2 function(Input, InputSP, EmpiricalR, EmpiricalRSP, NumOfEachGroup, AlphaIn, BetaIn, PIn, NoneZeroLength)
4 #2 condition case (skip the loop then maybe run faster? Code multi condition cases later)
6 #For each gene (m rows of Input---m genes)
7 #Save each gene's F0, F1 for further likelihood calculation.
10 F0=f0(Input, AlphaIn, BetaIn, EmpiricalR, NumOfEachGroup, log=F)
12 F1=f1(InputSP[[1]], InputSP[[2]], AlphaIn, BetaIn, EmpiricalRSP[[1]],EmpiricalRSP[[2]], NumOfEachGroup, log=F)
15 #Use data.list in logfunction
17 z.list=PIn*F1/(PIn*F1+(1-PIn)*F0)
18 zNaNName=names(z.list)[is.na(z.list)]
19 zGood=which(!is.na(z.list))
21 #PFromZ=sapply(1:NoneZeroLength,function(i) sum(z.list[[i]])/length(z.list[[i]]))
22 PFromZ=sum(z.list[zGood])/length(z.list[zGood])
26 # Since we dont wanna update p and Z in this step
29 NumGroupVector=rep(c(1:NoneZeroLength),NumOfEachGroup)
31 NumGroupVector.zGood=NumGroupVector[zGood]
32 NumOfEachGroup.zGood=tapply(NumGroupVector.zGood,NumGroupVector.zGood,length)
34 StartValue=c(AlphaIn, BetaIn,PIn)
36 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))
37 #LikeOutput=Likelihood( StartValue, Input , InputSP , PNEW.list, z.list)
38 AlphaNew= Result$par[1]
39 BetaNew=Result$par[2:(1+NoneZeroLength)]
40 PNew=Result$par[2+NoneZeroLength]
42 Output=list(AlphaNew=AlphaNew,BetaNew=BetaNew,PNew=PNew,ZNew.list=z.list,PFromZ=PFromZ, zGood=zGood, zNaNName=zNaNName,F0Out=F0Good, F1Out=F1Good)