculate the Fold Change (FC)
+of the raw data as well as the posterior FC of the normalized data.
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+GeneFC=PostFC(EBOut)
+str(GeneFC)
+PlotPostVsRawFC(EBOut,GeneFC)
+@
+\caption{
+FC vs. Posterior FC for 1,000 gene expression estimates}
+\label{fig:GeneFC}
+\end{figure}
+Figure \ref{fig:GeneFC} shows the FC vs. Posterior FC on 1,000 gene expression estimates.
+The genes are ranked by their cross-condition mean (adjusted by the normalization factors).
+The posterior FC tends to shrink genes with low expressions (small rank); in this case the differences
+are minor.
+
+
+\newpage
+
+\subsubsection{Checking convergence}
+\label{sec:detailedgenedeconverge}
+As detailed in Section \ref{sec:model}, we assume the prior distribution of $q_g^C$ is
+$Beta(\alpha,\beta)$. The EM algorithm is used to estimate the
+hyper-parameters $\alpha,\beta$ and the mixture parameter $p$.
+The optimized parameters at each iteration may be obtained as follows (recall
+we are using 5 iterations for demonstration purposes):
+<<>>=
+EBOut$Alpha
+EBOut$Beta
+EBOut$P
+@
+In this case the differences between the 4th and 5th iterations are always less
+than 0.01.
+
+
+\subsubsection{Checking the model fit and other diagnostics}
+\label{sec:detailedgenedeplot}
+As noted in Leng {\it et al.}, 2013 \cite{Leng13}, EBSeq relies on parametric assumptions that should
+be checked following each analysis.
+The \verb+QQP+ function may be used to assess prior assumptions.
+In practice, \verb+QQP+ generates the Q-Q plot of the empirical $q$'s
+vs. the simulated $q$'s from the Beta prior distribution with
+estimated hyper-parameters. Figure \ref{fig:GeneQQ} shows that the
+data points lie on the $y=x$ line for both conditions, which indicates
+that the Beta prior is appropriate.
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(1,2))
+QQP(EBOut)
+@
+\caption{QQ-plots for checking the assumption of a Beta prior (upper panels) as well as the
+model fit using data from condition 1 and condition 2 (lower panels)}
+\label{fig:GeneQQ}
+\end{figure}
+
+\newpage
+\noindent
+Likewise, the \verb+DenNHist+ function may be used to check the density plot of empirical $q$'s vs the simulated
+$q$'s from the fitted Beta prior distribution.
+Figure \ref{fig:GeneDenNHist} also shows our estimated distribution fits the
+data very well.
+
+\begin{figure}[h!]
+\centering
+<<fig=T>>=
+par(mfrow=c(1,2))
+DenNHist(EBOut)
+@
+\caption{Density plots for checking the model fit using data from condition 1 and condition 2}
+\label{fig:GeneDenNHist}
+\end{figure}
+
+\newpage
+\subsection{Isoform level DE analysis (two conditions)}
+\label{sec:detailedisode}
+\subsubsection{The $I_g$ vector}
+\label{sec:detailedisodeNg}
+Since EBSeq fits rely on $I_g$,
+we need to obtain the $I_g$ for each isoform. This can be done using the
+function \verb+GetNg+.
+The required inputs of \verb+GetNg+ are the isoform names (\verb+IsoformNames+) and
+their corresponding gene names (\verb+IsosGeneNames+), described above.
+In the simulated data, we assume that the isoforms in the $I_g=1$ group belong to genes \verb+Gene_1, ... , Gene_200+;
+The isoforms in the $I_g=2$ group belong to genes
+\verb+Gene_201, ..., Gene_400+; and isoforms in the $I_g=3$ group
+belong to \verb+Gene_401, ..., Gene_600+.
+
+<<eval=FALSE>>=
+data(IsoList)
+IsoMat=IsoList$IsoMat
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+NgList=GetNg(IsoNames, IsosGeneNames, TrunThre=3)
+@
+<<>>=
+names(NgList)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+@
+
+The output of \verb+GetNg+ contains 4 vectors. \verb+GeneNg+ (\verb+IsoformNg+) provides
+the number of isoforms $N_g$ within each gene (within each isoform's host gene).
+\verb+GeneNgTrun+ (\verb+IsoformNgTrun+) provides the $I_g$ group assignments.
+The default number of groups is 3, which means the isoforms
+with $N_g$ greater than 3 will be assigned to $I_g=3$ group.
+We use 3 in the case studies
+since the number of isoforms with $N_g$ larger than 3 is relatively small and
+the small sample size may induce poor parameter fitting if we treat them
+as separate groups.
+In practice, if there is evidence that the $N_g=4,5,6...$ groups should be
+treated as separate groups, a user can change \verb+TrunThre+ to define
+a different truncation threshold.
+
+\subsubsection{Using mappability ambiguity clusters instead of
+the $I_g$ vector when the gene-isoform relationship is unknown}
+\label{sec:detailedisodeNoNg}
+When working with a de-novo assembled transcriptome, in which case the gene-isoform
+relationship is unknown,
+a user can use read mapping ambiguity cluster information instead of Ng,
+as provided by RSEM \cite{Li11b} in the
+output file \verb+output_name.ngvec+. The file contains a vector with the same
+length as the total number of transcripts.
+Each transcript has been assigned to one of 3 levels
+(1, 2, or 3) to indicate the mapping uncertainty level of that transcript.
+The mapping ambiguity clusters are partitioned via a k-means algorithm on the unmapability
+scores that are provided by RSEM. A user can read in the mapping ambiguity cluster information
+using:
+
+<<eval=FALSE>>=
+IsoNgTrun = scan(file="output_name.ngvec", what=0, sep="\n")
+@\\
+Where \verb+"output_name.ngvec"+ is the output file obtained from RSEM function rsem-generate-ngvector.
+More details on using the RSEM-EBSeq pipeline
+on de novo assembled transcriptomes can be found
+at \url{http://deweylab.biostat.wisc.edu/rsem/README.html#de}.
+
+Other unmappability scores and other cluster methods (e.g. Gaussian Mixed Model)
+could also be used to form the uncertainty clusters.
+
+\subsubsection{Running EBSeq on simulated isoform expression estimates}
+\label{sec:detailedisoderun}
+EBSeq can be applied as described in Section \ref{sec:startisoderun}.
+<<eval=FALSE>>=
+IsoSizes=MedianNorm(IsoMat)
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+@
+<<>>=
+str(IsoDE)
+@
+\noindent We see that EBSeq found 105 DE isoforms at a target FDR of 0.05.
+The function \verb+PostFC+ could also be used here to calculate the Fold Change (FC)
+as well as the posterior FC on the normalization factor adjusted data.
+<<>>=
+IsoFC=PostFC(IsoEBOut)
+str(IsoFC)
+@
+
+
+\subsubsection{Checking convergence}
+\label{sec:detailedisodeconverge}
+For isoform level data, we assume the prior distribution of $q_{gi}^C$ is
+$Beta(\alpha,\beta^{I_g})$.
+As in Section \ref{sec:detailedgenedeconverge}, the optimized parameters at each iteration
+may be obtained as follows (recall
+we are using 5 iterations for demonstration purposes):
+<<>>=
+IsoEBOut$Alpha
+IsoEBOut$Beta
+IsoEBOut$P
+@
+Here we have 3 $\beta$'s in each iteration corresponding to
+$\beta^{I_g=1},\beta^{I_g=2},\beta^{I_g=3}$.
+We see that parameters are changing less than $10^{-2}$ or $10^{-3}$.
+In practice, we require changes less than $10^{-3}$ to declare convergence.
+
+\subsubsection{Checking the model fit and other diagnostics}
+\label{sec:detailedisodeplot}
+In Leng {\it et al.}, 2013\citep{Leng13}, we showed the mean-variance differences across different
+isoform groups on multiple data sets.
+In practice, if it is of interest to check differences among
+isoform groups defined by truncated $I_g$ (such as those shown here
+in Figure 1), the function \verb+PolyFitPlot+ may be used.
+The following code generates the three
+panels shown in Figure \ref{fig:IsoSimuNgEach}
+(if condition 2 is of interest, a user could change each \verb+C1+ to \verb+C2+.):
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,2))
+PolyFitValue=vector("list",3)
+for(i in 1:3)
+ PolyFitValue[[i]]=PolyFitPlot(IsoEBOut$C1Mean[[i]],
+ IsoEBOut$C1EstVar[[i]],5)
+@
+\caption{ The mean-variance fitting plot for each Ng group}
+\label{fig:IsoSimuNgEach}
+\end{figure}
+
+\newpage
+Superimposing all $I_g$ groups using the code below will generate the figure (shown
+here in Figure \ref{fig:IsoSimuNg}), which is similar in structure to Figure 1:
+
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+PolyAll=PolyFitPlot(unlist(IsoEBOut$C1Mean), unlist(IsoEBOut$C1EstVar),5)
+lines(log10(IsoEBOut$C1Mean[[1]][PolyFitValue[[1]]$sort]),
+PolyFitValue[[1]]$fit[PolyFitValue[[1]]$sort],col="yellow",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[2]][PolyFitValue[[2]]$sort]),
+PolyFitValue[[2]]$fit[PolyFitValue[[2]]$sort],col="pink",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[3]][PolyFitValue[[3]]$sort]),
+PolyFitValue[[3]]$fit[PolyFitValue[[3]]$sort],col="green",lwd=2)
+legend("topleft",c("All Isoforms","Ng = 1","Ng = 2","Ng = 3"),
+col=c("red","yellow","pink","green"),lty=1,lwd=3,box.lwd=2)
+@
+\caption{The mean-variance plot for each Ng group}
+\label{fig:IsoSimuNg}
+\end{figure}
+
+
+\newpage
+\noindent To generate a QQ-plot of the fitted Beta prior distribution
+and the $\hat{q}^C$'s within condition, a user may
+use the following code to generate 6 panels (as shown in Figure \ref{fig:IsoQQ}).
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,3))
+QQP(IsoEBOut)
+@
+\caption{ QQ-plots of the fitted prior distributions within each condition and each Ig group}
+\label{fig:IsoQQ}
+\end{figure}
+
+\newpage
+\noindent And in order to produce the plot of the fitted Beta prior densities
+and the histograms of $\hat{q}^C$'s within each condition,
+the following may be used (it generates Figure \ref{fig:IsoDenNHist}):
+\begin{figure}[h]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,3))
+DenNHist(IsoEBOut)
+@
+\caption{ Prior distribution fit within each condition and each Ig group.
+(Note only a small set of isoforms are considered here for demonstration.
+Better fitting should be expected while using full set of isoforms.)}
+\label{fig:IsoDenNHist}
+\end{figure}
+
+\clearpage
+\subsection{Gene level DE analysis (more than two conditions)}
+\label{sec:detailedmulticond}
+As described in Section \ref{sec:startmulticond},
+the function \verb+GetPatterns+ allows the user to generate all possible patterns given the conditions.
+To visualize the patterns, the function \verb+PlotPattern+ may be used.
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+PlotPattern(PosParti)
+@
+\caption{ All possible patterns}
+\label{fig:Patterns}
+\end{figure}
+\newpage
+\noindent If we were interested in Patterns 1, 2, 4 and 5 only, we'd define:
+<<>>=
+Parti=PosParti[-3,]
+Parti
+@
+
+\noindent
+Moving on to the analysis, \verb+MedianNorm+ or one of its competitors should be used to determine the normalization factors.
+Once this is done, the formal test is performed by \verb+EBMultiTest+.
+<<eval=FALSE>>=
+data(MultiGeneMat)
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,
+NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize,
+maxround=5)
+@
+\noindent The posterior probability of being in each pattern for every gene is obtained using the
+function \verb+GetMultiPP+:
+<<>>=
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+@
+\noindent where \verb+MultiPP$PP+ provides the posterior probability of being in each pattern for every gene.
+\verb+MultiPP$MAP+ provides the most likely pattern of each gene based on the posterior
+probabilities. \verb+MultiPP$Patterns+ provides the details of the patterns. The FC and posterior FC for multiple condition data can
+be obtained by the function \verb+GetMultiFC+:
+
+<<>>=
+MultiFC=GetMultiFC(MultiOut)
+str(MultiFC)
+@
+
+\noindent To generate a QQ-plot of the fitted Beta prior distribution
+and the $\hat{q}^C$'s within condition, a user could also use function
+\verb+DenNHist+ and \verb+QQP+.
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,2))
+QQP(MultiOut)
+@
+\caption{ QQ-plots of the fitted prior distributions within each condition and each Ig group}
+\label{fig:GeneMultiQQ}
+\end{figure}
+
+\begin{figure}[h]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,2))
+DenNHist(MultiOut)
+@
+\caption{ Prior distributions fit within each condition.
+(Note only a small set of genes are considered here for demonstration.
+Better fitting should be expected while using full set of genes.)}
+\label{fig:GeneMultiDenNHist}
+\end{figure}
+\newpage
+\clearpage
+\newpage
+\subsection{Isoform level DE analysis (more than two conditions)}
+\label{sec:detailedisomulticond}
+Similar to Section \ref{sec:startmulticond},
+the function \verb+GetPatterns+ allows a user to generate all possible patterns given the conditions.
+To visualize the patterns, the function \verb+PlotPattern+ may be used.
+<<>>=
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+@
+\newpage
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+PlotPattern(PosParti.4Cond)
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+@
+\caption{All possible patterns for 4 conditions}
+\label{fig:Patterns4Cond}
+\end{figure}
+
+\newpage
+<<eval=FALSE>>=
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+IsoMultiOut=EBMultiTest(IsoMultiMat,NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond,
+sizeFactors=IsoMultiSize, maxround=5)
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+@
+<<>>=
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+IsoMultiFC=GetMultiFC(IsoMultiOut)
+@
+The FC and posterior FC for multiple condition data can be obtained by the function \verb+GetMultiFC+:
+
+
+\noindent To generate a QQ-plot of the fitted Beta prior distribution
+and the $\hat{q}^C$'s within condition, a user could also use the functions
+\verb+DenNHist+ and \verb+QQP+.
+\newpage
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(3,4))
+QQP(IsoMultiOut)
+
+@
+\caption{ QQ-plots of the fitted prior distributions within each condition and Ig group.
+(Note only a small set of isoforms are considered here for demonstration.
+Better fitting should be expected while using full set of isoforms.)}
+\label{fig:IsoMultiQQ}
+\end{figure}
+
+\begin{figure}[h]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(3,4))
+DenNHist(IsoMultiOut)
+@
+\caption{ Prior distributions fit within each condition and Ig group.
+(Note only a small set of isoforms are considered here for demonstration.
+Better fitting should be expected while using full set of isoforms.)}
+\label{fig:IsoMultiDenNHist}
+\end{figure}
+\clearpage
+\newpage
+
+
+\newpage
+\subsection{Working without replicates}
+When replicates are not available, it is difficult to estimate the transcript specific variance.
+In this case, EBSeq estimates the variance by pooling similar genes together.
+Specifically, we take genes with FC in the 25\% - 75\% quantile of all FC's as
+candidate genes. By defining \verb+NumBin = 1000+ (default in \verb+EBTest+), EBSeq
+will group genes with similar means into 1,000 bins.
+For each candidate gene, we use the across-condition variance estimate as its variance estimate.
+For each bin, the bin-wise variance estimation is taken to be the median of the
+across-condition variance estimates of the candidate genes within that bin.
+For each non-candidate gene, we use the bin-wise variance estimate of the host bin (the bin containing this gene)
+as its variance estimate.
+This approach works well when there are no more than 50\% DE genes in the data set.
+
+\subsubsection{Gene counts with two conditions}
+\label{sec:norepgenede}
+
+To generate a data set with no replicates, we take the first sample of each condition.
+For example, using the data from Section \ref{sec:detailedgenede}, we take sample 1 from condition 1 and
+sample 6 from condition 2. Functions \verb+MedianNorm+, \verb+GetPPMat+ and
+\verb+PostFC+ may be used on data without replicates.
+<<>>=
+data(GeneMat)
+GeneMat.norep=GeneMat[,c(1,6)]
+Sizes.norep=MedianNorm(GeneMat.norep)
+EBOut.norep=EBTest(Data=GeneMat.norep,
+Conditions=as.factor(rep(c("C1","C2"))),
+sizeFactors=Sizes.norep, maxround=5)
+PP.norep=GetPPMat(EBOut.norep)
+DEfound.norep=rownames(PP.norep)[which(PP.norep[,"PPDE"]>=.95)]
+GeneFC.norep=PostFC(EBOut.norep)
+@
+
+\subsubsection{Isoform counts with two conditions}
+\label{norepisode}
+To generate an isoform level data set with no replicates, we
+also take sample 1 and sample 6 in the data we used in Section
+\ref{sec:detailedisode}.
+Example codes are shown below.
+
+<<>>=
+data(IsoList)
+IsoMat=IsoList$IsoMat
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoMat.norep=IsoMat[,c(1,6)]
+IsoSizes.norep=MedianNorm(IsoMat.norep)
+IsoEBOut.norep=EBTest(Data=IsoMat.norep, NgVector=IsoNgTrun,
+Conditions=as.factor(c("C1","C2")),
+sizeFactors=IsoSizes.norep, maxround=5)
+IsoPP.norep=GetPPMat(IsoEBOut.norep)
+IsoDE.norep=rownames(IsoPP.norep)[which(IsoPP.norep[,"PPDE"]>=.95)]
+IsoFC.norep=PostFC(IsoEBOut.norep)
+@
+
+\subsubsection{Gene counts with more than two conditions}
+\label{norepisode}
+To generate a data set with multiple conditions and no replicates,
+we take the first sample from each condition (sample 1, 3 and 5) in the data we used
+in Section \ref{sec:detailedmulticond}.
+Example codes are shown below.
+<<>>=
+data(MultiGeneMat)
+MultiGeneMat.norep=MultiGeneMat[,c(1,3,5)]
+Conditions=c("C1","C2","C3")
+PosParti=GetPatterns(Conditions)
+Parti=PosParti[-3,]
+MultiSize.norep=MedianNorm(MultiGeneMat.norep)
+MultiOut.norep=EBMultiTest(MultiGeneMat.norep,
+NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize.norep,
+maxround=5)
+MultiPP.norep=GetMultiPP(MultiOut.norep)
+MultiFC.norep=GetMultiFC(MultiOut.norep)
+@
+
+\subsubsection{Isoform counts with more than two conditions}
+\label{sec:norepmulticond}
+To generate an isoform level data set with multiple conditions and no replicates,
+we take the first sample from each condition (sample 1, 3, 5 and 7) in the data we used
+in Section \ref{sec:detailedisomulticond}.
+Example codes are shown below.
+
+
+
+<<>>=
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiMat.norep=IsoMultiMat[,c(1,3,5,7)]
+IsoMultiSize.norep=MedianNorm(IsoMultiMat.norep)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C2","C3","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+IsoMultiOut.norep=EBMultiTest(IsoMultiMat.norep,
+NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond, sizeFactors=IsoMultiSize.norep,
+maxround=5)
+IsoMultiPP.norep=GetMultiPP(IsoMultiOut.norep)
+IsoMultiFC.norep=GetMultiFC(IsoMultiOut.norep)
+@
+
+\section{EBSeq pipelines and extensions}
+\subsection{RSEM-EBSeq pipeline: from raw reads to differential expression analysis results}
+EBSeq is coupled with RSEM \cite{Li11b} as an RSEM-EBSeq pipeline which provides
+quantification and DE testing on both gene and isoform levels.
+
+For more details, see
+\url{http://deweylab.biostat.wisc.edu/rsem/README.html#de}
+
+\subsection{EBSeq interface: A user-friendly graphical interface for differetial expression analysis}
+EBSeq interface provides a graphical interface implementation for users who are not familiar with the R
+programming language. It takes .xls, .xlsx and .csv files as input.
+Additional packages need be downloaded; they may be found at
+\url{http://www.biostat.wisc.edu/~ningleng/EBSeq_Package/EBSeq_Interface/}
+
+\subsection{EBSeq Galaxy tool shed}
+EBSeq tool shed contains EBSeq wrappers for a local Galaxy implementation.
+For more details, see
+\url{http://www.biostat.wisc.edu/~ningleng/EBSeq_Package/EBSeq_Galaxy_toolshed/}
+
+\section{Acknowledgment}
+We would like to thank Haolin Xu for checking the package and
+proofreading the vignette.
+
+\section{News}
+2014-1-30: In EBSeq 1.3.3, the default setting of EBTest function will remove
+low expressed genes (genes whose 75th quantile of normalized counts is less
+than 10) before identifying DE genes.
+These two thresholds can be changed in EBTest function.
+We found that low expressed genes are more easily to be affected by noises.
