Exploiting the past and the future in protein secondary structure prediction

By Pierre Baldi, Søren Brunak, Paolo Frasconi, Giovanni Soda, Gianluca Pollastri. 1999

Subfields: Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Biology & Bioinformatics

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “BRNNs were successfully applied to secondary protein structure prediction (Baldi, Brunak, Frasconi, Pollastri, & Soda, 1999).”
Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction (2014, background): “Secondary structures are commonly classiﬁed to 8 states (Kabsch & Sander, 1983) or be further combined into 3 states (Singh, 2005).”
Classifying Unprompted Speech by Retraining LSTM Nets (2005, background): “A solution is bidirectional training [13] [1] [2]: the input is presented forwards and backwards to two separate recurrent nets, both of which are connected to the same output layer.”
Learning to play Go using recursive neural networks (2008, unknown): “(Baldi et al., 1999) to two dimensional problems.”
Protein secondary structure prediction for a single-sequence using hidden semi-Markov models (2006, methodology): “Among the current best methods that use evolutionary information (multiple alignments, PSI-BLAST profiles), one can mention PSIPRED [1], Porter [23], SSpro [24], APSSP2 [2], SVMpsi [9], PHDpsi [25], JPRED2 [4] and PROF [26].”
Deep learning methods in protein structure prediction (2020, background): “Bidirectional versions of RNNs (BRNN) are also possible [47] and particularly appropriate in PSA predictions, where data instances are not sequences in time but in space and propagation of contextual information in both directions is desirable.”
Combining prediction of secondary structure and solvent accessibility in proteins (2005, methodology): “5,9,27,37 Using a training set consisting of 860 NR protein chains, we ﬁrst trained a number of Elman-type recurrent NNs that do not use the information about RSA of an amino acid residue.”
A New Model for Stock Price Movements Prediction Using Deep Neural Network (2017, background): “The idea behind BGRU is the idea of bidirectional recurrent neural network in [2, 22].”
Protein secondary structure prediction using modular reciprocal bidirectional recurrent neural networks (2010, methodology): “[8] are resorted by creating shorter paths (shortcuts) between the inputs and outputs [14].”
Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles (2002, methodology): “Finally, at the algorithmic level, new bidirectional recurrent neural network architectures were introduced in [6] in combination with BLAST pro les to produce a rst-generation secondary structure predictor SSpro 1.”
Framewise phoneme classification with bidirectional LSTM and other neural network architectures (2005, unknown): “BIDIRECTIONAL RECURRENT NEURAL NETS The basic idea of bidirectional recurrent neural nets (BRNNs) (Schuster and Paliwal, 1997; Baldi et al., 1999) is to present each training sequence forwards and backwards to two separate recurrent nets, both of which are connected to the same output layer.”
Prediction of continuous B‐cell epitopes in an antigen using recurrent neural network (2006, methodology): “45 Therefore, we tried RNN in our study and interestingly the performance of RNN is found to be better than FNN (Table III).”