HOTGpred: Enhancing human O-linked threonine glycosylation prediction using integrated pretrained protein language model-based features and multi-stage feature selection approach.
Nhat Truong PhamYing ZhangRajan RakkiyappanBalachandran ManavalanPublished in: Comput. Biol. Medicine (2024)
Keyphrases
- multistage
- feature selection
- feature set
- feature extraction
- selected features
- feature selection algorithms
- feature subset
- feature space
- subcellular localization
- production system
- classification accuracy
- prediction accuracy
- single stage
- feature vectors
- stochastic optimization
- stochastic programming
- text categorization
- optimal policy
- dynamic programming
- lot sizing
- discriminative features
- irrelevant features
- attack detection
- feature ranking
- informative features
- text classification
- amino acids
- support vector machine
- redundant features
- machine learning
- support vector
- natural language
- classification models
- high dimensionality
- svm classifier