Functional identification of biological neural networks using reservoir adaptation for point processes

The complexity of biological neural networks does not allow to directly relate their biophysical properties to the dynamics of their electrical activity. We present a reservoir computing approach for functionally identifying a biological neural network, i.e. for building an artificial system that is functionally equivalent to the reference biological network. Employing feed-forward and recurrent networks with fading memory, i.e. reservoirs, we propose a point process based learning algorithm to train the internal parameters of the reservoir and the connectivity between the reservoir and the memoryless readout neurons. Specifically, the model is an Echo State Network (ESN) with leaky integrator neurons, whose individual leakage time constants are also adapted. The proposed ESN algorithm learns a predictive model of stimulus-response relations in in vitro and simulated networks, i.e. it models their response dynamics. Receiver Operating Characteristic (ROC) curve analysis indicates that these ESNs can imitate the response signal of a reference biological network. Reservoir adaptation improved the performance of an ESN over readout-only training methods in many cases. This also held for adaptive feed-forward reservoirs, which had no recurrent dynamics. We demonstrate the predictive power of these ESNs on various tasks with cultured and simulated biological neural networks.     

β-sheet topology prediction with high precision and recall for β and mixed α/β proteins

The prediction of the correct β-sheet topology for pure β and mixed α/β proteins is a critical intermediate step toward the three dimensional protein structure prediction. The predicted beta sheet topology provides distance constraints between sequentially separated residues, which reduces the three dimensional search space for a protein structure prediction algorithm. Here, we present a novel mixed integer linear optimization based framework for the prediction of β-sheet topology in β and mixed α/β proteins. The objective is to maximize the total strand-to-strand contact potential of the protein. A large number of physical constraints are applied to provide biologically meaningful topology results. The formulation permits the creation of a rank-ordered list of preferred β-sheet arrangements. Finally, the generated topologies are re-ranked using a fully atomistic approach involving torsion angle dynamics and clustering. For a large, non-redundant data set of 2102 β and mixed α/β proteins with at least 3 strands taken from the PDB, the proposed approach provides the top 5 solutions with average precision and recall greater than 78%. Consistent results are obtained in the β-sheet topology prediction for blind targets provided during the CASP8 and CASP9 experiments, as well as for actual and predicted secondary structures. The β-sheet topology prediction algorithm, BeST, is available to the scientific community at http://selene.princeton.edu/BeST/.     

A modified statistically optimal null filter method for recognizing protein-coding regions

Computer-aided protein-coding gene prediction in uncharacterized genomic DNA sequences is one of the most important issues of biological signal processing.A modified filter method based on a statistically optimal null filter(SONF) theory is proposed for recognizing protein-coding regions.The square deviation gain(SDG) between the input and output of the model is used to identify the coding regions.The effective SDG amplification model with Class I and Class II enhancement is designed to suppress the non-coding regions.Also,an evaluation algorithm has been used to compare the modified model with most gene prediction methods currently available in terms of sensitivity,specificity and precision.The performance for identification of protein-coding regions has been evaluated at the nucleotide level using benchmark datasets and 91.4%,96%,93.7% were obtained for sensitivity,specificity and precision,respectively.These results suggest that the proposed model is potentially useful in gene finding field,which can help recognize protein-coding regions with higher precision and speed than present algorithms.     

Genetic structure of a native cyprinid in a reservoir‐altered stream network

1. Reservoirs modify riverine ecosystems worldwide, and often with deleterious impacts on native biota. The immediate effects of reservoirs on native fish species below dams and in impounded reaches have received considerable attention, but it is unclear how reservoirs may affect fish species at larger spatial and temporal scales. Documented declines of stream fish populations in direct tributaries of reservoirs suggest reservoir pools may reduce gene flow among historically connected populations. 2. Because of increased predator densities in reservoirs and the extent of habitat alteration in impounded reaches, I predicted reservoir habitats would reduce gene flow among small‐bodied fish populations separated by reservoir habitat. I used microsatellite markers to assess the spatial genetic structure of populations of the red shiner (Cyprinella lutrensis), in a reservoir‐fragmented stream network (Lake Texoma, U.S.A.). I also tested the prediction that populations in two direct tributaries that have experienced population declines would have low genetic diversity. Individuals were collected from six sites upstream of the reservoir, three sites in the reservoir and three sites in direct tributaries of the reservoir during 2008 and 2009. 3. Results indicate that most populations were isolated by distance with little divergence among populations. In one direct tributary population, however, there was substantial genetic divergence, and genetic diversity was significantly lower than in other populations. Gene flow also seemed to be lower in reservoir habitats than in intact stream habitats, suggesting reservoir habitats may be reducing gene flow among the reservoir‐separated populations. These results indicate that reservoirs may reduce gene flow among reservoir‐fragmented stream fish populations, altering the evolutionary trajectories of fragmented populations.     

