Prediction of road traffic death rate using neural networks optimised by genetic algorithm.

Road traffic injuries (RTIs) are realised as a main cause of public health problems at global, regional and national levels. Therefore, prediction of road traffic death rate will be helpful in its management. Based on this fact, we used an artificial neural network model optimised through Genetic algorithm to predict mortality. In this study, a five-fold cross-validation procedure on a data set containing total of 178 countries was used to verify the performance of models. The best-fit model was selected according to the root mean square errors (RMSE). Genetic algorithm, as a powerful model which has not been introduced in prediction of mortality to this extent in previous studies, showed high performance. The lowest RMSE obtained was 0.0808. Such satisfactory results could be attributed to the use of Genetic algorithm as a powerful optimiser which selects the best input feature set to be fed into the neural networks. Seven factors have been known as the most effective factors on the road traffic mortality rate by high accuracy. The gained results displayed that our model is very promising and may play a useful role in developing a better method for assessing the influence of road traffic mortality risk factors.

Predictions of Protein-Protein Interfaces within Membrane Protein Complexes.

BACKGROUND: Prediction of interaction sites within the membrane protein complexes using the sequence data is of a great importance, because it would find applications in modification of molecules transport through membrane, signaling pathways and drug targets of many diseases. Nevertheless, it has gained little attention from the protein structural bioinformatics community. METHODS: In this study, a wide variety of prediction and classification tools were applied to distinguish the residues at the interfaces of membrane proteins from those not in the interfaces. RESULTS: The tuned SVM model achieved the high accuracy of 86.95% and the AUC of 0.812 which outperforms the results of the only previous similar study. Nevertheless, prediction performances obtained using most employed models cannot be used in applied fields and needs more effort to improve. CONCLUSION: Considering the variety of the applied tools in this study, the present investigation could be a good starting point to develop more efficient tools to predict the membrane protein interaction site residues.

Novel inhibitor discovery against aromatase through virtual screening and molecular dynamic simulation: a computational approach in drug design.

Inhibition of aromatase (CYTP450) as a key enzyme in the estrogen biosynthesis could result in regression of estrogen-dependent tumors and even preventing the promotion of breast cancer. Although today potent steroid and non-steroid inhibitors of aromatase are available, isoflavanone derivatives as natural compounds with least side effects have been described as the candidate for a new generation of aromatase inhibitors. 2a as an isoflavanone derivative is the most potent inhibitor of aromatase, synthesized by Bonfield et al. (2012[7]). In our computational study, the mentioned compound was used as the template for virtual screening. Between 286 selected compounds with 70 % of structural similarity to 2a, 150 of them showed lower docking energy in comparison with 2a. Compound 2a_1 with 11.2 kcal/mol had the lowest docking energy. Interaction of 2a_1 with aromatase was further investigated and compared with 2a and androstenedione (ASD) as a natural substrate of aromatase, through 20 ns of molecular dynamic simulation. Analysis of trajectories showed, while ASD interacts with aromatase through hydrogen bonds and 2a just interacts via hydrophobic forces, 2a_1 not only accommodates in the hydrophobic active site of aromatase in a suitable manner but it also makes a stable coordination with iron atom of aromatase heme group via OB.

Prevalent mutations of human prion protein: a molecular modeling and molecular dynamics study.

Point mutations in the human prion protein gene, leading to amino acid substitutions in the human prion protein contribute to conversion of PrPC to PrPSc and amyloid formation, resulting in prion diseases such as familial Creutzfeldt-Jakob disease (CJD), Gerstmann-Straussler-Scheinker disease (GSS), and fatal familial insomnia. We have investigated impressions of prevalent mutations including Q217R, D202N, F198S, on the human prion protein and compared the mutant models with wild types. Structural analyses of models were performed with molecular modeling and molecular dynamics simulation methods. According to our results, frequently occurred mutations are observed in conserved and fully conserved sequences of human prion protein and the most fluctuation values occur in the Helix 1 around residues 144-152 and C-terminal end of the Helix 2. Our analysis of results obtained from MD simulation clearly shows that this long-range effect plays an important role in the conformational fluctuations in mutant structures of human prion protein. Results obtained from molecular modeling such as creation or elimination of some hydrogen bonds, increase or decrease of the accessible surface area and molecular surface, loss or accumulation of negative or positive charges on specific positions, and altering the polarity and pKa values, show that amino acid point mutations, though not urgently change the stability of PrP, might have some local impacts on the protein interactions which are required for oligomerization into fibrillar species.

