Stability of different feature selection methods for selecting protein sequence descriptors in protein solubility classification problem.
Simon KocbekGregor StiglicIgor PernekPeter KokolPublished in: CBMS (2010)
Keyphrases
- protein sequences
- protein classification
- protein structure
- amino acids
- remote homology detection
- computational biology
- protein structure prediction
- protein folding
- amino acid sequences
- secondary structure
- protein function
- protein secondary structure
- multiple sequence alignment
- structural motifs
- protein structural
- amino acid composition
- support vector
- biological sequences
- coarse grained
- feature vectors
- machine learning
- protein secondary structure prediction
- sequence alignment
- sequence analysis
- protein protein
- computational approaches
- protein families
- predicting protein
- multiple sequence alignments