Evaluation of methods for the prediction of membrane spanning regions.

MOTIVATION: A variety of tools are available to predict the topology of transmembrane proteins. To date no independent evaluation of the performance of these tools has been published. A better understanding of the strengths and weaknesses of the different tools would guide both the biologist and the bioinformatician to make better predictions of membrane protein topology. RESULTS: Here we present an evaluation of the performance of the currently best known and most widely used methods for the prediction of transmembrane regions in proteins. Our results show that TMHMM is currently the best performing transmembrane prediction program.     

BMP and Delta/Notch signaling control the development of amphioxus epidermal sensory neurons: insights into the evolution of the peripheral sensory system

The evolution of the nervous system has been a topic of great interest. To gain more insight into the evolution of the peripheral sensory system, we used the cephalochordate amphioxus. Amphioxus is a basal chordate that has a dorsal central nervous system (CNS) and a peripheral nervous system (PNS) comprising several types of epidermal sensory neurons (ESNs). Here, we show that a proneural basic helix-loop-helix gene (Ash) is co-expressed with the Delta ligand in ESN progenitor cells. Using pharmacological treatments, we demonstrate that Delta/Notch signaling is likely to be involved in the specification of amphioxus ESNs from their neighboring epidermal cells. We also show that BMP signaling functions upstream of Delta/Notch signaling to induce a ventral neurogenic domain. This patterning mechanism is highly similar to that of the peripheral sensory neurons in the protostome and vertebrate model animals, suggesting that they might share the same ancestry. Interestingly, when BMP signaling is globally elevated in amphioxus embryos, the distribution of ESNs expands to the entire epidermal ectoderm. These results suggest that by manipulating BMP signaling levels, a conserved neurogenesis circuit can be initiated at various locations in the epidermal ectoderm to generate peripheral sensory neurons in amphioxus embryos. We hypothesize that during chordate evolution, PNS progenitors might have been polarized to different positions in various chordate lineages owing to differential regulation of BMP signaling in the ectoderm.     

The importance of larger data sets for protein secondary structure prediction with neural networks.

A neural network algorithm is applied to secondary structure and structural class prediction for a database of 318 nonhomologous protein chains. Significant improvement in accuracy is obtained as compared with performance on smaller databases. A systematic study of the effects of network topology shows that, for the larger database, better results are obtained with more units in the hidden layer. In a 32-fold cross validated test, secondary structure prediction accuracy is 67.0%, relative to 62.6% obtained previously, without any evolutionary information on the sequence. Introduction of sequence profiles increases this value to 72.9%, suggesting that the two types of information are essentially independent. Tertiary structural class is predicted with 80.2% accuracy, relative to 73.9% obtained previously. The use of a larger database is facilitated by the introduction of a scaled conjugate gradient algorithm for optimizing the neural network. This algorithm is about 10-20 times as fast as the standard steepest descent algorithm.     

The prediction of EEG signals using a feedback-structured adaptive rational function filter

 In this article, we present a feedback-structured adaptive rational function filter based on a recursive modified Gram-Schmidt algorithm and apply it to the prediction of an EEG signal that has nonlinear and nonstationary characteristics. For the evaluation of the prediction performance, the proposed filter is compared with other methods, where a single-step prediction and a multi-step prediction are considered for a short-term prediction, and the prediction performance is assessed in normalized mean square error. The experimental results show that the proposed filter shows better performance than other methods considered for the short-term prediction of EEG signals. Received: 22 September 1998 / Accepted in revised form: 29 February 2000     

AlignNemo: a local network alignment method to integrate homology and topology

Local network alignment is an important component of the analysis of protein-protein interaction networks that may lead to the identification of evolutionary related complexes. We present AlignNemo, a new algorithm that, given the networks of two organisms, uncovers subnetworks of proteins that relate in biological function and topology of interactions. The discovered conserved subnetworks have a general topology and need not to correspond to specific interaction patterns, so that they more closely fit the models of functional complexes proposed in the literature. The algorithm is able to handle sparse interaction data with an expansion process that at each step explores the local topology of the networks beyond the proteins directly interacting with the current solution. To assess the performance of AlignNemo, we ran a series of benchmarks using statistical measures as well as biological knowledge. Based on reference datasets of protein complexes, AlignNemo shows better performance than other methods in terms of both precision and recall. We show our solutions to be biologically sound using the concept of semantic similarity applied to Gene Ontology vocabularies. The binaries of AlignNemo and supplementary details about the algorithms and the experiments are available at: sourceforge.net/p/alignnemo.     

