Prediction of C^{α}-H·O and C^{α}-H·π Interactions in Proteins Using Recurrent Neural Network

Article type: Research Article

Authors: Kaur, Harpreet | Raghava, Gajendra Pal Singh

Affiliations: Institute of Microbial Technology, Sector – 39A, Chandigarh, India

Note: [] Corresponding author: Bioinformatics Centre Institute of Microbial Technology Sector 39A, Chandigarh, India. Tel.: +91 172 2690557; Fax: +91 172 2690632; E-mail: [email protected]; URL: http://imtech.res.in/raghava/

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

Journal: In Silico Biology, vol. 6, no. 1-2, pp. 111-125, 2006