利用神经网络对蛋白质家族进行预测

提出了一种利用神经网络为蛋白质家族建立模型的方法,这一方法的理论出发点是利用神经网络从一组同家族蛋白质序列中识别出共同的特征模式,建好的模型可用于预测蛋白质家族,使用这一方法。所能识别的模式在长度、位点等方面都不受限制。而且建模及预测过程中输入神经网络的蛋白质序列不需要作预对齐。对Pfam蛋白质库中的二十个家族运用此方法,预测的平均正确率达到了95．5％。     

Detection of dairy fouling: Combining ultrasonic measurements and classification methods

Fouling and cleaning in heat exchangers are severe and costly (up to 0.3% of gross national product) issues in dairy and food processing. Therefore, reducing cleaning time and cost is urgently needed. In this study, two classification methods [artificial neural network (ANN) and support vector machine (SVM)] for detecting protein and mineral fouling presence and absence based on ultrasonic measurements were presented and compared. ANN is based on a multilayer perceptron feed forward neural network, whereas SVM is based on clustering between fouling and no fouling using a hyperplane. When both fouling types (1239 datasets) were combined, ANN showed an accuracy of 71.9% while SVM displayed an accuracy of 97.6%. Separate fouling detection of mineral/protein fouling by ANN/SVM was comparable: dependent on fouling type detection accuracies of 100% (protein fouling, ANN and SVM), and 98.2% (SVM), and 93.5% (ANN) for mineral fouling was reached. It was shown that it was possible to detect fouling presence and absence offline in a static setup using ultrasonic measurements in combination with a classification method. This study proved the applicability of combining classification methods and fouling measurements to take a step toward reducing cleaning costs and time.     

Potentiometric bioelectronic tongue for the analysis of urea and alkaline ions in clinical samples

Urea biosensors based on urease covalently immobilized on to ammonium and hydrogen ion-selective electrodes were included in arrays together with ammonium, potassium, sodium, hydrogen and generic response to alkaline sensors. Response models based on artificial neural network (ANN) and partial least squares (PLS1) were built, tested and compared for the simultaneous determination of urea, ammonium, potassium and sodium. The results show that it is possible to obtain good ANN and PLS calibration models for simultaneous determination of these four species, but with better prediction capability when the ANN are used. The developed bioelectronic tongue was applied to multidetermination in urine samples. The ANN model showed again better agreement with reference methods, allowing a simple direct determination of urea in the real samples without the necessity of eliminating the alkaline interferences, or compensating endogenous ammonium.     

Physics and chemistry-driven artificial neural network for predicting bioactivity of peptides and proteins and their design

Predicting the bioactivity of peptides and proteins is an important challenge in drug development and protein engineering. In this study we introduce a novel approach, the so-called “physics and chemistry-driven artificial neural network (Phys-Chem ANN)”, to deal with such a problem. Unlike the existing ANN approaches, which were designed under the inspiration of biological neural system, the Phys-Chem ANN approach is based on the physical and chemical principles, as well as the structural features of proteins. In the Phys-Chem ANN model the “hidden layers” are no longer virtual “neurons”, but real structural units of proteins and peptides. It is a hybridization approach, which combines the linear free energy concept of quantitative structure-activity relationship (QSAR) with the advanced mathematical technique of ANN. The Phys-Chem ANN approach has adopted an iterative and feedback procedure, incorporating both machine-learning and artificial intelligence capabilities. In addition to making more accurate predictions for the bioactivities of proteins and peptides than is possible with the traditional QSAR approach, the Phys-Chem ANN approach can also provide more insights about the relationship between bioactivities and the structures involved than the ANN approach does. As an example of the application of the Phys-Chem ANN approach, a predictive model for the conformational stability of human lysozyme is presented.     

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.     

