Analysis and identification of beta-turn types using multinomial logistic regression and artificial neural network.

Abstract

So far various statistical and machine learning techniques applied for prediction of beta-turns. The majority of these techniques have been only focused on the prediction of beta-turn location in proteins. We developed a hybrid approach for analysis and prediction of different types of beta-turn. A two-stage hybrid model developed to predict the beta-turn Types I, II, IV and VIII. Multinomial logistic regression was initially used for the first time to select significant parameters in prediction of beta-turn types using a self-consistency test procedure. The extracted parameters were consisted of 80 amino acid positional occurrences and 20 amino acid percentages in beta-turn sequence. The most significant parameters were then selected using multinomial logistic regression model. Among these, the occurrences of glutamine, histidine, glutamic acid and arginine, respectively, in positions i, i + 1, i + 2 and i + 3 of beta-turn sequence had an overall relationship with five beta-turn types. A neural network model was then constructed and fed by the parameters selected by multinomial logistic regression to build a hybrid predictor. The networks have been trained and tested on a non-homologous dataset of 565 protein chains by 9-fold cross-validation. It has been observed that the hybrid model gives a Matthews correlation coefficient (MCC) of 0.235, 0.473, 0.103 and 0.124, respectively, for beta-turn Types I, II, IV and VIII. Our model also distinguished the different types of beta-turn in the embedded binary logit comparisons which have not carried out so far. Available on request from the authors.