A hybrid of back propagation neural network and genetic algorithm for optimization of collagen extraction from Malaysian cultured catfish (Hybrid Clarias sp.)

Fractional factorial design (FFD) was applied to evaluate the effects of various process parameters in influencing the extraction efficiency of pepsin soluble collagen (PSC) from muscles of cultured catfish (Clarias gariepinus×C. macrocephalus). Result of the first order factorial design showed that acetic acid concentration, acid extraction time, acetic acid to muscles ratio, and stirring speed posed significant effect (P<0.05) on the yield of PSC obtained at the end of the extraction process. Two different artificial intelligence techniques namely artificial neural network (ANN) and genetic algorithm (GA) were then integrated for optimizing the extraction conditions to obtain the highest yield of PSC. The ANN was trained using the back propagation algorithm. A model was successfully generated with R ² value of 0.9527 and MSE value of 0.1672 for unseen data set, implying a good generalization of the network. Input parameters of the established ANN model were subsequently optimized using GA. The hybrid of ANN-GA model predicted a maximum extraction yield of PSC at 238.25 mg/g under the following conditions: an acetic acid concentration of 0.70 M, the acetic acid to muscles ratio of 25.78 mL/g, and the stirring speed of 432.50 rpm. Verification of the optimization showed the percentage error differences between the experimental and predicted values were less than 5%, indicating excellent modeling, predicting ability and optimization by the ANN-GA model.     

Enhanced antibiotic production by Streptomyces sindenensis using artificial neural networks coupled with genetic algorithm and Nelder-Mead downhill simplex

Antibiotic production with Streptomyces sindenensis MTCC 8122 was optimized under submerged fermentation conditions by artificial neural network (ANN) coupled with genetic algorithm (GA) and Nelder-Mead downhill simplex (NMDS). Feed forward back-propagation ANN was trained to establish the mathematical relationship among the medium components and length of incubation period for achieving maximum antibiotic yield. The optimization strategy involved growing the culture with varying concentrations of various medium components for different incubation periods. Under non-optimized condition, antibiotic production was found to be 95 microgram/ml, which nearly doubled (176 microgram/ml) with the ANN-GA optimization. ANN-NMDS optimization was found to be more efficacious, and maximum antibiotic production (197 microgram/ml) was obtained by cultivating the cells with (g/l) fructose 2.7602, MgSO4 1.2369, (NH4)2PO4 0.2742, DL-threonine 3.069%, and soyabean meal 1.952%, for 9.8531 days of incubation, which was roughly 12% higher than the yield obtained by ANN coupled with GA under the same conditions.     

Application of artificial neural network coupling particle swarm optimization algorithm to biocatalytic production of GABA

The biotransformation of L-sodium glutamate (L-MSG) to gamma-aminobutyric acid (GABA) catalyzed by the cells of Lactobacillus brevis with higher glutamate decarboxylase activity was investigated. The results showed that pH, temperature, and FeSO(4) x 7H(2)O concentration had significantly positive effect on GABA yield. The individual and interactive effects of pH, temperature, and FeSO(4) x 7H(2)O concentration were further optimized in terms of GABA yield. In the present work, an artificial neural network (ANN) and response surface methodology (RSM) models were developed, which incorporated pH, temperature, and FeSO(4) x 7H(2)O concentration as input variables, and GABA yield as output variable. The optimized ANN topology included four neurons in the hidden layer and the best network architecture was 3-4-1. The trained ANN gave total root-mean square error (sigma) equal to 1.84 for GABA yield while the RSM gave sigma equal to 2.63. The results demonstrated a slightly higher prediction accuracy of ANN compared to RSM. The modeled maximum GABA yield was identified by applying particle swarm optimization algorithm to the ANN model developed. The modeled maximum GABA yield reached 91 mM under the following optimal conditions: 25 mL Na(2)HPO(4)-citric acid buffer (100 mM, pH 4.23), 120 mM L-MSG, 0.83 g/L FeSO(4) x 7H(2)O, 10 microM PLP, the resting cells obtained from a 60-h culture broth, 2.68 g dry cell weight (DCW)/L, and without agitation at 40 degrees C for 5 h. The previous high value of GABA yield that was observed was 81.8 mM. The optimized conditions allowed GABA yield to be increased from 81.8 to 90.57 mM after verification experiments test.     