+Removing these genes prior to downstream analyses can improve the
+model fitting and reduce impacts of noisy genes (e.g. genes with outliers).
+
+2014-5-22: In EBSeq 1.5.2, numerical approximations are implemented to deal with
+underflow. The underflow is likely due to large number of samples.
+\pagebreak
+\bibliographystyle{plain}
+\bibliography{lengetal}
+
+\end{document}
+
diff --git a/inst/doc/EBSeq_Vignette.pdf b/inst/doc/EBSeq_Vignette.pdf
new file mode 100644
index 0000000..106d468
Binary files /dev/null and b/inst/doc/EBSeq_Vignette.pdf differ
diff --git a/man/DenNHist.Rd b/man/DenNHist.Rd
new file mode 100644
index 0000000..62c5f45
--- /dev/null
+++ b/man/DenNHist.Rd
@@ -0,0 +1,46 @@
+\name{DenNHist}
+\alias{DenNHist}
+\title{
+Density plot to compare the empirical q's and the simulated q's from the fitted beta distribution.
+}
+\description{
+'DenNHist' gives the density plot that compares the empirical q's and the simulated q's from the fitted beta distribution.
+}
+\usage{
+DenNHist(EBOut, GeneLevel = F)
+}
+\arguments{
+ \item{EBOut}{The output of EBTest or EBMultiTest.}
+ \item{GeneLevel}{Indicate whether the results are from data at gene level.}
+}
+
+\value{
+For data with n1 conditions and n2 uncertainty groups, n1*n2
+plots will be generated. Each plot represents a subset of the data.
+The empirical estimation of q's will be represented as blue histograms
+and the density of the fitted beta distribution will be represented as
+the green line.
+}
+
+\references{
+ Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{
+beta.mom, QQP, EBTest, EBMultiTest
+}
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(500:1000),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+par(mfrow = c(2,2))
+DenNHist(EBOut)
+}
+\keyword{ beta }
diff --git a/man/EBMultiTest.Rd b/man/EBMultiTest.Rd
new file mode 100644
index 0000000..28a5c34
--- /dev/null
+++ b/man/EBMultiTest.Rd
@@ -0,0 +1,97 @@
+\name{EBMultiTest}
+\alias{EBMultiTest}
+\title{
+Using EM algorithm to calculate the posterior probabilities
+of interested patterns in a multiple condition study
+}
+\description{
+'EBMultiTest' is built based on the assumption of NB-Beta Empirical Bayes model. It utilizes the EM algorithm to give the posterior probability of the interested patterns.
+}
+\usage{
+EBMultiTest(Data, NgVector = NULL, Conditions, AllParti = NULL,
+ sizeFactors, maxround, Pool = F, NumBin = 1000,
+ ApproxVal=10^-10, PoolLower=.25, PoolUpper = .75, Print=T,Qtrm=.75,QtrmCut=10)
+}
+\arguments{
+
+ \item{Data}{A data matrix contains expression values for each transcript (gene or isoform level). In which rows should be transcripts and columns should be samples.}
+ \item{NgVector}{A vector indicates the uncertainty group assignment of each isoform.
+e.g. if we use number of isoforms in the host gene to define the uncertainty groups,
+suppose the isoform is in a gene with 2 isoforms, Ng of this isoform should be 2.
+The length of this vector should be the same as the number of rows in Data.
+If it's gene level data, Ngvector could be left as NULL.}
+ \item{Conditions}{A vector indicates the condition in which each sample belongs to. }
+
+ \item{AllParti}{A matrix indicates the interested patterns. Columns shoule be conditions and rows should be patterns. The matrix could be obtained by the GetPatterns function. If AllParti=NULL, all possible patterns will be used.}
+
+ \item{sizeFactors}{The normalization factors. It should be a vector with lane specific numbers (the length of the vector should be the same as the number of samples, with the same order as the columns of Data).}
+ \item{maxround}{Number of iterations. The default value is 5.
+Users should always check the convergency by looking at the Alpha and
+Beta in output. If the hyper-parameter estimations are not converged
+in 5 iterations, larger number is suggested.}
+
+
+\item{Pool}{While working without replicates, user could define the Pool = TRUE in the EBTest function to enable pooling.}
+\item{NumBin}{By defining NumBin = 1000, EBSeq will group the genes with similar means together into 1,000 bins.}
+\item{PoolLower, PoolUpper}{
+With the assumption that only subset of the genes are DE in the data set, we take genes whose FC are in the PoolLower - PoolUpper quantile of the FC's as the candidate genes (default is 25\%-75\%).
+
+For each bin, the bin-wise variance estimation is defined as the median of the cross condition variance estimations of the candidate genes within that bin.
+
+We use the cross condition variance estimations for the candidate genes and the bin-wise variance estimations of the host bin for the non-candidate genes.}
+
+\item{ApproxVal}{The variances of the transcripts with mean < var will be approximated as mean/(1-ApproxVal).}
+
+\item{Print}{Whether print the elapsed-time while running the test.}
+
+\item{Qtrm, QtrmCut}{
+Transcripts with Qtrm th quantile < = QtrmCut will be removed before testing. The default value is Qtrm = 0.75 and QtrmCut=10.
+By default setting, transcripts that have >75\% of the samples with expression less than 10
+won't be tested.
+}
+}
+
+
+\value{
+\item{Alpha}{Fitted parameter alpha of the prior beta distribution. Rows are the values for each iteration.}
+\item{Beta}{Fitted parameter beta of the prior beta distribution. Rows are the values for each iteration.}
+\item{P, PFromZ}{The bayes estimator of following each pattern of interest. Rows are the values for each iteration.}
+\item{Z, PoissonZ}{The Posterior Probability of following each pattern of interest for each transcript. (Maybe not in the same order of input).}
+\item{RList}{The fitted values of r for each transcript.}
+\item{MeanList}{The mean of each transcript. (across conditions).}
+\item{VarList}{The variance of each transcript. (across conditions).}
+\item{QList}{The fitted q values of each transcript within each condition.}
+\item{SPMean}{The mean of each transcript within each condition (adjusted by the normalization factors).}
+\item{SPEstVar}{The estimated variance of each transcript within each condition (adjusted by the normalization factors).}
+\item{PoolVar}{The variance of each transcript (The pooled value of within condition EstVar).}
+\item{DataList}{A List of data that grouped with Ng and bias.}
+\item{PPpattern}{The Posterior Probability of following each pattern (columns) for each transcript (rows). Transcripts with expression 0 for all samples are not shown in this matrix.}
+\item{f}{The likelihood of likelihood of prior predictive distribution of being each pattern for each transcript. }
+\item{AllParti}{The matrix describe the patterns.}
+\item{PPpatternWith0}{The Posterior Probability of following each pattern (columns) for each transcript (rows). Transcripts with expression 0 for all samples are shown in this matrix with PP(any_pattrn)=NA.}
+\item{ConditionOrder}{The condition assignment for C1Mean, C2Mean, etc.}
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\seealso{
+EBTest, GetMultiPP, GetMultiFC
+}
+\examples{
+data(MultiGeneMat)
+MultiGeneMat.small = MultiGeneMat[201:210,]
+Conditions = c("C1","C1","C2","C2","C3","C3")
+PosParti = GetPatterns(Conditions)
+Parti = PosParti[-3,]
+MultiSize = MedianNorm(MultiGeneMat.small)
+MultiOut = EBMultiTest(MultiGeneMat.small, NgVector = NULL,
+ Conditions = Conditions, AllParti = Parti,
+ sizeFactors = MultiSize, maxround = 5)
+MultiPP = GetMultiPP(MultiOut)
+}
+\keyword{ DE }
+\keyword{ Multiple Condition }% __ONLY ONE__ keyword per line
diff --git a/man/EBSeq_NingLeng-package.Rd b/man/EBSeq_NingLeng-package.Rd
new file mode 100644
index 0000000..62f2e26
--- /dev/null
+++ b/man/EBSeq_NingLeng-package.Rd
@@ -0,0 +1,40 @@
+\name{EBSeq_NingLeng-package}
+\alias{EBSeq_NingLeng-package}
+\alias{EBSeq_NingLeng}
+\docType{package}
+\title{
+EBSeq: RNA-Seq Differential Expression Analysis on both gene and isoform level
+}
+\description{
+In 'EBSeq_NingLeng-package,' a Negative Binomial-beta model was built to analyze the RNASeq data. We used the empirical bayes method and EM algrithom.
+}
+\details{
+\tabular{ll}{
+Package: \tab EBSeq_NingLeng\cr
+Type: \tab Package\cr
+Version: \tab 1.0\cr
+Date: \tab 2011-06-13\cr
+License: \tab What license is it under?\cr
+LazyLoad: \tab yes\cr
+}
+}
+\author{
+Ning Leng, Christina Kendziorski
+
+Maintainer: Ning Leng <nleng at wisc.edu>
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\keyword{ package }
+\seealso{
+EBTest, EBMultiTest
+}
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(1:10,511:550),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data=GeneMat.small,
+ Conditions=as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors=Sizes, maxround=5)
+}
diff --git a/man/EBTest.Rd b/man/EBTest.Rd
new file mode 100644
index 0000000..97e4d39
--- /dev/null
+++ b/man/EBTest.Rd
@@ -0,0 +1,103 @@
+\name{EBTest}
+\alias{EBTest}
+%- Also NEED an '\alias' for EACH other topic documented here.
+\title{
+Using EM algorithm to calculate the posterior probabilities of being DE
+}
+\description{
+Base on the assumption of NB-Beta Empirical Bayes model, the EM algorithm is used to get the posterior probability of being DE.
+}
+\usage{
+EBTest(Data, NgVector = NULL, Conditions, sizeFactors, maxround,
+ Pool = F, NumBin = 1000, ApproxVal = 10^-10, Alpha = NULL,
+ Beta = NULL, PInput = NULL, RInput = NULL,
+ PoolLower = .25, PoolUpper = .75, Print = T, Qtrm = .75,QtrmCut=10)
+}
+\arguments{
+
+ \item{Data}{A data matrix contains expression values for each transcript (gene or isoform level). In which rows should be transcripts and columns should be samples.}
+ \item{NgVector}{A vector indicates the uncertainty group assignment of each isoform.
+e.g. if we use number of isoforms in the host gene to define the uncertainty groups, suppose the isoform is in a gene with 2 isoforms, Ng of this isoform should be 2. The length of this vector should be the same as the number of rows in Data. If it's gene level data, Ngvector could be left as NULL.}
+ \item{Conditions}{A factor indicates the condition which each sample belongs to. }
+ \item{sizeFactors}{The normalization factors. It should be a vector with lane specific numbers (the length of the vector should be the same as the number of samples, with the same order as the columns of Data).}
+ \item{maxround}{Number of iterations. The default value is 5. Users should always check the convergency by looking at the Alpha and Beta in output. If the hyper-parameter estimations are not converged in 5 iterations, larger number is suggested.}
+\item{Pool}{While working without replicates, user could define the Pool = TRUE in the EBTest function to enable pooling.}
+\item{NumBin}{By defining NumBin = 1000, EBSeq will group the genes with similar means together into 1,000 bins.}
+\item{PoolLower, PoolUpper}{
+With the assumption that only subset of the genes are DE in the data set, we take genes whose FC are in the PoolLower - PoolUpper quantile of the FC's as the candidate genes (default is 25\%-75\%).
+
+For each bin, the bin-wise variance estimation is defined as the median of the cross condition variance estimations of the candidate genes within that bin.
+
+We use the cross condition variance estimations for the candidate genes and the bin-wise variance estimations of the host bin for the non-candidate genes.
+}
+
+\item{ApproxVal}{The variances of the transcripts with mean < var will be approximated as mean/(1-ApproxVal). }
+
+\item{Alpha, Beta, PInput, RInput}{If the parameters are known and the user doesn't want to estimate them from the data, user could specify them here.}
+\item{Print}{Whether print the elapsed-time while running the test.}
+\item{Qtrm, QtrmCut}{
+Transcripts with Qtrm th quantile < = QtrmCut will be removed before testing. The default value is Qtrm = 0.75 and QtrmCut=10.
+By default setting, transcripts that have >75\% of the samples with expression less than 10
+won't be tested.
+}
+}
+
+\details{For each transcript gi within condition, the model assumes:
+X_{gis}|mu_{gi} ~ NB (r_{gi0} * l_s, q_{gi})
+q_gi|alpha, beta^N_g ~ Beta (alpha, beta^N_g)
+In which the l_s is the sizeFactors of samples.
+
+The function will test "H0: q_{gi}^{C1} = q_{gi}^{C2}" and "H1: q_{gi}^{C1} != q_{gi}^{C2}."
+}
+\value{
+\item{Alpha}{Fitted parameter alpha of the prior beta distribution. Rows are the values for each iteration.}
+\item{Beta}{Fitted parameter beta of the prior beta distribution. Rows are the values for each iteration.}
+\item{P, PFromZ}{The bayes estimator of being DE. Rows are the values for each iteration.}
+\item{Z, PoissonZ}{The Posterior Probability of being DE for each transcript(Maybe not in the same order of input). }
+\item{RList}{The fitted values of r for each transcript.}
+\item{MeanList}{The mean of each transcript (across conditions).}
+\item{VarList}{The variance of each transcript (across conditions).}
+\item{QListi1}{The fitted q values of each transcript within condition 1.}
+\item{QListi2}{The fitted q values of each transcript within condition 2.}
+\item{C1Mean}{The mean of each transcript within Condition 1 (adjusted by normalization factors).}
+\item{C2Mean}{The mean of each transcript within Condition 2 (adjusted by normalization factors).}
+\item{C1EstVar}{The estimated variance of each transcript within Condition 1 (adjusted by normalization factors).}
+\item{C2EstVar}{The estimated variance of each transcript within Condition 2 (adjusted by normalization factors).}
+\item{PoolVar}{The variance of each transcript (The pooled value of within condition EstVar).}
+\item{DataList}{A List of data that grouped with Ng.}
+\item{PPDE}{The Posterior Probability of being DE for each transcript (The same order of input).}
+\item{f0,f1}{The likelihood of the prior predictive distribution of being EE or DE (in log scale).}
+\item{AllZeroIndex}{The transcript with expression 0 for all samples (which are not tested).}
+\item{PPMat}{A matrix contains posterior probabilities of being EE (the first column) or DE (the second column).
+Rows are transcripts.
+Transcripts with expression 0 for all samples are not shown in this matrix.}
+\item{PPMatWith0}{A matrix contains posterior probabilities of being EE (the first column) or DE (the second column).
+Rows are transcripts.
+Transcripts with expression 0 for all samples are shown as PP(EE) = PP(DE) = NA in this matrix.
+The transcript order is exactly the same as the order of the input data.}
+\item{ConditionOrder}{The condition assignment for C1Mean, C2Mean, etc.}
+\item{Conditions}{The input conditions.}
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{
+EBMultiTest, PostFC, GetPPMat
+}
+\examples{
+data(GeneMat)
+str(GeneMat)
+GeneMat.small = GeneMat[c(1:10,511:550),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each = 5)),
+ sizeFactors = Sizes, maxround = 5)
+PP = GetPPMat(EBOut)
+}
+\keyword{ DE }
+\keyword{ Two condition }% __ONLY ONE__ keyword per line
diff --git a/man/GeneMat.Rd b/man/GeneMat.Rd
new file mode 100644
index 0000000..e17f6c1
--- /dev/null
+++ b/man/GeneMat.Rd
@@ -0,0 +1,20 @@
+\name{GeneMat}
+\alias{GeneMat}
+\docType{data}
+\title{
+The simulated data for two condition gene DE analysis
+}
+\description{
+'GeneMat' gives the simulated data for two condition gene DE analysis.
+}
+\usage{data(GeneMat)}
+\source{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\seealso{
+IsoList
+}
+\examples{
+data(GeneMat)
+}
+\keyword{datasets}
diff --git a/man/GetMultiFC.Rd b/man/GetMultiFC.Rd
new file mode 100644
index 0000000..ddd2478
--- /dev/null
+++ b/man/GetMultiFC.Rd
@@ -0,0 +1,64 @@
+\name{GetMultiFC}
+\alias{GetMultiFC}
+\title{
+Calculate the Fold Changes for Multiple Conditions
+}
+\description{
+'GetMultiFC' calculates the Fold Changes for each pair of conditions in a multiple condition study.}
+\usage{
+GetMultiFC(EBMultiOut, SmallNum = 0.01)
+}
+\arguments{
+ \item{EBMultiOut}{The output of EBMultiTest function.}
+\item{SmallNum}{A small number will be added for each transcript in each condition to avoid Inf and NA.
+Default is 0.01.}
+}
+\details{
+Provide the FC (adjusted by the normalization factors) for each pair of comparisons.
+A small number will be added for each transcript in each condition to avoid Inf and NA.
+Default is set to be 0.01.
+}
+\value{
+\item{FCMat}{The FC of each pair of comparison (adjusted by the normalization factors).}
+\item{Log2FCMat}{The log 2 FC of each pair of comparison (adjusted by the normalization factors).}
+\item{PostFCMat}{The posterior FC of each pair of comparison.}
+\item{Log2PostFCMat}{The log 2 posterior FC of each pair of comparison.}
+\item{CondMean}{The mean of each transcript within each condition (adjusted by the normalization factors).}
+\item{ConditionOrder}{The condition assignment for C1Mean, C2Mean, etc.}
+}
+
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+
+
+\seealso{
+EBMultiTest, PostFC
+}
+\examples{
+data(MultiGeneMat)
+MultiGeneMat.small = MultiGeneMat[201:210,]
+
+Conditions = c("C1","C1","C2","C2","C3","C3")
+
+PosParti = GetPatterns(Conditions)
+Parti = PosParti[-3,]
+
+MultiSize = MedianNorm(MultiGeneMat.small)
+
+MultiOut = EBMultiTest(MultiGeneMat.small,
+ NgVector=NULL, Conditions=Conditions,
+ AllParti=Parti, sizeFactors=MultiSize,
+ maxround=5)
+
+MultiFC = GetMultiFC(MultiOut)
+
+}
+% Add one or more standard keywords, see file 'KEYWORDS' in the
+% R documentation directory.
+\keyword{ Posterior Probability }
diff --git a/man/GetMultiPP.Rd b/man/GetMultiPP.Rd
new file mode 100644
index 0000000..11977fd
--- /dev/null
+++ b/man/GetMultiPP.Rd
@@ -0,0 +1,46 @@
+\name{GetMultiPP}
+\alias{GetMultiPP}
+\title{
+Posterior Probability of Each Transcript
+}
+\description{
+'GetMultiPP' generates the Posterior Probability of being each pattern of each transcript based on the EBMultiTest output.
+}
+\usage{
+GetMultiPP(EBout)
+}
+%- maybe also 'usage' for other objects documented here.
+\arguments{
+ \item{EBout}{The output of EBMultiTest function.}
+
+}
+\value{
+\item{PP}{The poster probabilities of being each pattern.}
+\item{MAP}{Gives the most likely pattern.}
+\item{Patterns}{The Patterns.}
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{GetPPMat}
+\examples{
+data(MultiGeneMat)
+MultiGeneMat.small = MultiGeneMat[201:210,]
+
+Conditions = c("C1","C1","C2","C2","C3","C3")
+PosParti = GetPatterns(Conditions)
+Parti = PosParti[-3,]
+MultiSize = MedianNorm(MultiGeneMat.small)
+
+MultiOut = EBMultiTest(MultiGeneMat.small,
+ NgVector=NULL, Conditions=Conditions,
+ AllParti=Parti, sizeFactors=MultiSize,
+ maxround=5)
+MultiPP = GetMultiPP(MultiOut)
+}
+\keyword{ Posterior Probability }
diff --git a/man/GetNg.Rd b/man/GetNg.Rd
new file mode 100644
index 0000000..7ca78f2
--- /dev/null
+++ b/man/GetNg.Rd
@@ -0,0 +1,52 @@
+\name{GetNg}
+\alias{GetNg}
+\title{
+Ng Vector
+}
+\description{
+'GetNg' generates the Ng vector for the isoform level data.
+(While using the number of isoform in the host gene to define the uncertainty groups.)
+}
+\usage{
+GetNg(IsoformName, GeneName, TrunThre = 3)
+}
+%- maybe also 'usage' for other objects documented here.
+\arguments{
+ \item{IsoformName}{A vector contains the isoform names.}
+ \item{GeneName}{The gene names of the isoforms in IsoformNames (Should be in the same order).}
+\item{TrunThre}{The number of uncertainty groups the user wish to define. The default is 3.}
+}
+\value{
+ \item{GeneNg}{The number of isoforms that are contained in each gene.
+ }
+ \item{GeneNgTrun}{The truncated Ng of each gene. (The genes contain more than 3 isoforms are with Ng 3.)
