Sequence-Based Random Projection Ensemble Approach to Identify Hotspot Residues from Whole Protein Sequence.
Peng ChenShanShan HuBing WangJun ZhangPublished in: ICIC (2) (2015)
Keyphrases
- protein sequences
- random projections
- biological sequences
- sequence analysis
- amino acids
- protein structural
- protein structure
- sequence alignment
- multiple sequence alignments
- multiple sequence alignment
- genome sequences
- multiple alignment
- solvent accessibility
- amino acid sequences
- secondary structure
- protein folding
- protein structure prediction
- protein families
- structural motifs
- amino acid composition
- original data
- principal component analysis
- protein function
- dimensionality reduction
- image reconstruction
- tertiary structure
- experimentally determined
- dimension reduction
- random sampling
- machine learning
- psi blast
- high quality
- protein protein
- document clustering
- hash functions
- feature vectors
- image classification
- molecular biology