A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

By Matthew Spencer, Jesse Eickholt, Jianlin Cheng. 2014

281 citations recorded by the source corpus.

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80 percent and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test dataset of 198 proteins, achieving a Q3 accuracy of 80.7 percent and a Sov accuracy of 74.2 percent.

Subfields: Materials Chemistry, Molecular Biology, 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 Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks (2015, background): “However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images.”
Generating functional protein variants with variational autoencoders (2020, background): “61 While there have recently been several successes in applying deep learning techniques to mod62 elling protein sequences in tasks including contact prediction [19], secondary structure prediction 63 [20, 21], and prediction of the fitness effects of mutations [22], the possibility of applying gene”
DeepSF: deep convolutional neural network for mapping protein sequences to folds (2017, methodology): “eep residual convolutional neural network was designed to further improve the accuracy of contact prediction [23]. Deep learning methods have also been applied to predict protein secondary structures [24, 25] and identify protein pairs that have the same fold [8, 14]. Here, we design a one-dimension”
Adversarial vulnerability for any classifier (2018, background): “Deep neural networks are powerful models that achieve state-of-the-art performance across several domains, such as bioinformatics [1, 2], speech [3], and computer vision [4, 5].”
Deep learning for computational biology (2016, neutral): “Restricted Boltzmann machines can also be used for unsupervised pre-training of deep networks to subsequently train supervised models of protein secondary structures (Spencer et al , 2015), disordered protein regions (Eickholt & Cheng, 2013) or amino acid contacts (Eickholt & Cheng, 2012).”
Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning (2015, unknown): “Spencer et al. 30 showed that”
Sixty-five years of the long march in protein secondary structure prediction: the final stretch? (2016, methodology): “SPIDER2 was not the first method that used deep neural networks for secondary structure prediction but is the most accurate according to reported accuracy [98, 99].”
Deep learning in bioinformatics (2016, methodology): “Research in bioinformatics using human designed features as input data such as PSSM from genomics sequences or wavelet energy from EEG signals can be understood in the same context [86, 92, 172, 176].”
Deep Learning and Its Applications in Biomedicine (2018, methodology): “Spencer et al. proposed DNSS, an ab initio approach to predicting the secondary structure of proteins using deep learning network architectures [171].”
Deep learning improves antimicrobial peptide recognition (2018, methodology): “While, to the best of our knowledge, this paper is the first to propose DNN models for AMP classification, other recent DNN models improve protein secondary structure prediction (Spencer et al. , 2015), protein fold recognition (Jo et al. , 2015), drug discovery and more (LeCun et al. , 2015).”