Bioinformatics Advance Access originally published online on May 14, 2004
Bioinformatics 2004 20(16):2751-2758; doi:10.1093/bioinformatics/bth322
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Bioinformatics vol. 20 issue 16 © Oxford University Press 2004; all rights reserved.
A neural network method for prediction of ß-turn types in proteins using evolutionary information
Institute of Microbial Technology, Sector-39A, Chandigarh, India
Received on March 9, 2004; accepted on April 29, 2004
Advance Access Publication May 14, 2004
Motivation: The prediction of ß-turns is an important element of protein secondary structure prediction. Recently, a highly accurate neural network based method Betatpred2 has been developed for predicting ß-turns in proteins using position-specific scoring matrices (PSSM) generated by PSI-BLAST and secondary structure information predicted by PSIPRED. However, the major limitation of Betatpred2 is that it predicts only ß-turn and non-ß-turn residues and does not provide any information of different ß-turn types. Thus, there is a need to predict ß-turn types using an approach based on multiple sequence alignment, which will be useful in overall tertiary structure prediction.
Results: In the present work, a method has been developed for the prediction of ß-turn types I, II, IV and VIII. For each turn type, two consecutive feed-forward back-propagation networks with a single hidden layer have been used where the first sequence-to-structure network has been trained on single sequences as well as on PSI-BLAST PSSM. The output from the first network along with PSIPRED predicted secondary structure has been used as input for the second-level structure-to-structure network. The networks have been trained and tested on a non-homologous dataset of 426 proteins chains by 7-fold cross-validation. It has been observed that the prediction performance for each turn type is improved significantly by using multiple sequence alignment. The performance has been further improved by using a second level structure-to-structure network and PSIPRED predicted secondary structure information. It has been observed that Type I and II ß-turns have better prediction performance than Type IV and VIII ß-turns. The final network yields an overall accuracy of 74.5, 93.5, 67.9 and 96.5% with MCC values of 0.29, 0.29, 0.23 and 0.02 for Type I, II, IV and VIII ß-turns, respectively, and is better than random prediction.
Availability: A web server for prediction of ß-turn types I, II, IV and VIII based on above approach is available at http://www.imtech.res.in/raghava/betaturns/ and http://bioinformatics.uams.edu/mirror/betaturns/ (mirror site).
Contact: raghava{at}imtech.res.in
* To whom correspondence should be addressed.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  M. Poursheikhali Asgary, S. Jahandideh, P. Abdolmaleki, and A. Kazemnejad Analysis and identification of -turn types using multinomial logistic regression and artificial neural network Bioinformatics, December 1, 2007; 23(23): 3125 - 3130. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 M. Kumar, M. Bhasin, N. K. Natt, and G. P. S. Raghava BhairPred: prediction of {beta}-hairpins in a protein from multiple alignment information using ANN and SVM techniques Nucleic Acids Res., July 1, 2005; 33(suppl_2): W154 - W159. [Abstract] [Full Text] [PDF]
|
|