Design of Tunable Multi-Band Metamaterial Perfect Absorbers Based on Magnetic Polaritons

A tunable multi-band metamaterial perfect absorber is designed in this paper. The absorber made of a composite array of gold elliptical and circular disks on a thick metallic substrate, separated by a thin dielectric spacer. The absorptivity and the field enhancement of proposed structures are numerically investigated by the finite difference time domain method. Three absorption peaks (1.15, 1.55, and 2.05 μm) with the maximal absorption of 99.2, 99.7, and 97.3% have been achieved, respectively. By altering the dimensions of associated geometric parameters in the structure, three resonance wavelengths can be tuned individually. Physical mechanism of the multi-band absorption is construed as the resonance of magnetic polaritons. And the absorber exhibits the characteristics that are insensitive to the polarization angle due to its symmetry. The research results can have access to selective control of thermal radiation and the design of multi-band photodetectors.

     

Control of bioreactors using a neural network model

Control of a continuous bioreactor based on a artificial neural network (ANN) model is carried out theoretically. The ANN model is identified, from input-output data of a bioreactor, using a three-layer feedforward network trained by a back propagation algorithm. The performance of the controller designed on the ANN model is compared with that of a conventional PI controller.     

Use of artificial neural networks to accurately identify Cryptosporidium oocyst and Giardia cyst images

Cryptosporidium parvum and Giardia lamblia are protozoa capable of causing gastrointestinal diseases. Currently, these organisms are identified using immunofluorescent antibody (IFA)-based microscopy, and identification requires trained individuals for final confirmation. Since artificial neural networks (ANN) can provide an automated means of identification, thereby reducing human errors related to misidentification, ANN were developed to identify Cryptosporidium oocyst and Giardia cyst images. Digitized images of C. parvum oocysts and G. lamblia cysts stained with various commercial IFA reagents were used as positive controls. The images were captured using a color digital camera at 400 x (total magnification), processed, and converted into a binary numerical array. A variety of "negative" images were also captured and processed. The ANN were developed using these images and a rigorous training and testing protocol. The Cryptosporidium oocyst ANN were trained with 1,586 images, while Giardia cyst ANN were trained with 2,431 images. After training, the best-performing ANN were selected based on an initial testing performance against 100 images (50 positive and 50 negative images). The networks were validated against previously "unseen" images of 500 Cryptosporidium oocysts (250 positive, 250 negative) and 282 Giardia cysts (232 positive, 50 negative). The selected ANNs correctly identified 91.8 and 99.6% of the Cryptosporidium oocyst and Giardia cyst images, respectively. These results indicate that ANN technology can be an alternate to having trained personnel for detecting these pathogens and can be a boon to underdeveloped regions of the world where there is a chronic shortage of adequately skilled individuals to detect these pathogens.     

Predicting expected progeny difference for marbling score in Angus cattle using artificial neural networks and Bayesian regression models

Background

Artificial neural networks (ANN) mimic the function of the human brain and are capable of performing massively parallel computations for data processing and knowledge representation. ANN can capture nonlinear relationships between predictors and responses and can adaptively learn complex functional forms, in particular, for situations where conventional regression models are ineffective. In a previous study, ANN with Bayesian regularization outperformed a benchmark linear model when predicting milk yield in dairy cattle or grain yield of wheat. Although breeding values rely on the assumption of additive inheritance, the predictive capabilities of ANN are of interest from the perspective of their potential to increase the accuracy of prediction of molecular breeding values used for genomic selection. This motivated the present study, in which the aim was to investigate the accuracy of ANN when predicting the expected progeny difference (EPD) of marbling score in Angus cattle. Various ANN architectures were explored, which involved two training algorithms, two types of activation functions, and from 1 to 4 neurons in hidden layers. For comparison, BayesCπ models were used to select a subset of optimal markers (referred to as feature selection), under the assumption of additive inheritance, and then the marker effects were estimated using BayesCπ with π set equal to zero. This procedure is referred to as BayesCpC and was implemented on a high-throughput computing cluster.

Results

The ANN with Bayesian regularization method performed equally well for prediction of EPD as BayesCpC, based on prediction accuracy and sum of squared errors. With the 3K-SNP panel, for example, prediction accuracy was 0.776 using BayesCpC, and ranged from 0.776 to 0.807 using BRANN. With the selected 700-SNP panel, prediction accuracy was 0.863 for BayesCpC and ranged from 0.842 to 0.858 for BRANN. However, prediction accuracy for the ANN with scaled conjugate gradient back-propagation was lower, ranging from 0.653 to 0.689 with the 3K-SNP panel, and from 0.743 to 0.793 with the selected 700-SNP panel.

