Skip to content

Latest commit

 

History

History
60 lines (50 loc) · 2.51 KB

README.md

File metadata and controls

60 lines (50 loc) · 2.51 KB

ranktreeEnsemble: an R package for implementing ensemble methods of rank-based trees as single-sample predictors for gene expression classification

CRAN status CRAN version CRAN release date CRAN downloads

Authors

Ruijie Yin ([email protected]), Chen Ye ([email protected]) and Min Lu ([email protected])

Reference

Lu M. Yin R. and Chen X.S. Ensemble Methods of Rank-Based Trees for Single Sample Classification with Gene Expression Profiles. Journal of Translational Medicine. 22, 140 (2024). https://doi.org/10.1186/s12967-024-04940-2

Description

Fast computing an ensemble of rank-based trees via boosting or random forest on binary and multi-class problems. It converts continuous gene expression profiles into ranked gene pairs, for which the variable importance indices are computed and adopted for dimension reduction. Decision rules can be extracted from trees.

Installation

install.packages("ranktreeEnsemble")
library(ranktreeEnsemble)

Examples

  • Build a Random Rank Forest with Variable Importance:
data(tnbc)
obj <- rforest(subtype~., data = tnbc[1:100,c(1:5,337)])
importance(obj)
predict(obj)$label
predict(obj, tnbc[101:110,1:5])$label

### pair() to convert continuous variables to binary ranked pairs
tnbc[101:110,1:5]
datp <- pair(tnbc[101:110,1:5])
datp
predict(obj, datp, newdata.pair = TRUE)$label
  • Extract Interpretable Decision Rules:
objr <- extract.rules(obj)
objr$rule[1:5,]
predict(objr)$label[1:5]

objrs <- select.rules(objr,tnbc[110:130,c(1:5,337)])
predict(objrs, tnbc[111:120,1:5])$label
objrs$rule[1:5,]
  • Build a Boosting model with LogitBoost Cost with Variable Importance:
objb <- rboost(subtype~., data = tnbc[1:100,c(1:5,337)])
importance(objb)
predict(objb)$label
predict(objb, tnbc[101:110,1:5])$label