DisoLipPred: accurate prediction of disordered lipid-binding residues in protein sequences with deep recurrent networks and transfer learning.
Akila KatuwawalaBi ZhaoLukasz A. KurganPublished in: Bioinform. (2021)
Keyphrases
- protein sequences
- transfer learning
- recurrent networks
- protein secondary structure
- protein classification
- protein structure prediction
- multiple sequence alignments
- computational biology
- learning tasks
- protein structure
- amino acids
- labeled data
- experimentally determined
- amino acid sequences
- active learning
- reinforcement learning
- protein function
- recurrent neural networks
- structure learning
- machine learning
- sequence analysis
- solvent accessibility
- secondary structure
- transfer knowledge
- multi task
- semi supervised learning
- collaborative filtering
- feed forward
- text categorization
- protein structural
- learning algorithm
- amino acid composition
- neural network
- biologically inspired
- text classification
- multiple sequence alignment
- machine learning algorithms
- remote homology detection
- multiple alignment
- psi blast
- physicochemical properties
- unlabeled data
- semi supervised
- data sets