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
Comparative Study
. 2001 Nov;10(11):2354-62.
doi: 10.1110/ps.08501.

Pcons: a neural-network-based consensus predictor that improves fold recognition

J Lundström  1 , L Rychlewski, J Bujnicki, A Elofsson
Affiliations
Comparative Study

Pcons: a neural-network-based consensus predictor that improves fold recognition

J Lundström et al. Protein Sci. 2001 Nov.

Abstract

During recent years many protein fold recognition methods have been developed, based on different algorithms and using various kinds of information. To examine the performance of these methods several evaluation experiments have been conducted. These include blind tests in CASP/CAFASP, large scale benchmarks, and long-term, continuous assessment with newly solved protein structures. These studies confirm the expectation that for different targets different methods produce the best predictions, and the final prediction accuracy could be improved if the available methods were combined in a perfect manner. In this article a neural-network-based consensus predictor, Pcons, is presented that attempts this task. Pcons attempts to select the best model out of those produced by six prediction servers, each using different methods. Pcons translates the confidence scores reported by each server into uniformly scaled values corresponding to the expected accuracy of each model. The translated scores as well as the similarity between models produced by different servers is used in the final selection. According to the analysis based on two unrelated sets of newly solved proteins, Pcons outperforms any single server by generating approximately 8%-10% more correct predictions. Furthermore, the specificity of Pcons is significantly higher than for any individual server. From analyzing different input data to Pcons it can be shown that the improvement is mainly attributable to measurement of the similarity between the different models. Pcons is freely accessible for the academic community through the protein structure-prediction metaserver at http://bioinfo.pl/meta/.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.
Description of the NN-all neural networks used in this study. (Top panel) Generation of the inputs to NN-all. First, up to 60 models are collected from six different web servers. The structure of these models and the related templates are compared to the structure of all other models and templates. Three data points are fed into the network—the score, the fraction of similar models, and the fraction of similar templates. A separate network is trained for each server. For each model obtained from one server the log of LGscore2 is predicted by a first-layer neural network. The output from these networks is then fed into the jury network.
Fig. 2.
Fig. 2.
Cumulative plot of correct versus incorrect models. To make the curves easier to analyze they are smoothed by a running average. Correct and incorrect models are defined by using LGscore2 and a cutoff of 10−3. The X-axis reports the number of incorrect models according to Scop, and the Y-axis indicates the number of correct models.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Abagyan, R.A. and Batalov, S. 1997. Do aligned sequences share the same fold? J. Mol. Biol. 273 355–368. - PubMed
    1. Alexandrov, N.N. and Luethy, R. 1998. Alignment algorithm for homology modeling and threading. Protein Sci. 7 254–258. - PMC - PubMed
    1. Altschul, S.F., Madden, T.L., Schaffer, A.A., Zhang, J., Zhang, Z., Miller, W., and Lipman, D.J. 1997. Gapped BLAST and PSI-BLAST: A new generation of protein database search programs. Nucleic Acids Res. 25 3389–3402. - PMC - PubMed
    1. Bishop, Christopher M. 1995. Neural networks for pattern recognition. Oxford University Press, Oxford, UK.
    1. Brenner, S.E., Chothia, C., and Hubbard, T.J. 1998. Assessing sequence comparison methods with reliable structurally ideied distant evolutionary relationships. Proc. Natl. Acad. Sci. 95 6073–6078. - PMC - PubMed

Publication types

LinkOut - more resources

-