Accurate prediction of protein contact maps by coupling residual two-dimensional bidirectional long short-term memory with convolutional neural networks
By Jack Hanson, Kuldip K. Paliwal, Thomas Litfin, Yuedong Yang, Yaoqi Zhou. 2018
158 citations recorded by the source corpus.
Motivation Accurate prediction of a protein contact map depends greatly on capturing as much contextual information as possible from surrounding residues for a target residue pair. Recently, ultra-deep residual convolutional networks were found to be state-of-the-art in the latest Critical Assessment of Structure Prediction techniques (CASP12) for protein contact map prediction by attempting to provide a protein-wide context at each residue pair. Recurrent neural networks have seen great success in recent protein residue classification problems due to their ability to propagate information through long protein sequences, especially Long Short-Term Memory (LSTM) cells. Here, we propose a novel protein contact map prediction method by stacking residual convolutional networks with two-dimensional residual bidirectional recurrent LSTM networks, and using both one-dimensional sequence-based and two-dimensional evolutionary coupling-based information. Results We show that the proposed method achieves a robust performance over validation and independent test sets with the Area Under the receiver operating characteristic Curve (AUC) > 0.95 in all tests. When compared to several state-of-the-art methods for independent testing of 228 proteins, the method yields an AUC value of 0.958, whereas the next-best method obtains an AUC of 0.909. More importantly, the improvement is over contacts at all sequence-position separations. Specifically, a 8.95%, 5.65% and 2.84% increase in precision were observed for the top L∕10 predictions over the next best for short, medium and long-range contacts, respectively. This confirms the usefulness of ResNets to congregate the short-range relations and 2D-BRLSTM to propagate the long-range dependencies throughout the entire protein contact map 'image'. Availability and implementation SPOT-Contact server url: http://sparks-lab.org/jack/server/SPOT-Contact/. Supplementary information Supplementary data are available at Bioinformatics online.
Subfields: 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 Molecular Biology
- Joe G. Greener
- Shaun M. Kandathil
- David T. Jones
- Kuldip K. Paliwal
- Jack Hanson
- Yaoqi Zhou
- Thomas Litfin
- Yang Zhang
Citations in the corpus
- SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning (2019, methodology): “The size limitation is mainly due to the use of SPOT-1D in the input of SPOT-Disorder2 input, which relies on the contact map prediction tool SPOT-Contact [25].”
- RNA secondary structure prediction using an ensemble of two-dimensional deep neural networks and transfer learning (2019, methodology): “Also, 2D-BLSTMs proved very effective in propagating long-range sequence dependencies in protein structure prediction 29 because of the ability of LSTM cells to remember the structural relationship between the residues that are far from each other in their sequence positions during training.”
- Deep Learning in Protein Structural Modeling and Design (2020, unknown): “909) 1,250 chains after June 2015 Hanson et al.(149)”
- Recent developments in deep learning applied to protein structure prediction (2019, methodology): “Recurrent architectures have also been used in contact prediction.(48,89) More recently, a recurrent architecture has been used to model tertiary structure.”