Mathematical modeling and optimization of cellulase protein production using Trichoderma reesei RL-P37

The enzyme cellulase, a multienzyme complex made up of several proteins, catalyzes the conversion of cellulose to glucose in an enzymatic hydrolysis-based biomass-to-ethanol process. Production of cellulase enzyme proteins in large quantities using the fungus Trichoderma reesei requires understanding the dynamics of growth and enzyme production. The method of neural network parameter function modeling, which combines the approximation capabilities of neural networks with fundamental process knowledge, is utilized to develop a mathematical model of this dynamic system. In addition, kinetic models are also developed. Laboratory data from bench-scale fermentations involving growth and protein production by T. reesei on lactose and xylose are used to estimate the parameters in these models. The relative performances of the various models and the results of optimizing these models on two different performance measures are presented. An approximately 33% lower root-mean-squared error (RMSE) in protein predictions and about 40% lower total RMSE is obtained with the neural network-based model as opposed to kinetic models. Using the neural network-based model, the RMSE in predicting optimal conditions for two performance indices, is about 67% and 40% lower, respectively, when compared with the kinetic models. Thus, both model predictions and optimization results from the neural network-based model are found to be closer to the experimental data than the kinetic models developed in this work. It is shown that the neural network parameter function modeling method can be useful as a "macromodeling" technique to rapidly develop dynamic models of a process.     

Optimization of fed-batch bioreactor using neural network model

An algorithm using feedforward neural network model for determining optimal substrate feeding policies for fed-batch fermentation process is presented in this work. The algorithm involves developing the neural network model of the process using the sampled data. The trained neural network model in turn is used for optimization purposes. The advantages of this technique is that optimization can be achieved without detailed kinetic model of the process and the computation of gradient of objective function with respect to control variables is straightforward. The application of the technique is demonstrated with two examples, namely, production of secreted protein and invertase. The simulation results show that the discrete-time dynamics of fed-batch bioreactor can be satisfactorily approximated using a feedforward sigmoidal neural network. The optimal policies obtained with the neural network model agree reasonably well with the previously reported results.     

基于小波神经网络的麦蚜发生程度预测模型

【目的】建立基于小波神经网络病虫害预测预报模型,对提前采取防病防虫措施、减少农作物病虫害损失、提高农作物产量与质量具有重要意义。【方法】本研究以山西省运城市芮城县1980-2014年麦蚜发生程度和气象因子数据为基础,采用主成分分析法从40个基础气象因子中整合形成9个新的自变量输入模型,采用试凑法筛选隐含层节点数,用1980-2009年的数据进行网络训练,对2010-2014年麦蚜发生程度进行回测,建立了以Morlet小波函数为传递函数的小波神经网络模型,并与以Sigmoid函数为传递函数的BP神经网络模型进行了比较。【结果】小波和BP神经网络两种模型对训练样本的平均拟合精度均有10年以上超过80%,两者MAPE 值分别为 89.83% 和83.07%,MSE 值分别为0.0578和0.6192。【结论】两个模型都能较好地描述麦蚜发生程度;从预测精度和模型的稳定性来看,小波神经网络好于BP神经网络。     

Protein secondary structure prediction using three neural networks and a segmental semi Markov model

Prediction of protein secondary structure is an important step towards elucidating its three dimensional structure and its function. This is a challenging problem in bioinformatics. Segmental semi Markov models (SSMMs) are one of the best studied methods in this field. However, incorporating evolutionary information to these methods is somewhat difficult. On the other hand, the systems of multiple neural networks (NNs) are powerful tools for multi-class pattern classification which can easily be applied to take these sorts of information into account.To overcome the weakness of SSMMs in prediction, in this work we consider a SSMM as a decision function on outputs of three NNs that uses multiple sequence alignment profiles. We consider four types of observations for outputs of a neural network. Then profile table related to each sequence is reduced to a sequence of four observations. In order to predict secondary structure of each amino acid we need to consider a decision function. We use an SSMM on outputs of three neural networks. The proposed SSMM has discriminative power and weights over different dependency models for outputs of neural networks. The results show that the accuracy of our model in predictions, particularly for strands, is considerably increased.     

