H-DROP: an SVM based helical domain linker predictor trained with features optimized by combining random forest and stepwise selection.
Teppei EbinaRyosuke SuzukiRyotaro TsujiYutaka KurodaPublished in: J. Comput. Aided Mol. Des. (2014)
Keyphrases
- random forest
- feature set
- svm classifier
- selected features
- feature importance
- random forests
- fold cross validation
- feature vectors
- decision trees
- feature extraction
- neural network
- ensemble methods
- support vector machine svm
- support vector machine
- classification accuracy
- feature space
- image features
- feature ranking
- training set
- feature selection
- multi label
- machine learning
- ensemble learning
- data mining
- cancer classification
- benchmark datasets
- ensemble classifier
- graph cuts
- prior knowledge
- pairwise
- support vector