Novel optimal temperature profile for acidification process of <Emphasis Type="Italic">Lactobacillus bulgaricus</Emphasis> and <Emphasis Type="Italic">Streptococcus thermophilus</Emphasis> in yoghurt fermentation using artificial neural network and genetic algorithm

The acidification behavior of Lactobacillus bulgaricus and Streptococcus thermophilus for yoghurt production was investigated along temperature profiles within the optimal window of 38–44 °C. For the optimal acidification temperature profile search, an optimization engine module built on a modular artificial neural network (ANN) and genetic algorithm (GA) was used. Fourteen batches of yoghurt fermentations were evaluated using different temperature profiles in order to train and validate the ANN sub-module. The ANN captured the nonlinear relationship between temperature profiles and acidification patterns on training data after 150 epochs. This served as an evaluation function for the GA. The acidification slope of the temperature profile was the performance index. The GA sub-module iteratively evolved better temperature profiles across generations using GA operations. The stopping criterion was met after 11 generations. The optimal profile showed an acidification slope of 0.06117 compared to an initial value of 0.0127 and at a set point sequence of 43, 38, 44, 43, and 39 °C. Laboratory evaluation of three replicates of the GA suggested optimum profile of 43, 38, 44, 43, and 39 °C gave an average slope of 0.04132. The optimization engine used (to be published elsewhere) could effectively search for optimal profiles of different physico-chemical parameters of fermentation processes.     

基于人工神经网络-遗传算法的樟芝发酵培养基优化

采用优化模型对药用丝状真菌樟芝的复杂发酵过程进行建模,并获得最优发酵培养基组成.对樟芝发酵过程中的形态变化过程进行了观察,并分别采用人工神经网络(ANN)和响应面法(RSM)对樟芝发酵过程进行建模,同时采用遗传算法(GA)优化了发酵培养基组成.结果表明,ANN模型比RSM模型具有更好的实验数据拟合能力和预测能力,GA计算得到樟芝生物量理论最大值为6.2 g/L,并获得发酵最佳接种量及培养基组成:孢子浓度1.76× 105个/mL,葡萄糖29.1 g/L,蛋白胨9.4 g/L,黄豆粉2.8 g/L.在最佳培养条件下,樟芝生物量为(6.1±0.2)g/L.基于ANN-GA的优化方法可用于优化其他丝状真菌的复杂发酵过程,从而获得生物量或活性代谢产物.     

Design of experiments and artificial neural network linked genetic algorithm for modeling and optimization of L-asparaginase production by <Emphasis Type="Italic">Aspergillus terreus</Emphasis> MTCC 1782

The sequential optimization strategy for design of an experimental and artificial neural network (ANN) linked genetic algorithm (GA) were applied to evaluate and optimize media component for L-asparaginase production by Aspergillus terreus MTCC 1782 in submerged fermentation. The significant media components identified by Plackett-Burman design (PBD) were fitted into a second order polynomial model (R² = 0.910) and optimized for maximum L-asparaginase production using a five-level central composite design (CCD). A nonlinear model describing the effect of variables on L-asparaginase production was developed (R² = 0.995) and optimized by a back propagation NN linked GA. Ground nut oil cake (GNOC) flour 3.99% (w/v), sodium nitrate (NaNO₃) 1.04%, L-asparagine 1.84%, and sucrose 0.64% were found to be the optimum concentration with a maximum predicted L-asparaginase activity of 36.64 IU/mL using a back propagation NN linked GA. The experimental activity of 36.97 IU/mL obtained using the optimum concentration of media components is close to the predicted L-asparaginase activity of the ANN linked GA.     

