Mahalanobis distance with radial basis function network on protein secondary structures

Ibrikci T., Brandt M., Wang G., Acikkar M.

24th Annual International Conference of the Engineering-in-Medicine-and-Biology-Society/Annual Fall Meeting of the Biomedical-Engineering-Society (EMBS 2002 BMES), Texas, United States Of America, 23 - 26 October 2002, pp.2184-2185, (Full Text) identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/iembs.2002.1053230
  • City: Texas
  • Country: United States Of America
  • Page Numbers: pp.2184-2185
  • Çukurova University Affiliated: Yes

Abstract

In this paper, the radial basis function (RBF) network method with the Mahalanobis distance was applied to predict the content of protein secondary structure elements. A study of the Mahalanobis-RBF with different window sizes on the dataset developed by Qian-Sejnowski is given. The RBF network predicts each position in turn based on a local window of residues, by sliding this window along the length of the sequence. Comparison of Gaussian-RBF and Mahalanobis-RBF on the Qian dataset shows that the Mahalanobis distance in using RBF gives better results in the prediction of secondary structure for local sequence structural state.