| CytoDx.pred {CytoDx} | R Documentation |
A function that makes prediction using the CytoDx model.
CytoDx.pred(fit, xNew, xSampleNew)
fit |
The two stage statistical model. Must be the object returned by CytoDx.fit. |
xNew |
The marker profile of cells pooled from all new samples. Each row is a cell, each column is a marker. |
xSampleNew |
A vector specifying which sample each cell belongs to. Length must equal to nrow(xNew). |
Returns a list. xNew.Pred1 contains the predicted y for the new data at the cell level. xNew.Pred2 contains the predicted y for the new data at the sample level.
# Find the table containing fcs file names in CytoDx package
path <- system.file("extdata",package="CytoDx")
# read the table
fcs_info <- read.csv(file.path(path,"fcs_info.csv"))
# Specify the path to the cytometry files
fn <- file.path(path,fcs_info$fcsName)
train_data <- fcs2DF(fcsFiles=fn,
y=fcs_info$Label,
assay="FCM",
b=1/150,
excludeTransformParameters=
c("FSC-A","FSC-W","FSC-H","Time"))
# build the model
fit <- CytoDx.fit(x=as.matrix(train_data[,1:7]),
y=train_data$y,
xSample = train_data$xSample,
reg=FALSE,
family="binomial")
# check accuracy for training data
pred <- CytoDx.pred(fit,
xNew=as.matrix(train_data[,1:7]),
xSampleNew=train_data$xSample)
boxplot(pred$xNew.Pred.sample$y.Pred.s0~
fcs_info$Label)