A combinatorial feature selection approach to describe the QSAR of dual site inhibitors of acetylcholinesterase.

Regarding the great potential of dual binding site inhibitors of acetylcholinesterase as the future potent drugs of Alzheimer's disease, this study was devoted to extraction of the most effective structural features of these inhibitors from among a large number of quantitative descriptors. To do this, we adopted a unique approach in quantitative structure-activity relationships. An efficient feature selection method was emphasized in such an approach, using the confirmative results of different routine and novel feature selection methods. The proposed methods generated quite consistent results ensuring the effectiveness of the selected structural features.

The use of artificial neural networks and multiple linear regression to predict rate of medical waste generation.

Prediction of the amount of hospital waste production will be helpful in the storage, transportation and disposal of hospital waste management. Based on this fact, two predictor models including artificial neural networks (ANNs) and multiple linear regression (MLR) were applied to predict the rate of medical waste generation totally and in different types of sharp, infectious and general. In this study, a 5-fold cross-validation procedure on a database containing total of 50 hospitals of Fars province (Iran) were used to verify the performance of the models. Three performance measures including MAR, RMSE and R(2) were used to evaluate performance of models. The MLR as a conventional model obtained poor prediction performance measure values. However, MLR distinguished hospital capacity and bed occupancy as more significant parameters. On the other hand, ANNs as a more powerful model, which has not been introduced in predicting rate of medical waste generation, showed high performance measure values, especially 0.99 value of R(2) confirming the good fit of the data. Such satisfactory results could be attributed to the non-linear nature of ANNs in problem solving which provides the opportunity for relating independent variables to dependent ones non-linearly. In conclusion, the obtained results showed that our ANN-based model approach is very promising and may play a useful role in developing a better cost-effective strategy for waste management in future.

Analysis of factors that induce cysteine bonding state.

Regarding the fact that the protein structure is principally encoded in its sequence, investigating the bonding state of cysteine has gained a great deal of attention due to its significance in the formation of protein structure. Due to lack of evident influence of free cysteines on the protein structure, it may be expected that only half-cystines convey encoded information. The results obtained from the analysis of amino acid distribution in proximity of both states of cysteines explicitly indicated that perquisite information for inducing cysteine bonding state is present even in the flanking amino acid sequences of free cysteines.

Elucidating the protein cold-adaptation: Investigation of the parameters enhancing protein psychrophilicity.

To investigate the role of the critical parameters in adaptation of proteins to low temperatures, a comparative systematic analysis was performed. Several parameters were proposed to have contribution to cold adaptation of proteins. Among proposed parameters, total values of residual structure states, secondary structure states and oligomeric states were alike in both psychrophilic and mesophilic proteins. In addition, our results provided new quantitative information about the trends in the substitution preference of Ile, Phe, Tyr, Lys, Arg, His, Glu and Leu with most of amino acids and substitution avoidance of Gly, Thr and Ala with most of amino acids. These findings would help future efforts propose a strategy for designing psychrophilic proteins.

Prediction of membrane protein types by means of wavelet analysis and cascaded neural networks.

In this study, membrane proteins were classified using the information hidden in their sequences. It was achieved by applying the wavelet analysis to the sequences and consequently extracting several features, each of them revealing a proportion of the information content present in the sequence. The resultant features were made normalized and subsequently fed into a cascaded model developed in order to reduce the effect of the existing bias in the dataset, rising from the difference in size of the membrane protein classes. The results indicate an improvement in prediction accuracy of the model in comparison with similar works. The application of the presented model can be extended to other fields of structural biology due to its efficiency, simplicity and flexibility.

Novel two-stage hybrid neural discriminant model for predicting proteins structural classes.

In order to establish novel hybrid neural discriminant model, linear discriminant analysis (LDA) was used at the first stage to evaluate the contribution of sequence parameters in determining the protein structural class. An in-house program generated parameters including single amino acid and all dipeptide composition frequencies for 498 proteins came from Zhou [An intriguing controversy over protein structural class prediction, J. Protein Chem. 17(8) (1998) 729-738]. Then, 127 statistically effective parameters were selected by stepwise LDA and were used as inputs of the artificial neural networks (ANNs) to build a two-stage hybrid predictor. In this study, self-consistency and jackknife tests were used to verify the performance of this hybrid model, and were compared with some of prior works. The results showed that our two-stage hybrid neural discriminant model approach is very promising and may play a complementary role to the existing powerful approaches.