Designing fermentation media: A comparison of neural networks to factorial design

Summary Neural networks were compared to factorial experiments as techniques for designing fermentation media. The production of intracellular oil byRhodotorula gracilis (Rhodosporidium toruloides) was used as a model system. Investigating three factors, the molasses, ammonium nitrate and yeast extract concentrations, each at three concentrations, 27 experiments were required for a complete factorial expriment. In contrast, neural networks could be trained on 10 experiments and predict the test experiments with reasonable accuracy. This represents a 63% saving in the number of experiments that need to be conducted. Thus neural networks are a useful tool in developing fermentation medium.     

Data and knowledge based experimental design for fermentation process optimization

A novel method for the sequential experimental design in order to optimize fed-batch fermentations was applied to a hyaluronidase fermentation by Streptococcus agalactiae. A Λ-optimal design was introduced to minimize the model parameter estimation error and to maximize the performance of the fermentation process. The method employs hybrid models that contain mechanistic, fuzzy and neural network components.     

Strategies for improving fermentation medium performance: a review

Many techniques are available in the fermentation medium designer’s toolbox (borrowing, component swapping, biological mimicry, one-at-a-time, statistical and mathematical techniques—experimental design and optimization, artificial neural networks, fuzzy logic, genetic algorithms, continuous fermentation, pulsed batch and stoichiometric analysis). Each technique has advantages and disadvantages, and situations where they are best applied. No one ‘magic bullet’ technique exists for all situations. However, considerable advantage can be gained by logical application of the techniques, combined with good experimental design. Received 24 December 1998/ Accepted in revised form 18 August 1999     

Comparing the performance of multilayer perceptrons networks and neuro-fuzzy systems for on-line inference of <Emphasis Type="Italic">Bacillus megaterium</Emphasis> cellular concentrations

Penicillin G acylase (PGA) is one of the most important enzymes for the pharmaceutical industry. Bacillus megaterium has the advantage of producing extra-cellular PGA. This work compares two neural networks (NNs) architectures for on-line inference of B. megaterium cell mass in an aerated stirred tank bioreactor, during the production of PGA. Nowadays, intelligent computing tools such as artificial NNs and fuzzy logic are commonly applied for state inference and modeling of bioreactors. Combining these two approaches in hybrid, neuro-fuzzy systems, may be advantageous. Our results indicate that a neuro-fuzzy inference system showed a better performance to infer cell concentrations, when compared to multilayer perceptrons networks.     

An evaluation of a neural network for the start-up phase of a continuous recombinant fermentation subject to disturbances

Summary A radial basis neural network was applied to a process for glyceraldehyde-3-phosphate dehydrogenase produced by an Escherichia coli strain containing the plasmid pBR Eco gap. A neural network trained with a pure culture predicted the performance of a fermentation containing wild type cells and/or product in the inoculum better than in the reverse case; this is explained. In general, the network learnt the trends in the concentrations of plasmid-containing cells and the recombinant product more accurately than those of wild type cells and the substrate. This similarity with deterministic networks and the good predictability with some training vectors suggests that neural networks can be used to simulate the start-up phase of recombinant fermentations corrupted by disturbances.     

Uniform design: A new approach of designing fermentation media

Summary Uniform design was introduced as a new approach of designing fermentation medium. The production of ethanol by Saccharomyces cerevisiae was used as a model system to investigate its applicability. Six factors, each at 10 levels experiments based on uniform design were carried out. As a result, the empirical mathematical models could successfully predict the experimental results with very good accuracy. In contrast with orthogonal design, uniform design has advantages of less experiments and higher working effeciency. Furthermore, factor influences on operation performance can be easily analyzed.     

