Artificial neural network method for predicting HIV protease cleavage sites in protein

Knowledge of the polyprotein cleavage sites by HIV protease will refine our understanding of its specificity, and the information thus acquired will be useful for designing specific and efficient HIV protease inhibitors. The search for inhibitors of HIV protease will be greatly expedited if one can find and accurate, robust, and rapid method for predicting the cleavage sites in proteins by HIV protease. In this paper, Kohonen’s self-organization model, which uses typical artificial neural networks, is applied to predict the cleavability of oligopeptides by proteases with multiple and extended specificity subsites. We selected HIV-1 protease as the subject of study. We chose 299 oligopeptides for the training set, and another 63 oligopeptides for the test set. Because of its high rate of correct prediction (58/63=92.06%) and stronger fault-tolerant ability, the neural network method should be a useful technique for finding effective inhibitors of HIV protease, which is one of the targets in designing potential drugs against AIDS. The principle of the artificial neural network method can also be applied to analyzing the specificity of any multisubsite enzyme.     

A vector projection approach to predicting HIV protease cleavage sites in proteins

A vector projection method is proposed to predict the cleavability of oligopeptides by extended-specificity site proteases. For an enzyme with eight specificity subsites the substrate octapeptide can be uniquely expressed as a vector in an 8-dimensional space, whose eight bases correspond to the amino acids at the eight subsites, P₁, P_1′, P_2′, P_3′ and P_4′, respectively. The component of such a characteristic vector on each of the eight bases is defined as the frequency of an amino acid occurring at a given site. These frequencies were derived from a set of octapeptides known to be cleaved by HIV protease. The cleavability of an octapeptide can then be estimated from the projection of its characteristic vector on an idealized, optimally cleavable vector. The high ratio of correct prediction vs. total prediction for the data in both the training and the testing sets indicates that the new method is self-consistent and efficient. It provides a rapid and accurate algorithm for analyzing the specificity of any multisubsite enzyme for which there is no coupling between subsites. In particular, it is useful for predicting the cleavability of an oligopeptide by either HIV-1 or HIV-2 protease, and hence offers a supplementary means for finding effective inhibitors of HIV protease as potential drugs against AIDS. © Wiley-Liss, Inc.     

ChloroP, a neural network-based method for predicting chloroplast transit peptides and their cleavage sites.

We present a neural network based method (ChloroP) for identifying chloroplast transit peptides and their cleavage sites. Using cross-validation, 88% of the sequences in our homology reduced training set were correctly classified as transit peptides or nontransit peptides. This performance level is well above that of the publicly available chloroplast localization predictor PSORT. Cleavage sites are predicted using a scoring matrix derived by an automatic motif-finding algorithm. Approximately 60% of the known cleavage sites in our sequence collection were predicted to within +/-2 residues from the cleavage sites given in SWISS-PROT. An analysis of 715 Arabidopsis thaliana sequences from SWISS-PROT suggests that the ChloroP method should be useful for the identification of putative transit peptides in genome-wide sequence data. The ChloroP predictor is available as a web-server at http://www.cbs.dtu.dk/services/ChloroP/.     

人工神经网络与相容性生物量模型预测单木地上生物量的比较

森林生物量是林业生产经营和森林资源监测的重要指标,为探索高效低偏的单木生物量估测方法,引入人工神经网络.本研究采用黑龙江省东折棱河林场的101株长白落叶松地上生物量数据,基于不同变量(胸径、树高、冠幅)组合建立了4个聚合模型体系(AMS),采用加权回归消除模型的异方差.然后,基于最优的变量组合建立人工神经网络(ANN)...     

利用BP神经网络方法预测西湖叶绿素a的浓度

在西湖共设了 8个采样点 ,通过主成分分析选取了最能代表西湖水质状况的 7号点 (湖心 )作为研究对象。根据 2 0 0 0年 1月至 2 0 0 1年 4月西湖常规监测的水生生态数据 ,并用插值的方法使其生成足够多的样本数 ,利用 BP人工神经网络 ,探索其用于西湖水生生态状况 (叶绿素 a的浓度 )的短期变化趋势预测的可行性 ,从中找出最能反映西湖水生生态状况变化趋势的水质因子用来建立网络。并用 3号点的数据来检验网络的泛化性能 ,发现网络输出值与实际值吻合度较高。结果表明 ,水温和叶绿素a对未来一周的叶绿素 a含量影响最大 ,以这两者作为输入变量建立的网络简单、快捷 ,比其他线性数值模拟预测有较大的优势。说明人工神经网络对叶绿素 a的预测是一种有效工具 ,可为西湖富营养化治理提供科学依据。     

半干旱区春小麦生长系统的人工神经网络模型与产量预测

以半干旱区春小麦生长系统为研究对象。探讨了作物生长系统中水分、土壤养分等生态因子的时空变化特征及春小麦产量形成机制,应用人工神经网络方法建立了半干旱区春小麦生长系统的产量随环境因子变化的神经网络模型,并与传统的CTM模型进行了比较。模拟结果表明,人工神经网络模型可适用于半干旱区春小麦生长系统产量随环境因子变化规律描述,且优于传统模型,从而为春小麦产量预测提供了新的途径,也为作物生态系统的人工调控提供了新的模式与定量依据。     