A novel algorithm with differential evolution and coral reef optimization for extreme learning machine training

Extreme learning machine (ELM) is a novel and fast learning method to train single layer feed-forward networks. However due to the demand for larger number of hidden neurons, the prediction speed of ELM is not fast enough. An evolutionary based ELM with differential evolution (DE) has been proposed to reduce the prediction time of original ELM. But it may still get stuck at local optima. In this paper, a novel algorithm hybridizing DE and metaheuristic coral reef optimization (CRO), which is called differential evolution coral reef optimization (DECRO), is proposed to balance the explorative power and exploitive power to reach better performance. The thought and the implement of DECRO algorithm are discussed in this article with detail. DE, CRO and DECRO are applied to ELM training respectively. Experimental results show that DECRO-ELM can reduce the prediction time of original ELM, and obtain better performance for training ELM than both DE and CRO.     

Adaptive Neural Network Structure Optimization Algorithm Based on Dynamic Nodes

Large-scale artificial neural networks have many redundant structures, making the network fall into the issue of local optimization and extended training time. Moreover, existing neural network topology optimization algorithms have the disadvantage of many calculations and complex network structure modeling. We propose a Dynamic Node-based neural network Structure optimization algorithm (DNS) to handle these issues. DNS consists of two steps: the generation step and the pruning step. In the generation step, the network generates hidden layers layer by layer until accuracy reaches the threshold. Then, the network uses a pruning algorithm based on Hebb’s rule or Pearson’s correlation for adaptation in the pruning step. In addition, we combine genetic algorithm to optimize DNS (GA-DNS). Experimental results show that compared with traditional neural network topology optimization algorithms, GA-DNS can generate neural networks with higher construction efficiency, lower structure complexity, and higher classification accuracy.     

Model identification of signal transduction networks from data using a state regulator problem

Advances in molecular biology provide an opportunity to develop detailed models of biological processes that can be used to obtain an integrated understanding of the system. However, development of useful models from the available knowledge of the system and experimental observations still remains a daunting task. In this work, a model identification strategy for complex biological networks is proposed. The approach includes a state regulator problem (SRP) that provides estimates of all the component concentrations and the reaction rates of the network using the available measurements. The full set of the estimates is utilised for model parameter identification for the network of known topology. An a priori model complexity test that indicates the feasibility of performance of the proposed algorithm is developed. Fisher information matrix (FIM) theory is used to address model identifiability issues. Two signalling pathway case studies, the caspase function in apoptosis and the MAP kinase cascade system, are considered. The MAP kinase cascade, with measurements restricted to protein complex concentrations, fails the a priori test and the SRP estimates are poor as expected. The apoptosis network structure used in this work has moderate complexity and is suitable for application of the proposed tools. Using a measurement set of seven protein concentrations, accurate estimates for all unknowns are obtained. Furthermore, the effects of measurement sampling frequency and quality of information in the measurement set on the performance of the identified model are described.     

A novel efficient learning algorithm for self-generating fuzzy neural network with applications

In this paper, a novel efficient learning algorithm towards self-generating fuzzy neural network (SGFNN) is proposed based on ellipsoidal basis function (EBF) and is functionally equivalent to a Takagi-Sugeno-Kang (TSK) fuzzy system. The proposed algorithm is simple and efficient and is able to generate a fuzzy neural network with high accuracy and compact structure. The structure learning algorithm of the proposed SGFNN combines criteria of fuzzy-rule generation with a pruning technology. The Kalman filter (KF) algorithm is used to adjust the consequent parameters of the SGFNN. The SGFNN is employed in a wide range of applications ranging from function approximation and nonlinear system identification to chaotic time-series prediction problem and real-world fuel consumption prediction problem. Simulation results and comparative studies with other algorithms demonstrate that a more compact architecture with high performance can be obtained by the proposed algorithm. In particular, this paper presents an adaptive modeling and control scheme for drug delivery system based on the proposed SGFNN. Simulation study demonstrates the ability of the proposed approach for estimating the drug's effect and regulating blood pressure at a prescribed level.     

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.     

