Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks

By Z. Li, Yizhou Yu. 2016

121 citations recorded by the source corpus.

Protein secondary structure prediction is an important problem in bioinformatics. Inspired by the recent successes of deep neural networks, in this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features. Our deep architecture leverages convolutional neural networks with different kernel sizes to extract multiscale local contextual features. In addition, considering long-range dependencies existing in amino acid sequences, we set up a bidirectional neural network consisting of gated recurrent unit to capture global contextual features. Furthermore, multi-task learning is utilized to predict secondary structure labels and amino-acid solvent accessibility simultaneously. Our proposed deep network demonstrates its effectiveness by achieving state-of-the-art performance, i.e., 69.7% Q8 accuracy on the public benchmark CB513, 76.9% Q8 accuracy on CASP10 and 73.1% Q8 accuracy on CASP11. Our model and results are publicly available.

Subfields: Materials Chemistry, Molecular Biology

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

Citations in the corpus

Mut2Vec: distributed representation of cancerous mutations (2018, background): “…learning techniques has been making remarkable improvements in various applications such as text mining [1], speech recognition [2], image classification [3] and even the prediction tasks in biomedical domain such as protein secondary structure prediction [4] and DNA-protein binding prediction [5].”
High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures (2018, methodology): “its training set is twice as large as the one used by the other methods. Model Best Single Ensemble MUFOLD-SS [11] 70.5 70.6 NCCNN [3] 70.3 71.4 biRNN-CRF [17] 69.4 70.9 DeepMSCNN [2] 70.0 70.6 DCRNN [21] 69.4 69.7 BLSTM [28] 67.4 N/A GSN [40] 66.4 N/A DeepCNF [33] N/A 68.3 Ours 69.8 70.7 Table 4: C”
Ensemble deep learning in bioinformatics (2020, methodology): “Extending on the use of a single RNN, the ensemble of variants of RNNs with CNNs is a common hybrid architecture in recent applications that seeks to combine the power of RNN in analysing sequential data and CNN on extracting local features 71,72 .”
Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction (2017, methodology): “We focus here on the particular details of our ﬁnal convolutional architecture, which outperforms previously reported attempts at using convolutions for protein secondary structure prediction (Li & Yu, 2016; Zhou & Troyanskaya, 2014; Lin, Lanchantin, & Qi, 2016; Wang et al ., 2016).”
Neural Network Detection of Data Sequences in Communication Systems (2018, background): “can be performed using recurrent neural networks (RNN) [6], [7], which are well established for sequence estimation in different problems such as neural machine translation [32], speech recognition [29], or bioinformatics [34].”