Using a neural network and spatial clustering to predict the location of active sites in enzymes

Structural genomics projects aim to provide a sharp increase in the number of structures of functionally unannotated, and largely unstudied, proteins. Algorithms and tools capable of deriving information about the nature, and location, of functional sites within a structure are increasingly useful therefore. Here, a neural network is trained to identify the catalytic residues found in enzymes, based on an analysis of the structure and sequence. The neural network output, and spatial clustering of the highly scoring residues are then used to predict the location of the active site.A comparison of the performance of differently trained neural networks is presented that shows how information from sequence and structure come together to improve the prediction accuracy of the network. Spatial clustering of the network results provides a reliable way of finding likely active sites. In over 69% of the test cases the active site is correctly predicted, and a further 25% are partially correctly predicted. The failures are generally due to the poor quality of the automatically generated sequence alignments.We also present predictions identifying the active site, and potential functional residues in five recently solved enzyme structures, not used in developing the method. The method correctly identifies the putative active site in each case. In most cases the likely functional residues are identified correctly, as well as some potentially novel functional groups.     

Modelling and optimization of fermentation factors for enhancement of alkaline protease production by isolated Bacillus circulans using feed-forward neural network and genetic algorithm

Aim: Modelling and optimization of fermentation factors and evaluation for enhanced alkaline protease production by Bacillus circulans. Methods and Results: A hybrid system of feed‐forward neural network (FFNN) and genetic algorithm (GA) was used to optimize the fermentation conditions to enhance the alkaline protease production by B. circulans. Different microbial metabolism regulating fermentation factors (incubation temperature, medium pH, inoculum level, medium volume, carbon and nitrogen sources) were used to construct a ‘6‐13‐1’ topology of the FFNN for identifying the nonlinear relationship between fermentation factors and enzyme yield. FFNN predicted values were further optimized for alkaline protease production using GA. The overall mean absolute predictive error and the mean square errors were observed to be 0·0048, 27·9, 0·001128 and 22·45 U ml^?1 for training and testing, respectively. The goodness of the neural network prediction (coefficient of R²) was found to be 0·9993. Conclusions: Four different optimum fermentation conditions revealed maximum enzyme production out of 500 simulated data. Concentration‐dependent carbon and nitrogen sources, showed major impact on bacterial metabolism mediated alkaline protease production. Improved enzyme yield could be achieved by this microbial strain in wide nutrient concentration range and each selected factor concentration depends on rest of the factors concentration. The usage of FFNN–GA hybrid methodology has resulted in a significant improvement (>2·5‐fold) in the alkaline protease yield. Significance and Impact of the Study: The present study helps to optimize enzyme production and its regulation pattern by combinatorial influence of different fermentation factors. Further, the information obtained in this study signifies its importance during scale‐up studies.     

Artificial neural network (ANN)‐based prediction of depth filter loading capacity for filter sizing

This article presents an application of artificial neural network (ANN) modelling towards prediction of depth filter loading capacity for clarification of a monoclonal antibody (mAb) product during commercial manufacturing. The effect of operating parameters on filter loading capacity was evaluated based on the analysis of change in the differential pressure (DP) as a function of time. The proposed ANN model uses inlet stream properties (feed turbidity, feed cell count, feed cell viability), flux, and time to predict the corresponding DP. The ANN contained a single output layer with ten neurons in hidden layer and employed a sigmoidal activation function. This network was trained with 174 training points, 37 validation points, and 37 test points. Further, a pressure cut‐off of 1.1 bar was used for sizing the filter area required under each operating condition. The modelling results showed that there was excellent agreement between the predicted and experimental data with a regression coefficient (R²) of 0.98. The developed ANN model was used for performing variable depth filter sizing for different clarification lots. Monte‐Carlo simulation was performed to estimate the cost savings by using different filter areas for different clarification lots rather than using the same filter area. A 10% saving in cost of goods was obtained for this operation. © 2016 American Institute of Chemical Engineers Biotechnol. Prog., 32:1436–1443, 2016     

A neural network model for estimating O2 absorption coefficient in shake-flasks

A comprehensive, simple, neural network model was constructed to replace the common semi-empirical mathematical models used for predicting individual O₂ absorption coefficients (K _L a) within Erlenmeyer and Hinton shake-flasks. Different factors that influence K _L a within shake-flasks, such as flask dimensions, working volumes, baffle-heights, and shaking speeds, were investigated and the experimental results employed to deduce the mathematical model for each type of shake-flask. Meanwhile, the K _L a values calculated from the mathematical models were used to derive a non-linear neural network estimator (NNE). The NNE for K _L a prediction was implemented to evaluate the O₂ absorption effect within the flasks and gave a promising result.     