Hierarchical genetic algorithm for near optimal feedforward neural network design

In this paper, we propose a genetic algorithm based design procedure for a multi layer feed forward neural network. A hierarchical genetic algorithm is used to evolve both the neural networks topology and weighting parameters. Compared with traditional genetic algorithm based designs for neural networks, the hierarchical approach addresses several deficiencies, including a feasibility check highlighted in literature. A multi objective cost function is used herein to optimize the performance and topology of the evolved neural network simultaneously. In the prediction of Mackey Glass chaotic time series, the networks designed by the proposed approach prove to be competitive, or even superior, to traditional learning algorithms for the multi layer Perceptron networks and radial basis function networks. Based upon the chosen cost function, a linear weight combination decision making approach has been applied to derive an approximated Pareto optimal solution set. Therefore, designing a set of neural networks can be considered as solving a two objective optimization problem.     

Using highly efficient nonlinear experimental design methods for optimization of Lactococcus lactis fermentation in chemically defined media

Optimization of fermentation media and processes is a difficult task due to the potential for high dimensionality and nonlinearity. Here we develop and evaluate variations on two novel and highly efficient methods for experimental fermentation optimization. The first approach is based on using a truncated genetic algorithm with a developing neural network model to choose the best experiments to run. The second approach uses information theory, along with Bayesian regularized neural network models, for experiment selection. To evaluate these methods experimentally, we used them to develop a new chemically defined medium for Lactococcus lactis IL1403, along with an optimal temperature and initial pH, to achieve maximum cell growth. The media consisted of 19 defined components or groups of components. The optimization results show that the maximum cell growth from the optimal process of each novel method is generally comparable to or higher than that achieved using a traditional statistical experimental design method, but these optima are reached in about half of the experiments (73–94 vs. 161, depending on the variants of methods). The optimal chemically defined media developed in this work are rich media that can support high cell density growth 3.5–4 times higher than the best reported synthetic medium and 72% higher than a commonly used complex medium (M17) at optimization scale. The best chemically defined medium found using the method was evaluated and compared with other defined or complex media at flask‐ and fermentor‐scales. © 2009 American Institute of Chemical Engineers Biotechnol. Prog., 2009     

Modeling of the pyruvate production with Escherichia coli: comparison of mechanistic and neural networks-based models

Three different models: the unstructured mechanistic black-box model, the input–output neural network-based model and the externally recurrent neural network model were used to describe the pyruvate production process from glucose and acetate using the genetically modified Escherichia coli YYC202 ldhA::Kan strain. The experimental data were used from the recently described batch and fed-batch experiments [ Zelić B, Study of the process development for Escherichia coli-based pyruvate production. PhD Thesis, University of Zagreb, Faculty of Chemical Engineering and Technology, Zagreb, Croatia, July 2003. (In English); Zelić et al. Bioproc Biosyst Eng 26:249–258 (2004); Zelić et al. Eng Life Sci 3:299–305 (2003); Zelić et al Biotechnol Bioeng 85:638–646 (2004)]. The neural networks were built out of the experimental data obtained in the fed-batch pyruvate production experiments with the constant glucose feed rate. The model validation was performed using the experimental results obtained from the batch and fed-batch pyruvate production experiments with the constant acetate feed rate. Dynamics of the substrate and product concentration changes was estimated using two neural network-based models for biomass and pyruvate. It was shown that neural networks could be used for the modeling of complex microbial fermentation processes, even in conditions in which mechanistic unstructured models cannot be applied.     

A self-tuning vision system for monitoring biotechnological processes: I. Application to production of pullulan by Aureobasidium pullulans

A prototype of a self-tuning vision system (STVS) has been developed to monitor cell population in fermentations. The STVS combines classical image processing techniques, neural networks and fuzzy logic technologies. By combining these technologies the STVS is able to analyze sampled images of the culture. The proposed system can be "tailored" with minimum effort by an expert who can "teach" the system to recognize cells by showing examples of different morphologies. After adaptation, the STVS is able to capture images, isolate the different cells, classify them according to the expert's criteria, and provide the profile of the cell's population. The system was applied to the classification and analysis of Aureobasidium pullulans. The importance of understanding the changes of population distribution during the fermentation and its effect in the production of pullulan are emphasized. The STVS can be used for monitoring and control of the cell population in small research fermentors or in large-scale production.     