Biosynthesis of gibberellic acid from milk permeate in repeated batch operation by a mutant Fusarium moniliforme cells immobilized on loofa sponge

Gibberellic acid (GA) production from milk permeate was studied by 28 mutants of Fusarium moniliforme, among which mutant gamma-14 was selected as the best producer. Experiments were carried out in shaker flasks and fermentative process was analyzed with free and immobilized cells. Immobilization of mutant gamma-14 cells onto loofa sponge discs was studied with respect to the optimization of the incubation temperature, initial pH, inoculum size (number of discs) and its reusability for GA production. Best yield of GA (2.40 gl(-1)) was recorded by immobilized cells under optimized cultural conditions (4 immobilized discs, 30 degrees C and pH 5). Data obtained during four reusable cycles showed high stability of GA production and reduction in the initiation time of acid production, resulting in higher levels of GA in shorter time duration. Immobilization of mutant gamma-14 cells onto loofa sponge discs, permitted repeated reuse under the specified fermentation conditions for GA production from milk permeate.     

利用固定化黑曲霉单宁酶制备没食子酸的研究

用海藻酸钙载体包埋单宁酶,制备出转化五倍子单宁成没食子酸能力较好的固定化酶。研究了固定化条件和固定化单宁酶的部分性质,结果表明：最佳固定化条件为海藻酸钠90mg包埋单宁酶546u(3mL,182u/Ml),在1%～2%CaCl₂中作硬化处理;固定化单宁酶的最适温度为45℃,在10～50℃范围内稳定;其最适Ph值为6.5,在Ph5～7之间基本稳定;在此基础上,进行了没食子酸实验室克量级酶法制备实验,3次实验没食子酸产品的平均产率达到61%。和目前所用工业生产没食子酸的硫酸水解法相当,具有潜在的工业开发价值。     

Rapid nested-PCR for tyrosinase gene detection on chip

The availability of non-invasive, fast and sensitive technologies for detection of circulating cancer cells is still a critical need of clinical oncology, particularly for diagnosis of aggressive and highly metastatic tumors, like malignant melanoma. Here we present the first nested polymerase chain reaction process carried out by a microfabricated, hybrid plastic-glass microfluidic chip on the tyrosinase gene, a predictive marker for melanoma diagnosis. The device is a hybrid system consisting of a glass microchannel embedded in an elastomeric matrix, and operating in flow-oscillating modality on a droplet of biological sample. The convection heat transfer and the temperature distribution inside the carrier fluid in the device are investigated. The oil responds to temperature changes with a characteristic time around 53 s, and exhibits three different thermal gradients along the capillary, with temperature variations below 4°C in correspondence of heater electrodes. The sample heating/cooling rates in the chip are as high as 16°C/s, allowing rapid processes. The nested polymerase chain reaction process is performed in less than 50 min, namely more than four times faster than in a standard thermocycler. The rapidity of the analysis method, combined with the simple and low-cost fabrication, reduced sample evaporation, and flexibility of the overall microfluidic platform, make it promising for the detection of events of tumor spreading.     

Thermoperiodic stem elongation involves transcriptional regulation of gibberellin deactivation in pea

The physiological basis of thermoperiodic stem elongation is as yet poorly understood. Thermoperiodic control of gibberellin (GA) metabolism has been suggested as an underlying mechanism. We have investigated the influence of different day and night temperature combinations on GA levels, and diurnal steady-state expression of genes involved in GA biosynthesis (LS, LH, NA, PSGA20ox1, and PsGA3ox1) and GA deactivation (PsGA2ox1 and PsGA2ox2), and related this to diurnal stem elongation in pea (Pisum sativum L. cv Torsdag). The plants were grown under a 12-h light period with an average temperature of 17 degrees C. A day temperature/night temperature combination of 13 degrees C/21 degrees C reduced stem elongation after 12 d by 30% as compared to 21 degrees C/13 degrees C. This was correlated with a 55% reduction of GA1. Although plant height correlated with GA1 content, there was no correlation between diurnal growth rhythms and GA1 content. NA, PsGA20ox1, and PsGA2ox2 showed diurnal rhythms of expression. PsGA2ox2 was up-regulated in 13 degrees C/21 degrees C (compared to 21 degrees C/13 degrees C), at certain time points, by up to 19-fold. Relative to PsGA2ox2, the expression of LS, LH, NA, PSGA20ox1, PsGA3ox1, and PsGA2ox1 was not or only slightly affected by the different temperature treatments. The sln mutant having a nonfunctional PsGA2ox1 gene product showed the same relative stem elongation response to temperature as the wild type. This supports the importance of PsGA2ox2 in mediating thermoperiodic stem elongation responses in pea. We present evidence for an important role of GA catabolism in thermoperiodic effect on stem elongation and conclude that PsGA2ox2 is the main mediator of this effect in pea.     