+ }
+ \item{IsoformNg}{The Ng of each isoform.}
+ \item{IsoformNgTrun}{The truncated Ng of each isoform (could be used to define the uncertainty group assignment).}
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\examples{
+
+data(IsoList)
+
+IsoMat = IsoList$IsoMat
+IsoNames = IsoList$IsoNames
+IsosGeneNames = IsoList$IsosGeneNames
+IsoSizes = MedianNorm(IsoMat)
+NgList = GetNg(IsoNames, IsosGeneNames)
+
+#IsoNgTrun = NgList$IsoformNgTrun
+#IsoEBOut = EBTest(Data = IsoMat, NgVector = IsoNgTrun,
+# Conditions = as.factor(rep(c("C1","C2"), each=5)),
+# sizeFactors = IsoSizes, maxround = 5)
+
+}
+
+\keyword{ Ng }
diff --git a/man/GetNormalizedMat.Rd b/man/GetNormalizedMat.Rd
new file mode 100644
index 0000000..dc33015
--- /dev/null
+++ b/man/GetNormalizedMat.Rd
@@ -0,0 +1,33 @@
+\name{GetNormalizedMat}
+\alias{GetNormalizedMat}
+\title{
+Calculate normalized expression matrix
+}
+\description{
+'GetNormalizedMat' calculates the normalized expression matrix.
+(Note: this matrix is only used for visualization etc. EBTes and EBMultiTest request *un-adjusted* expressions and normalization factors.)
+}
+\usage{
+GetNormalizedMat(Data, Sizes)
+}
+\arguments{
+
+ \item{Data}{The data matrix with transcripts in rows and lanes in columns.}
+\item{Sizes}{A vector contains the normalization factor for each lane.}
+}
+\value{The function will return a normalized matrix.}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\examples{
+
+data(GeneMat)
+str(GeneMat)
+Sizes = MedianNorm(GeneMat)
+NormData = GetNormalizedMat(GeneMat, Sizes)
+}
+\keyword{ Normalization }% __ONLY ONE__ keyword per line
diff --git a/man/GetPP.Rd b/man/GetPP.Rd
new file mode 100644
index 0000000..bcac162
--- /dev/null
+++ b/man/GetPP.Rd
@@ -0,0 +1,42 @@
+\name{GetPP}
+\alias{GetPP}
+%- Also NEED an '\alias' for EACH other topic documented here.
+\title{
+Generate the Posterior Probability of each transcript.
+}
+\description{
+'GetPP' generates the Posterior Probability of being DE of each transcript based on the EBTest output.
+}
+\usage{
+GetPP(EBout)
+}
+%- maybe also 'usage' for other objects documented here.
+\arguments{
+ \item{EBout}{The output of EBTest function.}
+}
+
+\value{The poster probabilities of being DE.
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+%% ~Make other sections like Warning with \section{Warning }{....} ~
+
+\seealso{GetPPMat
+}
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(1:10,500:550),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+PPDE = GetPP(EBOut)
+str(PPDE)
+head(PPDE)
+}
+\keyword{ Posterior Probability }
diff --git a/man/GetPPMat.Rd b/man/GetPPMat.Rd
new file mode 100644
index 0000000..ac9505f
--- /dev/null
+++ b/man/GetPPMat.Rd
@@ -0,0 +1,39 @@
+\name{GetPPMat}
+\alias{GetPPMat}
+\title{
+Posterior Probability of Transcripts
+}
+\description{
+'GetPPMat' generates the Posterior Probability of being each pattern of each transcript based on the EBTest output.
+}
+\usage{
+GetPPMat(EBout)
+}
+\arguments{
+ \item{EBout}{The output of EBTest function.}
+
+}
+\value{The poster probabilities of being EE (first column) and DE (second column).
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\examples{
+
+data(GeneMat)
+GeneMat.small = GeneMat[c(500:550),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+PP = GetPPMat(EBOut)
+str(PP)
+head(PP)
+}
+% Add one or more standard keywords, see file 'KEYWORDS' in the
+% R documentation directory.
+\keyword{ Posterior Probability }
diff --git a/man/GetPatterns.Rd b/man/GetPatterns.Rd
new file mode 100644
index 0000000..704dfd1
--- /dev/null
+++ b/man/GetPatterns.Rd
@@ -0,0 +1,29 @@
+\name{GetPatterns}
+\alias{GetPatterns}
+\title{
+Generate all possible patterns in a multiple condition study
+}
+\description{
+'GetPatterns' generates all possible patterns in a multiple condition study.
+}
+\usage{
+GetPatterns(Conditions)
+}
+\arguments{
+ \item{Conditions}{The names of the Conditions in the study.}
+}
+
+\value{A matrix describe all possible patterns. }
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+
+\examples{
+Conditions = c("C1","C1","C2","C2","C3","C3")
+PosParti = GetPatterns(Conditions)
+}
diff --git a/man/IsoList.Rd b/man/IsoList.Rd
new file mode 100644
index 0000000..3e08019
--- /dev/null
+++ b/man/IsoList.Rd
@@ -0,0 +1,19 @@
+\name{IsoList}
+\alias{IsoList}
+\docType{data}
+\title{
+The simulated data for two condition isoform DE analysis
+}
+\description{
+'IsoList' gives the simulated data for two condition isoform DE analysis.
+}
+\usage{data(IsoList)}
+\source{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\seealso{GeteMat}
+
+\examples{
+data(IsoList)
+}
+\keyword{datasets}
diff --git a/man/IsoMultiList.Rd b/man/IsoMultiList.Rd
new file mode 100644
index 0000000..fd4ee6a
--- /dev/null
+++ b/man/IsoMultiList.Rd
@@ -0,0 +1,19 @@
+\name{IsoMultiList}
+\alias{IsoMultiList}
+\docType{data}
+\title{
+The simulated data for multiple condition isoform DE analysis
+}
+\description{
+'IsoMultiList' gives a set of simulated data for multiple condition isoform DE analysis.
+}
+\usage{data(IsoMultiList)}
+\source{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\seealso{IsoList
+}
+\examples{
+data(IsoMultiList)
+}
+\keyword{datasets}
diff --git a/man/Likefun.Rd b/man/Likefun.Rd
new file mode 100644
index 0000000..5048e92
--- /dev/null
+++ b/man/Likefun.Rd
@@ -0,0 +1,36 @@
+\name{Likefun}
+\alias{Likefun}
+\title{
+Likelihood Function of the NB-Beta Model
+}
+\description{
+'Likefun' specifies the Likelihood Function of the NB-Beta Model.
+}
+\usage{
+Likefun(ParamPool, InputPool)
+}
+\arguments{
+ \item{ParamPool}{The parameters that will be estimated in EM.}
+ \item{InputPool}{The control parameters that will not be estimated in EM.}
+}
+
+\value{The function will return the log-likelihood.
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+
+
+\examples{
+#x1 = c(.6,.7,.3)
+#Input = matrix(rnorm(100,100,1), ncol=10)
+#RIn = matrix(rnorm(100,200,1), ncol=10)
+#InputPool = list(Input[,1:5], Input[,6:10], Input,
+# rep(.1,100), 1, RIn, RIn[,1:5], RIn[,6:10], 100)
+#Likefun(x1, InputPool)
+}
diff --git a/man/LikefunMulti.Rd b/man/LikefunMulti.Rd
new file mode 100644
index 0000000..aa93979
--- /dev/null
+++ b/man/LikefunMulti.Rd
@@ -0,0 +1,40 @@
+\name{LikefunMulti}
+\alias{LikefunMulti}
+\title{
+Likelihood Function of the NB-Beta Model In Multiple Condition Test
+}
+\description{
+'LikefunMulti' specifies the Likelihood Function of the NB-Beta Model In Multiple Condition Test.
+}
+\usage{
+LikefunMulti(ParamPool, InputPool)
+}
+
+\arguments{
+ \item{ParamPool}{The parameters that will be estimated in EM.}
+ \item{InputPool}{The control parameters that will not be estimated in EM.}
+}
+
+\value{The function will return the log-likelihood.}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+
+\examples{
+#x1 = c(.6,.7,.3)
+#Input = matrix(rnorm(100,100,1),ncol=10)
+#RIn = matrix(rnorm(100,200,1),ncol=10)
+#InputPool = list(list(Input[,1:5],Input[,6:10]),
+# Input, cbind(rep(.1, 10), rep(.9,10)), 1,
+# RIn, list(RIn[,1:5],RIn[,6:10]),
+# 10, rbind(c(1,1),c(1,2)))
+#LikefunMulti(x1, InputPool)
+
+}
+
+
diff --git a/man/LogN.Rd b/man/LogN.Rd
new file mode 100644
index 0000000..30ba666
--- /dev/null
+++ b/man/LogN.Rd
@@ -0,0 +1,39 @@
+\name{LogN}
+\alias{LogN}
+\title{
+The function to run EM (one round) algorithm for the NB-beta model.
+}
+\description{
+'LogN' specifies the function to run (one round of) the EM algorithm for the NB-beta model.
+}
+\usage{
+LogN(Input, InputSP, EmpiricalR, EmpiricalRSP, NumOfEachGroup,
+ AlphaIn, BetaIn, PIn, NoneZeroLength)
+}
+\arguments{
+ \item{Input, InputSP}{The expressions among all the samples.}
+ \item{NumOfEachGroup}{Number of genes in each Ng group.}
+ \item{AlphaIn, PIn, BetaIn, EmpiricalR, EmpiricalRSP}{The parameters from the last EM step.}
+ \item{NoneZeroLength}{Number of Ng groups.}
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+
+}
+\author{
+Ning Leng
+}
+
+
+\examples{
+
+#Input = matrix(rnorm(100,100,1), ncol=10)
+#rownames(Input) = paste("g",1:10)
+#RIn = matrix(rnorm(100,200,1), ncol=10)
+#res = LogN(Input, list(Input[,1:5], Input[,6:10]),
+# RIn, list(RIn[,1:5], RIn[,6:10]),
+# 10, .6, .7, .3, 1)
+
+}
+
diff --git a/man/LogNMulti.Rd b/man/LogNMulti.Rd
new file mode 100644
index 0000000..bbec726
--- /dev/null
+++ b/man/LogNMulti.Rd
@@ -0,0 +1,44 @@
+\name{LogNMulti}
+\alias{LogNMulti}
+%- Also NEED an '\alias' for EACH other topic documented here.
+\title{
+EM algorithm for the NB-beta model in the multiple condition test
+}
+\description{
+'LogNMulti' specifies the function to run (one round of) the EM algorithm for the NB-beta model in the multiple condition test.}
+\usage{
+LogNMulti(Input, InputSP, EmpiricalR, EmpiricalRSP,
+ NumOfEachGroup, AlphaIn, BetaIn, PIn,
+ NoneZeroLength, AllParti, Conditions)
+}
+
+\arguments{
+ \item{Input, InputSP}{The expressions among all the samples.}
+ \item{NumOfEachGroup}{Number of genes in each Ng group.}
+ \item{AlphaIn, PIn, BetaIn, EmpiricalR, EmpiricalRSP}{The parameters from the last EM step.}
+ \item{NoneZeroLength}{Number of Ng groups.}
+ \item{AllParti}{The patterns of interests.}
+ \item{Conditions}{The condition assignment for each sample.}
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+
+}
+\author{
+Ning Leng
+}
+
+
+\examples{
+#
+
+#Input = matrix(rnorm(100,100,1),ncol=10)
+#rownames(Input) = paste("g",1:10)
+#RIn = matrix(rnorm(100,200,1), ncol=10)
+#res = LogNMulti(Input, list(Input[,1:5], Input[,6:10]),
+# RIn, list(RIn[,1:5], RIn[,6:10]), 10, .6, .7,
+# c(.3,.7), 1, rbind(c(1,1), c(1,2)),
+# as.factor(rep(c("C1","C2"), each=5)))
+}
+
diff --git a/man/MedianNorm.Rd b/man/MedianNorm.Rd
new file mode 100644
index 0000000..9fc47ff
--- /dev/null
+++ b/man/MedianNorm.Rd
@@ -0,0 +1,38 @@
+\name{MedianNorm}
+\alias{MedianNorm}
+\title{
+Median Normalization
+}
+\description{
+'MedianNorm' specifies the median normalization function from Anders et. al., 2010.
+}
+\usage{
+MedianNorm(Data)
+}
+\arguments{
+ \item{Data}{The data matrix with transcripts in rows and lanes in columns.}
+}
+
+\value{The function will return a vector contains the normalization factor for each lane.}
+
+\references{
+Simon Anders and Wolfgang Huber. Differential expression analysis for sequence count data.
+Genome Biology (2010) 11:R106 (open access)
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{
+QuantileNorm
+}
+\examples{
+data(GeneMat)
+Sizes = MedianNorm(GeneMat)
+#EBOut = EBTest(Data = GeneMat,
+# Conditions = as.factor(rep(c("C1","C2"), each=5)),
+# sizeFactors = Sizes, maxround = 5)
+
+}
+\keyword{ Normalization }
diff --git a/man/MultiGeneMat.Rd b/man/MultiGeneMat.Rd
new file mode 100644
index 0000000..9f76f8b
--- /dev/null
+++ b/man/MultiGeneMat.Rd
@@ -0,0 +1,20 @@
+\name{MultiGeneMat}
+\alias{MultiGeneMat}
+\docType{data}
+\title{
+The simulated data for multiple condition gene DE analysis
+}
+\description{
+'MultiGeneMat' generates a set of the simulated data for multiple condition gene DE analysis.
+}
+\usage{data(MultiGeneMat)}
+\source{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\seealso{
+ GeneMat
+}
+\examples{
+data(MultiGeneMat)
+}
+\keyword{datasets}
diff --git a/man/PlotPattern.Rd b/man/PlotPattern.Rd
new file mode 100644
index 0000000..27f5a8d
--- /dev/null
+++ b/man/PlotPattern.Rd
@@ -0,0 +1,36 @@
+\name{PlotPattern}
+\alias{PlotPattern}
+\title{
+Visualize the patterns
+}
+\description{
+'PlotPattern' generates the visualized patterns before the multiple condition test.
+}
+\usage{
+PlotPattern(Patterns)
+}
+\arguments{
+ \item{Patterns}{
+The output of GetPatterns function.
+}
+
+}
+\value{
+A heatmap to visualize the patterns of interest.
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+
+\examples{
+Conditions = c("C1","C1","C2","C2","C3","C3")
+Patterns = GetPatterns(Conditions)
+PlotPattern(Patterns)
+
+}
+\keyword{ patterns }
diff --git a/man/PlotPostVsRawFC.Rd b/man/PlotPostVsRawFC.Rd
new file mode 100644
index 0000000..9924b3e
--- /dev/null
+++ b/man/PlotPostVsRawFC.Rd
@@ -0,0 +1,45 @@
+\name{PlotPostVsRawFC}
+\alias{PlotPostVsRawFC}
+\title{
+Plot Posterior FC vs FC
+}
+\description{
+'PlotPostVsRawFC' helps the users visualize the posterior FC vs FC in a two condition study.
+}
+\usage{
+PlotPostVsRawFC(EBOut, FCOut)
+}
+\arguments{
+ \item{EBOut}{
+The output of EBMultiTest function.
+}
+ \item{FCOut}{The output of PostFC function.}
+
+}
+\value{
+A figure shows fold change vs posterior fold change.
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+
+\seealso{
+PostFC
+}
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(500:600),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+FC = PostFC(EBOut)
+PlotPostVsRawFC(EBOut,FC)
+
+}
+\keyword{ Posterior Probability }
diff --git a/man/PolyFitPlot.Rd b/man/PolyFitPlot.Rd
new file mode 100644
index 0000000..ec4cee0
--- /dev/null
+++ b/man/PolyFitPlot.Rd
@@ -0,0 +1,101 @@
+\name{PolyFitPlot}
+\alias{PolyFitPlot}
+\title{
+Fit the mean-var relationship using polynomial regression
+}
+\description{
+'PolyFitPlot' fits the mean-var relationship using polynomial regression.
+}
+
+\usage{
+PolyFitPlot(X, Y, nterms, xname = "Estimated Mean",
+ yname = "Estimated Var", pdfname = "",
+ xlim = c(-1,5), ylim = c(-1,7), ChangeXY = F,
+ col = "red")
+}
+
+%- maybe also 'usage' for other objects documented here.
+\arguments{
+ \item{X}{
+The first group of values want to be fitted by the polynomial regression (e.g Mean of the data).
+}
+ \item{Y}{
+The second group of values want to be fitted by the polynomial regression (e.g. variance of the data). The length of Y should be the same as the length of X.
+}
+ \item{nterms}{
+How many polynomial terms want to be used.
+}
+ \item{xname}{
+Name of the x axis.
+}
+ \item{yname}{
+Name of the y axis.
+}
+ \item{pdfname}{
+Name of the plot.
+}
+ \item{xlim}{
+The x limits of the plot.
+}
+ \item{ylim}{
+The y limits of the plot.
+
+}
+ \item{ChangeXY}{
+If ChangeXY is setted to be TRUE, X will be treated as the dependent variable and Y will be treated as the independent one. Default is FALSE.
+}
+ \item{col}{
+Color of the fitted line.
+}
+}
+\value{The PolyFitPlot function provides a smooth scatter plot of two variables and their best fitting line of polynomial regression.
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+
+\examples{
+data(IsoList)
+str(IsoList)
+IsoMat = IsoList$IsoMat
+IsoNames = IsoList$IsoNames
+IsosGeneNames = IsoList$IsosGeneNames
+IsoSizes = MedianNorm(IsoMat)
+NgList = GetNg(IsoNames, IsosGeneNames)
+
+IsoNgTrun = NgList$IsoformNgTrun
+#IsoEBOut = EBTest(Data = IsoMat.small,
+# NgVector = IsoNgTrun,
+# Conditions = as.factor(rep(c("C1","C2"), each=5)),
+# sizeFactors = IsoSizes, maxround = 5)
+
+#par(mfrow=c(2,2))
+#PolyFitValue = vector("list",3)
+
+#for(i in 1:3)
+# PolyFitValue[[i]] = PolyFitPlot(IsoEBOut$C1Mean[[i]],
+# IsoEBOut$C1EstVar[[i]], 5)
+
+#PolyAll = PolyFitPlot(unlist(IsoEBOut$C1Mean),
+# unlist(IsoEBOut$C1EstVar), 5)
+
+#lines(log10(IsoEBOut$C1Mean[[1]][PolyFitValue[[1]]$sort]),
+# PolyFitValue[[1]]$fit[PolyFitValue[[1]]$sort],
+# col="yellow", lwd=2)
+#lines(log10(IsoEBOut$C1Mean[[2]][PolyFitValue[[2]]$sort]),
+# PolyFitValue[[2]]$fit[PolyFitValue[[2]]$sort],
+# col="pink", lwd=2)
+#lines(log10(IsoEBOut$C1Mean[[3]][PolyFitValue[[3]]$sort]),
+# PolyFitValue[[3]]$fit[PolyFitValue[[3]]$sort],
+# col="green", lwd=2)
+
+#legend("topleft",c("All Isoforms","Ng = 1","Ng = 2","Ng = 3"),
+# col = c("red","yellow","pink","green"),
+# lty=1, lwd=3, box.lwd=2)
+
+}
diff --git a/man/PostFC.Rd b/man/PostFC.Rd
new file mode 100644
index 0000000..de4abf5
--- /dev/null
+++ b/man/PostFC.Rd
@@ -0,0 +1,58 @@
+\name{PostFC}
+\alias{PostFC}
+\title{
+Calculate the posterior fold change for each transcript across conditions
+}
+\description{
+'PostFC' calculates the posterior fold change for each transcript across conditions.
+}
+\usage{
+PostFC(EBoutput, SmallNum = 0.01)
+}
+\arguments{
+ \item{EBoutput}{
+The ourput from function EBTest.
+}
+
+\item{SmallNum}{A small number will be added for each transcript in each condition to avoid Inf and NA. Default is 0.01.}
+
+}
+\value{
+Provide both FC and posterior FC across two conditions.
+FC is calculated as (MeanC1+SmallNum)/(MeanC2+SmallNum).
+And Posterior FC is calculated as:
+
+# Post alpha P_a_C1 = alpha + r_C1 * n_C1
+
+# Post beta P_b_C1 = beta + Mean_C1 * n_C1
+
+# P_q_C1 = P_a_C1 / (P_a_C1 + P_b_C1)
+
+# Post FC = ((1-P_q_C1)/P_q_c1) / ( (1-P_q_c2)/P_q_c2)
+
+\item{PostFC}{The posterior FC across two conditions.}
+\item{RealFC}{The FC across two conditions (adjusted by the normalization factors).}
+\item{Direction}{The diretion of FC calculation.}
+
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{
+EBTest, GetMultiFC
+}
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(500:550),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+FC=PostFC(EBOut)
+}
+\keyword{ Fold Change }
diff --git a/man/QQP.Rd b/man/QQP.Rd
new file mode 100644
index 0000000..d477452
--- /dev/null
+++ b/man/QQP.Rd
@@ -0,0 +1,43 @@
+\name{QQP}
+\alias{QQP}
+\title{
+The Quantile-Quantile Plot to compare the empirical q's and simulated q's from fitted beta distribution
+}
+\description{
+'QQP' gives the Quantile-Quantile Plot to compare the empirical q's and simulated q's from fitted beta distribution.