Artificial neural network based experimental design procedure for enhancing fermentation development

Conventional experimental design techniques are available to assist in the optimization of fermentation processes, but due to the nonlinearities in the bioprocess, they are limited in their effectiveness. This problem is further complicated with recombinant systems as a result of the additional complexities of the process. This article describes a general strategy using artificial neural networks as an alternative approach to fermentation process development laboratory are presented for the neural network based procedures. (c) 1994 John Wiley & Sons, Inc.     

Control of fed-batch fermentations

Fed-batch fermentation is used to prevent or reduce substrate-associated growth inhibition by controlling nutrient supply. Here we review the advances in control of fed-batch fermentations. Simple exponential feeding and inferential methods are examined, as are newer methods based on fuzzy control and neural networks. Considerable interest has developed in these more advanced methods that hold promise for optimizing fed-batch techniques for complex fermentation systems.     

High-cell-density cultivation of microorganisms

High-cell-density cultivation (HCDC) is required to improve microbial biomass and product formation substantially. An overview of HCDC is given for microorganisms including bacteria, archae and eukarya (yeasts). Problems encountered by HCDC and their possible solutions are discussed. Improvements of strains, different types of bioreactors and cultivation strategies for successful HCDC are described. Stirred-tank reactors with and without cell retention, a dialysis-membrane reactor, a gas-lift reactor and a membrane cyclone reactor used for HCDC are outlined. Recently modified traditional feeding strategies and new ones are included, in particular those for unlimited growth to very dense cultures. Emphasis is placed on robust fermentation control because of the growing industrial interest in this field. Therefore, developments in the application of multivariate statistical control, artificial neural networks, fuzzy control and knowledge-based supervision (expert systems) are summarized. Recent advances using Escherichia coli– the pioneer organism for HCDC – are outlined. Received: 20 October 1998 / Received revision: 18 December 1998 / Accepted: 21 December 1998     

Predicting optimal in vitro culture medium for <Emphasis Type="Italic">Pistacia vera</Emphasis> micropropagation using neural networks models

In this study, artificial intelligence techniques—specifically artificial neural networks (ANNs) in combination with fuzzy logic (neurofuzzy logic) or with genetic algorithms (ANNs–GA)—have been employed, as modeling tools, to get insight, to predict and to optimize the effect of several independent factors on four growth parameters during Pistacia vera micropropagation. Twenty-six media ingredients, including mineral ions (or salts), glycine, vitamins and plant growth regulators (PGRs) at different concentrations, were used as inputs and four growth parameters: proliferation rate, shoot length, total and healthy fresh weight as outputs on the models. The IF-THEN rules from neurofuzzy logic models have allowed discovering the positive (BAP, nicotinic-acid and pyridoxine-HCl) and negative (NO₃ ^?, Mg²⁺, Ag⁺ and gluconate^?) effects on the growth parameters and the fundamental role of BAP over all of them. Also, ANNs–GA technology has permitted to estimate the best combination of media ingredients to simultaneously maximize the four parameters of growth: 4.4 new shoots per explant; 28.7 mm length; 1.1 and 0.53 g total and healthy fresh weight, respectively, minimizing physiological disorders. In our opinion, the information obtained in this study is extremely useful to improve the massive multiplication of pistachio plant, in particular, but also demonstrate the ability of artificial intelligence technology to design plant tissue culture media with predictable and tailorable characteristics.     

