pubmed.ncbi.nlm.nih.gov

Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network - PubMed

Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network

Eshel Faraggi et al. Proteins. 2009 Mar.

Abstract

This article attempts to increase the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins through improved learning. Most methods developed for improving the backpropagation algorithm of artificial neural networks are limited to small neural networks. Here, we introduce a guided-learning method suitable for networks of any size. The method employs a part of the weights for guiding and the other part for training and optimization. We demonstrate this technique by predicting residue solvent accessibility and real-value backbone torsion angles of proteins. In this application, the guiding factor is designed to satisfy the intuitive condition that for most residues, the contribution of a residue to the structural properties of another residue is smaller for greater separation in the protein-sequence distance between the two residues. We show that the guided-learning method makes a 2-4% reduction in 10-fold cross-validated mean absolute errors (MAE) for predicting residue solvent accessibility and backbone torsion angles, regardless of the size of database, the number of hidden layers and the size of input windows. This together with introduction of two-layer neural network with a bipolar activation function leads to a new method that has a MAE of 0.11 for residue solvent accessibility, 36 degrees for psi, and 22 degrees for phi. The method is available as a Real-SPINE 3.0 server in http://sparks.informatics.iupui.edu.

PubMed Disclaimer

Figures

**Figure 1**
Q₁₀ score for the ϕ angle for 10 evenly spaced bins.

**Figure 2**
Q₁₀ score for the ψ angle for 10 evenly spaced bins.

**Figure 3**
Q₁₀ score for the residue surface accessibility for 10 evenly spaced bins with a [0,1] normalization.

Cited by

Computational prediction of MoRFs based on protein sequences and minimax probability machine.
He H, Zhao J, Sun G. He H, et al. BMC Bioinformatics. 2019 Oct 28;20(1):529. doi: 10.1186/s12859-019-3111-z. BMC Bioinformatics. 2019. PMID: 31660849 Free PMC article.
A sparse autoencoder-based deep neural network for protein solvent accessibility and contact number prediction.
Deng L, Fan C, Zeng Z. Deng L, et al. BMC Bioinformatics. 2017 Dec 28;18(Suppl 16):569. doi: 10.1186/s12859-017-1971-7. BMC Bioinformatics. 2017. PMID: 29297299 Free PMC article.
AcconPred: Predicting Solvent Accessibility and Contact Number Simultaneously by a Multitask Learning Framework under the Conditional Neural Fields Model.
Ma J, Wang S. Ma J, et al. Biomed Res Int. 2015;2015:678764. doi: 10.1155/2015/678764. Epub 2015 Aug 3. Biomed Res Int. 2015. PMID: 26339631 Free PMC article.
Improved de novo structure prediction in CASP11 by incorporating coevolution information into Rosetta.
Ovchinnikov S, Kim DE, Wang RY, Liu Y, DiMaio F, Baker D. Ovchinnikov S, et al. Proteins. 2016 Sep;84 Suppl 1(Suppl 1):67-75. doi: 10.1002/prot.24974. Epub 2016 Feb 24. Proteins. 2016. PMID: 26677056 Free PMC article.
Fluctuations of backbone torsion angles obtained from NMR-determined structures and their prediction.
Zhang T, Faraggi E, Zhou Y. Zhang T, et al. Proteins. 2010 Dec;78(16):3353-62. doi: 10.1002/prot.22842. Proteins. 2010. PMID: 20818661 Free PMC article.

References

1. Cheng J, Baldi P. A machine learning information retrieval approach to protein fold recognition. Bioinformatics. 2006;22:1456–1463. - PubMed
1. Rost B. TOPITS: Threading one-dimensional predictions into three-dimensional structures; Third International Conference on Intelligent Systems for Molecular Biology; 1995; AAAI Press; pp. 314–321. - PubMed
1. Rost B, Sander C. Protein fold recognition by prediction-based threading. J. Mol. Biol. 1997;270:471–480. - PubMed
1. Przybylski D, Rost B. Improving fold recognition without folds. J. Mol. Biol. 2004;341:255–269. - PubMed
1. Qiu J, Elber R. SSALN: an alignment algorithm using structure-dependent substitution matrices and gap penalties learned from structurally aligned protein pairs. Proteins. 2006;62:881–891. - PubMed

Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network - PubMed