Impute missing values and run t test for proteomic data

analyze.proteomic.data.R

analyze.proteomic.data<-function(intensities,meta_data,condA,condB){
  
  #parse conditions to prepare for t test with replicates
  colnames(intensities)<-meta_data
  
  condA.regex<-paste("^",condA,"$",sep="")
  condB.regex<-paste("^",condB,"$",sep="")
  
  condA.indices<-grep(condA.regex,colnames(intensities))
  condB.indices<-grep(condB.regex,colnames(intensities))
  

  
  #meta_data<-as.factor(meta_data)
  #create a matrix of binary values to represent present and missing values
  binary_mat<-as.data.frame(ifelse(intensities!="NaN", 1, 0))
  
  #split the data set such that >half missing values will be imputed by min value technique
  #and less than half imputed by k-nearest neighbor
  knn.impute.bin<-filtered[rowSums(filtered)>ncol(intensities)/2,]
  min.impute.bin<-filtered[rowSums(filtered)<ncol(intensities)/2,]
  
  #use R impute package to impute by knn using default parameters
  library(impute)
  knn.impute<-intensities[rownames(knn.impute.bin),]
  imputation.by.knn<-impute.knn(as.matrix(knn.impute))$data
 
  
  
  knn.t.test<-apply(imputation.by.knn, 1, function(data) {t.test(x = data[condA.indices], y = data[condB.indices])$p.value})
  
  
  knn.results<-as.matrix(knn.t.test)

  #get minimum value of data set
  min.impute.min.val<-min(intensities,na.rm=TRUE)
  
  
  
  
  #since we are using rnorm to replace missing values, t-test should be performed over
  #user-defined number of iterations to get an approximate p-value.
  
  #reset seed overwritten by knn
  as.numeric(Sys.time())-> t; set.seed((t - floor(t)) * 1e8 -> seed); print(seed)
  #randomize and test over iterations
  
  all.p.vals<-list()
  for(i in 1:10){
    
    min.impute<-intensities[rownames(min.impute.bin),]
    min.impute[min.impute == "NaN"] <- rnorm(min.impute[min.impute == "NaN"], m= min.impute.min.val,sd=sqrt(min.impute.min.val))
    
    min.t.test<-apply(min.impute, 1, function(data) {t.test(x = data[condA.indices], y = data[condB.indices])$p.value})
    all.p.vals[[i]]<-min.t.test
    
  }
  
  p.val.mat<-data.frame(matrix(unlist(all.p.vals), nrow=nrow(min.impute), byrow=T))
  min.results<-as.matrix(rowMeans(p.val.mat))
  rownames(min.results)<-rownames(min.impute)
  pvals<-rbind(knn.results,min.results)

  return(pvals)
}