Limits...
Is EC class predictable from reaction mechanism?

Nath N, Mitchell JB - BMC Bioinformatics (2012)

Bottom Line: SVM and RF models perform comparably well; kNN is less successful.Oxidoreductases, hydrolases, and to some extent isomerases and ligases, have clear chemical signatures, making them easier to predict than transferases and lyases.We find evidence that isomerases as a class are notably mechanistically diverse and that their one shared property, of substrate and product being isomers, can arise in various unrelated ways.The performance of the different machine learning algorithms is in line with many cheminformatics applications, with SVM and RF being roughly equally effective. kNN is less successful, given the role that non-local information plays in successful classification.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biomedical Sciences Research Complex and EaStCHEM School of Chemistry, Purdie Building, University of St Andrews, North Haugh, St Andrews, Scotland KY16 9ST, UK.

ABSTRACT

Background: We investigate the relationships between the EC (Enzyme Commission) class, the associated chemical reaction, and the reaction mechanism by building predictive models using Support Vector Machine (SVM), Random Forest (RF) and k-Nearest Neighbours (kNN). We consider two ways of encoding the reaction mechanism in descriptors, and also three approaches that encode only the overall chemical reaction. Both cross-validation and also an external test set are used.

Results: The three descriptor sets encoding overall chemical transformation perform better than the two descriptions of mechanism. SVM and RF models perform comparably well; kNN is less successful. Oxidoreductases and hydrolases are relatively well predicted by all types of descriptor; isomerases are well predicted by overall reaction descriptors but not by mechanistic ones.

Conclusions: Our results suggest that pairs of similar enzyme reactions tend to proceed by different mechanisms. Oxidoreductases, hydrolases, and to some extent isomerases and ligases, have clear chemical signatures, making them easier to predict than transferases and lyases. We find evidence that isomerases as a class are notably mechanistically diverse and that their one shared property, of substrate and product being isomers, can arise in various unrelated ways.The performance of the different machine learning algorithms is in line with many cheminformatics applications, with SVM and RF being roughly equally effective. kNN is less successful, given the role that non-local information plays in successful classification. We note also that, despite a lack of clarity in the literature, EC number prediction is not a single problem; the challenge of predicting protein function from available sequence data is quite different from assigning an EC classification from a cheminformatics representation of a reaction.

Show MeSH

Related in: MedlinePlus

Workflow of the cross-validation exercise. Flow chart illustrating the workflow used in the cross-validation part of this study.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3368749&req=5

Figure 2: Workflow of the cross-validation exercise. Flow chart illustrating the workflow used in the cross-validation part of this study.

Mentions: There are many methods for estimating the performance of machine learning such as the hold-out method, leave-one-out, and k-fold cross-validation. In the first part of this study, we performed 10 fold cross-validation to estimate classifier performance. The cross-validation involves training and prediction procedures in which the class instances were randomly distributed into 10 folds, where nine out of 10 were used as a training set, and the remaining one as the test set. N-fold cross-validation has been widely accepted as a reliable method for calculating generalization accuracy and experiments have shown that cross-validation is relatively unbiased [49]. Our procedure is illustrated in the flow chart of Figure 2. In addition to the cross-validation results, we also calculate the out-of-bag accuracy for the RF models.


Is EC class predictable from reaction mechanism?

Nath N, Mitchell JB - BMC Bioinformatics (2012)

Workflow of the cross-validation exercise. Flow chart illustrating the workflow used in the cross-validation part of this study.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3368749&req=5

Figure 2: Workflow of the cross-validation exercise. Flow chart illustrating the workflow used in the cross-validation part of this study.
Mentions: There are many methods for estimating the performance of machine learning such as the hold-out method, leave-one-out, and k-fold cross-validation. In the first part of this study, we performed 10 fold cross-validation to estimate classifier performance. The cross-validation involves training and prediction procedures in which the class instances were randomly distributed into 10 folds, where nine out of 10 were used as a training set, and the remaining one as the test set. N-fold cross-validation has been widely accepted as a reliable method for calculating generalization accuracy and experiments have shown that cross-validation is relatively unbiased [49]. Our procedure is illustrated in the flow chart of Figure 2. In addition to the cross-validation results, we also calculate the out-of-bag accuracy for the RF models.

Bottom Line: SVM and RF models perform comparably well; kNN is less successful.Oxidoreductases, hydrolases, and to some extent isomerases and ligases, have clear chemical signatures, making them easier to predict than transferases and lyases.We find evidence that isomerases as a class are notably mechanistically diverse and that their one shared property, of substrate and product being isomers, can arise in various unrelated ways.The performance of the different machine learning algorithms is in line with many cheminformatics applications, with SVM and RF being roughly equally effective. kNN is less successful, given the role that non-local information plays in successful classification.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biomedical Sciences Research Complex and EaStCHEM School of Chemistry, Purdie Building, University of St Andrews, North Haugh, St Andrews, Scotland KY16 9ST, UK.

ABSTRACT

Background: We investigate the relationships between the EC (Enzyme Commission) class, the associated chemical reaction, and the reaction mechanism by building predictive models using Support Vector Machine (SVM), Random Forest (RF) and k-Nearest Neighbours (kNN). We consider two ways of encoding the reaction mechanism in descriptors, and also three approaches that encode only the overall chemical reaction. Both cross-validation and also an external test set are used.

Results: The three descriptor sets encoding overall chemical transformation perform better than the two descriptions of mechanism. SVM and RF models perform comparably well; kNN is less successful. Oxidoreductases and hydrolases are relatively well predicted by all types of descriptor; isomerases are well predicted by overall reaction descriptors but not by mechanistic ones.

Conclusions: Our results suggest that pairs of similar enzyme reactions tend to proceed by different mechanisms. Oxidoreductases, hydrolases, and to some extent isomerases and ligases, have clear chemical signatures, making them easier to predict than transferases and lyases. We find evidence that isomerases as a class are notably mechanistically diverse and that their one shared property, of substrate and product being isomers, can arise in various unrelated ways.The performance of the different machine learning algorithms is in line with many cheminformatics applications, with SVM and RF being roughly equally effective. kNN is less successful, given the role that non-local information plays in successful classification. We note also that, despite a lack of clarity in the literature, EC number prediction is not a single problem; the challenge of predicting protein function from available sequence data is quite different from assigning an EC classification from a cheminformatics representation of a reaction.

Show MeSH
Related in: MedlinePlus