pubmed.ncbi.nlm.nih.gov

Protein contact prediction using metagenome sequence data and residual neural networks - PubMed

  • ️Wed Jan 01 2020

Protein contact prediction using metagenome sequence data and residual neural networks

Qi Wu et al. Bioinformatics. 2020.

Abstract

Motivation: Almost all protein residue contact prediction methods rely on the availability of deep multiple sequence alignments (MSAs). However, many proteins from the poorly populated families do not have sufficient number of homologs in the conventional UniProt database. Here we aim to solve this issue by exploring the rich sequence data from the metagenome sequencing projects.

Results: Based on the improved MSA constructed from the metagenome sequence data, we developed MapPred, a new deep learning-based contact prediction method. MapPred consists of two component methods, DeepMSA and DeepMeta, both trained with the residual neural networks. DeepMSA was inspired by the recent method DeepCov, which was trained on 441 matrices of covariance features. By considering the symmetry of contact map, we reduced the number of matrices to 231, which makes the training more efficient in DeepMSA. Experiments show that DeepMSA outperforms DeepCov by 10-13% in precision. DeepMeta works by combining predicted contacts and other sequence profile features. Experiments on three benchmark datasets suggest that the contribution from the metagenome sequence data is significant with P-values less than 4.04E-17. MapPred is shown to be complementary and comparable the state-of-the-art methods. The success of MapPred is attributed to three factors: the deeper MSA from the metagenome sequence data, improved feature design in DeepMSA and optimized training by the residual neural networks.

Availability and implementation: http://yanglab.nankai.edu.cn/mappred/.

Supplementary information: Supplementary data are available at Bioinformatics online.

© The Author(s) 2019. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.

The architecture of the proposed methods. (A) is the flowchart of MapPred for contact map prediction. (B) is the MSA generator for constructing an MSA for a protein sequence. (C) is structure for the network used in the method DeepMSA. (D) is the structure for each residual block

Fig. 2.
Fig. 2.

The comparison of DeepMSA with DeepCov on the three benchmark datasets

Fig. 3.
Fig. 3.

Head-to-head comparisons between the precisions (%) of DeepMSA and DeepCov on three benchmark datasets

Fig. 4.
Fig. 4.

The precisions of DeepMSA on the benchmark datasets with MSAs enriched with metagenomic sequences at varying bit score thresholds

Fig. 5.
Fig. 5.

The precisions of CCMpred and DeepMSA on the benchmark datasets with MSAs generated from the Uniclust30 and the MetaDB databases

Similar articles

Cited by

References

    1. Adhikari B. et al. (2018) DNCON2: improved protein contact prediction using two-level deep convolutional neural networks. Bioinformatics, 34, 1466–1472. - PMC - PubMed
    1. Berman H.M. et al. (2000) The Protein Data Bank. Nucleic Acids Res., 28, 235–242. - PMC - PubMed
    1. Cheng J., Baldi P. (2007) Improved residue contact prediction using support vector machines and a large feature set. BMC Bioinformatics, 8, 113. - PMC - PubMed
    1. Ekeberg M. et al. (2013) Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models. Phys. Rev. E Stat. Nonlinear Soft Matter Phys., 87, 012707. - PubMed
    1. Göbel U. et al. (1994) Correlated mutations and residue contacts in proteins. Proteins Struct. Funct. Bioinform., 18, 309–317. - PubMed

Publication types

MeSH terms

Substances