基于遗传算法的人工神经网络模型在冬小麦根系分布预报中的应用

In this study, a controlled experiment of winter wheat under water stress at the seedling stage was conducted in soil columns in greenhouse. Based on the data gotten from the experiment, a model to estimate root length density distribution was developed through optimizing the weights of neural network by genetic algorithm. The neural network model was constructed by using forward neural network framework, by applying the strategy of the roulette wheel selection and reserving the most optimizing series of weights, which were composed by real codes.This model was applied to predict the root length density distribution of winter wheat, and the predicted root length density had good agreement with experiment data. The way could save a lot of manpower and material resources for determining the root length density distribution of winter wheat.     

Optimization of culture parameters for extracellular protease production from a newly isolated Pseudomonas sp. using response surface and artificial neural network models

Radial basis function (RBF) artificial neural network (ANN) and response surface methodology (RSM) were used to build a predictive model of the combined effects of independent variables (pH, temperature, inoculum volume) for extracellular protease production from a newly isolated Pseudomonas sp. The optimum operating conditions obtained from the quadratic form of the RSM and ANN models were pH 7.6, temperature 38 °C, and inoculum volume of 1.5 with 58.5 U/ml of predicted protease activity within 24 h of incubation. The normalized percentage mean squared error obtained from ANN and RSM models were 0.05 and 0.1%, respectively. The results demonstrated an higher prediction accuracy of ANN compared to RSM. This superiority of ANN over other multi factorial approaches could make this estimation technique a very helpful tool for fermentation monitoring and control.     

Use of mutual information arrays to predict coevolving sites in the full length HIV gp120 protein for subtypes B and C

It is well established that different sites within a protein evolve at different rates according to their role within the protein; identification of these correlated mutations can aid in tasks such as ab initio protein structure, structure function analysis or sequence alignment. Mutual Information is a standard measure for coevolution between two sites but its application is limited by signal to noise ratio. In this work we report a preliminary study to investigate whether larger sequence sets could circumvent this problem by calculating mutual information arrays for two sets of drug naïve sequences from the HIV gp120 protein for the B and C subtypes. Our results suggest that while the larger sequences sets can improve the signal to noise ratio, the gain is offset by the high mutation rate of the HIV virus which makes it more difficult to achieve consistent alignments. Nevertheless, we were able to predict a number of coevolving sites that were supported by previous experimental studies as well as a region close to the C terminal of the protein that was highly variable in the C subtype but highly conserved in the B subtype.     

Using an artificial neural network to characterize the relative suitability of environments for forest types in a complex tropical vegetation mosaic

A predictive understanding of the environmental controls on forest distributions is essential for the conservation of biodiversity and management of landscapes in the tropics. This is particularly true now because of potentially rapid climate change. The floristic complexity of tropical forests and the lack or absence of data severely limits the applicability of modelling methods based on the ecology or distribution of individual species. Here we present an artificial neural network (ANN) model using the information available in the humid tropics of North Queensland: a structural classification of forest types, maps of the forest mosaic, and estimates of spatial environmental variables. The ANN model characterizes the relative suitabilities of environments for 15 forest classes defined by their physiognomy and canopy structure. Inputs include seven climate variables, nine soil parent-material classes, and seven terrain variables. The data used to train the model consisted of a stratified random sample of 75000 points. Output of the model is used to measure the dissimilarity between the environment at each location and the environment that would be most suitable for the forest type that is mapped there. The model is highly successful at distinguishing the relative suitability of environments for the forest classes with 75% of the region's forest mosaic accurately predicted by the model at a one hectare resolution. In contrast, a comparable maximum likelihood classification has an accuracy of only 38%. In the remaining 25% of the region the environments are quite dissimilar to what would be expected for the forest types present there. This is especially the case at boundaries between forest classes and for a transitional forest class. Areas mapped as this disturbed, transitional class are generally classified by the model as having environments suitable to the forest type they are most likely to become. The approach has high potential for the analysis of climate change impacts as well as inferring vegetation patterns in the past and should be applicable wherever vegetation maps and spatial estimates of climate variables are available.     

Novel hybrid method for the evaluation of parameters contributing in determination of protein structural classes

Due to the increasing gap between structure-determined and sequenced proteins, prediction of protein structural classes has been an important problem. It is very important to use efficient sequential parameters for developing class predictors because of the close sequence-structure relationship. The multinomial logistic regression model was used for the first time 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. Then, the most effective parameters were selected by a multinomial logistic regression. Selected variables in the multinomial logistic model were Valine among single amino acid composition frequencies and Ala-Gly, Cys-Arg, Asp-Cys, Glu-Tyr, Gly-Glu, His-Tyr, Lys-Lys, Leu-Asp, Leu-Arg, Pro-Cys, Gln-Met, Gln-Thr, Ser-Trp, Val-Asn and Trp-Asn among dipeptide composition frequencies. Also a neural network model was constructed and fed by the parameters selected by multinomial logistic regression to build a hybrid predictor. In this study, self-consistency and jackknife tests on a database constructed by Zhou [1998. An intriguing controversy over protein structural class prediction. J. Protein Chem. 17(8), 729-738] containing 498 proteins are used to verify the performance of this hybrid method, and are compared with some of prior works. The results showed that our two-stage hybrid model approach is very promising and may play a complementary role to the existing powerful approaches.