人工神经原网络处理PCR数据在细菌鉴定中的应用

目的16SrRNA和16S-23SrRNA间区片段是常用细菌分类鉴定靶点,本研究探讨人工神经原网络（ANN）对上述位点PCR扩增产物数据分析在细菌快速鉴定方面的价值。方法2对15SrRNA基因荧光引物和1对16S-23SrRNA区间基因引物用于扩增血液标本中分离出的317株细菌。相关毛细管电泳（CE）限制性片段长度多态性（RFLP）和单链构象多态性（SSCP）数据进行人工神经原网络分析。结果16S-23SrRNA基因的RFLP数据对未知菌鉴定的准确率高于16SrRNA基因的SSCP数据,分别为98．0％和79．6％。结论实验证明了人工神经原网络作为一种模式识别方法对于简化细菌鉴定十分有价值。     

Enteric viruses in molluscan shellfish

One hundred and thirty-seven bivalves were collected for environmental monitoring and the market; all the samples were analysed by RT-PCR test. Bacteriological counts meeting the European Union shellfish criteria were reached by 69.5% of all the samples, whereas the overall positive values for enteric virus presence were: 25.5%, 18.2%, 8.0% and 2.1% for Rotavirus, Astrovirus, Enteroviruses, Norovirus, respectively. Mussels appear to be the most contaminated bivalves, with 64.8% of positive samples, 55.7% and 22.7% respectively for clams and oysters, whereas in the bivalves collected for human consumption 50.7% were enteric virus positive, as compared to 56.4% of the samples collected for growing-area classification. The overall positive sample was 54.0%.     

Accumulation of sediment-associated viruses in shellfish

The present study focused on the importance of contaminated sediments in shellfish accumulation of human viruses. Epifaunal (Crassostrea virginica) and infaunal (Mercenaria mercenaria) shellfish, placed on or in cores, were exposed to either resuspended or undisturbed sediments containing bound poliovirus type 1 (LSc 2ab). Consistent bioaccumulation by oysters (four of five trials) was only noted when sediment-bound viruses occurred in the water column. Virus accumulation was observed in a single instance where sediments remained in an undisturbed state. While the incidence of bioaccumulation was higher with resuspended rather than undisturbed contaminated sediment, the actual concentration of accumulated viruses was not significantly different. The accumulation of viruses from oysters residing on uninoculated sediments. When clams were exposed to undisturbed, virus-contaminated sediments, two of five shellfish pools yielded viral isolates. Bioaccumulation of undisturbed sediments by these bivalves was considered marginal when related to the concentration of virus in contaminated sediments; they would only represent a significant threat when suspended in the water column. Arguments were advanced for water-column sampling in the region of the water-sediment interface to provide an accurate determination of the virological quality of shellfish harvesting waters.     

应用人工神经网络评价湖泊的富营养化

应用人工神经网络方法,以化学需氧量、总氮、总磷和透明度作为评价参数,经反复尝试,构建了具有４层结构用于评价湖泊富营养化的误差逆传播网络．其输入层有４个神经元,２个隐含层也各有４个神经元,输出层有１个神经元．以太湖富营养化评价标准作为样本模式提供给网络,按照误差逆传播网络的学习规则对网络进行训练,经过３７６８４次学习后,网络达到预先给定的收敛标准．使网络具备了识别湖泊富营养化程度的功能．应用该网络对我国１７个湖泊的富营养化程度进行评价,操作过程简便易行,评价结果切合实际,展示了这种方法的一系列优点．     

Artificial metaplasticity neural network applied to credit scoring

The assessment of the risk of default on credit is important for financial institutions. Different Artificial Neural Networks (ANN) have been suggested to tackle the credit scoring problem, however, the obtained error rates are often high. In the search for the best ANN algorithm for credit scoring, this paper contributes with the application of an ANN Training Algorithm inspired by the neurons' biological property of metaplasticity. This algorithm is especially efficient when few patterns of a class are available, or when information inherent to low probability events is crucial for a successful application, as weight updating is overemphasized in the less frequent activations than in the more frequent ones. Two well-known and readily available such as: Australia and German data sets has been used to test the algorithm. The results obtained by AMMLP shown have been superior to state-of-the-art classification algorithms in credit scoring.     

