Research Article

SOMCD: Method for evaluating protein secondary structure from UV circular dichroism spectra†

  1. Per Unneberg1,
  2. Juan J. Merelo2,
  3. Pablo Chacón3,‖,
  4. Federico Morán4,*

Article first published online: 10 JAN 2001

DOI: 10.1002/1097-0134(20010301)42:4<460::AID-PROT50>3.0.CO;2-U

Issue

Proteins: Structure, Function, and Bioinformatics

Proteins: Structure, Function, and Bioinformatics

Volume 42, Issue 4, pages 460–470, 1 March 2001

Additional Information

How to Cite

Unneberg, P., Merelo, J. J., Chacón, P. and Morán, F. (2001), SOMCD: Method for evaluating protein secondary structure from UV circular dichroism spectra. Proteins, 42: 460–470. doi: 10.1002/1097-0134(20010301)42:4<460::AID-PROT50>3.0.CO;2-U

Author Information

  1. 1

    Department of Biotechnology, Royal Institute of Technology (KTH), Stockholm, Sweden

  2. 2

    Departamento de Arquitectura y Tecnología de Computadores, Facultad de Ciencias, Universidad de Granada, Granada, Spain

  3. 3

    Centro de Astrobiología, INTA-CSIC, Madrid, Spain

  4. 4

    Departamento de Bioquímica y Biología Molecular I, Facultad de Químicas, Universidad Complutense de Madrid, Madrid, Spain

  1. ‖

    Department of Molecular Biology, The Scripps Research Institute, La Jolla, California

*Departamento de Bioquímica y Biología Molecular I, Universidad Complutense de Madrid, 280 40 Madrid, Spain

  1. †

    An implementation of the method presented in this article will be available online at http://somcd.geneura.org.

Publication History

  1. Issue published online: 10 JAN 2001
  2. Article first published online: 10 JAN 2001
  3. Manuscript Accepted: 6 OCT 2000
  4. Manuscript Received: 3 FEB 2000

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article (HTML) Get PDF (297K)

Keywords:

  • neural networks;
  • prediction;
  • secondary structure;
  • unsupervised learning;
  • circular dichroism

Abstract

This article presents SOMCD, an improved method for the evaluation of protein secondary structure from circular dichroism spectra, based on Kohonen's self-organizing maps (SOM). Protein circular dichroism (CD) spectra are used to train a SOM, which arranges the spectra on a two-dimensional map. Location in the map reflects the secondary structure composition of a protein. With SOMCD, the prediction of β-turn has been included. The number of spectra in the training set has been increased, and it now includes 39 protein spectra and 6 reference spectra. Finally, SOM parameters have been chosen to minimize distortion and make the network produce clusters with known properties. Estimation results show improvements compared with the previous version, K2D, which, in addition, estimated only three secondary structure components; the accuracy of the method is more uniform over the different secondary structures. Proteins 2001;42:460–470. © 2001 Wiley-Liss, Inc.

View Full Article (HTML) Get PDF (297K)