Rapid cycle DNA amplification: time and temperature optimization

Rapid temperature cycling with hot air allows rigorous optimization of the times and temperatures required for each stage of the polymerase chain reaction. A thermal cycler based on recirculating hot air was used for rapid temperature control of 10-microliters samples in thin glass capillary tubes with the sample temperature monitored by a miniature thermocouple probe. The temperatures and times of denaturation, annealing and elongation were individually optimized for the amplification of a 536-base pair beta-globin fragment from human genomic DNA. Optimal denaturation at 92 degrees-94 degrees C occurred in less than one second; yield decreased with denaturation times greater than 30 seconds. Annealing for one second or less at 54 degrees-56 degrees C gave the best product specificity and yield. Non-specific amplification was minimized with a rapid denaturation to annealing temperature transition (9 seconds) as compared to a longer transition (25 seconds). An elongation temperature of 75 degrees-79 degrees C gave the greatest yield and increased yields were obtained with longer elongation times. Product specificity was improved with rapid air cycling when compared to slower conventional heat block cycling. Rapid thermal control of the temperature-dependent reactions in DNA amplification can improve product specificity significantly while decreasing the required amplification time by an order of magnitude.     

Impact of temperature on plum curculio (Coleoptera: Curculionidae) responses to odor-baited traps

In 2005, captures of overwintered adult plum curculios, Conotrachelus nenuphar (Herbst) (Coleoptera: Curculionidae), in standard black masonite pyramid traps deployed in apple (Malus spp.) orchards from half-inch green until fruit reached 7 mm and baited with known attractants did not result in significant captures compared with unbaited traps as they had in 2003 and 2004. These baits included the synthetic aggregation pheromone, grandisoic acid (GA) alone, a six-component synthetic host plant volatile combination (6-Tree) identified from foliar and woody tissues of a Stanley plum tree in combination with GA (6-Tree+GA), and the synthetic fruit volatile benzaldehyde (BEN) in combination with GA (BEN+GA). In 2005, the average daily temperature was below 13 degrees C, much cooler than in 2003 and 2004. We hypothesized that plum curculio could not discriminate between baited and unbaited traps because of reduced release rates of odor-bait stimuli due to their temperature-driven release system. From data collected from 2003 to 2005, we found that plum curculio captures in traps baited with GA alone, 6-Tree+GA, and BEN+GA were significantly related to temperature. We created a predictive model to determine the level of activity, i.e., trap captures in baited traps compared with unbaited traps, we would expect to observe at a particular temperature for these same odor stimuli. Our models predicts that at temperatures between approximately 11 to 13 degrees C we would expect to see no difference between captures in baited and unbaited traps. For captures in odor-baited traps to reach twice those in unbaited traps, our model predicts that temperatures must reach 19.2 degrees C for GA alone, 18.5 degrees C for 6-Tree+GA, and 15.8 degrees C for BEN+GA.     

Utilization of newly developed immobilized enzyme reactors for preparation and study of immunoglobulin G fragments

The newly developed immobilized enzyme reactors (IMERs) with proteolytic enzymes chymotrypsin, trypsin or papain were used for specific fragmentation of high molecular-mass and heterogeneous glycoproteins immunoglobulin G (IgG) and crystallizable fragment of IgG (Fc). The efficiency of splitting or digestion were controlled by RP-HPLC. The specificity of digestion by trypsin reactor was controlled by MS. IMERs (trypsin immobilized on magnetic microparticles focused in a channel of magnetically active microfluidic device) was used for digestion of the whole IgG molecule. The sufficient conditions for IgG digestion in microfluidic device (flow rate, ratio S:E, pH, temperature) were optimized. It was confirmed that the combination of IMERs with microfluidic device enables efficient digestion of highly heterogeneous glycoproteins such as IgG in extremely short time and minimal reaction volume.     