Hybrid neural network modeling of a full-scale industrial wastewater treatment process

In recent years, hybrid neural network approaches, which combine mechanistic and neural network models, have received considerable attention. These approaches are potentially very efficient for obtaining more accurate predictions of process dynamics by combining mechanistic and neural network models in such a way that the neural network model properly accounts for unknown and nonlinear parts of the mechanistic model. In this work, a full-scale coke-plant wastewater treatment process was chosen as a model system. Initially, a process data analysis was performed on the actual operational data by using principal component analysis. Next, a simplified mechanistic model and a neural network model were developed based on the specific process knowledge and the operational data of the coke-plant wastewater treatment process, respectively. Finally, the neural network was incorporated into the mechanistic model in both parallel and serial configurations. Simulation results showed that the parallel hybrid modeling approach achieved much more accurate predictions with good extrapolation properties as compared with the other modeling approaches even in the case of process upset caused by, for example, shock loading of toxic compounds. These results indicate that the parallel hybrid neural modeling approach is a useful tool for accurate and cost-effective modeling of biochemical processes, in the absence of other reasonably accurate process models.     

Artificial neural network based soft estimator for estimation of transducer static nonlinearity

In this work, the development of an Artificial Neural Network (ANN) based soft estimator is reported for the estimation of static-nonlinearity associated with the transducers. Under the realm of ANN based transducer modeling, only two neural models have been suggested to estimate the static-nonlinearity associated with the transducers with quite successful results. The first existing model is based on the concept of a functional link artificial neural network (FLANN) trained with mu-LMS (Least Mean Squares) learning algorithm. The second one is based on the architecture of a single layer linear ANN trained with alpha-LMS learning algorithm. However, both these models suffer from the problem of slow convergence (learning). In order to circumvent this problem, it is proposed to synthesize the direct model of transducers using the concept of a Polynomial-ANN (polynomial artificial neural network) trained with Levenberg-Marquardt (LM) learning algorithm. The proposed Polynomial-ANN oriented transducer model is implemented based on the topology of a single-layer feed-forward back-propagation-ANN. The proposed neural modeling technique provided an extremely fast convergence speed with increased accuracy for the estimation of transducer static nonlinearity. The results of convergence are very stimulating with the LM learning algorithm.     

Near infrared spectroscopy coupled with radial basis function neural network for at-line monitoring of Lactococcus lactis subsp. fermentation

In our previous work, partial least squares (PLSs) were employed to develop the near infrared spectroscopy (NIRs) models for at-line (fast off-line) monitoring key parameters of Lactococcus lactis subsp. fermentation. In this study, radial basis function neural network (RBFNN) as a non-linear modeling method was investigated to develop NIRs models instead of PLS. A method named moving window radial basis function neural network (MWRBFNN) was applied to select the characteristic wavelength variables by using the degree approximation (Da) as criterion. Next, the RBFNN models with selected wavelength variables were optimized by selecting a suitable constant spread. Finally, the effective spectra pretreatment methods were selected by comparing the robustness of the optimum RBFNN models developed with pretreated spectra. The results demonstrated that the robustness of the optimal RBFNN models were better than the PLS models for at-line monitoring of glucose and pH of L. lactis subsp. fermentation.     

Artificial neural networks in the modeling and optimization of aspirin extended release tablets with eudragit L 100 as matrix substance

The purpose of the present study was to model the effects of the concentration of Eudragit L 100 and compression pressure as the most important process and formulation variables on the in vitro release profile of aspirin from matrix tables formulated with Eudragit L 100 as matrix substance and to optimize the formulation by artificial neural network. As model formulations, 10 kinds of aspirin matrix tablets were prepared. The amount of Eudragit L 100 and the compression pressure were selected as causal factors. In vitro dissolution time profiles at 4 different sampling times were chosen as responses. A set of release parameters and causal factors were used as tutorial data for the generalized regression neural, network (GRNN) and analyzed using a computer. Observed results of drug release studies indicate that drug release rates vary widely between investigated formulations, with a range of 5 hours to more than 10 hours to complete dissolution. The GRNN model was optimized. The root mean square value for the trained network was 1.12%, which indicated that the optimal GRNN model was reached. Applying the generalized distance function method, the optimal tablet formulation predicted by GRNN was with 5% of Eudragit L 100 and tablet hardness 60N. Calculated difference (f ₁ 2.465) and similarity (f ₂ 85.61) factors indicate that there is no difference between predicted and experimentally observed drug release profiles for the optimal formulation. This work illustrates the potential for an artificial neural network, GRNN, to assist in development of extended release dosage forms.     

