Machine learning revealed stemness features and a novel stemness-based classification with appealing implications in discriminating the prognosis, immunotherapy and temozolomide responses of 906 glioblastoma patients.
Zihao WangYaning WangTianrui YangHao XingYuekun WangLu GaoXiaopeng GuoBing XingYu WangWenbin MaPublished in: Briefings Bioinform. (2021)
Keyphrases
- machine learning
- machine learning methods
- classification accuracy
- feature set
- machine learning approaches
- feature construction
- feature vectors
- decision trees
- support vector machine
- classification models
- discriminating features
- feature extraction
- pattern recognition
- feature space
- classification process
- svm classifier
- classification method
- machine learning algorithms
- benchmark datasets
- feature selection
- supervised learning
- text classification
- extracted features
- supervised machine learning
- feature analysis
- extracting features
- machine learning models
- discriminating power
- feature values
- svm classification
- feature generation
- model selection
- support vector machine svm
- class labels
- training set
- normal controls
- spatially localized
- therapy planning
- lung disease
- weak classifiers
- eeg signals
- supervised classification
- feature subset
- data mining
- active learning