Maximizing the native concentration and shelf life of protein: a multiobjective optimization to reduce aggregation

A multiobjective optimization was performed to maximize native protein concentration and shelf life of ASD, using artificial neural network (ANN) and genetic algorithm (GA). Optimum pH, storage temperature, concentration of protein, and protein stabilizers (Glycerol, NaCl) were determined satisfying the twin objective: maximum relative area of the dimer peak (native state) after 48 h of storage, and maximum shelf life. The relative area of the dimer peak, obtained from size exclusion chromatography performed as per the central composite design (CCD), and shelf life (obtained as turbidity change) served as training targets for the ANN. The ANN was used to establish mathematical relationship between the inputs and targets (from CCD). GA was then used to optimize the above determinants of aggregation, maximizing the twin objectives of the network. An almost fourfold increase in shelf life (~196 h) was observed at the GA-predicted optimum (protein concentration: 6.49 mg/ml, storage temperature: 20.8 °C, Glycerol: 10.02%, NaCl: 51.65 mM and pH: 8.2). Since no aggregation was observed at the optimum till 48 h, all the protein was found at the dimer position with maximum relative area (64.49). Predictions of the finally adapted network also reveal that storage temperature and solvent glycerol concentration plays key role in deciding the degree of ASD aggregation. This multiobjective optimization strategy was also successfully applied in minimizing the batch culture period and determining optimum combination of medium components required for most economical production of actinomycin D.     

Thirty-cycle temperature optimization of a closed-cycle capillary PCR machine

The performance of a novel thermal cycler has been characterized in a 30-cycle PCR. The device consists of a microcapillary equipped with bidirectional pressure-driven flow and in situ optical position sensors. A 1-microL droplet of reaction mixture moves between three heat zones in a 1-mm i.d., oil-filled capillary using a multi-element scattered light detector and active feedback. The design permits time and number of cycles to be changed without hardware modification, unlike other flow-in-capillary PCR systems. Temperature optimization has been performed on the three PCR heat steps. The optimal denaturation temperature is 94 degrees C-96 degrees C, which is identical to commercial machines. The optimal extension temperature of 62 degrees C-66 degrees C is lower than reported for Taq DNA polymerase (70 degrees C-80 degrees C) because of the high enzyme concentration and/or the absence of detergent in the PCR mixture. The optimal annealing temperature seems to be the same as the optimal extension temperature. This is because extension occurs when the sample is inside of the annealing heat zone. Annealing takes place as the sample travels between heat zones. Device speed (23 minfor 30 cycles without time optimization) is competitive with other rapid PCR designs for efficiencies comparable to a commercial machine.     

Optimization of fermentation medium for triterpenoid production from <Emphasis Type="Italic">Antrodia camphorata</Emphasis> ATCC 200183 using artificial intelligence-based techniques

In this study, alteration in morphology of submergedly cultured Antrodia camphorata ATCC 200183 including arthroconidia, mycelia, external and internal structures of pellets was investigated. Two optimization models namely response surface methodology (RSM) and artificial neural network (ANN) were built to optimize the inoculum size and medium components for intracellular triterpenoid production from A. camphorata. Root mean squares error, R ², and standard error of prediction given by ANN model were 0.31%, 0.99%, and 0.63%, respectively, while RSM model gave 1.02%, 0.98%, and 2.08%, which indicated that fitness and prediction accuracy of ANN model was higher when compared to RSM model. Furthermore, using genetic algorithm (GA), the input space of ANN model was optimized, and maximum triterpenoid production of 62.84 mg l⁻¹ was obtained at the GA-optimized concentrations of arthroconidia (1.78 × 10⁵ ml⁻¹) and medium components (glucose, 25.25 g l⁻¹; peptone, 4.48 g l⁻¹; and soybean flour, 2.74 g l⁻¹). The triterpenoid production experimentally obtained using the ANN–GA designed medium was 64.79 ± 2.32 mg l⁻¹ which was in agreement with the predicted value. The same optimization process may be used to optimize many environmental and genetic factors such as temperature and agitation that can also affect the triterpenoid production from A. camphorata and to improve the production of bioactive metabolites from potent medicinal fungi by changing the fermentation parameters.     