+}
+\usage{
+QQP(EBOut, GeneLevel = F)
+}
+\arguments{
+ \item{EBOut}{The output of EBTest or EBMultiTest.
+ }
+ \item{GeneLevel}{Indicate whether the results are from data at gene level.}
+}
+
+\value{
+For data with n1 conditions and n2 uncertainty groups, n1*n2 plots will be generated. Each plot represents a subset of the data.
+}
+
+\references{
+ Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+
+\author{
+Ning Leng
+}
+\seealso{
+ EBTest, EBMultiTest, DenNHist
+}
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(500:1000),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+par(mfrow=c(2,2))
+QQP(EBOut)
+
+}
+\keyword{ Q-Q plot }
diff --git a/man/QuantileNorm.Rd b/man/QuantileNorm.Rd
new file mode 100644
index 0000000..7dc1021
--- /dev/null
+++ b/man/QuantileNorm.Rd
@@ -0,0 +1,47 @@
+\name{QuantileNorm}
+\alias{QuantileNorm}
+\title{
+Quantile Normalization
+}
+\description{
+'QuantileNorm' gives the quantile normalization.
+}
+\usage{
+QuantileNorm(Data, Quantile)
+}
+\arguments{
+
+ \item{Data}{
+The data matrix with transcripts in rows and lanes in columns.
+}
+\item{Quantile}{
+The quantile the user wishs to use. Should be a number between 0 and 1.
+}
+}
+\details{
+Use a quantile point to normalize the data.
+}
+\value{
+The function will return a vector contains the normalization factor for each lane.
+% ...
+}
+\references{
+Bullard, James H., et al. Evaluation of statistical methods for normalization and differential expression in mRNA-Seq experiments. BMC bioinformatics 11.1 (2010): 94.
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{
+MedianNorm
+}
+\examples{
+data(GeneMat)
+Sizes = QuantileNorm(GeneMat,.75)
+#EBOut = EBTest(Data = GeneMat,
+# Conditions = as.factor(rep(c("C1","C2"), each=5)),
+# sizeFactors = Sizes, maxround = 5)
+
+}
+\keyword{ Normalization }% __ONLY ONE__ keyword per line
diff --git a/man/RankNorm.Rd b/man/RankNorm.Rd
new file mode 100644
index 0000000..05a4c66
--- /dev/null
+++ b/man/RankNorm.Rd
@@ -0,0 +1,40 @@
+\name{RankNorm}
+\alias{RankNorm}
+\title{
+Rank Normalization
+}
+\description{
+'RankNorm' gives the rank normalization.
+}
+\usage{
+RankNorm(Data)
+}
+\arguments{
+ \item{Data}{
+The data matrix with transcripts in rows and lanes in columns.
+}
+}
+
+\value{
+The function will return a matrix contains the normalization factor for each lane and each transcript.
+}
+
+\author{
+Ning Leng
+}
+
+
+\seealso{
+MedianNorm, QuantileNorm
+}
+
+\examples{
+data(GeneMat)
+Sizes = RankNorm(GeneMat)
+# Run EBSeq
+# EBres = EBTest(Data = GeneData, NgVector = rep(1,10^4),
+# Vect5End = rep(1,10^4), Vect3End = rep(1,10^4),
+# Conditions = as.factor(rep(c(1,2), each=5)),
+# sizeFactors = Sizes, maxround=5)
+}
+\keyword{ Normalization }
diff --git a/man/beta.mom.Rd b/man/beta.mom.Rd
new file mode 100644
index 0000000..3fa12fb
--- /dev/null
+++ b/man/beta.mom.Rd
@@ -0,0 +1,39 @@
+\name{beta.mom}
+\alias{beta.mom}
+
+\title{
+Fit the beta distribution by method of moments
+}
+
+\description{
+'beta.mom' fits the beta distribution by method of moments.
+}
+
+\usage{
+beta.mom(qs.in)
+}
+
+\arguments{
+ \item{qs.in}{A vector contains the numbers that are assumed to follow a beta distribution.}
+}
+
+\value{
+ \item{alpha.hat}{Returns the estimation of alpha.}
+ \item{beta.hat}{Returns the estimation of beta.}
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+
+\seealso{
+DenNHist, DenNHistTable
+}
+\examples{
+#tmp = rbeta(5, 5, 100)
+#param = beta.mom(tmp)
+}
+\keyword{ beta }
diff --git a/man/crit_fun.Rd b/man/crit_fun.Rd
new file mode 100644
index 0000000..39fc8ee
--- /dev/null
+++ b/man/crit_fun.Rd
@@ -0,0 +1,51 @@
+\name{crit_fun}
+\alias{crit_fun}
+\title{
+Calculate the soft threshold for a target FDR
+}
+\description{
+'crit_fun' calculates the soft threshold for a target FDR.
+}
+\usage{
+crit_fun(PPEE, thre)
+}
+\arguments{
+ \item{PPEE}{The posterior probabilities of being EE.}
+ \item{thre}{The target FDR.}
+
+}
+\details{
+Regarding a target FDR alpha, both hard threshold and soft threshold could be used.
+If the hard threshold is preferred, user could simply take the transcripts with
+PP(DE) greater than (1-alpha). Using the hard threshold, any DE transcript in the
+list is with FDR <= alpha.
+
+If the soft threshold is preferred, user could take the transcripts with PP(DE)
+greater than crit_fun(PPEE, alpha). Using the soft threshold, the list of
+DE transcripts is with average FDR alpha.
+}
+\value{
+The adjusted FDR threshold of target FDR.
+}
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\examples{
+data(GeneMat)
+GeneMat.small = GeneMat[c(1:10, 500:600),]
+Sizes = MedianNorm(GeneMat.small)
+EBOut = EBTest(Data = GeneMat.small,
+ Conditions = as.factor(rep(c("C1","C2"), each=5)),
+ sizeFactors = Sizes, maxround = 5)
+PP = GetPPMat(EBOut)
+DEfound = rownames(PP)[which(PP[,"PPDE"] >= 0.95)]
+str(DEfound)
+
+SoftThre = crit_fun(PP[,"PPEE"], 0.05)
+DEfound_soft = rownames(PP)[which(PP[,"PPDE"] >= SoftThre)]
+}
+\keyword{ FDR }
diff --git a/man/f0.Rd b/man/f0.Rd
new file mode 100644
index 0000000..f5d8fef
--- /dev/null
+++ b/man/f0.Rd
@@ -0,0 +1,37 @@
+\name{f0}
+\alias{f0}
+%- Also NEED an '\alias' for EACH other topic documented here.
+\title{
+The Prior Predictive Distribution of being EE
+}
+\description{
+'f0' gives the Prior Predictive Distribution of being EE.
+}
+\usage{
+f0(Input, AlphaIn, BetaIn, EmpiricalR, NumOfGroups, log)
+}
+\arguments{
+ \item{Input}{Expression Values.}
+ \item{AlphaIn, BetaIn, EmpiricalR}{The parameters estimated from last iteration of EM.}
+ \item{NumOfGroups}{How many transcripts within each Ng group.}
+ \item{log}{If true, will give the log of the output.}
+}
+\value{
+The function will return the prior predictive distribution values of being EE.
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\seealso{
+f1
+}
+\examples{
+#
+#f0(matrix(rnorm(100,100,1),ncol=10), .5, .6,
+# matrix(rnorm(100,200,1),ncol=10), 100, TRUE)
+}
diff --git a/man/f1.Rd b/man/f1.Rd
new file mode 100644
index 0000000..5aaf254
--- /dev/null
+++ b/man/f1.Rd
@@ -0,0 +1,42 @@
+\name{f1}
+\alias{f1}
+\title{
+The Prior Predictive Distribution of being DE
+}
+\description{
+'f1' gives the Prior Predictive Distribution of DE.
+}
+\usage{
+f1(Input1, Input2, AlphaIn, BetaIn, EmpiricalRSP1,
+ EmpiricalRSP2, NumOfGroup, log)
+}
+\arguments{
+
+ \item{Input1}{Expressions from Condition1.}
+ \item{Input2}{Expressions from Condition2.}
+ \item{AlphaIn, BetaIn, EmpiricalRSP1, EmpiricalRSP2}{The parameters estimated from last iteration of EM.}
+ \item{NumOfGroup}{ How many transcripts within each Ng group.}
+ \item{log}{If true, will give the log of the output.}
+}
+
+\value{
+The function will return the prior predictive distribution values of being DE.
+}
+
+\references{
+Ning Leng, John A. Dawson, James A. Thomson, Victor Ruotti, Anna I. Rissman, Bart M.G. Smits, Jill D. Haag, Michael N. Gould, Ron M. Stewart, and Christina Kendziorski. EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments. Bioinformatics (2013)
+}
+\author{
+Ning Leng
+}
+
+\seealso{
+f0
+}
+\examples{
+#f1(matrix(rnorm(100,100,1),ncol=10),
+# matrix(rnorm(100,100,1),ncol=10), .5, .6,
+# matrix(rnorm(100,200,1),ncol=10),
+# matrix(rnorm(100,200,1),ncol=10), 100, TRUE)
+
+}
diff --git a/vignettes/EBSeq_Vignette.Rnw b/vignettes/EBSeq_Vignette.Rnw
new file mode 100644
index 0000000..b384e0c
--- /dev/null
+++ b/vignettes/EBSeq_Vignette.Rnw
@@ -0,0 +1,1054 @@
+%\VignetteIndexEntry{EBSeq}
+
+\documentclass{article}
+\usepackage{fullpage}
+\usepackage{graphicx, graphics, epsfig,setspace,amsmath, amsthm}
+\usepackage{hyperref}
+\usepackage{natbib}
+%\usepackage{listings}
+\usepackage{moreverb}
+\begin{document}
+\title{EBSeq: An R package for differential expression analysis using RNA-seq data}
+\author{Ning Leng, John Dawson, and Christina Kendziorski}
+\maketitle
+\tableofcontents
+\setcounter{tocdepth}{2}
+
+\section{Introduction}
+EBSeq may be used to identify differentially expressed (DE)
+genes and isoforms in an RNA-Seq experiment. As detailed in
+Leng {\it et al.}, 2013 \cite{Leng13},
+EBSeq is an empirical Bayesian approach that models a number of features
+observed in RNA-seq data. Importantly, for isoform level inference,
+EBSeq directly accommodates isoform expression estimation uncertainty by
+modeling the differential variability observed in distinct groups of isoforms.
+Consider Figure 1, where we have plotted variance against mean
+for all isoforms using RNA-Seq expression data from Leng {\it et al.}, 2013 \cite{Leng13}.
+Also shown is the fit within three sub-groups of isoforms defined
+by the number of constituent isoforms of the parent gene.
+An isoform of gene $g$ is assigned to the $I_g=k$ group, where $k=1,2,3$,
+if the total number of isoforms from gene $g$ is $k$ (the $I_g=3$ group contains
+all isoforms from genes having 3 or more isoforms).
+As shown in Figure 1, there is decreased variability in the $I_g=1$ group,
+but increased variability in the others, due to the relative increase in
+uncertainty inherent in estimating isoform expression when multiple isoforms of a given gene are
+present. If this structure is not accommodated, there is reduced power for
+identifying isoforms in the $I_g=1$ group (since the true variances in that group are
+lower, on average, than that derived from the full collection of isoforms) as well as increased
+false discoveries in the $I_g=2$ and $I_g=3$ groups (since the true variances are higher, on average,
+than those derived from the full collection). EBSeq directly models differential variability
+as a function of $I_g$ providing a powerful approach for isoform level inference. As shown in Leng {\it et al.}, 2013
+\cite{Leng13}, the model is also useful for identifying DE genes.
+We will briefly detail the model in Section \ref{sec:model} and then describe
+the flow of analysis in Section \ref{sec:quickstart} for both isoform and gene-level inference.
+
+\begin{figure}[t]
+\centering
+\includegraphics[width=0.6\textwidth]{PlotExample.png}
+\label{fig:GouldNg}
+\caption{Empirical variance vs. mean for
+each isoform profiled in the ESCs vs iPSCs experiment detailed in
+the Case Study section of Leng {\it et al.}, 2013 \cite{Leng13}.
+A spline fit to all isoforms is shown in red with splines fit within the $I_g=1$, $I_g=2$, and $I_g=3$ isoform groups
+shown in yellow, pink, and green, respectively.}
+\end{figure}
+
+
+\section{Citing this software}
+\label{sec:cite}
+Please cite the following article when reporting results from the software.
+
+\noindent Leng, N., J.A. Dawson, J.A. Thomson, V. Ruotti, A.I. Rissman,
+B.M.G. Smits, J.D. Haag, M.N. Gould, R.M. Stewart, and C. Kendziorski.
+EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq
+experiments, {\it Bioinformatics}, 2013.
+
+\section{The Model}
+\label{sec:model}
+\subsection{Two conditions}
+\label{sec:twocondmodel}
+We let $X_{g_i}^{C1} = X_{g_i,1} ,X_{g_i,2}, ...,X_{g_i,S_1}$ denote data from condition 1
+and $ X_{g_i}^{C2} = X_{g_i,(S_1+1)},X_{g_i,(S_1+2)},...,X_{g_i,S}$ data from condition 2.
+We assume that counts within condition $C$ are distributed as Negative Binomial:
+$X_{g_i,s}^C|r_{g_i,s}, q_{g_i}^C \sim NB(r_{g_i,s}, q_{g_i}^C)$ where
+\begin{equation}
+P(X_{g_i,s}|r_{g_i,s},q_{g_i}^C) = {X_{g_i,s}+r_{g_i,s}-1\choose X_{g_i,s}}(1-q_{g_i}^C)^{X_{g_i,s}}(q_{g_i}^C)^{r_{g_i,s}}\label{eq:01}
+\end{equation}
+
+\noindent and $\mu_{g_i,s}^C=r_{g_i,s} (1-q_{g_i}^C)/q_{g_i}^C$;
+$(\sigma_{g_i,s}^C)^2=r_{g_i,s} (1-q_{g_i}^C)/(q_{g_i}^C)^2.$
+
+\medskip
+
+We assume a prior distribution on $q_{g_i}^C$: $q_{g_i}^C|\alpha, \beta^{I_g} \sim Beta(\alpha, \beta^{I_g})$.
+The hyperparameter $\alpha$ is shared by all the isoforms and $\beta^{I_g}$ is $I_g$ specific (note this is an index, not a power).
+We further assume that $r_{g_i,s}=r_{g_i,0} l_s$, where $r_{g_i,0}$ is an isoform specific
+parameter common across conditions and $r_{g_i,s}$ depends on it through the sample-specific normalization factor $l_s$.
+Of interest in this two group comparison is distinguishing between two cases, or what we will refer to subsequently as
+two patterns of expression, namely equivalent expression (EE) and differential expression (DE):
+\begin{center}
+$H_0$ (EE) : $q_{g_i}^{C1}=q_{g_i}^{C2}$ vs $H_1$ (DE) : $q_{g_i}^{C1} \neq q_{g_i}^{C2}$.
+\end{center}
+Under the null hypothesis (EE), the data $X_{g_i}^{C1,C2} = X_{g_i}^{C1}, X_{g_i}^{C2}$ arises
+from the prior predictive distribution $f_0^{I_g}(X_{g_i}^{C1,C2})$:
+%\tiny
+\begin{equation}
+f_0^{I_g}(X_{g_i}^{C1,C2})=\Bigg[\prod_{s=1}^S {X_{g_i,s}+r_{g_i,s}-1\choose X_{g_i,s}}\Bigg]
+\frac{Beta(\alpha+\sum_{s=1}^S r_{g_i,s}, \beta^{I_g}+\sum_{s=1}^SX_{g_i,s} )}{Beta(\alpha, \beta^{I_g})}\label{eq:05}
+\end{equation}
+%\normalsize
+
+Alternatively (in a DE scenario), $X_{g_i}^{C1,C2}$ follows the prior predictive distribution $f_1^{I_g}(X_{g_i}^{C1,C2})$:
+\begin{equation}
+f_1^{I_g}(X_{g_i}^{C1,C2})=f_0^{I_g}(X_{g_i}^{C1})f_0^{I_g}(X_{g_i}^{C2}) \label{eq:06}
+\end{equation}
+
+Let the latent variable $Z_{g_i}$ be defined so that $Z_{g_i} = 1$ indicates that
+isoform $g_i$ is DE and $Z_{g_i} = 0$ indicates isoform $g_i$ is EE, and
+$Z_{g_i} \sim Bernoulli(p)$.
+Then, the marginal distribution of $X_{g_i}^{C1,C2}$ and $Z_{g_i}$ is:
+\begin{equation}
+(1-p)f_0^{I_g}(X_{g_i}^{C1,C2}) + pf_1^{I_g}(X_{g_i}^{C1,C2})\label{eq:07}
+\end{equation}
+
+\noindent The posterior probability of being DE at isoform $g_i$ is obtained by Bayes' rule:
+\begin{equation}
+\frac{pf_1^{I_g}(X_{g_i}^{C1,C2})}{(1-p)f_0^{I_g}(X_{g_i}^{C1,C2}) + pf_1^{I_g}(X_{g_i}^{C1,C2})}\label{eq:08}
+\end{equation}
+
+%\newpage
+\subsection{More than two conditions}
+\label{sec:multicondmodel}
+EBSeq naturally accommodates multiple condition comparisons.
+For example, in a study with 3 conditions, there are K=5 possible expression patterns (P1,...,P5), or ways in which
+latent levels of expression may vary across conditions:
+\begin{align}
+\textrm {P1:}& \hspace{0.05in} q_{g_i}^{C1} = q_{g_i}^{C2}=q_{g_i}^{C3} \nonumber \\
+\textrm {P2:}& \hspace{0.05in} q_{g_i}^{C1} = q_{g_i}^{C2} \neq q_{g_i}^{C3} \nonumber \\
+\textrm {P3:}& \hspace{0.05in} q_{g_i}^{C1} = q_{g_i}^{C3} \neq q_{g_i}^{C2} \nonumber \\
+\textrm {P4:}& \hspace{0.05in} q_{g_i}^{C1} \neq q_{g_i}^{C2} = q_{g_i}^{C3} \nonumber \\
+\textrm {P5:}& \hspace{0.05in} q_{g_i}^{C1} \neq q_{g_i}^{C2} \neq
+q_{g_i}^{C3} \textrm{ and } q_{g_i}^{C1} \neq q_{g_i}^{C3} \nonumber
+\end{align}
+
+\noindent The prior predictive distributions for these are given, respectively, by:
+
+\begin{align}
+g_1^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1,C2,C3}) \nonumber \\
+g_2^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1,C2})f_0^{I_g}(X_{g_i}^{C3}) \nonumber \\
+g_3^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1,C3})f_0^{I_g}(X_{g_i}^{C2}) \nonumber \\
+g_4^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1})f_0^{I_g}(X_{g_i}^{C2,C3}) \nonumber \\
+g_5^{I_g}(X_{g_i}^{C1,C2,C3}) &= f_0^{I_g}(X_{g_i}^{C1})f_0^{I_g}(X_{g_i}^{C2})f_0^{I_g}(X_{g_i}^{C3}) \nonumber
+\end{align}
+
+\noindent where $f_0^{I_g}$ is the same as in equation \ref{eq:05}. Then the marginal distribution in
+equation \ref{eq:07} becomes:
+
+\begin{equation}
+\sum_{k=1}^5 p_k g_k^{I_g}(X_{g_i}^{C1,C2,C3}) \label{eq:11}
+\end{equation}
+\noindent where $\sum_{k=1}^5 p_k = 1$. Thus, the posterior probability of
+isoform $g_i$ coming from pattern $K$ is readily obtained by:
+
+\begin{equation}
+\frac{p_K g_K^{I_g}(X_{g_i}^{C1,C2,C3})}{\sum_{k=1}^5 p_k g_k^{I_g}(X_{g_i}^{C1,C2,C3})} \label{eq:12}
+\end{equation}
+
+\subsection{Getting a false discovery rate (FDR) controlled list of genes or isoforms}
+\label{sec:fdrlist}
+To obtain a list of DE genes with false discovery rate (FDR) controlled
+at $\alpha$ in an experiment comparing two biological conditions, the genes
+with posterior probability of being DE (PPDE) greater than 1 - $\alpha$ should be used.
