- Article -

Volume 6

Full article

Prediction of Cα-H····O and Cα-H···π interactions in proteins using recurrent neural network

Harpreet Kaur and Gajendra Pal Singh Raghava*

Institute of Microbial Technology, Sector - 39A, Chandigarh, India

* Corresponding author
   Bioinformatics Centre Institute of Microbial Technology Sector 39A, Chandigarh, INDIA
   Email: raghava@imtech.res.in
   URL: http://imtech.res.in/raghava/


Edited by H. Michael; received October 12, 2005; revised and accepted February 01, 2006; published March 01, 2006

Abstract

In this study, an attempt has been made to develop a method for predicting weak hydrogen bonding interactions, namely, C^α-H···O and C^α-H···π interactions in proteins using artificial neural network. Both standard feed-forward neural network (FNN) and recurrent neural networks (RNN) have been trained and tested using five-fold cross-validation on a non-homologous dataset of 2298 protein chains where no pair of sequences has more than 25% sequence identity. It has been found that the prediction accuracy varies with the separation distance between donor and acceptor residues. The maximum sensitivity achieved with RNN for C^α-H···O is 51.2% when donor and acceptor residues are four residues apart (i. e. at Δ_D-A = 4) and for C^α-H···π is 82.1% at Δ_D-A = 3. The performance of RNN is increased by 1-3% for both types of interactions when PSIPRED predicted protein secondary structure is used. Overall, RNN performs better than feed-forward networks at all separation distances between donor-acceptor pair for both types of interactions. Based on the observations, a web server CHpredict (available at http://www.imtech.res.in/raghava/chpredict/) has been developed for predicting donor and acceptor residues in C^α-H···O and C^α-H···π interactions in proteins.

Keywords: weak hydrogen bonds, donor, acceptor, prediction, neural network, secondary structure