Identification of protein hot regions by combining structure-based classification, energy-based clustering and sequence-based conservation in evolution.
Jing HuHaomin GanNansheng ChenXiaolong ZhangPublished in: Int. J. Data Min. Bioinform. (2020)
Keyphrases
- tertiary structure
- output space
- sequence similarity
- secondary structure
- clustering analysis
- unsupervised learning
- clustering algorithm
- supervised classification
- high dimensionality
- machine learning
- text classification
- clustering method
- sequence analysis
- unsupervised clustering
- classification accuracy
- k means
- feature selection
- supervised learning
- decision trees
- protein secondary structure prediction
- mass spectrometry
- training set
- feature vectors
- geometric structure
- support vector machine
- amino acids
- feature space
- protein classification
- support vector
- self organizing maps
- remote homology detection
- multiple classifier systems
- protein structure prediction
- protein sequences
- image structure
- input image