SVMQA: support–vector-machine-based protein single-model quality assessment
Authors:
Open Access
- 13 April 2017
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 33 (16) , 2496-2503
Abstract
The accurate ranking of predicted structural models and selecting the best model from a given candidate pool remain as open problems in the field of structural bioinformatics. The quality assessment (QA) methods used to address these problems can be grouped into two categories: consensus methods and single-model methods. Consensus methods in general perform better and attain higher correlation between predicted and true quality measures. However, these methods frequently fail to generate proper quality scores for native-like structures which are distinct from the rest of the pool. Conversely, single-model methods do not suffer from this drawback and are better suited for real-life applications where many models from various sources may not be readily available. In this study, we developed a support-vector-machine-based single-model global quality assessment (SVMQA) method. For a given protein model, the SVMQA method predicts TM-score and GDT_TS score based on a feature vector containing statistical potential energy terms and consistency-based terms between the actual structural features (extracted from the three-dimensional coordinates) and predicted values (from primary sequence). We trained SVMQA using CASP8, CASP9 and CASP10 targets and determined the machine parameters by 10-fold cross-validation. We evaluated the performance of our SVMQA method on various benchmarking datasets. Results show that SVMQA outperformed the existing best single-model QA methods both in ranking provided protein models and in selecting the best model from the pool. According to the CASP12 assessment, SVMQA was the best method in selecting good-quality models from decoys in terms of GDTloss. SVMQA method can be freely downloaded from http://lee.kias.re.kr/SVMQA/SVMQA_eval.tar.gz. Supplementary data are available at Bioinformatics online.Keywords
This publication has 37 references indexed in Scilit:
- Hidden Information Revealed by Optimal Community Structure from a Protein-Complex Bipartite Network Improves Protein Function PredictionPLOS ONE, 2013
- Improved model quality assessment using ProQ2BMC Bioinformatics, 2012
- GOAP: A Generalized Orientation-Dependent, All-Atom Statistical Potential for Protein Structure PredictionBiophysical Journal, 2011
- A Novel Side-Chain Orientation Dependent Potential Derived from Random-Walk Reference State for Protein Fold Selection and Structure PredictionPLOS ONE, 2010
- How significant is a protein structure similarity with TM-score = 0.5?Bioinformatics, 2010
- Assessment of global and local model quality in CASP8 using Pcons and ProQProteins: Structure, Function, and Bioinformatics, 2009
- Evaluating the absolute quality of a single protein model using structural features and support vector machinesProteins: Structure, Function, and Bioinformatics, 2008
- Ab initio folding of terminal segments with secondary structures reveals the fine difference between two closely related all‐atom statistical energy functionsProtein Science, 2008
- OPUS-PSP: An Orientation-dependent Statistical All-atom Potential Derived from Side-chain PackingJournal of Molecular Biology, 2008
- Initial sequencing and analysis of the human genomeNature, 2001