Limits...
Using neural networks and evolutionary information in decoy discrimination for protein tertiary structure prediction.

Tan CW, Jones DT - BMC Bioinformatics (2008)

Bottom Line: Various features are extracted from the training dataset of positive and negative examples and used as inputs to the neural networks.This neural network is the best among all methods tested in discriminating the native structure from a set of decoys for all decoy datasets tested.This method is demonstrated to be viable, and furthermore evolutionary information is successfully used in the neural networks to improve decoy discrimination.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Computer Science, University College London, London, UK. chingwai@ntu.edu.sg

ABSTRACT

Background: We present a novel method of protein fold decoy discrimination using machine learning, more specifically using neural networks. Here, decoy discrimination is represented as a machine learning problem, where neural networks are used to learn the native-like features of protein structures using a set of positive and negative training examples. A set of native protein structures provides the positive training examples, while negative training examples are simulated decoy structures obtained by reversing the sequences of native structures. Various features are extracted from the training dataset of positive and negative examples and used as inputs to the neural networks.

Results: Results have shown that the best performing neural network is the one that uses input information comprising of PSI-BLAST 1 profiles of residue pairs, pairwise distance and the relative solvent accessibilities of the residues. This neural network is the best among all methods tested in discriminating the native structure from a set of decoys for all decoy datasets tested.

Conclusion: This method is demonstrated to be viable, and furthermore evolutionary information is successfully used in the neural networks to improve decoy discrimination.

Show MeSH

Related in: MedlinePlus

Homologue threading method.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2267779&req=5

Figure 10: Homologue threading method.

Mentions: For the sake of convenience, this particular way of using multiple sequence information is referred to as the homologue threading method. The motivation of the homologue threading method is primarily to reduce the noise of the neural-network based decoy discrimination method by applying it to many related sequences, instead of just one sequence, and then averaging the scores obtained. This is done under the assumption that the close homologues adopt similar 3D structures to that of the native sequence. The previous neural networks used for the homologue threading method are NN-dist, NN-solvpair and NN-solvpairndist shown in Table 4. Figure 10 shows an outline of the homologue threading method.


Using neural networks and evolutionary information in decoy discrimination for protein tertiary structure prediction.

Tan CW, Jones DT - BMC Bioinformatics (2008)

Homologue threading method.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2267779&req=5

Figure 10: Homologue threading method.
Mentions: For the sake of convenience, this particular way of using multiple sequence information is referred to as the homologue threading method. The motivation of the homologue threading method is primarily to reduce the noise of the neural-network based decoy discrimination method by applying it to many related sequences, instead of just one sequence, and then averaging the scores obtained. This is done under the assumption that the close homologues adopt similar 3D structures to that of the native sequence. The previous neural networks used for the homologue threading method are NN-dist, NN-solvpair and NN-solvpairndist shown in Table 4. Figure 10 shows an outline of the homologue threading method.

Bottom Line: Various features are extracted from the training dataset of positive and negative examples and used as inputs to the neural networks.This neural network is the best among all methods tested in discriminating the native structure from a set of decoys for all decoy datasets tested.This method is demonstrated to be viable, and furthermore evolutionary information is successfully used in the neural networks to improve decoy discrimination.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Computer Science, University College London, London, UK. chingwai@ntu.edu.sg

ABSTRACT

Background: We present a novel method of protein fold decoy discrimination using machine learning, more specifically using neural networks. Here, decoy discrimination is represented as a machine learning problem, where neural networks are used to learn the native-like features of protein structures using a set of positive and negative training examples. A set of native protein structures provides the positive training examples, while negative training examples are simulated decoy structures obtained by reversing the sequences of native structures. Various features are extracted from the training dataset of positive and negative examples and used as inputs to the neural networks.

Results: Results have shown that the best performing neural network is the one that uses input information comprising of PSI-BLAST 1 profiles of residue pairs, pairwise distance and the relative solvent accessibilities of the residues. This neural network is the best among all methods tested in discriminating the native structure from a set of decoys for all decoy datasets tested.

Conclusion: This method is demonstrated to be viable, and furthermore evolutionary information is successfully used in the neural networks to improve decoy discrimination.

Show MeSH
Related in: MedlinePlus