Limits...
Predicting the effect of missense mutations on protein function: analysis with Bayesian networks.

Needham CJ, Bradford JR, Bulpitt AJ, Care MA, Westhead DR - BMC Bioinformatics (2006)

Bottom Line: The ability of the Bayesian network to make predictions when only structural or evolutionary data was observed allowed us to conclude that structural information is a significantly better predictor of the functional consequences of a missense mutation than evolutionary information, for the dataset used.Analysis of the posterior distribution of model structures revealed that the top three strongest connections with the class node all involved structural nodes.With this in mind, we derived a simplified Bayesian network that used just these three structural descriptors, with comparable performance to that of an all node network.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing, University of Leeds, Leeds, LS2 9JT, UK. chrisn@comp.leeds.ac.uk

ABSTRACT

Background: A number of methods that use both protein structural and evolutionary information are available to predict the functional consequences of missense mutations. However, many of these methods break down if either one of the two types of data are missing. Furthermore, there is a lack of rigorous assessment of how important the different factors are to prediction.

Results: Here we use Bayesian networks to predict whether or not a missense mutation will affect the function of the protein. Bayesian networks provide a concise representation for inferring models from data, and are known to generalise well to new data. More importantly, they can handle the noisy, incomplete and uncertain nature of biological data. Our Bayesian network achieved comparable performance with previous machine learning methods. The predictive performance of learned model structures was no better than a naïve Bayes classifier. However, analysis of the posterior distribution of model structures allows biologically meaningful interpretation of relationships between the input variables.

Conclusion: The ability of the Bayesian network to make predictions when only structural or evolutionary data was observed allowed us to conclude that structural information is a significantly better predictor of the functional consequences of a missense mutation than evolutionary information, for the dataset used. Analysis of the posterior distribution of model structures revealed that the top three strongest connections with the class node all involved structural nodes. With this in mind, we derived a simplified Bayesian network that used just these three structural descriptors, with comparable performance to that of an all node network.

Show MeSH
Training set size. Performance of naïve Bayes classifier and structure  with parameters learned sequentially. The AUC (area under the ROC curve) is plotted against the number of training examples.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC1586217&req=5

Figure 5: Training set size. Performance of naïve Bayes classifier and structure with parameters learned sequentially. The AUC (area under the ROC curve) is plotted against the number of training examples.

Mentions: In order to assess how much data is needed for training the Bayesian networks, sequential learning of the model parameters was performed. The 'mixed' dataset was divided into two. One half was used as the test validation set, and the Bayesian networks were trained on the other half. Figure 5 shows a plot of training set size vs. classifier performance, measured using area under the ROC curve. The result is as expected. The naïve model (with its 43 parameters) gradually improves its performance as its parameters are sequentially learned, with excellent performance after 400 examples (and good after as few as 50). The learned BN structure has 182 free parameters and it out performs the naïve classifier after 1000 training examples.


Predicting the effect of missense mutations on protein function: analysis with Bayesian networks.

Needham CJ, Bradford JR, Bulpitt AJ, Care MA, Westhead DR - BMC Bioinformatics (2006)

Training set size. Performance of naïve Bayes classifier and structure  with parameters learned sequentially. The AUC (area under the ROC curve) is plotted against the number of training examples.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC1586217&req=5

Figure 5: Training set size. Performance of naïve Bayes classifier and structure with parameters learned sequentially. The AUC (area under the ROC curve) is plotted against the number of training examples.
Mentions: In order to assess how much data is needed for training the Bayesian networks, sequential learning of the model parameters was performed. The 'mixed' dataset was divided into two. One half was used as the test validation set, and the Bayesian networks were trained on the other half. Figure 5 shows a plot of training set size vs. classifier performance, measured using area under the ROC curve. The result is as expected. The naïve model (with its 43 parameters) gradually improves its performance as its parameters are sequentially learned, with excellent performance after 400 examples (and good after as few as 50). The learned BN structure has 182 free parameters and it out performs the naïve classifier after 1000 training examples.

Bottom Line: The ability of the Bayesian network to make predictions when only structural or evolutionary data was observed allowed us to conclude that structural information is a significantly better predictor of the functional consequences of a missense mutation than evolutionary information, for the dataset used.Analysis of the posterior distribution of model structures revealed that the top three strongest connections with the class node all involved structural nodes.With this in mind, we derived a simplified Bayesian network that used just these three structural descriptors, with comparable performance to that of an all node network.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing, University of Leeds, Leeds, LS2 9JT, UK. chrisn@comp.leeds.ac.uk

ABSTRACT

Background: A number of methods that use both protein structural and evolutionary information are available to predict the functional consequences of missense mutations. However, many of these methods break down if either one of the two types of data are missing. Furthermore, there is a lack of rigorous assessment of how important the different factors are to prediction.

Results: Here we use Bayesian networks to predict whether or not a missense mutation will affect the function of the protein. Bayesian networks provide a concise representation for inferring models from data, and are known to generalise well to new data. More importantly, they can handle the noisy, incomplete and uncertain nature of biological data. Our Bayesian network achieved comparable performance with previous machine learning methods. The predictive performance of learned model structures was no better than a naïve Bayes classifier. However, analysis of the posterior distribution of model structures allows biologically meaningful interpretation of relationships between the input variables.

Conclusion: The ability of the Bayesian network to make predictions when only structural or evolutionary data was observed allowed us to conclude that structural information is a significantly better predictor of the functional consequences of a missense mutation than evolutionary information, for the dataset used. Analysis of the posterior distribution of model structures revealed that the top three strongest connections with the class node all involved structural nodes. With this in mind, we derived a simplified Bayesian network that used just these three structural descriptors, with comparable performance to that of an all node network.

Show MeSH