Rapid report
Using neural networks for prediction of domain structural classes

https://doi.org/10.1016/S0167-4838(99)00217-4Get rights and content

References (9)

  • K.C. Chou et al.

    J. Biol. Chem.

    (1994)
  • A.G. Murzin et al.

    J. Mol. Biol.

    (1995)
  • T. Kohonen

    Neural Networks

    (1988)
  • K.C. Chou et al.

    Protein Eng.

    (1998)
There are more references available in the full text version of this article.

Cited by (27)

  • Some remarks on protein attribute prediction and pseudo amino acid composition

    2011, Journal of Theoretical Biology
    Citation Excerpt :

    It is particularly important to follow such a self-consistency principle when hybridizing different PseAAC modes or building an ensemble classifier by fusing many individual classifiers (Chou and Shen, 2006d). Many different prediction algorithms have been introduced to address this problem, such as discriminant algorithm (Chou and Maggiora, 1998; Chou and Elrod, 1999), neural network algorithm (Cai et al., 2000; Cai et al., 2001), support vector machine (SVM) (Cai et al., 2003; Cai et al., 2004; Chou and Cai, 2002), and K-nearest Neighbor algorithm (Cai and Chou, 2003; Chou and Shen, 2006b). In this paper we shall focus on the K-nearest neighbor algorithm (Denoeux, 1995) and show how to generate a powerful ensemble classifier by fusing many individual basic classifiers characterized with different control parameters.

  • A novel feature representation method based on Chou's pseudo amino acid composition for protein structural class prediction

    2010, Computational Biology and Chemistry
    Citation Excerpt :

    Later on auto-correlation functions based on non-bonded residue energy, polypeptide composition (Luo et al., 2002) and complexity measure factor (Xiao et al., 2006; Liu et al., 2009) have been used by many researchers. Subsequently several classification methods such as distance classifier (Du et al., 2006; Chou, 1999), component coupled methods (Chou and Zhang, 1994), principal component analysis (Du et al., 2006), Bayesian classifier, fuzzy clustering (Shen et al., 2005; Ding et al., 2007), neural network (Chandonia and Karplus, 1995; Cai et al., 2000), rough sets (Cao et al., 2006) and support vector machines (Cai et al., 2001; Chao et al., 2006; Sun and Huang, 2006) have been suggested in the literature. Although promising results have been achieved in many cases, the representation of protein with AAC lacks sequence-order and sequence-length information (Chou, 1995, 2000).

  • Identification of proteases and their types

    2009, Analytical Biochemistry
    Citation Excerpt :

    The jackknife cross-validation can exclude the memory effects during the entire testing process; thus, the result obtained is always unique for a given benchmark dataset. Therefore, of the above three examination methods, the jackknife test is deemed as the most objective [65] and has been increasingly and widely used or recognized by investigators to examine the accuracy of various predictors [31,32,35,36,39,40,44,46–48,51,57,59,60,62,64,66–72,76–79,81–83,85–88,90–92,96,97,99,102,115,128–164]. ProtIdent is freely accessible to the public as a user-friendly web server.

  • Using genetic algorithm to design protein sequence

    2008, Applied Mathematics and Computation
  • Predicting peptides structure with solvation potential and rotamer library dependent of the backbone

    2008, Applied Mathematics and Computation
    Citation Excerpt :

    The information for life is stored by a four-letters alphabet in the genes (DNA). Proteins are, among others, the macromolecules that perform all the important tasks in the organisms as catalysis of biochemical reactions, transport, recognition, signal transduction, etc. [21]. The three-dimensional structure (tertiary structure) of proteins determines their function [27–29].

  • Use of genetic algorithms and solvation potential to study peptides structure

    2008, Applied Mathematics and Computation
    Citation Excerpt :

    The information for life is stored by a four-letters alphabet in the genes (DNA). Proteins are, among others, the macromolecules that perform all the important tasks in the organisms as catalysis of biochemical reactions, transport, recognition, signal transduction, etc. [21]. The three-dimensional structure (tertiary structure) of proteins determines their function [27,28].

View all citing articles on Scopus
View full text