Driving reservoir models with oscillations: a solution to the extreme structural sensitivity of chaotic networks

A large body of experimental and theoretical work on neural coding suggests that the information stored in brain circuits is represented by time-varying patterns of neural activity. Reservoir computing, where the activity of a recurrently connected pool of neurons is read by one or more units that provide an output response, successfully exploits this type of neural activity. However, the question of system robustness to small structural perturbations, such as failing neurons and synapses, has been largely overlooked. This contrasts with well-studied dynamical perturbations that lead to divergent network activity in the presence of chaos, as is the case for many reservoir networks. Here, we distinguish between two types of structural network perturbations, namely local (e.g., individual synaptic or neuronal failure) and global (e.g., network-wide fluctuations). Surprisingly, we show that while global perturbations have a limited impact on the ability of reservoir models to perform various tasks, local perturbations can produce drastic effects. To address this limitation, we introduce a new architecture where the reservoir is driven by a layer of oscillators that generate stable and repeatable trajectories. This model outperforms previous implementations while being resistant to relatively large local and global perturbations. This finding has implications for the design of reservoir models that capture the capacity of brain circuits to perform cognitively and behaviorally relevant tasks while remaining robust to various forms of perturbations. Further, our work proposes a novel role for neuronal oscillations found in cortical circuits, where they may serve as a collection of inputs from which a network can robustly generate complex dynamics and implement rich computations.     

A case for spiking neural network simulation based on configurable multiple-FPGA systems

Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.     

Optimization of auto-induction medium for G-CSF production by Escherichia coli using artificial neural networks coupled with genetic algorithm

Granulocyte colony-stimulating factor (G-CSF) is a cytokine widely used in cancer patients receiving high doses of chemotherapeutic drugs to prevent the chemotherapy-induced suppression of white blood cells. The production of recombinant G-CSF should be increased to meet the increasing market demand. This study aims to model and optimize the carbon source of auto-induction medium to enhance G-CSF production using artificial neural networks coupled with genetic algorithm. In this approach, artificial neural networks served as bioprocess modeling tools, and genetic algorithm (GA) was applied to optimize the established artificial neural network models. Two artificial neural network models were constructed: the back-propagation (BP) network and the radial basis function (RBF) network. The root mean square error, coefficient of determination, and standard error of prediction of the BP model were 0.0375, 0.959, and 8.49 %, respectively, whereas those of the RBF model were 0.0257, 0.980, and 5.82 %, respectively. These values indicated that the RBF model possessed higher fitness and prediction accuracy than the BP model. Under the optimized auto-induction medium, the predicted maximum G-CSF yield by the BP-GA approach was 71.66 %, whereas that by the RBF-GA approach was 75.17 %. These predicted values are in agreement with the experimental results, with 72.4 and 76.014 % for the BP-GA and RBF-GA models, respectively. These results suggest that RBF-GA is superior to BP-GA. The developed approach in this study may be helpful in modeling and optimizing other multivariable, non-linear, and time-variant bioprocesses.     

Inductive learning approaches to rainfall-runoff modelling

Trying to model the rainfall-runoff process is a complex activity as it is influenced by a number of implicit and explicit factors--for example, precipitation distribution, evaporation, transpiration, abstraction, watershed topography, and soil types. However, this kind of forecasting is particularly important as it is used to predict serious flooding, estimate erosion and identify problems associated with low flow. Inductive learning approaches (e.g. decision trees and artificial neural networks) are particularly well suited to problems of this nature as they can often interpret underlying factors (such as seasonal variations) which cannot be modelled by other techniques. In addition, these approaches can easily be trained on the explicit factors (e.g. rainfall) and the inexplicit factors (e.g. abstraction) that affect river flow. Inductive learning approaches can also be extended to account for new factors that emerge over a period of time. This paper evaluates the application of decision trees and two artificial neural network models (the multilayer perceptron and the radial basis function network) to river flow forecasting in two flood prone UK catchments using real hydrometric data. Comparisons are made between the performance of these approaches and conventional flood forecasting systems.     

