Prediction of protein thermostability by an efficient neural network approach

Introduction: Manipulation of protein stability is important for understanding the principles that govern protein thermostability, both in basic research and industrial applications

Various data mining techniques exist for prediction of thermostable proteins

Furthermore, ANN methods have attracted significant attention for prediction of thermostability, because they constitute an appropriate approach to mapping the non-linear input-output relationships and massive parallel computing

Method: An Extreme Learning Machine [ELM] was applied to estimate thermal behavior of 1289 proteins. In the proposed algorithm, the parameters of ELM were optimized using a Genetic Algorithm [GA], which tuned a set of input variables, hidden layer biases, and input weights, to and enhance the prediction performance

The method was executed on a set of amino acids, yielding a total of 613 protein features

A number of feature selection algorithms were used to build subsets of the features. A total of 1289 protein samples and 613 protein features were calculated from UniProt database to understand features contributing to the enzymes' thermostability and find out the main features that influence this valuable characteristic

Results:At the primary structure level, Gin, Glu and polar were the features that mostly contributed to protein thermostability

At the secondary structure level, Helix_S, Coil, and charged_Coil were the most important features affecting protein thermostability

These results suggest that the thermostability of proteins is mainly associated with primary structural features of the protein

According to the results, the influence of primary structure on the thermostabilty of a protein was more important than that of the secondary structure

It is shown that prediction accuracy of ELM [mean square error] can improve dramatically using GA with error rates RMSE=0.004 and MAPE=0.1003

Conclusion: The proposed approach for forecasting problem significantly improves the accuracy of ELM in prediction of thermostable enzymes. ELM tends to require more neurons in the hidden-layer than conventional tuning-based learning algorithms. To overcome these, the proposed approach uses a GA which optimizes the structure and the parameters of the ELM

In summary, optimization of ELM with GA results in an efficient prediction method; numerical experiments proved that our approach yields excellent results

Study on small ruminant lungworms and associated risk factors in northeastern Iran

OBJECTIVE@#To determine the prevalence, identify the species involved and assess possible risk factors of lungworm infection in small ruminant slaughtered in abattoir of Mashhad in the northeast of Iran from October 2010-August 2011.@*METHODS@#Faecal and post mortem examination were conducted on 350 and 2 500 animals, respectively.@*RESULTS@#The overall prevalence of lungworm infection was 10.85% and 3.80% in coproscopic and post mortem examination respectively, and this difference was found to be significant. Higher prevalence of lungworm infection was recorded in post mortem examination in sheep (4.1%) than in goats (0.5%) (P< 0.05). The proportion of infection with Dictyocaulus filaria, Protostrongylus rufescens and mixed infection were 3.7%, 0.1% and 0.2% in sheep while in goats, the infection was reported with Dictyocaulus filaria (0.5%) only. The seasonal dynamics of lungworm infection showed that prevalence was highest in winter (7.8%) with a remarkable decline during the dry time (summer) (0.8%) which the difference was significant (P<0.001). The animals of less than one year old showed greater infection in post mortem examination than older animals significantly (P<0.001). Also, the infection rate between male and female animals showed significant difference (P<0.05) with prevalence rate of 4.6% and 2.0%, respectively.@*CONCLUSIONS@#Due to its impact on production, emphasis should be given for the control and prevention of lungworm infection in this area.