Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility.
Rhys HeffernanYuedong YangKuldip K. PaliwalYaoqi ZhouPublished in: Bioinform. (2017)
Keyphrases
- recurrent neural networks
- protein secondary structure
- long short term memory
- secondary structure
- protein sequences
- protein secondary structure prediction
- solvent accessibility
- tertiary structure
- neural network
- feed forward
- protein structure
- amino acids
- computational methods
- protein folding
- amino acid sequences
- recurrent networks
- artificial neural networks
- protein structure prediction
- computational biology
- echo state networks
- prediction accuracy
- chaotic time series
- support vector machine
- coarse grained
- protein function
- protein interaction
- back propagation
- support vector