t-test each line of 2 groups of data
test2grp performs t-test on two groups of data using limma,
this is a custom implementation of moderTest2grp for proteomics.
The final obkect also includes the results without moderation by limma (eg BH-FDR in $nonMod.BH).
Furthermore, there is an option to make use of package ROTS (note, this will increase the time of computatins considerably).
test2grp( dat, questNo, useCol = NULL, grp = NULL, annot = NULL, ROTSn = 0, silent = FALSE, callFrom = NULL )
dat |
(matrix or data.frame) main data (may contain NAs) |
questNo |
(integer) specify here which question, ie comparison should be adressed |
useCol |
(integer or character) |
grp |
(character or factor) |
annot |
(matrix or data.frame) |
ROTSn |
(integer) number of iterations ROTS runs (stabilization of reseults may be seen with >300) |
silent |
(logical) suppress messages |
callFrom |
(character) allow easier tracking of message produced |
limma-type S3 object of class 'MArrayLM' which can be accessed; multiple testing correction types or modified testing by ROTS may get included ('p.value','FDR','BY','lfdr' or 'ROTS.BH')
moderTest2grp, pVal2lfdr, t.test, ROTS from the Bioconductor package ROTS
set.seed(2018); datT8 <- matrix(round(rnorm(800)+3,1),nc=8,dimnames=list(paste( "li",1:100,sep=""),paste(rep(LETTERS[1:3],c(3,3,2)),letters[18:25],sep=""))) datT8[3:6,1:2] <- datT8[3:6,1:2]+3 # augment lines 3:6 (c-f) datT8[5:8,5:6] <- datT8[5:8,5:6]+3 # augment lines 5:8 (e-h) grp8 <- gl(3,3,labels=LETTERS[1:3],length=8) datL <- list(data=datT8,filt= wrMisc::presenceFilt(datT8,grp=grp8,maxGrpM=1,ratMa=0.8)) testAvB0 <- wrMisc::moderTest2grp(datT8[,1:6],gl(2,3)) testAvB <- test2grp(datL,questNo=1)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.