Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2014 Apr 15:14:13.
doi: 10.1186/1472-6807-14-13.

Designing and evaluating the MULTICOM protein local and global model quality prediction methods in the CASP10 experiment

Renzhi Cao, Zheng Wang, Jianlin Cheng  1
Affiliations

Designing and evaluating the MULTICOM protein local and global model quality prediction methods in the CASP10 experiment

Renzhi Cao et al. BMC Struct Biol. .

Abstract

Background: Protein model quality assessment is an essential component of generating and using protein structural models. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein structural models.

Results: MULTICOM-REFINE was a clustering approach that used the average pairwise structural similarity between models to measure the global quality and the average Euclidean distance between a model and several top ranked models to measure the local quality. MULTICOM-CLUSTER and MULTICOM-NOVEL were two new support vector machine-based methods of predicting both the local and global quality of a single protein model. MULTICOM-CONSTRUCT was a new weighted pairwise model comparison (clustering) method that used the weighted average similarity between models in a pool to measure the global model quality. Our experiments showed that the pairwise model assessment methods worked better when a large portion of models in the pool were of good quality, whereas single-model quality assessment methods performed better on some hard targets when only a small portion of models in the pool were of reasonable quality.

Conclusions: Since digging out a few good models from a large pool of low-quality models is a major challenge in protein structure prediction, single model quality assessment methods appear to be poised to make important contributions to protein structure modeling. The other interesting finding was that single-model quality assessment scores could be used to weight the models by the consensus pairwise model comparison method to improve its accuracy.

PubMed Disclaimer

Figures

Figure 1
Figure 1
The per-target correlation scores of each target against the average real quality of the largest model cluster divided by the average real quality of all models of this target on Stage 2.
Figure 2
Figure 2
The influence of side chain on average correlation and loss of both Stage 1 and Stage 2. A shows the average correlation of the predictions with or without side-chain repacking, and B demonstrates the loss of the predictions with or without side-chain repacking on both Stage 1 and Stage 2. The tool SCWRL [30] is used for the side-chain repacking.
Figure 3
Figure 3
The hierarchy tree of T0741 on Stage 1. All models in the circle form the largest cluster in this target. The rightmost column of Figure  3 lists the real GDT-TS score of each model. The models in the circle form the largest cluster. The model with the underline real GDT-TS score is the best model in this target.
Figure 4
Figure 4
The real GDT-TS score and predicted GDT-TS score of MULTICOM-REFINE and MULTICOM-NOVEL for T0684 on Stage 1 and Stage 2.
See this image and copyright information in PMC

References

    1. Eisenhaber F, Persson B, Argos P. Protein structure prediction: recognition of primary, secondary, and tertiary structural features from amino acid sequence. Crit Rev Biochem Mol Biol. 1995;30(1):1–94. doi: 10.3109/10409239509085139. - DOI - PubMed
    1. Rost B. Protein structure prediction in 1D, 2D, and 3D. Encyclopaedia Comput Chem. 1998;3:2242–2255.
    1. Cheng J. A multi-template combination algorithm for protein comparative modeling. BMC Struct Biol. 2008;8(1):18. doi: 10.1186/1472-6807-8-18. - DOI - PMC - PubMed
    1. Zhang Y, Skolnick J. Automated structure prediction of weakly homologous proteins on a genomic scale. Proc Natl Acad Sci U S A. 2004;101(20):7594–7599. doi: 10.1073/pnas.0305695101. - DOI - PMC - PubMed
    1. Sali A, Blundell T. Comparative protein modelling by satisfaction of spatial restraints. Protein Structure Distance Anal. 1994;64:C86. - PubMed

Publication types

LinkOut - more resources