+For example, the genes with PPDE>=0.95 make up the list of DE genes with target
+FDR controlled at 5\%. With more than two biological conditions, there are multiple
+DE patterns (see Section \ref{sec:multicondmodel}). To obtain a list of genes in a specific DE pattern with target
+FDR $\alpha$, a user should
+take the genes with posterior probability of being in that pattern greater
+than 1 - $\alpha$. Isoform-based lists are obtained in the same way.
+\newpage
+\section{Quick Start}
+\label{sec:quickstart}
+Before analysis can proceed, the EBSeq package must be loaded into the working space:
+<<>>=
+library(EBSeq)
+@
+\subsection{Gene level DE analysis (two conditions)}
+\label{sec:startgenede}
+\subsubsection{Required input}
+\label{sec:startgenedeinput}
+\begin{flushleft}
+{\bf Data}: The object \verb+Data+ should be a $G-by-S$ matrix containing the expression values for each gene and each sample,
+where $G$ is the number of genes and $S$ is the number of samples. These
+values should exhibit raw counts, without normalization
+across samples. Counts of this nature may be obtained from RSEM \cite{Li11b},
+Cufflinks \cite{Trapnell12}, or a similar approach.
+
+\vspace{5 mm}
+
+{\bf Conditions}: The object \verb+Conditions+ should be a Factor vector of length $S$ that indicates to which condition each sample belongs.
+For example, if there are two conditions and three samples in each,
+$S=6$ and \verb+Conditions+ may be given by
+
+\verb+as.factor(c("C1","C1","C1","C2","C2","C2"))+
+
+\end{flushleft}
+\noindent The object \verb+GeneMat+ is a simulated data matrix containing
+1,000 rows of genes and 10 columns of samples. The genes are named
+\verb+Gene_1, Gene_2 ...+
+<<>>=
+data(GeneMat)
+str(GeneMat)
+@
+
+\subsubsection{Library size factor}
+\label{sec:startgenedesize}
+As detailed in Section \ref{sec:model}, EBSeq requires the library size factor $l_s$ for each sample $s$.
+Here, $l_s$ may be obtained via the function \verb+MedianNorm+, which reproduces the median normalization approach
+in DESeq \citep{Anders10}.
+<<>>=
+Sizes=MedianNorm(GeneMat)
+@
+
+\noindent If quantile normalization is preferred, $l_s$ may be obtained via the function \verb+QuantileNorm+.
+(e.g. \verb+QuantileNorm(GeneMat,.75)+ for Upper-Quantile Normalization in \cite{Bullard10})
+
+\subsubsection{Running EBSeq on gene expression estimates}
+\label{sec:startgenederun}
+The function \verb+EBTest+ is used to detect DE genes.
+For gene-level data, we don't need to specify the parameter
+\verb+NgVector+ since there are no differences in $I_g$ structure among the different genes.
+Here, we simulated the first five samples to be in condition 1 and the other five in condition 2, so define:
+
+\verb+Conditions=as.factor(rep(c("C1","C2"),each=5))+
+
+\noindent \verb+sizeFactors+ is used to define the library size factor of each sample.
+It could be obtained by summing up the total number of reads within each sample,
+Median Normalization \citep{Anders10},
+scaling normalization \citep{Robinson10}, Upper-Quantile Normalization \cite{Bullard10},
+or some other such approach.
+These in hand, we run the EM algorithm, setting the number
+of iterations to five via \verb+maxround=5+ for demonstration purposes.
+However, we note that in practice,
+additional iterations are usually required. Convergence should always be
+checked (see Section \ref{sec:detailedgenedeconverge} for details).
+Please note this may take several minutes:
+<<>>=
+EBOut=EBTest(Data=GeneMat,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+@
+\noindent The posterior probabilities of being DE are obtained as follows, where \verb+PP+ is a matrix containing the posterior probabilities of
+being EE or DE for each of the 1,000 simulated genes:
+<<>>=
+PP=GetPPMat(EBOut)
+str(PP)
+head(PP)
+@
+\noindent The matrix \verb+PP+ contains two columns \verb+PPEE+ and \verb+PPDE+,
+corresponding to the posterior probabilities of being EE or DE for each gene.
+\verb+PP+ may be used to form an FDR-controlled list of DE genes with a target FDR of 0.05 as follows:
+<<>>=
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+@
+\noindent EBSeq found 98 DE genes in total with target FDR 0.05.
+
+\subsection{Isoform level DE analysis (two conditions)}
+\label{sec:startisode}
+\subsubsection{Required inputs}
+\label{sec:startisodeinput}
+
+\begin{flushleft}
+{\bf Data}: The object \verb+Data+ should be a $I-by-S$ matrix containing the expression values for each isoform and each sample,
+where $I$ is the number of isoforms and $S$ is the number of sample. As in the gene-level analysis, these values should exhibit raw data, without normalization
+across samples.
+
+\vspace{5 mm}
+
+{\bf Conditions}: The object \verb+Conditions+ should be a vector with length $S$ to indicate the condition of each sample.
+
+\vspace{5 mm}
+
+{\bf IsoformNames}: The object \verb+IsoformNames+ should be a vector with length $I$ to indicate the isoform names.
+
+\vspace{5 mm}
+
+{\bf IsosGeneNames}: The object \verb+IsosGeneNames+ should be a vector with length $I$ to indicate the gene name of each isoform.
+(in the same order as \verb+IsoformNames+.)
+\end{flushleft}
+
+\noindent \verb+IsoList+ contains 1,200 simulated isoforms.
+In which \verb+IsoList$IsoMat+ is a data matrix containing
+1,200 rows of isoforms and 10 columns of samples;
+\verb+IsoList$IsoNames+ contains the isoform names;
+\verb+IsoList$IsosGeneNames+ contains the names of the genes the isoforms belong to.
+
+<<>>=
+data(IsoList)
+str(IsoList)
+IsoMat=IsoList$IsoMat
+str(IsoMat)
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+@
+
+\subsubsection{Library size factor}
+\label{sec:startisodesize}
+Similar to the gene-level analysis presented above, we may obtain the isoform-level
+library size factors via \verb+MedianNorm+:
+<<>>=
+IsoSizes=MedianNorm(IsoMat)
+@
+
+\subsubsection{The $I_g$ vector}
+\label{sec:startisodeNg}
+
+While working on isoform level data, EBSeq fits different prior
+parameters for different uncertainty groups (defined as $I_g$ groups).
+The default setting to define the uncertainty groups consists of using
+the number of isoforms the host gene contains ($N_g$) for each isoform.
+The default settings will provide three uncertainty groups:
+
+$I_g=1$ group: Isoforms with $N_g=1$;
+
+$I_g=2$ group: Isoforms with $N_g=2$;
+
+$I_g=3$ group: Isoforms with $N_g \geq 3$.
+
+The $N_g$ and $I_g$ group assignment can be obtained using the function \verb+GetNg+.
+The required inputs of \verb+GetNg+ are the isoform names (\verb+IsoformNames+) and
+their corresponding gene names (\verb+IsosGeneNames+).
+<<>>=
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+@
+More details could be found in Section \ref{sec:detailedisode}.
+
+\subsubsection{Running EBSeq on isoform expression estimates}
+\label{sec:startisoderun}
+The \verb+EBTest+ function is also used to run EBSeq for two condition comparisons
+on isoform-level data.
+Below we use 5 iterations to demonstrate. However, as
+in the gene level analysis, we advise that additional iterations will likely be
+required in practice (see Section \ref{sec:detailedisodeconverge} for details).
+
+<<>>=
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+str(IsoPP)
+head(IsoPP)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+str(IsoDE)
+@
+\noindent We see that EBSeq found 105 DE isoforms at the target FDR of 0.05.
+
+\subsection{Gene level DE analysis (more than two conditions)}
+\label{sec:startmulticond}
+\noindent The object \verb+MultiGeneMat+ is a matrix containing
+500 simulated genes with 6 samples:
+the first two samples are from condition 1; the second and the third sample are
+from condition 2; the last two samples are from condition 3.
+
+<<>>=
+data(MultiGeneMat)
+str(MultiGeneMat)
+@
+In analysis where the data are spread over more than two conditions,
+the set of possible patterns for each gene is more complicated
+than simply EE and DE. As noted in Section \ref{sec:model}, when we have 3 conditions, there are 5 expression
+patterns to consider. In the simulated data, we have 6 samples, 2 in each of 3 conditions.
+The function \verb+GetPatterns+ allows the user to generate all possible patterns given the conditions. For example:
+
+<<>>=
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+@
+
+\noindent where the first row means all three conditions have the same latent mean expression level;
+the second row means C1 and C2 have the same latent mean expression level but that of C3 is different;
+and the last row corresponds to the case where the three conditions all have different latent mean expression levels.
+The user may use all or only some of these possible patterns as an input to \verb+EBMultiTest+.
+For example, if we were interested in Patterns 1, 2, 4 and 5 only, we'd define:
+<<>>=
+Parti=PosParti[-3,]
+Parti
+@
+
+Moving on to the analysis, \verb+MedianNorm+ or one of its competitors should be used to determine the normalization factors.
+Once this is done, the formal test is performed by \verb+EBMultiTest+.
+<<>>=
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize, maxround=5)
+@
+\noindent The posterior probability of being in each pattern for every gene is obtained by using the
+function \verb+GetMultiPP+:
+<<>>=
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+@
+\noindent where \verb+MultiPP$PP+ provides the posterior probability of being in each pattern for every gene.
+\verb+MultiPP$MAP+ provides the most likely pattern of each gene based on the posterior
+probabilities. \verb+MultiPP$Patterns+ provides the details of the patterns.
+
+
+
+\subsection{Isoform level DE analysis (more than two conditions)}
+\label{sec:startisomulticond}
+\noindent Similar to \verb+IsoList+,
+the object \verb+IsoMultiList+ is an object containing the isoform expression estimates matrix, the isoform
+names, and the gene names of the isoforms' host genes.
+\verb+IsoMultiList$IsoMultiMat+ contains 300 simulated isoforms with 8 samples.
+The first two samples are from condition 1; the second and the third sample are
+from condition 2; the fifth and sixth sample are from condition 3;
+the last two samples are from condition 4.
+Similar to Section \ref{sec:startisode}, the function \verb+MedianNorm+ and \verb+GetNg+ could be used for normalization
+and calculating the $N_g$'s.
+<<>>=
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+@
+Here we have 4 conditions, there are 15 expression
+patterns to consider.
+The function \verb+GetPatterns+ allows the user to generate all possible patterns given the conditions. For example:
+
+<<>>=
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+@
+
+\noindent
+If we were interested in Patterns 1, 2, 3, 8 and 15 only, we'd define:
+<<>>=
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+@
+
+\noindent
+Moving on to the analysis, \verb+EBMultiTest+ could be used to perform the test:
+<<>>=
+IsoMultiOut=EBMultiTest(IsoMultiMat,
+NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond, sizeFactors=IsoMultiSize,
+maxround=5)
+@
+\noindent The posterior probability of being in each pattern for every gene is obtained by using the
+function \verb+GetMultiPP+:
+<<>>=
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+@
+\noindent where \verb+MultiPP$PP+ provides the posterior probability of being in each pattern for every gene.
+\verb+MultiPP$MAP+ provides the most likely pattern of each gene based on the posterior
+probabilities. \verb+MultiPP$Patterns+ provides the details of the patterns.
+
+
+
+\newpage
+\section{More detailed examples}
+\label{sec:detailed}
+\subsection{Gene level DE analysis (two conditions)}
+\label{sec:detailedgenede}
+
+\subsubsection{Running EBSeq on simulated gene expression estimates}
+\label{sec:detailedgenederun}
+EBSeq is applied as described in Section \ref{sec:startgenederun}.
+<<eval=FALSE>>=
+data(GeneMat)
+Sizes=MedianNorm(GeneMat)
+EBOut=EBTest(Data=GeneMat,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=Sizes, maxround=5)
+PP=GetPPMat(EBOut)
+@
+<<>>=
+str(PP)
+head(PP)
+DEfound=rownames(PP)[which(PP[,"PPDE"]>=.95)]
+str(DEfound)
+@
+\noindent EBSeq found 98 DE genes at a target FDR of 0.05.\\
+
+\subsubsection{Calculating FC}
+\label{sec:detailedgenedefc}
+The function \verb+PostFC+ may be used to calculate the Fold Change (FC)
+of the raw data as well as the posterior FC of the normalized data.
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+GeneFC=PostFC(EBOut)
+str(GeneFC)
+PlotPostVsRawFC(EBOut,GeneFC)
+@
+\caption{
+FC vs. Posterior FC for 1,000 gene expression estimates}
+\label{fig:GeneFC}
+\end{figure}
+Figure \ref{fig:GeneFC} shows the FC vs. Posterior FC on 1,000 gene expression estimates.
+The genes are ranked by their cross-condition mean (adjusted by the normalization factors).
+The posterior FC tends to shrink genes with low expressions (small rank); in this case the differences
+are minor.
+
+
+\newpage
+
+\subsubsection{Checking convergence}
+\label{sec:detailedgenedeconverge}
+As detailed in Section \ref{sec:model}, we assume the prior distribution of $q_g^C$ is
+$Beta(\alpha,\beta)$. The EM algorithm is used to estimate the
+hyper-parameters $\alpha,\beta$ and the mixture parameter $p$.
+The optimized parameters at each iteration may be obtained as follows (recall
+we are using 5 iterations for demonstration purposes):
+<<>>=
+EBOut$Alpha
+EBOut$Beta
+EBOut$P
+@
+In this case the differences between the 4th and 5th iterations are always less
+than 0.01.
+
+
+\subsubsection{Checking the model fit and other diagnostics}
+\label{sec:detailedgenedeplot}
+As noted in Leng {\it et al.}, 2013 \cite{Leng13}, EBSeq relies on parametric assumptions that should
+be checked following each analysis.
+The \verb+QQP+ function may be used to assess prior assumptions.
+In practice, \verb+QQP+ generates the Q-Q plot of the empirical $q$'s
+vs. the simulated $q$'s from the Beta prior distribution with
+estimated hyper-parameters. Figure \ref{fig:GeneQQ} shows that the
+data points lie on the $y=x$ line for both conditions, which indicates
+that the Beta prior is appropriate.
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(1,2))
+QQP(EBOut)
+@
+\caption{QQ-plots for checking the assumption of a Beta prior (upper panels) as well as the
+model fit using data from condition 1 and condition 2 (lower panels)}
+\label{fig:GeneQQ}
+\end{figure}
+
+\newpage
+\noindent
+Likewise, the \verb+DenNHist+ function may be used to check the density plot of empirical $q$'s vs the simulated
+$q$'s from the fitted Beta prior distribution.
+Figure \ref{fig:GeneDenNHist} also shows our estimated distribution fits the
+data very well.
+
+\begin{figure}[h!]
+\centering
+<<fig=T>>=
+par(mfrow=c(1,2))
+DenNHist(EBOut)
+@
+\caption{Density plots for checking the model fit using data from condition 1 and condition 2}
+\label{fig:GeneDenNHist}
+\end{figure}
+
+\newpage
+\subsection{Isoform level DE analysis (two conditions)}
+\label{sec:detailedisode}
+\subsubsection{The $I_g$ vector}
+\label{sec:detailedisodeNg}
+Since EBSeq fits rely on $I_g$,
+we need to obtain the $I_g$ for each isoform. This can be done using the
+function \verb+GetNg+.
+The required inputs of \verb+GetNg+ are the isoform names (\verb+IsoformNames+) and
+their corresponding gene names (\verb+IsosGeneNames+), described above.
+In the simulated data, we assume that the isoforms in the $I_g=1$ group belong to genes \verb+Gene_1, ... , Gene_200+;
+The isoforms in the $I_g=2$ group belong to genes
+\verb+Gene_201, ..., Gene_400+; and isoforms in the $I_g=3$ group
+belong to \verb+Gene_401, ..., Gene_600+.
+
+<<eval=FALSE>>=
+data(IsoList)
+IsoMat=IsoList$IsoMat
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+NgList=GetNg(IsoNames, IsosGeneNames, TrunThre=3)
+@
+<<>>=
+names(NgList)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoNgTrun[c(1:3,201:203,601:603)]
+@
+
+The output of \verb+GetNg+ contains 4 vectors. \verb+GeneNg+ (\verb+IsoformNg+) provides
+the number of isoforms $N_g$ within each gene (within each isoform's host gene).
+\verb+GeneNgTrun+ (\verb+IsoformNgTrun+) provides the $I_g$ group assignments.
+The default number of groups is 3, which means the isoforms
+with $N_g$ greater than 3 will be assigned to $I_g=3$ group.
+We use 3 in the case studies
+since the number of isoforms with $N_g$ larger than 3 is relatively small and
+the small sample size may induce poor parameter fitting if we treat them
+as separate groups.
+In practice, if there is evidence that the $N_g=4,5,6...$ groups should be
+treated as separate groups, a user can change \verb+TrunThre+ to define
+a different truncation threshold.
+
+\subsubsection{Using mappability ambiguity clusters instead of
+the $I_g$ vector when the gene-isoform relationship is unknown}
+\label{sec:detailedisodeNoNg}
+When working with a de-novo assembled transcriptome, in which case the gene-isoform
+relationship is unknown,
+a user can use read mapping ambiguity cluster information instead of Ng,
+as provided by RSEM \cite{Li11b} in the
+output file \verb+output_name.ngvec+. The file contains a vector with the same
+length as the total number of transcripts.
+Each transcript has been assigned to one of 3 levels
+(1, 2, or 3) to indicate the mapping uncertainty level of that transcript.
+The mapping ambiguity clusters are partitioned via a k-means algorithm on the unmapability
+scores that are provided by RSEM. A user can read in the mapping ambiguity cluster information
+using:
+
+<<eval=FALSE>>=
+IsoNgTrun = scan(file="output_name.ngvec", what=0, sep="\n")
+@\\
+Where \verb+"output_name.ngvec"+ is the output file obtained from RSEM function rsem-generate-ngvector.
+More details on using the RSEM-EBSeq pipeline
+on de novo assembled transcriptomes can be found
+at \url{http://deweylab.biostat.wisc.edu/rsem/README.html#de}.
+
+Other unmappability scores and other cluster methods (e.g. Gaussian Mixed Model)
+could also be used to form the uncertainty clusters.
+
+\subsubsection{Running EBSeq on simulated isoform expression estimates}
+\label{sec:detailedisoderun}
+EBSeq can be applied as described in Section \ref{sec:startisoderun}.
+<<eval=FALSE>>=
+IsoSizes=MedianNorm(IsoMat)
+IsoEBOut=EBTest(Data=IsoMat, NgVector=IsoNgTrun,
+Conditions=as.factor(rep(c("C1","C2"),each=5)),sizeFactors=IsoSizes, maxround=5)
+IsoPP=GetPPMat(IsoEBOut)
+IsoDE=rownames(IsoPP)[which(IsoPP[,"PPDE"]>=.95)]
+@
+<<>>=
+str(IsoDE)
+@
+\noindent We see that EBSeq found 105 DE isoforms at a target FDR of 0.05.
+The function \verb+PostFC+ could also be used here to calculate the Fold Change (FC)
+as well as the posterior FC on the normalization factor adjusted data.
+<<>>=
+IsoFC=PostFC(IsoEBOut)
+str(IsoFC)
+@
+
+
+\subsubsection{Checking convergence}
+\label{sec:detailedisodeconverge}
+For isoform level data, we assume the prior distribution of $q_{gi}^C$ is
+$Beta(\alpha,\beta^{I_g})$.
+As in Section \ref{sec:detailedgenedeconverge}, the optimized parameters at each iteration
+may be obtained as follows (recall
+we are using 5 iterations for demonstration purposes):
+<<>>=
+IsoEBOut$Alpha
+IsoEBOut$Beta
+IsoEBOut$P
+@
+Here we have 3 $\beta$'s in each iteration corresponding to
+$\beta^{I_g=1},\beta^{I_g=2},\beta^{I_g=3}$.
+We see that parameters are changing less than $10^{-2}$ or $10^{-3}$.
+In practice, we require changes less than $10^{-3}$ to declare convergence.
+
+\subsubsection{Checking the model fit and other diagnostics}
+\label{sec:detailedisodeplot}
+In Leng {\it et al.}, 2013\citep{Leng13}, we showed the mean-variance differences across different
+isoform groups on multiple data sets.
+In practice, if it is of interest to check differences among
+isoform groups defined by truncated $I_g$ (such as those shown here
+in Figure 1), the function \verb+PolyFitPlot+ may be used.
