SPOT-1D2: Improving Protein Secondary Structure Prediction using High Sequence Identity Training Set and an Ensemble of Recurrent and Residual-convolutional Neural Networks.
Jaspreet SinghJaswinder SinghKuldip K. PaliwalAndrew BuschYaoqi ZhouPublished in: CIBCB (2021)
Keyphrases
- protein secondary structure prediction
- training set
- convolutional neural networks
- tertiary structure
- protein secondary structure
- training data
- test set
- training samples
- psi blast
- data sets
- classification accuracy
- machine learning
- classification error
- base classifiers
- nearest neighbor
- cross validation
- convolutional network
- recurrent neural networks
- feature space
- classification algorithm
- supervised learning
- active learning
- decision trees
- feature selection
- neural network
- generalization error