ForestSubtype: a cancer subtype identifying approach based on high-dimensional genomic data and a parallel random forest.
Junwei LuoYading FengXuyang WuRuimin LiJiawei ShiWenjing ChangJunfeng WangPublished in: BMC Bioinform. (2023)
Keyphrases
- random forest
- genomic data
- gene expression data
- cancer classification
- high dimensional
- gene expression profiles
- gene selection
- high throughput
- microarray
- biological data
- decision trees
- gene expression
- microarray data
- high dimensionality
- feature set
- fold cross validation
- ensemble methods
- protein protein interactions
- low dimensional
- multi label
- data sets
- experimental conditions
- dimensionality reduction
- data integration
- nearest neighbor
- training samples
- gene ontology
- high dimensional data
- ensemble classifier
- feature ranking
- high precision
- microarray datasets
- data points
- pairwise