+The following code generates the three
+panels shown in Figure \ref{fig:IsoSimuNgEach}
+(if condition 2 is of interest, a user could change each \verb+C1+ to \verb+C2+.):
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,2))
+PolyFitValue=vector("list",3)
+for(i in 1:3)
+ PolyFitValue[[i]]=PolyFitPlot(IsoEBOut$C1Mean[[i]],
+ IsoEBOut$C1EstVar[[i]],5)
+@
+\caption{ The mean-variance fitting plot for each Ng group}
+\label{fig:IsoSimuNgEach}
+\end{figure}
+
+\newpage
+Superimposing all $I_g$ groups using the code below will generate the figure (shown
+here in Figure \ref{fig:IsoSimuNg}), which is similar in structure to Figure 1:
+
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+PolyAll=PolyFitPlot(unlist(IsoEBOut$C1Mean), unlist(IsoEBOut$C1EstVar),5)
+lines(log10(IsoEBOut$C1Mean[[1]][PolyFitValue[[1]]$sort]),
+PolyFitValue[[1]]$fit[PolyFitValue[[1]]$sort],col="yellow",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[2]][PolyFitValue[[2]]$sort]),
+PolyFitValue[[2]]$fit[PolyFitValue[[2]]$sort],col="pink",lwd=2)
+lines(log10(IsoEBOut$C1Mean[[3]][PolyFitValue[[3]]$sort]),
+PolyFitValue[[3]]$fit[PolyFitValue[[3]]$sort],col="green",lwd=2)
+legend("topleft",c("All Isoforms","Ng = 1","Ng = 2","Ng = 3"),
+col=c("red","yellow","pink","green"),lty=1,lwd=3,box.lwd=2)
+@
+\caption{The mean-variance plot for each Ng group}
+\label{fig:IsoSimuNg}
+\end{figure}
+
+
+\newpage
+\noindent To generate a QQ-plot of the fitted Beta prior distribution
+and the $\hat{q}^C$'s within condition, a user may
+use the following code to generate 6 panels (as shown in Figure \ref{fig:IsoQQ}).
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,3))
+QQP(IsoEBOut)
+@
+\caption{ QQ-plots of the fitted prior distributions within each condition and each Ig group}
+\label{fig:IsoQQ}
+\end{figure}
+
+\newpage
+\noindent And in order to produce the plot of the fitted Beta prior densities
+and the histograms of $\hat{q}^C$'s within each condition,
+the following may be used (it generates Figure \ref{fig:IsoDenNHist}):
+\begin{figure}[h]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,3))
+DenNHist(IsoEBOut)
+@
+\caption{ Prior distribution fit within each condition and each Ig group.
+(Note only a small set of isoforms are considered here for demonstration.
+Better fitting should be expected while using full set of isoforms.)}
+\label{fig:IsoDenNHist}
+\end{figure}
+
+\clearpage
+\subsection{Gene level DE analysis (more than two conditions)}
+\label{sec:detailedmulticond}
+As described in Section \ref{sec:startmulticond},
+the function \verb+GetPatterns+ allows the user to generate all possible patterns given the conditions.
+To visualize the patterns, the function \verb+PlotPattern+ may be used.
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+Conditions=c("C1","C1","C2","C2","C3","C3")
+PosParti=GetPatterns(Conditions)
+PosParti
+PlotPattern(PosParti)
+@
+\caption{ All possible patterns}
+\label{fig:Patterns}
+\end{figure}
+\newpage
+\noindent If we were interested in Patterns 1, 2, 4 and 5 only, we'd define:
+<<>>=
+Parti=PosParti[-3,]
+Parti
+@
+
+\noindent
+Moving on to the analysis, \verb+MedianNorm+ or one of its competitors should be used to determine the normalization factors.
+Once this is done, the formal test is performed by \verb+EBMultiTest+.
+<<eval=FALSE>>=
+data(MultiGeneMat)
+MultiSize=MedianNorm(MultiGeneMat)
+MultiOut=EBMultiTest(MultiGeneMat,
+NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize,
+maxround=5)
+@
+\noindent The posterior probability of being in each pattern for every gene is obtained using the
+function \verb+GetMultiPP+:
+<<>>=
+MultiPP=GetMultiPP(MultiOut)
+names(MultiPP)
+MultiPP$PP[1:10,]
+MultiPP$MAP[1:10]
+MultiPP$Patterns
+@
+\noindent where \verb+MultiPP$PP+ provides the posterior probability of being in each pattern for every gene.
+\verb+MultiPP$MAP+ provides the most likely pattern of each gene based on the posterior
+probabilities. \verb+MultiPP$Patterns+ provides the details of the patterns. The FC and posterior FC for multiple condition data can
+be obtained by the function \verb+GetMultiFC+:
+
+<<>>=
+MultiFC=GetMultiFC(MultiOut)
+str(MultiFC)
+@
+
+\noindent To generate a QQ-plot of the fitted Beta prior distribution
+and the $\hat{q}^C$'s within condition, a user could also use function
+\verb+DenNHist+ and \verb+QQP+.
+
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,2))
+QQP(MultiOut)
+@
+\caption{ QQ-plots of the fitted prior distributions within each condition and each Ig group}
+\label{fig:GeneMultiQQ}
+\end{figure}
+
+\begin{figure}[h]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(2,2))
+DenNHist(MultiOut)
+@
+\caption{ Prior distributions fit within each condition.
+(Note only a small set of genes are considered here for demonstration.
+Better fitting should be expected while using full set of genes.)}
+\label{fig:GeneMultiDenNHist}
+\end{figure}
+\newpage
+\clearpage
+\newpage
+\subsection{Isoform level DE analysis (more than two conditions)}
+\label{sec:detailedisomulticond}
+Similar to Section \ref{sec:startmulticond},
+the function \verb+GetPatterns+ allows a user to generate all possible patterns given the conditions.
+To visualize the patterns, the function \verb+PlotPattern+ may be used.
+<<>>=
+Conditions=c("C1","C1","C2","C2","C3","C3","C4","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+@
+\newpage
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+PlotPattern(PosParti.4Cond)
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+@
+\caption{All possible patterns for 4 conditions}
+\label{fig:Patterns4Cond}
+\end{figure}
+
+\newpage
+<<eval=FALSE>>=
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiSize=MedianNorm(IsoMultiMat)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+IsoMultiOut=EBMultiTest(IsoMultiMat,NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond,
+sizeFactors=IsoMultiSize, maxround=5)
+IsoMultiPP=GetMultiPP(IsoMultiOut)
+@
+<<>>=
+names(MultiPP)
+IsoMultiPP$PP[1:10,]
+IsoMultiPP$MAP[1:10]
+IsoMultiPP$Patterns
+IsoMultiFC=GetMultiFC(IsoMultiOut)
+@
+The FC and posterior FC for multiple condition data can be obtained by the function \verb+GetMultiFC+:
+
+
+\noindent To generate a QQ-plot of the fitted Beta prior distribution
+and the $\hat{q}^C$'s within condition, a user could also use the functions
+\verb+DenNHist+ and \verb+QQP+.
+\newpage
+\begin{figure}[h!]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(3,4))
+QQP(IsoMultiOut)
+
+@
+\caption{ QQ-plots of the fitted prior distributions within each condition and Ig group.
+(Note only a small set of isoforms are considered here for demonstration.
+Better fitting should be expected while using full set of isoforms.)}
+\label{fig:IsoMultiQQ}
+\end{figure}
+
+\begin{figure}[h]
+\centering
+<<fig=TRUE>>=
+par(mfrow=c(3,4))
+DenNHist(IsoMultiOut)
+@
+\caption{ Prior distributions fit within each condition and Ig group.
+(Note only a small set of isoforms are considered here for demonstration.
+Better fitting should be expected while using full set of isoforms.)}
+\label{fig:IsoMultiDenNHist}
+\end{figure}
+\clearpage
+\newpage
+
+
+\newpage
+\subsection{Working without replicates}
+When replicates are not available, it is difficult to estimate the transcript specific variance.
+In this case, EBSeq estimates the variance by pooling similar genes together.
+Specifically, we take genes with FC in the 25\% - 75\% quantile of all FC's as
+candidate genes. By defining \verb+NumBin = 1000+ (default in \verb+EBTest+), EBSeq
+will group genes with similar means into 1,000 bins.
+For each candidate gene, we use the across-condition variance estimate as its variance estimate.
+For each bin, the bin-wise variance estimation is taken to be the median of the
+across-condition variance estimates of the candidate genes within that bin.
+For each non-candidate gene, we use the bin-wise variance estimate of the host bin (the bin containing this gene)
+as its variance estimate.
+This approach works well when there are no more than 50\% DE genes in the data set.
+
+\subsubsection{Gene counts with two conditions}
+\label{sec:norepgenede}
+
+To generate a data set with no replicates, we take the first sample of each condition.
+For example, using the data from Section \ref{sec:detailedgenede}, we take sample 1 from condition 1 and
+sample 6 from condition 2. Functions \verb+MedianNorm+, \verb+GetPPMat+ and
+\verb+PostFC+ may be used on data without replicates.
+<<>>=
+data(GeneMat)
+GeneMat.norep=GeneMat[,c(1,6)]
+Sizes.norep=MedianNorm(GeneMat.norep)
+EBOut.norep=EBTest(Data=GeneMat.norep,
+Conditions=as.factor(rep(c("C1","C2"))),
+sizeFactors=Sizes.norep, maxround=5)
+PP.norep=GetPPMat(EBOut.norep)
+DEfound.norep=rownames(PP.norep)[which(PP.norep[,"PPDE"]>=.95)]
+GeneFC.norep=PostFC(EBOut.norep)
+@
+
+\subsubsection{Isoform counts with two conditions}
+\label{norepisode}
+To generate an isoform level data set with no replicates, we
+also take sample 1 and sample 6 in the data we used in Section
+\ref{sec:detailedisode}.
+Example codes are shown below.
+
+<<>>=
+data(IsoList)
+IsoMat=IsoList$IsoMat
+IsoNames=IsoList$IsoNames
+IsosGeneNames=IsoList$IsosGeneNames
+NgList=GetNg(IsoNames, IsosGeneNames)
+IsoNgTrun=NgList$IsoformNgTrun
+IsoMat.norep=IsoMat[,c(1,6)]
+IsoSizes.norep=MedianNorm(IsoMat.norep)
+IsoEBOut.norep=EBTest(Data=IsoMat.norep, NgVector=IsoNgTrun,
+Conditions=as.factor(c("C1","C2")),
+sizeFactors=IsoSizes.norep, maxround=5)
+IsoPP.norep=GetPPMat(IsoEBOut.norep)
+IsoDE.norep=rownames(IsoPP.norep)[which(IsoPP.norep[,"PPDE"]>=.95)]
+IsoFC.norep=PostFC(IsoEBOut.norep)
+@
+
+\subsubsection{Gene counts with more than two conditions}
+\label{norepisode}
+To generate a data set with multiple conditions and no replicates,
+we take the first sample from each condition (sample 1, 3 and 5) in the data we used
+in Section \ref{sec:detailedmulticond}.
+Example codes are shown below.
+<<>>=
+data(MultiGeneMat)
+MultiGeneMat.norep=MultiGeneMat[,c(1,3,5)]
+Conditions=c("C1","C2","C3")
+PosParti=GetPatterns(Conditions)
+Parti=PosParti[-3,]
+MultiSize.norep=MedianNorm(MultiGeneMat.norep)
+MultiOut.norep=EBMultiTest(MultiGeneMat.norep,
+NgVector=NULL,Conditions=Conditions,
+AllParti=Parti, sizeFactors=MultiSize.norep,
+maxround=5)
+MultiPP.norep=GetMultiPP(MultiOut.norep)
+MultiFC.norep=GetMultiFC(MultiOut.norep)
+@
+
+\subsubsection{Isoform counts with more than two conditions}
+\label{sec:norepmulticond}
+To generate an isoform level data set with multiple conditions and no replicates,
+we take the first sample from each condition (sample 1, 3, 5 and 7) in the data we used
+in Section \ref{sec:detailedisomulticond}.
+Example codes are shown below.
+
+
+
+<<>>=
+data(IsoMultiList)
+IsoMultiMat=IsoMultiList[[1]]
+IsoNames.Multi=IsoMultiList$IsoNames
+IsosGeneNames.Multi=IsoMultiList$IsosGeneNames
+IsoMultiMat.norep=IsoMultiMat[,c(1,3,5,7)]
+IsoMultiSize.norep=MedianNorm(IsoMultiMat.norep)
+NgList.Multi=GetNg(IsoNames.Multi, IsosGeneNames.Multi)
+IsoNgTrun.Multi=NgList.Multi$IsoformNgTrun
+Conditions=c("C1","C2","C3","C4")
+PosParti.4Cond=GetPatterns(Conditions)
+PosParti.4Cond
+Parti.4Cond=PosParti.4Cond[c(1,2,3,8,15),]
+Parti.4Cond
+IsoMultiOut.norep=EBMultiTest(IsoMultiMat.norep,
+NgVector=IsoNgTrun.Multi,Conditions=Conditions,
+AllParti=Parti.4Cond, sizeFactors=IsoMultiSize.norep,
+maxround=5)
+IsoMultiPP.norep=GetMultiPP(IsoMultiOut.norep)
+IsoMultiFC.norep=GetMultiFC(IsoMultiOut.norep)
+@
+
+\section{EBSeq pipelines and extensions}
+\subsection{RSEM-EBSeq pipeline: from raw reads to differential expression analysis results}
+EBSeq is coupled with RSEM \cite{Li11b} as an RSEM-EBSeq pipeline which provides
+quantification and DE testing on both gene and isoform levels.
+
+For more details, see
+\url{http://deweylab.biostat.wisc.edu/rsem/README.html#de}
+
+\subsection{EBSeq interface: A user-friendly graphical interface for differetial expression analysis}
+EBSeq interface provides a graphical interface implementation for users who are not familiar with the R
+programming language. It takes .xls, .xlsx and .csv files as input.
+Additional packages need be downloaded; they may be found at
+\url{http://www.biostat.wisc.edu/~ningleng/EBSeq_Package/EBSeq_Interface/}
+
+\subsection{EBSeq Galaxy tool shed}
+EBSeq tool shed contains EBSeq wrappers for a local Galaxy implementation.
+For more details, see
+\url{http://www.biostat.wisc.edu/~ningleng/EBSeq_Package/EBSeq_Galaxy_toolshed/}
+
+\section{Acknowledgment}
+We would like to thank Haolin Xu for checking the package and
+proofreading the vignette.
+
+\section{News}
+2014-1-30: In EBSeq 1.3.3, the default setting of EBTest function will remove
+low expressed genes (genes whose 75th quantile of normalized counts is less
+than 10) before identifying DE genes.
+These two thresholds can be changed in EBTest function.
+We found that low expressed genes are more easily to be affected by noises.
+Removing these genes prior to downstream analyses can improve the
+model fitting and reduce impacts of noisy genes (e.g. genes with outliers).
+
+2014-5-22: In EBSeq 1.5.2, numerical approximations are implemented to deal with
+underflow. The underflow is likely due to large number of samples.