一种自优化RBF神经网络的叶绿素a浓度时序预测模型

藻类水华发生过程具有复杂性、非线性、时变性等特点,其准确预测一直是一个国际性难题.以天津市于桥水库为研究对象,根据2000年1月至2003年12月常规监测的水生生态数据(采样周期为10 d),提出了一种结合时序方法的可自优化RBF神经网络智能预测模型,对判断藻类水华的重要指标叶绿素a浓度进行预测.研究了训练样本量及RBF神经网络扩展速度SPREAD值的可自优化性能,以及该模型用于于桥水库叶绿素a浓度的短期变化趋势预测的可行性.结果表明,预测性能指标随SPREAD值及样本量不同发生变化,该预测模型能自动寻到最优SPREAD值,并发现至少需要约两年的训练样本量才能达到较好预测效果.当样本量为105,SPREAD值为10时,预测效果最好,精度较高,预测值与实测值的相关系数R达到0.982.该方法对水库的藻类水华预警有一定的参考价值.     

Evaluating transmembrane topology prediction methods for the effect of signal peptide in topology prediction

Reported performance of existing transmembrane (TM) topology prediction methods were often based on evaluations which neglected the risk of signal peptides (SP) being predicted as putative TM as well. Here, we evaluated 12 selected TM topology prediction methods (TMpred, TopPred II, DAS, TMAP, MEMSAT 2, SOSUI, PRED-TMR2, TMHMM 2.0, HMMTOP 2.0, SPLIT 3.5, TM Finder, and MPEx) for the effect of SP in prediction performance considering three SP treatments, namely: "remain" (untreated), "removed first", and "removed later". The results showed that the presence of SP significantly affected the prediction performance of the 12 selected TM topology prediction methods for all three predicted attributes (the number of transmembrane segments (TMSs), the number of TMSs plus position, and the N-tail location) and for the predicted topology (combined predictions of three attributes) by causing a reduction in prediction accuracy. In particular, lower prediction accuracies were obtained if SP is left untreated (remain) while significant increases were observed if SP is removed either first or later. However, between "removed first" and "removed later" SP treatments, the difference was statistically insignificant. In addition, we found that machine learning-based prediction methods were less affected by the presence of SP than hydropathy-based methods, but still the potential risk of degrading the prediction performance is there however to a lesser degree. Thus, when performing genome-wide analysis, the SP issue should be addressed during TM topology prediction.     

Multi-objective optimization of cascade reservoirs using NSGA-II: A case study of the Three Gorges-Gezhouba cascade reservoirs in the middle Yangtze River,China

A multi-objective optimization model of cascade reservoirs was developed to maximize the power generation and minimizie the appropriate ecological flow shortage index (AEFSI) downstream from the reservoir. Additionally, the non-dominated sorting genetic algorithm (NSGA-II) was used to search for multi-objective Pareto optimal solutions. The paper took the Three Gorges-Gezhouba cascade reservoirs as a case study. After validating the model, data from three typical years were used in the optimization. The results indicated that maximizing power generation by adjusting the optimal rules increased power generation by 1.07%, 0.91%, and 1.03% in normal, wet, and dry hydrological years, respectively, while increasing the AEFSI by 22.12%, 11.78%, and 14.67% (compared to real operations). The AEFSI was improved (decreased) by 21.90%, 10.27%, and 18.52% when the optimal rules favored the downstream ecology, but power generation decreased by 1.61%, 1.06%, and 2.29%, respectively, in the different hydrological years. Moreover, the results provide a set of well-distributed optimal solutions along the Pareto front that allow decision-makers to easily determine the best compromised solutions based on the trade-offs between the economic and ecological benefits. The results of this study provide guidance for decision-makers to improve the comprehensive benefits of the Three Gorges-Gezhouba cascade reservoirs.     

Predicting acidic and alkaline enzymes by incorporating the average chemical shift and gene ontology informations into the general form of Chou's PseAAC

Knowledge of the adaptation mechanism of enzymes to extreme pH values and distinguishing them from one another are necessary in the proteomics field, and would help in the drug design of stable enzymes. In this work, we have systematically analyzed the information of 105 acidic and 112 alkaline enzymes, and propose an approach for distinguishing acidic enzymes from alkaline enzymes by combining the amino acid composition, reduced amino acid composition, gene ontology, evolutionary information, and auto covariance of averaged chemical shift (acACS). The overall prediction accuracy is 94.01% by 10-fold cross-validation using the algorithm of support vector machine. This result is better than that obtained by other existing methods. The improvement of the overall prediction accuracy reaches up to 3.3% higher than those of the random forest algorithm and secondary structure amino acid composition. The acACS performance is excellent, indicating that our approach is better than other existing methods in the literature. A user-friendly web-server pred-enzymes for predicting acidic and alkaline enzymes has been established, which is accessible to the public.