A novel feature selection based on apriori property and correlation analysis for protein sequence classification using MapReduce.
R. BhavaniG. Sudha SadasivamPublished in: Int. J. Data Min. Bioinform. (2017)
Keyphrases
- correlation analysis
- sequence classification
- feature selection
- sequence alignment
- sequence data
- hidden markov models
- cluster analysis
- regression analysis
- correlation coefficient
- conditional random fields
- markov models
- amino acids
- discriminative learning
- protein structure
- factor analysis
- feature set
- protein sequences
- dimensionality reduction
- machine learning
- text classification
- string kernels
- support vector machine
- pairwise
- association rules
- pattern recognition
- support vector
- feature extraction
- unsupervised learning
- model selection
- higher order
- information extraction
- classification accuracy
- binding sites
- data mining