+\pagebreak
+\bibliographystyle{plain}
+\bibliography{lengetal}
+
+\end{document}
+
diff --git a/vignettes/PlotExample.png b/vignettes/PlotExample.png
new file mode 100644
index 0000000..71a697a
Binary files /dev/null and b/vignettes/PlotExample.png differ
diff --git a/vignettes/lengetal.bib b/vignettes/lengetal.bib
new file mode 100755
index 0000000..44cda6a
--- /dev/null
+++ b/vignettes/lengetal.bib
@@ -0,0 +1,1342 @@
+ at manual{Rpackage,
+ author = "{R Development Core Team}",
+ title = "R: A language and environment for statistical computing",
+ organization = "R Foundation for Statistical Computing",
+ address = "Vienna, Austria",
+ year = "2009",
+}
+
+
+ at article{Newton01,
+author="M A Newton and Kendziorski, C M and Richmond, C S and Blattner, F R",
+title="On differential variability of expression ratios: Improved statistical inference
+about gene expression changes from microarray data",
+journal="Journal of Computational Biology",
+volume="8",
+pages="37--52",
+year="2001",
+}
+
+
+ at article{Wang09,
+author="Wang, Z and Gerstein M and Snyder M",
+title="RNA-Seq: a revolutionary tool for transcriptomics",
+journal="Nature Reviews Genetics",
+volume="10",
+pages="57--63",
+year="2009",
+}
+
+ at article{Bullard10,
+author="Bullard, J H and Purdom, E A and Hansen, K D and Dudoit, S",
+title="Evaluation of Statistical Methods for Normalization and Differential Expression in mRNA-Seq Experiments",
+journal="BMC Bioinformatics",
+volume="11",
+pages="94",
+year="2010",
+}
+
+ at article{Hansen10,
+author="Hansen, K D and Brenner, S E and Dudoit, S",
+title="Biases in Illumina transcriptome sequencing caused by random hexamer priming",
+journal="Nucleic Acids Research",
+volume="38(12)",
+pages="e131",
+year="2010",
+}
+
+ at article{Wang08,
+author="Wang, E T and Sandberg, R and Luo, S and Khrebtukova, I and Zhang, L and Mayr, C and Kingsmore, S F and Schroth, G P and Burge, C B",
+title="Alternative isoform regulation in human tissue transcriptomes",
+journal="Nature",
+volume="456",
+pages="470--476",
+year="2008",
+}
+
+ at article{Oshlack09,
+author="Oshlack, A and Wakefield M",
+title="Transcript length bias in RNA-seq data confounds systems biology",
+journal="Biology Direct",
+volume="4",
+pages="14",
+year="2009",
+}
+
+
+ at article{Robinson10,
+author="Robinson, M D and Oshlack, A",
+title="A scaling normalization method for differential expression analysis of RNA-seq data",
+journal="Genome Biology",
+volume="11",
+pages="R25",
+year="2010",
+}
+
+ at article{Trapnell09,
+author="Trapnell, C and Pachter, L and Salzberg, S L",
+title="TopHat: discovering splice junctions with RNA-Seq",
+journal="Bioinformatics",
+volume="25(9)",
+pages="1105--1111",
+year="2009",
+}
+
+
+ at article{Mortazavi08,
+author="Mortazavi, A and Williams, B A and McCue, K and Schaeffer, L and Wold, B",
+title="Mapping and quantifying mammalian transcriptomes by RNA-Seq",
+journal="Nature Methods",
+volume="5(1)",
+pages="621--628",
+year="2008",
+}
+
+
+ at article{Trapnell10,
+author="Trapnell, C and Williams, B A and Pertea, G and Mortazavi, A and Kwan, G and van Baren, M J and Salzberg, S L and Wold, B J and Pachter, L",
+title="Transcript assembly and quantification by RNA-Seq reveals unannotated transcripts and isoform switching during cell differentiation.",
+journal="Nat Biotechnol",
+volume="28(5)",
+pages="211--215",
+year="2010",
+}
+
+ at article{Pepke09,
+author="Pepke, S and Wold, B and Mortaazavi, A",
+title="Computation for ChIP-seq and RNA-seq studies",
+journal="Nat Methods",
+volume="6(11 Suppl)",
+pages="S22--32",
+year="2009",
+}
+
+
+ at article{Langmean10,
+author="Langmead, B and Trapnell, C and Pop, M and Salzberg, S L",
+title="Ultrafast and memory-efficient alignment of short DNA sequences to the human genome",
+journal="Genome Biology",
+pages="R25",
+year="2010",
+}
+
+ at article{Bloom09,
+author="Bloom, J S and Khan, Z and Kruglyak, L and Singh, M and Caudy, A A",
+title="Measuring differential gene expression by short read sequencing: quantitative
+ comparison to 2-channel gene expression microarrays",
+journal="BMC Genomics",
+volume="10",
+pages="221",
+year="2009",
+}
+
+ at article{Wang10,
+author="Wang, L and Feng, Z and Wang, X and Wang, X and Zhang, X",
+title="DEGseq: an R package for identifying differentially expressed genes from RNA-seq data",
+journal="Bioinformatics",
+volume="26",
+pages="136--138",
+year="2010",
+}
+
+ at article{Feng08,
+author="Feng, W and Liu, Y and Wu, J and Nephew, K P and Huang, T H M and Li, L",
+title="A Poisson mixture model to identify changes in RNA polymerase II binding quantity
+ using high-throughput sequencing technology",
+journal="BMC Genomics",
+volume="9(Supl 2)",
+pages="S23",
+year="2008",
+}
+
+
+ at article{Marioni08,
+author="Marioni, J C and Mason, C E and Mane, S M and Stephens, M and Gilad, Y",
+title="RNA-seq: An assessment of technical reproducibility and comparison with gene
+ expression arrays",
+journal="Genome Research",
+volume="18",
+pages="1509--1517",
+year="2008",
+}
+
+
+
+ at article{Nagalakshmi08,
+author="Nagalakshmi, U and Wang, Z and Waern, K and Shou, C and Raha, D and Gerstein, M",
+title="The Transcriptional Landscape of the Yeast Genome Defined by RNA Sequencing",
+journal="Science",
+volume="320(5881)",
+pages="1344--1349",
+year="2008",
+}
+
+
+ at article{Lu05,
+author="Lu, J and Tomfohr, J K and Kepler, T B",
+title="Identifying differential expression in multiple SAGE libraries: an overdispersed
+ log-linear model approach",
+journal="BMC Bioinformatics",
+volume="6",
+pages="165",
+year="2005",
+}
+
+
+ at article{Robinson08,
+author="Robinson, M D and Smyth, G K",
+title="Small-sample estimation of negative binomial dispersion, with applications to SAGE
+ data",
+journal="Biostatistics",
+volume="9",
+pages="321--332",
+year="2008",
+}
+
+ at article{Anders10,
+author="Anders, S and Huber, W",
+title="Differential expression analysis for sequence count data",
+journal="Genome Biology",
+volume="11",
+pages="R106",
+year="2010",
+}
+
+
+ at article{Zheng09,
+author="Zheng, S and Chen, L",
+title="A hierarchical Bayesian model for comparing transcriptomes at the individual
+ transcript isoform level",
+journal="Nucleic Acids Research",
+pages="1--16",
+year="2009",
+}
+
+
+ at article{Howard10,
+author="Howard, B E and Heber, S",
+title="Towards reliable isoform quantification using RNA-SEQ data",
+journal="BMC Bioinformatics",
+volume="11(Suppl 3)",
+pages="S6",
+year="2010",
+}
+
+ at article{Wang10b,
+author="Wang, X and Wu, Z and Zhang, X",
+title="Isoform abundance inference provides a more accurate estimation of gene expression levels in RNA-seq",
+journal="Journal of Bioinformatics and Computational Biology",
+volume="8(Suppl 1)",
+pages="177--192",
+year="2010",
+}
+
+ at article{Richard10,
+author="Richard, H and Schulz, M H and Sultan, M and Nürnberger, A and Schrinner, S and Balzereit, D and Dagand, E and Rasche, A and Lehrach, H and Vingron, M and Haas, S A and Yaspo, M L",
+title="Prediction of alternative isoforms from exon expression levels in RNA-Seq experiments",
+journal="Nucleic Acids Research",
+volume="38(10)",
+pages="e112",
+year="2010",
+}
+
+
+ at article{Datta10,
+author="Datta, S and Datta, S and Kim, S and Chakraborty, S and Gill, R S",
+title="Statistical Analyses of Next Generation Sequence Data: A Partial Overview ",
+journal="Journal of Proteomcs and Bioinformatics",
+volume="3(6)",
+pages="183--190",
+year="2010",
+}
+
+
+ at article{Lee10,
+author="Lee, S and Seo, C H and Lim, B and Yang, J O and Oh, J and Kim, M and Lee, S and Lee, B and Kang, C and Lee, S",
+title="Accurate quantification of transcriptome from RNA-Seq data by effective length
+ normalization",
+journal="Nucleic Acids Research",
+volume="39(2)",
+pages="e9",
+year="2010",
+}
+
+
+ at article{Srivastava10,
+author="Srivastava, S and Chen, L",
+title="A two-parameter generalized Poisson model to improve the analysis of RNA-seq data",
+journal="Nucleic Acids Research",
+volume="38(17)",
+pages="e170",
+year="2010",
+}
+
+
+ at article{Hiller09,
+author="Hiller, D and Jiang, H and Wu, W and Wong, W H",
+title="Identifiability of isoform deconvolution from junction arrays and RNA-Seq",
+journal="Bioinformatics",
+volume="25(23)",
+pages="3056--3059",
+year="2009",
+}
+
+
+ at article{Wegmann08,
+author="Wegmann, D and Dupanloup, I and Excoffier, L",
+title="Width of gene expression profile drives alternative splicing",
+journal="PLos one",
+volume="3(10)",
+pages="e3587",
+year="2008",
+}
+
+
+ at article{Li11,
+author="Li, Y and Terrel, A and Patel, J M",
+title="WHAM: A High-throughput Sequence Alignment Method",
+journal="ACM SIGMOD",
+volume="",
+pages="",
+year="2011",
+}
+
+
+ at article{Robinson07,
+author="Robinson, M D and Smyth, G K",
+title="Moderated statistical tests for assessing differences in tag abundance",
+journal="Bioinformatics",
+volume="23(21)",
+pages="2881--2887",
+year="2007",
+}
+
+
+ at article{Robinson10b,
+ author="Robinson, M D and McCarthy, D J and Smyth, G K",
+ title="edgeR: a Bioconductor package for differential expression analysis of digital gene expression data.",
+ journal="Bioinformatics",
+ volume="26(1)",
+ pages="139-40",
+ year="2010",
+}
+
+
+
+ at article{Hardcastle10,
+author="Hardcastle, T J and Kelly, K A",
+title="baySeq: empirical Bayesian methods for identifying differential expression in sequence count data",
+journal="BMC Bioinformatics",
+volume="11",
+pages="422",
+year="2010",
+}
+
+
+
+ at article{Gao11,
+author="Gao, L and Fang, Z and Zhang, K and Zhi, D and Cui, X",
+title="Length bias correction for RNA-seq data in gene set analyses",
+journal="Bioinformatics",
+volume="27(5)",
+pages="662--669",
+year="2011",
+}
+
+
+
+ at article{Jiang09,
+author="Jiang, H and Wing, W H",
+title="Statistical inferences for isoform expression in RNA-Seq",
+journal="Bioinformatics",
+volume="25(8)",
+pages="1026--1032",
+year="2009",
+}
+
+
+
+ at article{Li10,
+author="Li, B and Ruotti, V and Stewart, R M and Thomson, J A and Dewey, C N",
+title="RNA-Seq gene expression estimation with read mapping uncertainty",
+journal="Bioinformatics",
+volume="26(4)",
+pages="493--500",
+year="2010",
+}
+
+
+
+ at article{Ozsolak11,
+author="Ozsolak, F and Milos, P M",
+title="RNA sequencing: advances, challenges and opportunities",
+journal="Nature Reviews Genetics",
+volume="12",
+pages="87--98",
+year="2011",
+}
+
+
+
+ at article{Gao10,
+author="Gao, D and Kim, J and Kim, H and Phang, T L and Selby, H and Tan, A C and Tong, T",
+title="A survey of statistical software for analysing RNA-seq data",
+journal="Human Genomics",
+volume="5(1)",
+pages="56--60",
+year="2010",
+}
+
+
+
+ at article{Haas10,
+author="Haas, B J and Zody, M C",
+title="Advancing RNA-Seq analysis",
+journal="Nature Biotechnology",
+volume="28",
+pages="421--423",
+year="2010",
+}
+
+
+
+ at article{Salzberg10,
+author="Salzberg, S L",
+title="Recent advances in RNA sequence analysis",
+journal="F1000 Biology Reports",
+volume="2",
+pages="64",
+year="2010",
+}
+
+ at article{Turro09,
+author="Turro, E and Lewin, A and Rose, A and Dallman, M J and Richardson, S",
+title="MMBGX: a method for estimating expression at the isoform level and detecting
+ differential splicing using whole-transcript Affymetrix arrays",
+journal="Nucleic Acids Research",
+volume="38(1)",
+pages="e4",
+year="2009",
+}
+
+ at article{Bemmo08,
+author="Bemmo, A and Benovoy, D and Kwan, T and Gaffney, D J and Jensen, R V and Majewski, Jacek",
+title="Gene Expression and Isoform Variation Analysis using Affymetrix Exon Arrays",
+journal="BMC Genomics",
+volume="9",
+pages="529",
+year="2008",
+}
+
+ at article{Xing08,
+author="Xing, Y and Stoilov, P and Kapur, K and Han, A and Jiang, H and Shen, S and Black, D L and Wong, W H",
+title="MADS: a new and improved method for analysis of differential alternative splicing by
+ exon-tiling microarrays",
+journal="RNA",
+volume="14(8)",
+pages="1470--1479",
+year="2008",
+}
+
+
+ at article{Anton08,
+author="Anton, M A and Gorostiaga, D and Guruceaga, E and Segura, V and Carmona-Saez, P and Pascual-Montano, A and Pio, R and Montuenga, L M and Rubio, A",
+title="SPACE: an algorithm to predict and quantify alternatively spliced isoforms using microarrays",
+journal="Genome Biology",
+volume="9",
+pages="R46",
+year="2008",
+}
+
+
+ at article{Liu10,
+author="Liu, S and Lin, L and Wang, D and Xing, Y ",
+title="A comparison of RNA-Seq and high-density exon array for detecting differential
+ gene expression between closely related species",
+journal="Nucleic Acids Research",
+volume="39(2)",
+pages="578--588",
+year="2010",
+}
+
+ at article{Degner09,
+author="Degner, J F and Marioni, J C and Pai, A A and Pickrell, J K and Nkadori, E and Gilad, Y and Pritchard, J K",
+title="Effect of read-mapping biases on detecting allele-specific expression from
+ RNA-sequencing data",
+journal="Bioinformatics",
+volume="25(24)",
+pages="3207--3212",
+year="2009",
+}
+
+
+
+ at article{Neverov05,
+author="Neverov, A D and Nurtdinov, I A R N and Frishman, D and Gelfand, M S and Mironov, A A",
+title="Alternative splicing and protein function",
+journal="BMC Bioinformatics",
+volume="6",
+pages="266",
+year="2005",
+}
+
+
+
+ at article{Birzele07,
+author="Birzele, F and Csaba, G and Zimmer, R",
+title="Alternative splicing and protein structure evolution",
+journal="Nucleic Acids Research",
+volume="36(2)",
+pages="550--558",
+year="2007",
+}
+
+
+ at article{Jiang08,
+author="Jiang, H and Wing, W H",
+title="SeqMap: mapping massive amount of oligonucleotides to the genome",
+journal="Bioinformatics",
+volume="24(20)",
+pages="2395--2396",
+year="2008",
+}
+
+
+
+ at article{Hansen10,
+author="Hansen, K and Brenner, S and Dudoit S",
+title="Biases in Illumina transcriptome sequencing caused by random hexamer priming.",
+journal="Nucleic Acids Research",
+volume= "38",
+pages= "1-7",
+year="2010",
+}
+
+ at article{Zhou11,
+author="Zhou, Y.H. and Xia, K. and Wright, F.A.",
+title="A Powerful and Flexible Approach to the Analysis of RNA Sequence Count Data.",
+journal="Bioinformatics",
+volume= "27",
+pages= "2672-2678",
+year="2011",
+}
+
+ at article{Singh11,
+author="Singh, D. and Orellana, C.F. and Hu, Y. and Jones, C.D. and Liu, Y. and Chiang, D.Y. and Liu, J.
+and Prins, JF.",
+title="FDM: a graph-based statistical method to detect differential transcription using RNA-seq data",
+journal="Bioinformatics",
+volume= "27",
+pages= "2633-2640",
+year="2011",
+}
+
+
+ at article{Chang11,
+author="Chang, PL and Dunham, JP and Nuzhdin, SV and Arbeitman, MN.",
+title="Somatic sex-specific transcriptome differences in Drosophila revealed by whole transcriptome sequencing.",
+journal="BMC Genomics",
+volume= "12",
+pages= "364",
+year="2011",
+}
+
+
+ at article{Dempster77,
+author="Dempster, A.P. and Laird, N.M. and Rubin, D.B.",
+title="Maximum Likelihood from Incomplete Data via the EM Algorithm.",
+journal="Journal of the Royal Statistical Society",
+volume= "39",
+pages= "1-38",
+year="1977",
+}
+
+ at article{Katz10,
+author="Katz, Y. and Wang, E.T. and Airoldi, E.M. and Burge, C.B.",
+title="Analysis and design of RNA sequencing experiments for identifying isoform regulation.",
+journal="Nature Methods",
+volume= "7",
+pages= "1009-1015",
+year="2010",
+}
+
+ at manual{edgeRV,
+author="Robinson, M. and McCarthy, D. and Chen, Y. and Smyth, G.K.",
+title="edgeR: differential expression analysis
+ of digital gene expression data: User’s Guide",
+year="2014",
+url="http://www.bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf",
+}
+
+ at article{Stamm05,
+author="Stamm, S and Ben-Ari, S and Rafalska, I and Tang, Y and Zhang, Z and Toiber, D and Thanaraj, T A and Soreq H",
+title="Function of alternative splicing. ",
+year="2005",
+journal="Gene",
+volume= "344",
+pages= "1-20",
+}
+
+ at article{Smith89,
+author="Smith, C W and Patton, J G and Nadal-Ginard, B",
+title="Alternative splicing in the control of gene expression. ",
+year="1989",
+journal="Annu Rev Genet.",
+volume= "23",
+pages= "527-77",
+}
+
+ at article{gould09,
+author="Gould, M N",
+title="The Utility of Comparative Genetics to Inform Breast Cancer Prevention Strategies ",
+year="2009",
+journal="Genetics",
+volume= "183",
+pages= "409-412",
+}
+
+ at article{MAQC06,
+author="MAQC Consortium",
+title="The MicroArray Quality Control (MAQC) project shows inter- and intraplatform reproducibility of gene expression measurements.",
+year="2006",
+journal="Nature Biotechnology ",
+volume= "24",
+pages= "1151-1161",
+}
+
+ at article{Sengupta10,
+author="Sengupta, S. and Ruotti, V. and Bolin, J. and Elwell, A. and Hernandez, A. and Thomson, J. and Stewart, R.",
+title="Highly consistent, fully representative mRNA-Seq libraries from ten nanograms of total RNA.",
+year="2010",
+journal="Biotechniques",
+volume= "49",
+pages= "898-904",
+}
+
+ at article{Phanstiel11,
+author="Phanstiel, H P and Brumbaugh, J and Wenger, C D and Tian, S and Probasco,M D and Bailey,
+ D J and Swaney, D L and Tervo, M A and Bolin, J M and Ruotti, V and Stewart, R and
+ Thomson, J A and Coon, J J",
+title="Proteomic and phosphoproteomic comparison of human ES and iPS cells",
+year="2011",
+journal="Nature Methods",
+volume= "8",
+pages= "821-827",
+}
+
+ at article{Dixon50,
+author="Dixon, W J",
+title="Analysis of extreme values",
+year="1950",
+journal="The Annals of Mathematical Statistics",
+volume= "21",
+pages= "488",
+}
+
+ at article{Haag03,
+author="Haag, J D and Shepel, L A and Kolman, B D and Monson, D M and Benton, M E and Watts, K T and Waller, J L and Lopez-Guajardo,C C and Samuelson,D J and Gould, M N",
+title="Congenic Rats Reveal Three Independent Copenhagen Alleles within the Mcs1 Quantitative Trait Locus That Confer Resistance to Mammary Cancer",
+year="2003",
+journal="Cancer Res",
+volume= "63",
+pages= "5808",
+}
+
+
+ at article{Ludwig06,
+author="Ludwig, T E and Levenstein, M E and Jones, J M and Berggren, W T
+ and Mitchen, E R and Frane, J L and Crandall, L J and Daigh, C A and
+ Conard, K R and Piekarczyk, M S and Llanas, R A and Thomson, J A.",
+title="Derivation of human embryonic stem cells in defined conditions.",
+year="2006",
+journal="Nat Biotechnol",
+volume= "24(2)",
+pages= "185-7",
+}
+
+
+ at article{Guenther10,
+ author="Guenther, M Gand Frampton, G M and Soldner, F and Hockemeyer, D and Mitalipova,M and Jaenisch, R and Young, R A",
+ title="Chromatin structure and gene expression programs of
+ human embryonic and induced pluripotent stem cells.",
+ year="2010",
+ journal="Cell stem Cell",
+ volume= "7(2)",
+ pages= "249-257",
+}
+
+ at article{Chin09,
+ author="Chin, MH and Mason, MJ and Xie, W and Volinia, S and Singer, M and
+ Peterson, C and Ambartsumyan, G and Aimiuwu, O and Richter, L and Zhang, J and
+ Khvorostov, I and Ott, V and Grunstein, M and Lavon, N and Benvenisty, N and
+ Croce, CM and Clark, AT and Baxter, T and Pyle, AD and Teitell, MA and
+ Pelegrini, M and Plath, K and Lowry, WE",
+ title="Induced pluripotent stem cells and embryonic stem cells are distinguished by gene expression signatures.",
+ year="2009",
+ journal="Cell stem Cell",
+ volume= "5(1)",
+ pages= "111-123",
+}
+
+
+ at article{Ohi11,
+ author="Ohi, Y and Qin, H and Hong, C and Blouin, L and Polo, J M and
+ Guo, T and Qi, Z and Downey, S L and Manos, P D and Rossi, D J and
+ Yu, J and Hebrok, M and Hochedlinger, K and Costello, J F and Song, J S and Ramalho-Santos, M",
+ title="Incomplete DNA methylation underlies a transcriptional memory of somatic cells in human iPS cells.",
+ year="2011",
+ journal="Nat Cell Biol.",
+ volume= "13(5)",
+ pages= "541-9",
+}
+
+
+ at article{Bock11,
+ author="Bock, C and Kiskinis, E and Verstappen, G and Gu, H and Boulting, G and Smith, Z D and
+ Ziller, M and Croft, G F and Amoroso, M W and Oakley, D H and Gnirke, A and Eggan, K and Meissner, A",
+ title="Reference Maps of human ES and iPS cell variation enable high-throughput characterization of pluripotent cell lines.",
+ year="2011",
+ journal="Cell.",
+ volume= "144(3)",
+ pages= "439-52",
+}
+
+
+ at article{Trapnell12,
