csmpv (version 1.0.5)

XGpred_predict: Predicting Risk Group Classification for a New Data Set

Description

The XGpred_predict function is designed to predict risk group classifications for a new data set. This prediction is based on the assumption that an XGpred object is available from a training data set and that the new data set is comparable to the training data set.

In scenarios where the new and training data sets are not directly comparable, a calibration cohort is required to ensure accurate risk group predictions.

Usage

XGpred_predict(newdat = NULL, XGpredObj = NULL, scoreShift = 0)

Value

A data frame containing XGpred_score, XGpred_prob, and XGpred_prob_class

Arguments

newdat

A data matrix or a data frame where samples are in rows and features/traits are in columns. It should include all variables needed for the prediction model.

XGpredObj

An XGpred object returned by the XGpred function. Although not all items are needed for prediction purposes, using the XGpred object as input is convenient.

scoreShift

A calibration value to subtract from the current model score if needed.

Author

Aixiang Jiang

References

Aoki T, Jiang A, Xu A et al.,(2023) Spatially Resolved Tumor Microenvironment Predicts Treatment Outcomes in Relapsed/Refractory Hodgkin Lymphoma. J Clin Oncol. 2023 Dec 19:JCO2301115. doi: 10.1200/JCO.23.01115. PMID: 38113419.

Examples

# Load in data sets:
data("datlist", package = "csmpv")
tdat = datlist$training
vdat = datlist$validation

# The function saves files locally. You can define your own temporary directory. 
# If not, tempdir() can be used to get the system's temporary directory.
temp_dir = tempdir()
# As an example, let's define Xvars, which will be used later:
Xvars = c("highIPI", "B.Symptoms", "MYC.IHC", "BCL2.IHC", "CD10.IHC", "BCL6.IHC")
# For given time-to-event outcome and Xvars, we can build up a binary risk classification:
 xgobj = XGpred(data = tdat, varsIn = Xvars, 
               time = "FFP..Years.",
                event = "Code.FFP", outfile = paste0(temp_dir, "/XGpred"))
 tdat$XGpred_class = xgobj$XGpred_prob_class
# You might save the files to the directory you want.

# Now, we can predict the risk classification for a new data set:
 xgNew = XGpred_predict(newdat = vdat, XGpredObj = xgobj)

#' # To delete the "temp_dir", use the following:
unlink(temp_dir)