Conclusions

ANN with Bayesian regularization performed as well as linear Bayesian regression models in predicting additive genetic values, supporting the idea that ANN are useful as universal approximators of functions of interest in breeding contexts.     

Differentiation of probiotic and environmental Saccharomyces cerevisiae strains in animal feed

Aims: To establish an identification system for probiotic Saccharomyces cerevisiae strains based on artificial neural network (ANN)–assisted Fourier‐transform infrared (FTIR) spectroscopy to improve quality control of animal feed. Methods and Results: The ANN‐based system for differentiating environmental from probiotic S. cerevisiae strains comprises five authorized feed additive strains plus environmental strains isolated from different habitats. A total of 108 isolates were used as reference strains to create the ANN. DHPLC analysis and δ‐PCR were used as reference methods to type probiotic yeast isolates. The performance of the FTIR‐ANN was tested in an internal validation using unknown spectra of each reference strain. This validation step yielded a classification rate of 99·1 %. For an external validation, a test data set comprising 965 spectra of 63 probiotic and environmental S. cerevisiae isolates unknown to the ANN was used, resulting in a classification rate of 98·2 %. Conclusions: Our results demonstrate that probiotic S. cerevisiae strains in feed can be differentiated successfully from environmental isolates using both genotypic approaches and ANN‐based FTIR spectroscopy. Significance and Impact of the Study: FTIR‐based artificial neural network analysis provides a rapid and inexpensive technique for yeast identification both at the species and at the strain level in routine diagnostic laboratories, using a single sample preparation.     

Comparison of Prediction Model for Cardiovascular Autonomic Dysfunction Using Artificial Neural Network and Logistic Regression Analysis

Background

This study aimed to develop the artificial neural network (ANN) and multivariable logistic regression (LR) analyses for prediction modeling of cardiovascular autonomic (CA) dysfunction in the general population, and compare the prediction models using the two approaches.

Methods and Materials

We analyzed a previous dataset based on a Chinese population sample consisting of 2,092 individuals aged 30–80 years. The prediction models were derived from an exploratory set using ANN and LR analysis, and were tested in the validation set. Performances of these prediction models were then compared.

Results

Univariate analysis indicated that 14 risk factors showed statistically significant association with the prevalence of CA dysfunction (P<0.05). The mean area under the receiver-operating curve was 0.758 (95% CI 0.724–0.793) for LR and 0.762 (95% CI 0.732–0.793) for ANN analysis, but noninferiority result was found (P<0.001). The similar results were found in comparisons of sensitivity, specificity, and predictive values in the prediction models between the LR and ANN analyses.

Conclusion

The prediction models for CA dysfunction were developed using ANN and LR. ANN and LR are two effective tools for developing prediction models based on our dataset.     

Pulse design for broadband correlation NMR spectroscopy by multi-rotating frames

We present a method for designing radio-frequency (RF) pulses for broadband or multi-band isotropic mixing at low power, suitable for protein NMR spectroscopy. These mixing pulses are designed analytically, rather than by numerical optimization, by repeatedly constructing new rotating frames of reference. We show how pulse parameters can be chosen frame-by-frame to systematically reduce the effective chemical shift bandwidth, but maintain most of the effective J-coupling strength. The effective Hartmann-Hahn mixing condition is then satisfied in a multi-rotating frame of reference. This design method yields multi-band and broadband mixing pulses at low RF power. In particular, the ratio of RF power to mixing bandwidth for these pulses is lower than for existing mixing pulses, such as DIPSI and FLOPSY. Carbon-carbon TOCSY experiments at low RF power support our theoretical analysis.     

