Mining of protein contact maps for protein fold prediction
Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery
| Hi-index | 0.00 |
Motivation: Contact map is a key factor to represent a specific protein structure. As previous work reported, even a corrupted contact map can be used to reconstruct its corresponding protein structure. Thus we can predict the structure of a protein partially through the contact map prediction. To simplify the protein contact map prediction, we predict the inter-residue contact clusters centered at the groups of their neighboring contacts instead.Results: In this paper, we adopt a SVM predictor based approach to predict the inter-residue contact cluster centers. The input information of the SVM predictor includes sequence profile, evolutionary rate, and predicted secondary structure. The SVM predictor is based on hydrophobic cores that may be considered as locations of the groups of their neighboring inter-residue contacts. As a result, about 35% clustering centers of inter-residue contacts can accurately be predicted.