Background:
Amino acid physicochemical properties encoded in protein primary
structure play a crucial role in protein folding. However, it is not yet clear which of the properties
are the most suitable for protein fold classification.
Objective:
To avoid exhaustively searching the total properties space, an amino acid properties
selection method was proposed in this study to rapidly obtain a suitable properties combination for
protein fold classification.
Method:
The proposed amino acid properties selection method was based on sequential floating
forward selection strategy. Beginning with an empty set, variable number of features were added
iteratively until achieving the iteration termination condition.
Results:
The experimental results indicate that the proposed method improved prediction accuracies
by 0.26-5% on a widely used benchmark dataset with appropriately selected amino acid properties.
Conclusion:
The proposed properties selection method can be extended to other biomolecule
property related classification problems in bioinformatics.
Detection of protein fold similarity based on correlation of amino acid properties