Neuro-genetic optimization of temperature control for a continuous flow polymerase chain reaction microdevice

In this study, a hybridized neuro-genetic optimization methodology realized by embedding finite element analysis (FEA) trained artificial neural networks (ANN) into genetic algorithms (GA), is used to optimize temperature control in a ceramic based continuous flow polymerase chain reaction (CPCR) device. The CPCR device requires three thermally isolated reaction zones of 94 degrees C, 65 degrees C, and 72 degrees C for the denaturing, annealing, and extension processes, respectively, to complete a cycle of polymerase chain reaction. The most important aspect of temperature control in the CPCR is to maintain temperature distribution at each reaction zone with a precision of +/-1 degree C or better, irrespective of changing ambient conditions. Results obtained from the FEA simulation shows good comparison with published experimental work for the temperature control in each reaction zone of the microfluidic channels. The simulation data are then used to train the ANN to predict the temperature distribution of the microfluidic channel for various heater input power and fluid flow rate. Once trained, the ANN analysis is able to predict the temperature distribution in the microchannel in less than 20 min, whereas the FEA simulation takes approximately 7 h to do so. The final optimization of temperature control in the CPCR device is achieved by embedding the trained ANN results as a fitness function into GA. Finally, the GA optimized results are used to build a new FEA model for numerical simulation analysis. The simulation results for the neuro-genetic optimized CPCR model and the initial CPCR model are then compared. The neuro-genetic optimized model shows a significant improvement from the initial model, establishing the optimization method's superiority.     

Pose estimation in automated visual inspection using ANN

In this paper, we present an accurate and robust pose estimator of rigid, polyhedral objects, based on Artificial Neural Networks (ANN), as suitable for Automated Visual Inspection (AVI) applications. The estimator is novel in the sense that it is trained with different poses of the objects having dimensional deviations within its tolerance range and is therefore robust with respect to within tolerance dimensional errors. The estimation accuracy is scalable and our computer simulation experiments in the existing configurations of ANNs have shown an accuracy better than 4% of the placement error. The ANN based pose estimator offers several advantages over the classical implementations.     

An improved method for two-dimensional fluorescence monitoring of complex bioreactors

An improved method for deconvoluting complex spectral maps from bidimensional fluorescence monitoring is presented, relying on a combination of principal component analysis (PCA) and feedforward artificial neural networks (ANN). With the aim of reducing ANN complexity, spectral maps are first subjected to PCA, and the scores of the retained principal components are subsequently used as ANN input vector. The method is presented using the case study of an extractive membrane biofilm reactor, where fluorescence maps of a membrane-attached biofilm were analysed, which were collected under different reactor operating conditions. During ANN training, the spectral information is associated with process performance indicators. Originally, 231 excitation/emission pairs per fluorescence map were used as ANN input vector. Using PCA, each fluorescence map could be represented by a maximum of six principal components, thereby catching 99.5% of its variance. As a result, the dimension of the ANN input vector and hence the complexity of the artificial neural network was significantly reduced, and ANN training speed was increased. Correlations between principal components and ANN predicted process performance parameters were good with correlation coefficients in the order of 0.7 or higher.     

Interleaved EPI Based fMRI Improved by Multiplexed Sensitivity Encoding (MUSE) and Simultaneous Multi-Band Imaging

Functional magnetic resonance imaging (fMRI) is a non-invasive and powerful imaging tool for detecting brain activities. The majority of fMRI studies are performed with single-shot echo-planar imaging (EPI) due to its high temporal resolution. Recent studies have demonstrated that, by increasing the spatial-resolution of fMRI, previously unidentified neuronal networks can be measured. However, it is challenging to improve the spatial resolution of conventional single-shot EPI based fMRI. Although multi-shot interleaved EPI is superior to single-shot EPI in terms of the improved spatial-resolution, reduced geometric distortions, and sharper point spread function (PSF), interleaved EPI based fMRI has two main limitations: 1) the imaging throughput is lower in interleaved EPI; 2) the magnitude and phase signal variations among EPI segments (due to physiological noise, subject motion, and B₀ drift) are translated to significant in-plane aliasing artifact across the field of view (FOV). Here we report a method that integrates multiple approaches to address the technical limitations of interleaved EPI-based fMRI. Firstly, the multiplexed sensitivity-encoding (MUSE) post-processing algorithm is used to suppress in-plane aliasing artifacts resulting from time-domain signal instabilities during dynamic scans. Secondly, a simultaneous multi-band interleaved EPI pulse sequence, with a controlled aliasing scheme incorporated, is implemented to increase the imaging throughput. Thirdly, the MUSE algorithm is then generalized to accommodate fMRI data obtained with our multi-band interleaved EPI pulse sequence, suppressing both in-plane and through-plane aliasing artifacts. The blood-oxygenation-level-dependent (BOLD) signal detectability and the scan throughput can be significantly improved for interleaved EPI-based fMRI. Our human fMRI data obtained from 3 Tesla systems demonstrate the effectiveness of the developed methods. It is expected that future fMRI studies requiring high spatial-resolvability and fidelity will largely benefit from the reported techniques.     