Prediction model of PSO-BP neural network on coliform amount in special food

Special food safety supervision by means of intelligent models and methods is of great significance for the health of local people and tourists. Models like BP neural network have the problems of low accuracy and poor robustness in food safety prediction. So, firstly, the principal component analysis was used to extract the key factors that influenced the amount of coliform communities, which was applied to reduce the dimension of this model as the input variable of BP neural network. Secondly, both the particle swarm optimization (PSO) and BP neural network were implemented to optimize initial weights and threshold to obtain the optimal parameter, and a model was constructed to predict the amount of coliform bacteria in Dai Special Snacks, Sa pie, based on PSO-BP neural network model. Finally, the predicted value of the model is verified. The results show that MSE is 0.0097, MAPE is 0.3198 and MAE is 0.0079, respectively. It was clear that PSO-BP model was better accuracy and robustness. That means, this model can effectively predict the amount of coliform. The research has important guiding significance for the quality and the production of Sa pie.     

A deep survival interpretable radiomics model of hepatocellular carcinoma patients

This work aims to identify a new radiomics signature using imaging phenotypes and clinical variables for risk prediction of overall survival (OS) in hepatocellular carcinoma (HCC) patients treated with stereotactic body radiation therapy (SBRT). 167 patients were retrospectively analyzed with repeated nested cross-validation to mitigate overfitting issues. 56 radiomic features were extracted from pre-treatment contrast-enhanced (CE) CT images. 37 clinical factors were obtained from patients' electronic records. Variational autoencoders (VAE) based survival models were designed for radiomics and clinical features and a convolutional neural network (CNN) survival model was used for the CECT. Finally, radiomics, clinical and raw image deep learning network (DNN) models were combined to predict the risk probability for OS. The final models yielded c-indices of 0.579 (95%CI: 0.544–0.621), 0.629 (95%CI: 0.601–0.643), 0.581 (95%CI: 0.553–0.613) and 0.650 (95%CI: 0.635–0.683) for radiomics, clinical, image input and combined models on nested cross validation scheme, respectively. Integrated gradients method was used to interpret the trained models. Our interpretability analysis of the DNN showed that the top ranked features were clinical liver function and liver exclusive of tumor radiomics features, which suggests a prominent role of side effects and toxicities in liver outside the tumor region in determining the survival rate of these patients. In summary, novel deep radiomic analysis provides improved performance for risk assessment of HCC prognosis compared with Cox survival models and may facilitate stratification of HCC patients and personalization of their treatment strategies. Liver function was found to contribute most to the OS for these HCC patients and radiomics can aid in their management.     

Proposing a Radial Basis Function and CSDM Indices to Predict the Traumatic Brain Injury Risk

BackgroundMany head injury indices and finite element (FE) head models have been proposed to predict traumatic brain injury (TBI). Although FE head models are suitable methods with high accuracy, they are computationally intensive. Head motion-based brain injury criteria are usually fast tools with lower accuracy. So, the objective of this study is to propose new criteria along with an artificial neural network model to predict TBI risks, which can be fast and accurate.MethodsFor this purpose, 250 FE head simulations have been carried out at 5 magnitudes and 50 rotational impact directions using the SIMon model. The effects of directions and magnitudes of rotational impacts were assessed for cumulative strain damage measure (CSDM) values. Next, statistical analysis and neural network were applied to predict CSDM values.ResultsThe results of the present research showed that the direction of rotation in the sagittal and frontal planes had a considerable effect on the CSDM values. Furthermore, new brain injury indices and a radial basis function neural network have been proposed to predict CSDM values which having high correlation coefficients with SIMon responses.ConclusionsThe results of this research demonstrated that rotational impact directions should be used to develop new head injury criteria being able to predict CSDM values. However, findings of present research proved that head motion-based brain injury criteria and RBF network can be used to predict FE head model responses with high speed and accuracy.     