Neural network designs for poly- β-hydroxybutyrate production optimization under simulated industrial conditions

Improvement of the fermentation efficiency of poly--hydroxybutyrate (PHB) may make it competitive with chemically synthesized petroleum-based polymers. One step toward this is optimization of fluid dispersion and the feed rates to a fed-batch bioreactor. In a recent study using a fermentation model, dispersion corresponding to a Peclet number of 20 was shown to maximize the productivity of PHB. Here further improvement has been investigated using neural optimization. A comparison of seven neural topologies has shown that while feed-forward and radial basis neural networks are computationally efficient, recurrent networks generate higher concentrations of PHB. All networks enhanced the productivity by 16–93% over model-based optimization.     

Left ventricular geometric patterns in newly presenting nigerian hypertensives: An echocardiographic study

Background

In recent years a number of algorithms for cardiovascular risk assessment has been proposed to the medical community. These algorithms consider a number of variables and express their results as the percentage risk of developing a major fatal or non-fatal cardiovascular event in the following 10 to 20 years

Discussion

The author has identified three major pitfalls of these algorithms, linked to the limitation of the classical statistical approach in dealing with this kind of non linear and complex information. The pitfalls are the inability to capture the disease complexity, the inability to capture process dynamics, and the wide confidence interval of individual risk assessment. Artificial Intelligence tools can provide potential advantage in trying to overcome these limitations. The theoretical background and some application examples related to artificial neural networks and fuzzy logic have been reviewed and discussed.

Summary

The use of predictive algorithms to assess individual absolute risk of cardiovascular future events is currently hampered by methodological and mathematical flaws. The use of newer approaches, such as fuzzy logic and artificial neural networks, linked to artificial intelligence, seems to better address both the challenge of increasing complexity resulting from a correlation between predisposing factors, data on the occurrence of cardiovascular events, and the prediction of future events on an individual level.     

Explicit Logic Circuits Predict Local Properties of the Neocortex's Physiology and Anatomy

Background

Two previous articles proposed an explicit model of how the brain processes information by its organization of synaptic connections. The family of logic circuits was shown to generate neural correlates of complex psychophysical phenomena in different sensory systems.

Methodology/Principal Findings

Here it is shown that the most cost-effective architectures for these networks produce correlates of electrophysiological brain phenomena and predict major aspects of the anatomical structure and physiological organization of the neocortex. The logic circuits are markedly efficient in several respects and provide the foundation for all of the brain''s combinational processing of information.

Conclusions/Significance

At the local level, these networks account for much of the physical structure of the neocortex as well its organization of synaptic connections. Electronic implementations of the logic circuits may be more efficient than current electronic logic arrays in generating both Boolean and fuzzy logic.     

软计算在生态模型中的应用

由于生态系统的高度复杂性和非线性以及空间数据采集技术的快速发展,近年来越来越多的软计算方法开始应用到生态模拟中来。软计算是个非常广泛的领域,在模式上主要包括元胞自动机、基于个体和盒式模式等;在方法上代表性的有人工神经网络、模糊数学、遗传算法、混沌理论等。重点介绍元胞自动机和规律方法在生态模型中的应用,具体实例包括种群动态模拟、水华预警和生境栖息地模拟。     

Fuzzy Logic Control of Bioreactor for Enhanced Biosynthesis of Alkaline Protease by an Alkalophilic Strain of Bacillus subtilis

Present studies describe the optimization of some cultural parameters such as medium pH, incubation temperature, and agitation rate for the biosynthesis of alkaline protease by Bacillus subtilis IH-72 in a bioreactor using fuzzy logic control. The process of fermentation was carried out in a 7.5-L bioreactor (New Brunswick Scientific, USA) with a working volume of 5 L. All of the parameters were automatically controlled with the help of attached software. The optimum pH, temperature, and agitation for the production of alkaline protease by B. subtilis IH-72 were found to be 9.0, 35°C, and 175 rpm, respectively. The performance of the fuzzy logic of the bioreactor was found to be encouraging for enhanced production of the enzymes. The maximum production of alkaline protease during the present study was found to be 9.6 U mL⁻¹.