A new multiple classifier system for the prediction of protein's contacts map

• We analyze each possible amino acid pair by separate, simplifying the prediction.
• We activate just the classifier corresponding with the amino acid couple to predict.
• It provides an interpretable solution based on a collection of simple decision rules.
• A trees-based multiple classifier system improves the protein's structure prediction.

In this paper, we introduce FoDT, a new algorithm for the prediction of proteins contact map, one of the great challengers of the Bioinformatics. The need of more accurate predictions, aims to combining classifiers, beyond complexity increase. The proposed methodology can be considered as a set of cooperative classifiers, which employs a not trainable combination method and coverage optimization. The robustness and predictivity evaluation, with the dataset of 9th Critical Assessment of Techniques for Protein Structure Prediction, demonstrates that our algorithm can assign contacts with an average accuracy up to 58%. It performs similarly to free servers as SVM-SEQ, NNcon and LRcon, and overcoming FragHMMent. The FoDT main advantage is their capability to break down the complex process of protein folding into a collection of simple decision rules, providing a more easy and interpretable solution for the prediction of contact's maps.