Protein Fold Classi cation using Kohonen's Self-Organizing Map

Protein fold classi cation is an important problem in bioinformatics and a challenging task for machine-learning algorithms. In this paper we present a solution which classi es protein folds using Kohonen's Self-Organizing Map (SOM) and a comparison between few approaches for protein fold classi cation. We use SOM, Fisher Linear Discriminant Analysis (FLD), K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) methods to classify three SCOP folds with six features (amino acid composition, predicted secondary structure, hydrophobicity, normalized van der Waals volume, polarity and polarizability). This paper has a novelty in the way of applying SOM to these six features, and also portrays the capabilities of SOM among the other methods in protein fold classi cation. The methods are tested on 120 proteins by applying 10-fold cross-validation technique and 93.33% classi cation performance is obtained with SOM.