+ author="Trapnell, C and Roberts, A and Goff, L and Pertea, G and Kim, D and Kelley, D R and
+ Pimentel, H and Salzberg, S L and Rinn, J L and Pachter, L",
+ title="Differential gene and transcript expression analysis
+ of RNA-seq experiments with TopHat and Cufflinks",
+ year="2012",
+ journal="Nature Protocols",
+ volume= "7(3)",
+ pages= "562-578",
+}
+
+
+ at article{Li11b,
+ author="Li, B and Dewey, C N",
+ title="RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome",
+ year="2011",
+ journal="BMC Bioinformatics",
+ volume= "12",
+ pages= "323",
+}
+
+ at article{Yang07,
+ author="Yang, H and Churchill, G",
+ title="Estimating p-values in small microarray experiments",
+ year="2007",
+ journal="Bioinformatics",
+ volume= "23(1)",
+ pages= "38-43",
+}
+
+ at article{Sen10,
+ author="Sen, GL and Reuter, JA and Webster, DE and Zhu, L and Khavari, PA",
+ title="DNMT1 maintains progenitor function in self-renewing somatic tissue.",
+ year="2010",
+ journal="Nature",
+ volume= "463(7280)",
+ pages= "563-7",
+}
+
+ at article{Rai06,
+ author="Rai, K and Nadauld, LD and Chidester, S and
+ Manos, EJ and James, SR and Karpf, AR and Cairns, BR and Jones, DA.",
+ title="Zebra fish Dnmt1 and Suv39h1 regulate organ-specific terminal differentiation during development.",
+ year="2006",
+ journal="Mol Cell Biol.",
+ volume= "26(19)",
+ pages= "7077-85",
+}
+
+ at article{DAiuto11,
+ author="D'Aiuto, L and Di Maio, R and Mohan, KN and Minervini, C and Saporiti, F
+ and Soreca, I and Greenamyre, JT and Chaillet, JR.",
+ title="Mouse ES cells overexpressing DNMT1 produce abnormal neurons with upregulated NMDA/NR1 subunit.",
+ year="2011",
+ journal="Differentiation.",
+ volume= "82(1)",
+ pages= "9-17",
+}
+
+
+ at article{Grabherr11,
+ author="Grabherr, MG and Haas, BJ and Yassour, M and Levin, JZ and Thompson, DA and
+ Amit, I and Adiconis, X and Fan, L and Raychowdhury, R and Zeng, Q and Chen, Z and
+ Mauceli, E and Hacohen, N and Gnirke, A and Rhind, N and di Palma, F and
+ Birren, BW and Nusbaum, C and Lindblad-Toh, K and Friedman, N and Regev, A",
+ title="Full-length transcriptome assembly from RNA-Seq data without a reference genome",
+ year="2011",
+ journal="Nat Biotechnol.",
+ volume= "29",
+ pages= "644-652",
+}
+ at article{Leng12,
+ author="Leng, N. and Dawson, J.A. and Thomson, J.A and Ruotti, V and Rissman, R. A. and Smits, B.M.G and Hagg, J.D. and
+ Gould, M.N. and Stwart, R.M. and Kendziorski, C.",
+ title="EBSeq: An empirical Bayes hierarchical model for inference in RNA-seq experiments.",
+ journal="BMI technical report, University of Wisconsin Madison",
+ volume= "226",
+ year="2012",
+}
+
+
+ at article{Nicolae10,
+ title={Estimation of alternative splicing isoform frequencies from RNA-Seq data},
+ author={Nicolae, M. and Mangul, S. and M{\u{a}}ndoiu, I. and Zelikovsky, A.},
+ journal={Algorithms in Bioinformatics},
+ pages={202--214},
+ year={2010},
+ publisher={Springer}
+}
+
+ at article{Sandmann11,
+ title={The head-regeneration transcriptome of the planarian Schmidtea mediterranea},
+ author={Sandmann, T. and Vogg, M.C. and Owlarn, S. and Boutros, M. and Bartscherer, K.},
+ journal={Genome Biology},
+ volume={12},
+ number={8},
+ pages={R76},
+ year={2011},
+ publisher={BioMed Central Ltd}
+}
+
+ at article{Anders12,
+ author="Anders, S. and Reyes, A. and Huber, W",
+ title="Detecting differential usage of exons from RNA-Seq data",
+ journal="Nature Preceedings",
+ year="2012",
+}
+
+
+ at article{Delhomme12,
+ title={easyRNASeq: a bioconductor package for processing RNA-Seq data},
+ author={Delhomme, N. and Padioleau, I. and Furlong, E.E. and Steinmetz, L.M.},
+ journal={Bioinformatics},
+ year={2012},
+ publisher={Oxford Univ Press}
+}
+
+ at manual{easyRNASeq12,
+author="Delhomme,N and Padioleau, I",
+title="easyRNASeq, an overview",
+year="2012",
+url="http://www.bioconductor.org/packages/devel/bioc/vignettes/easyRNASeq/inst/doc/easyRNASeq.pdf",
+}
+
+ at manual{HTSeq,
+author="Anders, S",
+title="HTSeq: Analysing high-throughput sequencing data with Python",
+year="2012",
+url="http://www-huber.embl.de/users/anders/HTSeq/doc/overview.html",
+}
+
+ at manual{Cuff,
+title="Cufflinks
+ Transcript assembly, differential expression, and differential regulation for RNA-Seq",
+year="2012",
+url="http://cufflinks.cbcb.umd.edu/index.html",
+}
+ at article{Du12,
+ title={IQSeq: Integrated Isoform Quantification Analysis Based on Next-Generation Sequencing},
+ author={Du, J. and Leng, J. and Habegger, L. and Sboner, A. and McDermott, D. and Gerstein, M.},
+ journal={PloS one},
+ volume={7},
+ number={1},
+ pages={e29175},
+ year={2012},
+ publisher={Public Library of Science}
+}
+
+ at article{Pickrell10,
+ title={Understanding mechanisms underlying human gene expression variation with RNA sequencing},
+ author={Pickrell, J.K. and Marioni, J.C. and Pai, A.A. and Degner, J.F. and Engelhardt, B.E. and Nkadori, E. and Veyrieras, J.B. and Stephens, M. and Gilad, Y. and Pritchard, J.K.},
+ journal={Nature},
+ volume={464},
+ number={7289},
+ pages={768--772},
+ year={2010},
+ publisher={Nature Publishing Group}
+}
+
+
+
+ at article{Wang09regen,
+ title={Regeneration, repair and remembering identity: the three Rs of Hox gene expression},
+ author={Wang, K.C. and Helms, J.A. and Chang, H.Y.},
+ journal={Trends in cell biology},
+ volume={19},
+ number={6},
+ pages={268--275},
+ year={2009},
+ publisher={Elsevier}
+}
+
+ at article{Chang09,
+ title={Anatomic demarcation of cells: genes to patterns},
+ author={Chang, H.Y.},
+ journal={Science},
+ volume={326},
+ number={5957},
+ pages={1206--1207},
+ year={2009},
+ publisher={American Association for the Advancement of Science}
+}
+
+ at article{Rinn06,
+ title={Anatomic demarcation by positional variation in fibroblast gene expression programs},
+ author={Rinn, J.L. and Bondre, C. and Gladstone, H.B. and Brown, P.O. and Chang, H.Y.},
+ journal={PLoS genetics},
+ volume={2},
+ number={7},
+ pages={e119},
+ year={2006},
+ publisher={Public Library of Science}
+}
+
+ at article{Blei03,
+ title={Latent dirichlet allocation},
+ author={Blei, D.M. and Ng, A.Y. and Jordan, M.I.},
+ journal={the Journal of machine Learning research},
+ volume={3},
+ pages={993--1022},
+ year={2003},
+ publisher={JMLR. org}
+}
+
+ at inproceedings{Andrzejewski09,
+ title={Incorporating domain knowledge into topic modeling via Dirichlet forest priors},
+ author={Andrzejewski, D. and Zhu, X. and Craven, M.},
+ booktitle={Proceedings of the 26th Annual International Conference on Machine Learning},
+ pages={25--32},
+ year={2009},
+ organization={ACM}
+}
+ at article{Wu10,
+ title={Dynamic transcriptomes during neural differentiation of human embryonic stem cells revealed by short, long, and paired-end sequencing},
+ author={Wu, J.Q. and Habegger, L. and Noisa, P. and Szekely, A. and Qiu, C. and Hutchison, S. and Raha, D. and Egholm, M. and Lin, H. and Weissman, S. and others},
+ journal={Proceedings of the National Academy of Sciences},
+ volume={107},
+ number={11},
+ pages={5254--5259},
+ year={2010},
+ publisher={National Acad Sciences}
+}
+
+ at article{Monaghan09,
+ title={Microarray and cDNA sequence analysis of transcription during nerve-dependent limb regeneration},
+ author={Monaghan, J.R. and Epp, L.G. and Putta, S. and Page, R.B. and Walker, J.A. and Beachy, C.K. and Zhu, W. and Pao, G.M. and Verma, I.M. and Hunter, T. and others},
+ journal={BMC biology},
+ volume={7},
+ number={1},
+ pages={1},
+ year={2009},
+ publisher={BioMed Central Ltd}
+}
+
+ at article{Malone11,
+ title={Microarrays, deep sequencing and the true measure of the transcriptome},
+ author={Malone, J.H. and Oliver, B.},
+ journal={BMC biology},
+ volume={9},
+ number={1},
+ pages={34},
+ year={2011},
+ publisher={BioMed Central Ltd}
+}
+
+ at article{Auer10,
+ title={Statistical design and analysis of RNA sequencing data},
+ author={Auer, P.L. and Doerge, RW},
+ journal={Genetics},
+ volume={185},
+ number={2},
+ pages={405--416},
+ year={2010},
+ publisher={Genetics Soc America}
+}
+ at article{Schubert03,
+ title={Microarray to be used as routine clinical screen},
+ author={Schubert, C.M.},
+ journal={Nature medicine},
+ volume={9},
+ number={1},
+ pages={9--9},
+ year={2003},
+ publisher={Nature Publishing Group}
+}
+
+
+
+ at article{Ramaswamy02,
+ title={DNA microarrays in clinical oncology},
+ author={Ramaswamy, S. and Golub, T.R.},
+ journal={Journal of Clinical Oncology},
+ volume={20},
+ number={7},
+ pages={1932--1941},
+ year={2002},
+ publisher={American Society of Clinical Oncology}
+}
+
+ at article{Stewart12,
+ title={Comparative RNA-seq Analysis in the Unsequenced Axolotl: The Oncogene Burst of Expression Defines One of Three Phases of Gene Expression in the Blastema},
+ author={Stewart, R and Rascon,CA and Tian, S and Nie, J and
+Probasco, MD and Bolin, JM and Sengupta,S and Volkmer, M and
+Habermann, B and Tanaka, EM and Thomson, JA and Dewey, CN},
+ year={2012},
+}
+
+
+
+ at article{Grant11,
+ title={Comparative analysis of RNA-Seq alignment algorithms and the RNA-Seq unified mapper (RUM)},
+ author={Grant, G.R. and Farkas, M.H. and Pizarro, A.D. and Lahens, N.F. and Schug, J. and Brunk, B.P. and Stoeckert, C.J. and Hogenesch, J.B. and Pierce, E.A.},
+ journal={Bioinformatics},
+ volume={27},
+ number={18},
+ pages={2518--2528},
+ year={2011},
+ publisher={Oxford Univ Press}
+}
+
+
+ at article{Hester10,
+ title={Comprehensive comparison of RNA--Seq alignment packages},
+ author={Hester, J.},
+ year={2010},
+ publisher={Citeseer}
+}
+
+ at article{Wang10c,
+ title={MapSplice: accurate mapping of RNA-seq reads for splice junction discovery},
+ author={Wang, K. and Singh, D. and Zeng, Z. and Coleman, S.J. and Huang, Y. and Savich, G.L. and He, X. and Mieczkowski, P. and Grimm, S.A. and Perou, C.M. and others},
+ journal={Nucleic acids research},
+ volume={38},
+ number={18},
+ pages={e178--e178},
+ year={2010},
+ publisher={Oxford Univ Press}
+}
+ at article{Savage09,
+ title={R/BHC: fast Bayesian hierarchical clustering for microarray data},
+ author={Savage, R. and Heller, K. and Xu, Y. and Ghahramani, Z. and Truman, W. and Grant, M. and Denby, K. and Wild, D.},
+ journal={BMC bioinformatics},
+ volume={10},
+ number={1},
+ pages={242},
+ year={2009},
+ publisher={BioMed Central Ltd}
+}
+
+ at inproceedings{Heller05,
+ title={Bayesian hierarchical clustering},
+ author={Heller, K.A. and Ghahramani, Z.},
+ booktitle={Proceedings of the 22nd international conference on Machine learning},
+ pages={297--304},
+ year={2005},
+ organization={ACM}
+}
+ at article{Young10,
+ title={Method Gene ontology analysis for RNA-seq: accounting for selection bias},
+ author={Young, M.D. and Wakefield, M.J. and Smyth, G.K. and Oshlack, A.},
+ year={2010},
+ journal={Genome Biology},
+ volume={11}
+}
+
+ at article{Subramanian05,
+ title={Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles},
+ author={Subramanian, A. and Tamayo, P. and Mootha, V.K. and Mukherjee, S. and Ebert, B.L. and Gillette, M.A. and Paulovich, A. and Pomeroy, S.L. and Golub, T.R. and Lander, E.S. and others},
+ journal={Proceedings of the National Academy of Sciences of the United States of America},
+ volume={102},
+ number={43},
+ pages={15545--15550},
+ year={2005},
+ publisher={National Acad Sciences}
+}
+
+ at article{Da08,
+ title={Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources},
+ author={Da Wei Huang, B.T.S. and Lempicki, R.A. and others},
+ journal={Nature protocols},
+ volume={4},
+ number={1},
+ pages={44--57},
+ year={2008},
+ publisher={Nature Publishing Group}
+}
+
+
+ at article{Eng12,
+ title={Pathway index models for construction of patient-specific risk profiles},
+ author={Eng, K.H. and Wang, S. and Bradley, W.H. and Rader, J.S. and Kendziorski, C.},
+ journal={Statistics in Medicine},
+ year={2012},
+ publisher={Wiley Online Library}
+}
+
+ at article{WangS09,
+ title={Hierarchically penalized Cox regression with grouped variables},
+ author={Wang, S. and Nan, B. and Zhu, N. and Zhu, J.},
+ journal={Biometrika},
+ volume={96},
+ number={2},
+ pages={307--322},
+ year={2009},
+ publisher={Biometrika Trust}
+}
+
+ at article{Huang09,
+ title={A group bridge approach for variable selection},
+ author={Huang, J. and Ma, S. and Xie, H. and Zhang, C.H.},
+ journal={Biometrika},
+ volume={96},
+ number={2},
+ pages={339--355},
+ year={2009},
+ publisher={Biometrika Trust}
+}
+
+ at article{Zhou10,
+ title={Group variable selection via a hierarchical lasso and its oracle property},
+ author={Zhou, N. and Zhu, J.},
+ journal={arXiv preprint arXiv:1006.2871},
+ year={2010}
+}
+ at article{Segal06,
+ title={Microarray gene expression data with linked survival phenotypes: diffuse large-B-cell lymphoma revisited},
+ author={Segal, M.R.},
+ journal={Biostatistics},
+ volume={7},
+ number={2},
+ pages={268--285},
+ year={2006},
+ publisher={Biometrika Trust}
+}
+
+ at article{Binsl07,
+ title={FluxSimulator: an R package to simulate isotopomer distributions in metabolic networks},
+ author={Binsl, T.W. and Mullen, K.M. and Van Stokkum, I.H.M. and Heringa, J. and Van Beek, J.H.G.M.},
+ journal={J. Stat. Softw},
+ volume={18},
+ number={6},
+ pages={1--18},
+ year={2007}
+}
+
+ at article{Yuan06,
+ title={Hidden Markov models for microarray time course data in multiple biological conditions},
+ author={Yuan, M. and Kendziorski, C.},
+ journal={Journal of the American Statistical Association},
+ volume={101},
+ number={476},
+ pages={1323--1332},
+ year={2006},
+ publisher={American Statistical Association}
+}
+
+
+ at article{Tai06,
+ title={A multivariate empirical Bayes statistic for replicated microarray time course data},
+ author={Tai, Y.C. and Speed, T.P.},
+ journal={The Annals of Statistics},
+ volume={34},
+ number={5},
+ pages={2387--2412},
+ year={2006},
+ publisher={Institute of Mathematical Statistics}
+}
+
+ at article{Nueda07,
+ title={Discovering gene expression patterns in time course microarray experiments by ANOVA--SCA},
+ author={Nueda, M.J. and Conesa, A. and Westerhuis, J.A. and Hoefsloot, H.C.J. and Smilde, A.K. and Tal{\'o}n, M. and Ferrer, A.},
+ journal={Bioinformatics},
+ volume={23},
+ number={14},
+ pages={1792--1800},
+ year={2007},
+ publisher={Oxford Univ Press}
+}
+
+ at article{Storey05,
+ title={Significance analysis of time course microarray experiments},
+ author={Storey, J.D. and Xiao, W. and Leek, J.T. and Tompkins, R.G. and Davis, R.W.},
+ journal={Proceedings of the National Academy of Sciences of the United States of America},
+ volume={102},
+ number={36},
+ pages={12837--12842},
+ year={2005},
+ publisher={National Acad Sciences}
+}
+ at article{Luan03,
+ title={Clustering of time-course gene expression data using a mixed-effects model with B-splines},
+ author={Luan, Y. and Li, H.},
+ journal={Bioinformatics},
+ volume={19},
+ number={4},
+ pages={474--482},
+ year={2003},
+ publisher={Oxford Univ Press}
+}
+
+ at article{Bar03,
+ title={Continuous representations of time-series gene expression data},
+ author={Bar-Joseph, Z. and Gerber, G.K. and Gifford, D.K. and Jaakkola, T.S. and Simon, I.},
+ journal={Journal of Computational Biology},
+ volume={10},
+ number={3-4},
+ pages={341--356},
+ year={2003},
+ publisher={Mary Ann Liebert, Inc.}
+}
+ at article{Ma06,
+ title={A data-driven clustering method for time course gene expression data},
+ author={Ma, P. and Castillo-Davis, C.I. and Zhong, W. and Liu, J.S.},
+ journal={Nucleic Acids Research},
+ volume={34},
+ number={4},
+ pages={1261--1269},
+ year={2006},
+ publisher={Oxford Univ Press}
+}
+
+ at article{Sun11,
+ title={Multiple testing for pattern identification, with applications to microarray time-course experiments},
+ author={Sun, W. and Wei, Z.},
+ journal={Journal of the American Statistical Association},
+ volume={106},
+ number={493},
+ pages={73--88},
+ year={2011},
+ publisher={Taylor \& Francis}
+}
+
+ at article{Bertucci03,
+ title={DNA arrays in clinical oncology: promises and challenges},
+ author={Bertucci, F. and Viens, P. and Tagett, R. and Nguyen, C. and Houlgatte, R. and Birnbaum, D.},
+ journal={Laboratory investigation},
+ volume={83},
+ number={3},
+ pages={305--316},
+ year={2003},
+ publisher={Nature Publishing Group}
+}
+
+ at article{Azad06,
+ title={Proteomics in Clinical Trials and Practice Present Uses and Future Promise},
+ author={Azad, N.S. and Rasool, N. and Annunziata, C.M. and Minasian, L. and Whiteley, G. and Kohn, E.C.},
+ journal={Molecular \& Cellular Proteomics},
+ volume={5},
+ number={10},
+ pages={1819--1829},
+ year={2006},
+ publisher={ASBMB}
+}
+
+ at article{Aung10,
+ title={Current status and future potential of somatic mutation testing from circulating free DNA in patients with solid tumours},
+ author={Aung, KL and Board, RE and Ellison, G. and Donald, E. and Ward, T. and Clack, G. and Ranson, M. and Hughes, A. and Newman, W. and Dive, C.},
+ journal={The HUGO journal},
+ volume={4},
+ number={1},
+ pages={11--21},
+ year={2010},
+ publisher={Springer}
+}
+
+ at article{Glaus12,
+ title={Identifying differentially expressed transcripts from RNA-seq data with biological variation},
+ author={Glaus, P. and Honkela, A. and Rattray, M.},
+ journal={Bioinformatics},
+ volume={28},
+ number={13},
+ pages={1721--1728},
+ year={2012},
+ publisher={Oxford Univ Press}
+}
+
+ at article{Trapnell12b,
+ title={Differential analysis of gene regulation at transcript resolution with RNA-seq},
+ author={Trapnell, C. and Hendrickson, D.G. and Sauvageau, M. and Goff, L. and Rinn, J.L. and Pachter, L.},
+ journal={Nature Biotechnology},
+ year={2012},
+ publisher={Nature Publishing Group}
+}
+
+
+ at article{Leng13,
+ title={EBSeq: an empirical Bayes hierarchical model for inference in RNA-seq experiments},
+ author={Leng, Ning and Dawson, John A and Thomson, James A and Ruotti, Victor and Rissman, Anna I and Smits, Bart MG and Haag, Jill D and Gould, Michael N and Stewart, Ron M and Kendziorski, Christina},
+ journal={Bioinformatics},
+ volume={29},
+ number={8},
+ pages={1035--1043},
+ year={2013},
+ publisher={Oxford Univ Press}
+}
+
+ at article{Hamilton89,
+ title={A new approach to the economic analysis of nonstationary time series and the business cycle},
+ author={Hamilton, James D},
+ journal={Econometrica: Journal of the Econometric Society},
+ pages={357--384},
+ year={1989},
+ publisher={JSTOR}
+}
+ at article{Ailliot12,
+ title={Markov-switching autoregressive models for wind time series},
+ author={Ailliot, Pierre and Monbet, Val{\'e}rie},
+ journal={Environmental Modelling \& Software},
+ volume={30},
+ pages={92--101},
+ year={2012},
+ publisher={Elsevier}
+}
+ at article{Koehler11,
+ title={The uniqueome: a mappability resource for short-tag sequencing},
+ author={Koehler, Ryan and Issac, Hadar and Cloonan, Nicole and Grimmond, Sean M},
+ journal={Bioinformatics},
+ volume={27},
+ number={2},
+ pages={272--274},
+ year={2011},
+ publisher={Oxford University Press}
+}
+ at article{Derrien12,
+ title={Fast computation and applications of genome mappability},
+ author={Derrien, Thomas and Estell{\'e}, Jordi and Sola, Santiago Marco and Knowles, David G and Raineri, Emanuele and Guig{\'o}, Roderic and Ribeca, Paolo},
+ journal={PloS one},
+ volume={7},
+ number={1},
+ pages={e30377},
+ year={2012},
+ publisher={Public Library of Science}
+}
+ at article{Shi13,
+ title={rSeqDiff: Detecting Differential Isoform Expression from RNA-Seq Data Using Hierarchical Likelihood Ratio Test},
+ author={Shi, Yang and Jiang, Hui},
+ journal={PloS one},
+ volume={8},
+ number={11},
+ pages={e79448},
+ year={2013},
+ publisher={Public Library of Science}
+}
+ at inproceedings{Schluter05,
+ title={Bayes risk minimization using metric loss functions.},
+ author={Schl{\"u}ter, Ralf and Scharrenbach, Thomas and Steinbiss, Volker and Ney, Hermann},
+ booktitle={INTERSPEECH},
+ pages={1449--1452},
+ year={2005}
+}
+ at book{Berger85,
+ title={Statistical decision theory and Bayesian analysis},
+ author={Berger, James O},
+ year={1985},
+ publisher={Springer}
+}
+
+
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/r-bioc-ebseq.git
More information about the debian-med-commit
mailing list