Modeling <Emphasis Type="Italic">Euglena</Emphasis> sp. growth under different conditions using an artificial neural network

Microalgae are considered as the future source of biofuels because of their high biomass productivity and neutral lipid content as triacylglycerides (TAG). Microalgae have high photosynthetic efficiency and the possibility of being cultivated in different wastewaters. The isolation of potential microalgae followed by the optimization of cultivation conditions is prerequisite for successful cultivation and accumulation of high lipid content. In the present work, a three-layer artificial neural network (ANN) model is developed to predict the essential parameters (such as pH, temperature, light intensity, photoperiod, and medium composition) based on 156 sets of laboratory experiments for achieving maximum biomass from Euglena sp. The independent parameters (viz., temperature, light intensity, photoperiod and number of days at fixed pH, and media composition) were fed as input to the ANN, and biomass yield was investigated. The comparison of the simulated environmental conditions using the ANN model and experimental results are found to have an excellent correlation coefficient of about 0.97 for the model variables used in this study. The model results established that artificial neural network design may be judiciously employed for optimization of different environmental conditions for this isolated microalga.     

An ensemble model for predicting Rhopalosiphum padi abundance

A novel modeling method is proposed to predict the abundance of the main vector of barley yellow dwarf virus in autumn sown cereal crops. An ensemble model based on artificial neural networks (ANN) was developed to predict the number of Rhopalosiphum padi (L.) (Homoptera: Aphididae) caught in traps during the autumn flight period at Lincoln, Canterbury, New Zealand, over the period 1982–2003. Artificial neural networks were trained using historical weather data and aphid data collected from a suction trap. Model results were compared with those obtained using multiple regression (MR) models using the same independent variables. Both ANN and MR models were validated by leave‐one‐out validation, in other words, by sequentially jackknifing each year out of the data set, fitting a model to the remaining data, then using that model to predict the number of aphids for each jackknifed year. A linear ensemble of ANN models further improved the predictions and represented the trends in the number of aphids over the 22‐year period very well. The r² between the predicted and observed numbers of aphids for the ANN models changed from 0.68 to 0.83 using the linear ensemble model, but the ensemble approach did not change the prediction for the MR models. The absolute mean error (ABSME) of prediction was much lower for the ANN ensemble predictions compared to that for the MR models. The ABMSE for the ANN models dropped from 109 to 86 aphids compared to an ABMSE reduction from 245 to 220 aphids for the MR models. We discuss the potential for ensemble models for predicting insect abundance when long‐term historical data are available.     

Space partitioning strategies for indoor WLAN positioning with cascade-connected ANN structures

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores two strategies for space partitioning when utilizing cascade-connected Artificial Neural Networks (ANNs) structures for indoor WLAN positioning. A set of cascade-connected ANN structures with different space partitioning strategies are compared mutually and to the single ANN structure. The benefits of using cascade-connected ANNs structures are shown and discussed in terms of the size of the environment, number of subspaces and partitioning strategy. The optimal cascade-connected ANN structures with space partitioning show up to 50% decrease in median error and up to 12% decrease in the average error with respect to the single ANN model. Finally, the single ANN and the optimal cascade-connected ANN model are compared against other well-known positioning techniques.