Artificial intelligence based optimization of exocellular glucansucrase production from Leuconostoc dextranicum NRRL B-1146

Two different artificial intelligence techniques namely artificial neural network (ANN) and genetic algorithm (GA) were integrated for optimizing fermentation medium for the production of glucansucrase. The experimental data reported in a previous study were used to build the neural network. The ANN was trained using the back propagation algorithm. The ANN predicted values showed good agreement with the experimentally reported ones from a response surface based experiment. The concentrations of three medium components: viz Tween 80, sucrose and K(2)HPO(4) served as inputs to the neural network model and the enzyme activity as the output of the model. A model was generated with a coefficient of correlation (R(2)) of 1.0 for the training set and 0.90 for the test data. A genetic algorithm was used to optimize the input space of the neural network model to find the optimum settings for maximum enzyme activity. This artificial neural network supported genetic algorithm predicted a maximum glucansucrase activity of 6.92U/ml at medium composition of 0.54% (v/v) Tween 80, 5.98% (w/v) sucrose and 1.01% (w/v) K(2)HPO(4). ANN-GA predicted model gave a 6.0% increase of enzyme activity over the regression based prediction for optimized enzyme activity. The maximum enzyme activity experimentally obtained using the ANN-GA designed medium was 6.75+/-0.09U/ml which was in good agreement with the predicted value.     

A Microfluidic Platform for Precision Small-volume Sample Processing and Its Use to Size Separate Biological Particles with an Acoustic Microdevice

A major advantage of microfluidic devices is the ability to manipulate small sample volumes, thus reducing reagent waste and preserving precious sample. However, to achieve robust sample manipulation it is necessary to address device integration with the macroscale environment. To realize repeatable, sensitive particle separation with microfluidic devices, this protocol presents a complete automated and integrated microfluidic platform that enables precise processing of 0.15–1.5 ml samples using microfluidic devices. Important aspects of this system include modular device layout and robust fixtures resulting in reliable and flexible world to chip connections, and fully-automated fluid handling which accomplishes closed-loop sample collection, system cleaning and priming steps to ensure repeatable operation. Different microfluidic devices can be used interchangeably with this architecture. Here we incorporate an acoustofluidic device, detail its characterization, performance optimization, and demonstrate its use for size-separation of biological samples. By using real-time feedback during separation experiments, sample collection is optimized to conserve and concentrate sample. Although requiring the integration of multiple pieces of equipment, advantages of this architecture include the ability to process unknown samples with no additional system optimization, ease of device replacement, and precise, robust sample processing.     

Point of care testing system via enzymatic method for the rapid, efficient assay of glycated albumin

The ratio of glycated albumin to albumin concentration in serum is termed the glycated albumin (GA) value. The GA value provides a time-averaged index of the state of glycemic control for the previous 2 weeks. In this study, a dry chemistry system (GA monitor) via an enzymatic method was proposed in order to provide a GA value measurement for point of care testing (POCT). The GA monitor was made from three devices a set of test-tapes, a test-strip and an optical analyzer. A GA test-tape, a ketoamine test-tape and an albumin test-tape were enclosed in the fabricated test-strip. Time-course changes of the optical characteristics were evaluated using the test-strip. It was found that the three test tapes must be enclosed in the test-strip to create a dry chemistry system for small sample volumes (20 microl). A temperature control unit, which could hold the temperature of the GA test-tape at 45 degrees C and at 25 degrees C for the other two types of test-tape was incorporated into the optical analyzer. With the GA test-tape held separately and controlled at 45 degrees C, the analytical time decreased to one-third of the time taken for the three tapes at 25 degrees C. The analytical accuracy of the three types of test-tape showed favorable results, with R2 values of 0.96-0.98 and coefficients of variation (CV) of 2.4-6.8%. Compared with a commercially available liquid chemistry system, the analytical accuracy of the GA monitor exhibited a relatively favorable linearity of R=0.82. According to these results, a new GA value analytical system was realized, in which the GA value could be assayed within five minutes using only 20 microl of blood sample with a disposable test-strip. This system could potentially be used for clinical purposes as test equipment for rapid and efficient POCT.