Prediction of the disulfide bonding state of cysteines in proteins with hidden neural networks

Protein Eng. 2002 Dec;15(12):951-3. doi: 10.1093/protein/15.12.951.

Abstract

A hybrid system (hidden neural network) based on a hidden Markov model (HMM) and neural networks (NN) was trained to predict the bonding states of cysteines in proteins starting from the residue chains. Training was performed using 4136 cysteine-containing segments extracted from 969 non-homologous proteins of well-resolved 3D structure and without chain-breaks. After a 20-fold cross-validation procedure, the efficiency of the prediction scores as high as 80% using neural networks based on evolutionary information. When the whole protein is taken into account by means of an HMM, a hybrid system is generated, whose emission probabilities are computed using the NN output (hidden neural networks). In this case, the predictor accuracy increases up to 88%. Further, when tested on a protein basis, the hybrid system can correctly predict 84% of the chains in the data set, with a gain of at least 27% over the NN predictor.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Cysteine / chemistry*
  • Disulfides / chemistry*
  • Markov Chains
  • Models, Molecular*
  • Neural Networks, Computer*
  • Predictive Value of Tests
  • Proteins / chemistry*

Substances

  • Disulfides
  • Proteins
  • Cysteine