K-local hyperplane distance nearest-neighbor algorithm and protein fold recognition

Two proteins may be structurally similar but not have significant sequence similarity. Protein fold recognition is an approach usually applied in this case. It does not rely on sequence similarity and can be achieved with relevant features extracted from protein sequences. In this paper, we experiment with the K-local hyperplane distance nearest-neighbor algorithm [8] applied to the protein fold recognition and compare it with other methods. Preliminary results obtained on a real-world dataset [3] demonstrate that this algorithm can outperform many other methods tested on the same dataset.[PUBLICATION ABSTRACT]