Artificial neural network learning of nonstationary behavior in time series

We refine and complement a previously-proposed artificial neural network method for learning hidden signals forcing nonstationary behavior in time series. The method adds an extra input unit to the network and feeds it with the proposed profile for the unknown perturbing signal. The correct time evolution of this new input parameter is learned simultaneously with the intrinsic stationary dynamics underlying the series, which is accomplished by minimizing a suitably-defined error function for the training process. We incorporate here the use of validation data, held out from the training set, to accurately determine the optimal value of a hyperparameter required by the method. Furthermore, we evaluate this algorithm in a controlled situation and show that it outperforms other existing methods in the literature. Finally, we discuss a preliminary application to the real-world sunspot time series and link the obtained hidden perturbing signal to the secular evolution of the solar magnetic field.     

Artificial neural network classification of Drosophila courtship song mutants

Courtship songs produced by Drosophila males — wild-type, plus the cacophony and dissonance behavioral mutants — were examined with the aid of newly developed strategies for adaptive acoustic analysis and classification. This system used several techniques involving artificial neural networks (a.k.a. parallel distributed processing), including learned vector quantization of signals and non-linear adaption (back-propagation) of data analysis. Pulse song from several individual wild-type and mutant males were first vector-quantized according to their frequency spectra. The accumulated quantized data of this kind, for a given song, were then used to teach or adapt a multiple-layered feedforward artificial neural network, which classified that song according to its original genotype. Results are presented on the performance of the final adapted system when faced with novel test data and on acoustic features the system decides upon for predicting the song-mutant genotype in question. The potential applications and extensions of this new system are discussed, including how it could be used to screen for courtship mutants, search novel behavior patterns or cause-and-effect relationships associated with reproduction, compress these kinds of data for digital storage, and analyze Drosophila behavior beyond the case of courtship song.     

Curved trajectory prediction using a self-organizing neural network

Existing neural network models are capable of tracking linear trajectories of moving visual objects. This paper describes an additional neural mechanism, disfacilitation, that enhances the ability of a visual system to track curved trajectories. The added mechanism combines information about an object's trajectory with information about changes in the object's trajectory, to improve the estimates for the object's next probable location. Computational simulations are presented that show how the neural mechanism can learn to track the speed of objects and how the network operates to predict the trajectories of accelerating and decelerating objects.     

Artificial neural network model for predicting membrane protein types

Membrane proteins can be classified among the following five types: (1) type I membrane protein. (2) type II membrane protein. (3) multipass transmembrane proteins. (4) lipid chain-anchored membrane proteins, and (5) GPI-anchored membrane proteins. T. Kohonen's self-organization model which is a typical neural network is applied for predicting the type of a given membrane protein based on its amino acid composition. As a result, the high rates of self-consistency (94.80%) and cross-validation (77.76%), and stronger fault-tolerant ability were obtained.     

Artificial neural nets and abundance prediction of aquatic insects in small streams

Abundance prediction of aquatic insects (Ephemeroptera, Plecoptera, Trichoptera = EPT) based on environmental variables (precipitation, discharge, temperature) and abundance of the parent generation with Artificial Neural Nets (ANN) was carried out successfully. A general model for all species does not exist. Easy to understand models for individual species were restricted to stream sections with a characteristic set of variables. The amount of zero-values in the data did not affect the models. Transfer of one model to other stream sections resulted in a decrease of the determination coefficient B. Sufficient models for populations that have larvae in the stream all the year round required more information than for species with a diapause. All scaling options used decreased prediction quality. Long term mean values of variables and the deviation of actual from long term data were the best predictors, indicating a successful temporal link between seasonal variables and univoltine life cycles of most species tested. Prediction of monthly emergence in individual years was adequate with determination coefficients > 0.8 for five, and < 0.5 for only two out of ten years.     

NETASA: neural network based prediction of solvent accessibility

MOTIVATION: Prediction of the tertiary structure of a protein from its amino acid sequence is one of the most important problems in molecular biology. The successful prediction of solvent accessibility will be very helpful to achieve this goal. In the present work, we have implemented a server, NETASA for predicting solvent accessibility of amino acids using our newly optimized neural network algorithm. Several new features in the neural network architecture and training method have been introduced, and the network learns faster to provide accuracy values, which are comparable or better than other methods of ASA prediction. RESULTS: Prediction in two and three state classification systems with several thresholds are provided. Our prediction method achieved the accuracy level upto 90% for training and 88% for test data sets. Three state prediction results provide a maximum 65% accuracy for training and 63% for the test data. Applicability of neural networks for ASA prediction has been confirmed with a larger data set and wider range of state thresholds. Salient differences between a linear and exponential network for ASA prediction have been analysed. AVAILABILITY: Online predictions are freely available at: http://www.netasa.org. Linux ix86 binaries of the program written for this work may be obtained by email from the corresponding author.     