Fitting of dynamic recurrent neural network models to sensory stimulus-response data

We present a theoretical study aiming at model fitting for sensory neurons. Conventional neural network training approaches are not applicable to this problem due to lack of continuous data. Although the stimulus can be considered as a smooth time-dependent variable, the associated response will be a set of neural spike timings (roughly the instants of successive action potential peaks) that have no amplitude information. A recurrent neural network model can be fitted to such a stimulus-response data pair by using the maximum likelihood estimation method where the likelihood function is derived from Poisson statistics of neural spiking. The universal approximation feature of the recurrent dynamical neuron network models allows us to describe excitatory-inhibitory characteristics of an actual sensory neural network with any desired number of neurons. The stimulus data are generated by a phased cosine Fourier series having a fixed amplitude and frequency but a randomly shot phase. Various values of amplitude, stimulus component size, and sample size are applied in order to examine the effect of the stimulus to the identification process. Results are presented in tabular and graphical forms at the end of this text. In addition, to demonstrate the success of this research, a study involving the same model, nominal parameters and stimulus structure, and another study that works on different models are compared to that of this research.     

Successful Reconstruction of a Physiological Circuit with Known Connectivity from Spiking Activity Alone

Identifying the structure and dynamics of synaptic interactions between neurons is the first step to understanding neural network dynamics. The presence of synaptic connections is traditionally inferred through the use of targeted stimulation and paired recordings or by post-hoc histology. More recently, causal network inference algorithms have been proposed to deduce connectivity directly from electrophysiological signals, such as extracellularly recorded spiking activity. Usually, these algorithms have not been validated on a neurophysiological data set for which the actual circuitry is known. Recent work has shown that traditional network inference algorithms based on linear models typically fail to identify the correct coupling of a small central pattern generating circuit in the stomatogastric ganglion of the crab Cancer borealis. In this work, we show that point process models of observed spike trains can guide inference of relative connectivity estimates that match the known physiological connectivity of the central pattern generator up to a choice of threshold. We elucidate the necessary steps to derive faithful connectivity estimates from a model that incorporates the spike train nature of the data. We then apply the model to measure changes in the effective connectivity pattern in response to two pharmacological interventions, which affect both intrinsic neural dynamics and synaptic transmission. Our results provide the first successful application of a network inference algorithm to a circuit for which the actual physiological synapses between neurons are known. The point process methodology presented here generalizes well to larger networks and can describe the statistics of neural populations. In general we show that advanced statistical models allow for the characterization of effective network structure, deciphering underlying network dynamics and estimating information-processing capabilities.     

Modeling and optimization of microbial hyaluronic acid production by Streptococcus zooepidemicus using radial basis function neural network coupling quantum‐behaved particle swarm optimization algorithm

Hyaluronic acid (HA) is a natural biopolymer with unique physiochemical and biological properties and finds a wide range of applications in biomedical and cosmetic fields. It is important to increase HA production to meet the increasing HA market demand. This work is aimed to model and optimize the amino acids addition to enhance HA production of Streptococcus zooepidemicus with radial basis function (RBF) neural network coupling quantum‐behaved particle swarm optimization (QPSO) algorithm. In the RBF‐QPSO approach, RBF neural network is used as a bioprocess modeling tool and QPSO algorithm is applied to conduct the optimization with the established RBF neural network black model as the objective function. The predicted maximum HA yield was 6.92 g/L under the following conditions: arginine 0.062 g/L, cysteine 0.036 g/L, and lysine 0.043 g/L. The optimal amino acids addition allowed HA yield increased from 5.0 g/L of the control to 6.7 g/L in the validation experiments. Moreover, the modeling and optimization capacity of the RBF‐QPSO approach was compared with that of response surface methodology (RSM). It was indicated that the RBF‐QPSO approach gave a slightly better modeling and optimization result compared with RSM. The developed RBF‐QPSO approach in this work may be helpful for the modeling and optimization of the other multivariable, nonlinear, time‐variant bioprocesses. © 2009 American Institute of Chemical Engineers Biotechnol. Prog., 2009