An iterative self‐refining and self‐evaluating approach for protein model quality estimation

Zheng Wang; Jianlin Cheng

doi:10.1002/pro.764

journal article Open Access Nov 23, 2011

An iterative self‐refining and self‐evaluating approach for protein model quality estimation

Zheng Wang

Jianlin Cheng

Protein Science Vol. 21 No. 1 pp. 142-151 · Wiley

View at Publisher Save 10.1002/pro.764

Abstract

AbstractEvaluating or predicting the quality of protein models (i.e., predicted protein tertiary structures) without knowing their native structures is important for selecting and appropriately using protein models. We describe an iterative approach that improves the performances of protein Model Quality Assurance Programs (MQAPs). Given the initial quality scores of a list of models assigned by a MQAP, the method iteratively refines the scores until the ranking of the models does not change. We applied the method to the model quality assessment data generated by 30 MQAPs during the Eighth Critical Assessment of Techniques for Protein Structure Prediction. To various degrees, our method increased the average correlation between predicted and real quality scores of 25 out of 30 MQAPs and reduced the average loss (i.e., the difference between the top ranked model and the best model) for 28 MQAPs. Particularly, for MQAPs with low average correlations (<0.4), the correlation can be increased by several times. Similar experiments conducted on the CASP9 MQAPs also demonstrated the effectiveness of the method. Our method is a hybrid method that combines the original method of a MQAP and the pair‐wise comparison clustering method. It can achieve a high accuracy similar to a full pair‐wise clustering method, but with much less computation time when evaluating hundreds of models. Furthermore, without knowing native structures, the iterative refining method can evaluate the performance of a MQAP by analyzing its model quality predictions.

Topics

No keywords indexed for this article. Browse by subject →

References

23

[1]

Protein Structure Prediction and Structural Genomics

David Baker, Andrej Šali

Science 10.1126/science.1065659

[2]

A multi-template combination algorithm for protein comparative modeling

Jianlin Cheng

BMC Structural Biology 10.1186/1472-6807-8-18

[3]

Progress and challenges in protein structure prediction

Yang Zhang

Current Opinion in Structural Biology 10.1016/j.sbi.2008.02.004

[4]

Benchmarking consensus model quality assessment for protein fold recognition

Liam J. McGuffin

BMC Bioinformatics 10.1186/1471-2105-8-345

[5]

The ModFOLD server for the quality assessment of protein structural models

Liam J. McGuffin

Bioinformatics 10.1093/bioinformatics/btn014

[6]

Model quality assessment using distance constraints from alignments

Martin Paluszewski, Kevin Karplus

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.22262

[7]

Prediction of global and local model quality in CASP7 using Pcons and ProQ

Björn Wallner, Arne Elofsson

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.21774

[8]

SPICKER: A clustering approach to identify near‐native protein folds

Yang Zhang, Jeffrey Skolnick

Journal of Computational Chemistry 10.1002/jcc.20011

[9]

3D-Jury: a simple approach to improve protein structure predictions

Krzysztof Ginalski, Arne Elofsson, Daniel Fischer et al.

Bioinformatics 10.1093/bioinformatics/btg124

[10]

10.1002/prot.22491

[11]

10.1002/prot.22288

[12]

QMEAN: A comprehensive scoring function for model quality assessment

Pascal Benkert, Silvio C. E. Tosatto, Dietmar Schomburg

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.21715

[13]

Predicting reliable regions in protein sequence alignments

Melissa Cline, Richard Hughey, Kevin Karplus

Bioinformatics 10.1093/bioinformatics/18.2.306

[14]

Ranking predicted protein structures with support vector regression

Jian Qiu, Will Sheffler, David Baker et al.

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.21809

[15]

Can correct protein models be identified?

Björn Wallner, Arne Elofsson

Protein Science 10.1110/ps.0236803

[16]

Evaluating the absolute quality of a single protein model using structural features and support vector machines

Zheng Wang, Allison N. Tegge, Jianlin Cheng

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.22275

[17]

Assessment of predictions in the model quality assessment category

Domenico Cozzetto, Andriy Kryshtafovych, Michele Ceriani et al.

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.21669

[18]

Prediction of global and local quality of CASP8 models by MULTICOM series

Jianlin Cheng, Zheng Wang, Allison N. Tegge et al.

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.22487

[19]

Scoring function for automated assessment of protein structure template quality

Yang Zhang, Jeffrey Skolnick

Proteins: Structure, Function, and Bioinformatics 10.1002/prot.20264

[20]

LGA: a method for finding 3D similarities in protein structures

A. Zemla

Nucleic Acids Research 10.1093/nar/gkg571

[21]

OPUS‐Ca: A knowledge‐based potential function requiring only Cα positions

Yinghao Wu, Mingyang Lu, Mingzhi Chen et al.

Protein Science 10.1110/ps.072796107

[22]

10.1186/1472-6807-8-52

[23]

10.1093/bioinformatics/btr268

Cited By

4

Benchmarking Deep Networks for Predicting Residue-Specific Quality of Individual Protein Models in CASP11

Tong Liu, Yiheng Wang · 2016

Scientific Reports

Metrics

4

Citations

23

References

Details

Published: Nov 23, 2011
Vol/Issue: 21(1)
Pages: 142-151
License: View

Authors

Qinghai University

Department of Electrical Engineering and Computer Science, University of Missouri , Columbia, MO 65211, USA

Funding

National Institutes of Health Award: 1R01GM093123

Cite This Article

Zheng Wang, Jianlin Cheng (2011). An iterative self‐refining and self‐evaluating approach for protein model quality estimation. Protein Science, 21(1), 142-151. https://doi.org/10.1002/pro.764

An iterative self‐refining and self‐evaluating approach for protein model quality estimation

You May Also Like