A neural network for breakthrough prediction in packed bed adsorption

A single hidden layer back propagation neural network has been used to predict the occurrence of breakthrough in an ion-exchange adsorption column using signals derived from a thermal monitoring system. After training the neural network was capable of a complete prediction of breakthrough. This is in contrast with the mechanistic models used to date, which all show significant deviations in one or more regions of the breakthrough response.     

Computational antisense oligo prediction with a neural network model

MOTIVATION: The expression of a gene can be selectively inhibited by antisense oligonucleotides (AOs) targeting the mRNA. However, if the target site in the mRNA is picked randomly, typically 20% or less of the AOs are effective inhibitors in vivo. The sequence properties that make an AO effective are not well understood, thus many AOs need to be tested to find good inhibitors, which is time consuming and costly. So far computational models have been based exclusively on RNA structure prediction or motif searches while ignoring information from other aspects of AO design into the model. RESULTS: We present a computational model for AO prediction based on a neural network approach using a broad range of input parameters. Collecting sequence and efficacy data from AO scanning experiments in the literature generated a database of 490 AO molecules. Using a set of derived parameters based on AO sequence properties we trained a neural network model. The best model, an ensemble of 10 networks, gave an overall correlation coefficient of 0.30 (p=10(-8)). This model can predict effective AOs (>50% inhibition of gene expression) with a success rate of 92%. Using these thresholds the model predicts on average 12 effective AOs per 1000 base pairs, making it a stringent yet practical method for AO prediction.     

Limits on alpha-helix prediction with neural network models.

Using a backpropagation neural network model we have found a limit for secondary structure prediction from local sequence. By including only sequences from whole alpha-helix and non-alpha-helix structures in our training and test sets--sequences spanning boundaries between these two structures were excluded--it was possible to investigate directly the relationship between sequence and structure for alpha-helix. A group of non-alpha-helix sequences, that was disrupting overall prediction success, was indistinguishable to the network from alpha-helix sequences. These sequences were found to occur at regions adjacent to the termini of alpha-helices with statistical significance, suggesting that potentially longer alpha-helices are disrupted by global constraints. Some of these regions spanned more than 20 residues. On these whole structure sequences, 10 residues in length, a comparatively high prediction success of 78% with a correlation coefficient of 0.52 was achieved. In addition, the structure of the input space, the distribution of beta-sheet in this space, and the effect of segment length were also investigated.     

Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma

Background  

Screening of various gene markers such as single nucleotide polymorphism (SNP) and correlation between these markers and development of multifactorial disease have previously been studied. Here, we propose a susceptible marker-selectable artificial neural network (ANN) for predicting development of allergic disease.     

Fuzzy neural network based prediction model applied in primary component analysis

To solve the low accuracy and bad robustness problems in traditional water quality prediction method, this paper put forward a primary component analysis (PCA)–fuzzy neural network (FNN)–DEBP based prediction model of dissolved oxygen (DO) in aquaculture water quality. This model used PCA to extract the PC of aquaculture ecological indexes, then reduced the input vector dimension of the model, and utilized differential evolutionary algorithm to optimize the weight parameter of FNN, in order to automatically obtain the optimum parameters and build nonlinear prediction model of DO in aquaculture water quality. The model was applied in a predictive analysis on the water quality data online monitored from December 1st 2015 to December 8th 2015 in a Penaeus orientalis culture pond. The testing results show that this model has obtained a good predictive effect. Compared to BP-FNN model, in PCA–FNN–DEBP model, the absolute error of 95.8% test samples is less than 20%, and the maximum error is 0.22 mg/L, both of which are superior than BP-FNN prediction method. Due to rapid computation speed and high prediction accuracy, PCA–FNN–DEBP algorithm can provide strategic basis for the regulation and management of water quality in P. orientalis culture.