A multiple minima genetic algorithm for protein structure prediction

Protein structure prediction (PSP) has a large potential for valuable biotechnological applications. However the prediction itself encompasses a difficult optimization problem with thousands of degrees of freedom and is associated with extremely complex energy landscapes. In this work a simplified three-dimensional protein model (hydrophobic-polar model, HP in a cubic lattice) was used in order to allow for the fast development of a robust and efficient genetic algorithm based methodology. The new methodology employs a phenotype based crowding mechanism for the maintenance of useful diversity within the populations, which resulted in increased performance and granted the algorithm multiple solutions capabilities. Tests against several benchmark HP sequences and comparative results showed that the proposed genetic algorithm is superior to other evolutionary algorithms. The proposed algorithm was then successfully adapted to an all-atom protein model and tested on poly-alanines. The native structure, an alpha helix, was found in all test cases as a local or a global minimum, in addition to other conformations with similar energies. The results showed that optimization strategies with multiple solutions capability present two advantages for PSP applications. The first one is a more efficient investigation of complex energy landscapes; the second one is an increase in the probability of finding native structures, even when they are not at the global optimum.     

A multimodal neural network with single-state predictions for protein secondary structure

Prediction of protein secondary structure is considered to be an important step toward elucidating the three-dimensional structure and function of proteins. We have developed a multimodal neural network (MNN) to predict protein secondary structure. The MNN is composed of several subclassifiers for single-state predictions using neural networks and a decision neural network (DNN). Each subclassifier employs a number of subnetworks to predict the single-state of the secondary structure individually and produces the final results by majority decision. The DNN uses a three-layer neural network to produce the final overall prediction from the outputs of the single-state predictions. The MNN gives an overall accuracy of 71.1% with corresponding Matthews correlation coefficients of C_H = 0.62 and C_E = 0.53. The prediction test is based on a database of 126 nonhomologous protein sequences. This work was presented, in part, at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24#x2013;26, 2003.     

A neuromorphic architecture for cortical multilayer integration of early visual tasks

The characteristics and performance of a hierarchical neural architecture, inspired by models of mammalian visual cortex, are considered. The visual pathway from sensory space to the intermediate (cortical) representation is structured in three layers, with intra and interlayer connections through feedforward and recurrent pathways. These interconnections provide a complex perceptual organization that integrates the specific functional tasks performed by each layer. This improves the capabilities of the architecture in feature extraction and segregation, further providing clues on the information content of the intermediate representation (primal sketch). Applications to preattentive vision tasks (edge and contour extractions, texture analysis and boundary completion, and defect detection) are presented with satisfactory results.     

PITAGORAS-PSP: Including domain knowledge in a multi-objective approach for protein structure prediction

Whenever evolutionary algorithms are used to solve certain classes of problems such as those that present a huge search space, the incorporation of problem-specific knowledge is required to achieve adequate levels of performance. In this paper, we propose a multi-objective optimization-based procedure that includes such a domain-specific knowledge to cope with a difficult problem, the protein structure prediction (PSP). This problem is considered to be an open problem as there is no recognized “best” procedure to find solutions. It presents a vast search space and the analysis of each protein conformation requires significant amount of computing time. In our procedure, we provide a reduction of the search space by using the dependent rotamer library and include new heuristics to improve a multi-objective approach to PSP based on the PAES algorithm. As it is shown in the paper, by using benchmark proteins from the CASP8 set, this hybrid PSP procedure provides competitive results when it is compared with some of the better proposals appeared up to now.     

The prediction of protein secondary structure with a Cascade Correlation Learning Architecture of neural networks

A Cascade Correlation Learning Architecture (CCLA) of neural networks is tested on the task of predicting the secondary structure of proteins. The results are compared with those obtained with Neural Networks (NN) trained with the back-propagation algorithm (BPNN) and generated with genetic algorithms. CCLA proceeds towards the global minimum of the error function more efficiently than BPNN. However, only a slight improvement in the average efficiency value is noticeable (61.82% as compared with 61.61% obtained with BPNN). The values of the three correlation coefficients for the discriminated secondary structures are also rather similar (C_t8,C ,C and C_coil are 0.36, 0.29 and 0.36 with CCLA, and 0.36, 0.31 and 0.35 with BPNN). This indicates that the efficiency of the prediction does not depend upon the training algorithm, and confirms our previous observation that when single sequences are used as input code to the network system, different NN architectures can perform similarly.     

蛋白质二级结构预测方法研究

为提高蛋白质二级结构预测精度,提出一种新的网络模型和编码方法。首先利用基因表达式编程（GEP）的全局搜索能力同时进化设计神经网络的结构和连接权;其次,对神经网络输入层编码进行了改进,添加了氨基酸残基所处的疏水环境。用PDBSelect25中的36条蛋白质共6 122个残基进行测试,结果表明提出的网络模型和编码方法能有效提高蛋白质二级结构预测的精度。     

蛋白质二级结构预测方法的评价

蛋白质结构预测是后基因组时代的一项重要任务，蛋白质二级结构预测是蛋白质结构预测的关键步骤。现在一般认为，如果蛋白质二级结构的预测准确率达到80％的话，就可以基本准确地预测一个蛋白质分子的三维空间结构。目前蛋白质二级结构预测的方法不断涌现，提供二级结构预测的网站也逐渐增多。为给广大研究工作者在选择使用这些预测方法时提供一种参考，文章采用统一的标准对10种比较重要而且有效的方法进行测试，并在此基础上做出评价和分析，这10种方法是：GORI、PROF、GORⅣ、NNPREDICT、PHDsec、SSpro v 2．0、PSIPRED、PREDATOR、SOPMA和APSSP2。比较结果显示：APSSP2、SSpro v 2．0和PSIPRED方法的预测效果较好，可以作为使用时的首选方案，其中尤其以APSSP2方法的预测效果最佳。     

Multistage A2LVQ architecture and implementation for image compression

This paper presents the implementation of two hardware architectures, i.e., A₂ Lattice Vector Quantization (LVQ) and Multistage A₂LVQ (MA₂LVQ), using a Field-Programmable Gate Array (FPGA). First, the renowned LVQ quantizer by Conway and Sloane is implemented followed by a low-complexity A₂LVQ based on a new A₂LVQ algorithm. It is revealed that the implementation requires high number of multiplier circuits. Then the implementation of a low-complexity A₂LVQ is presented. This implementation uses only the first quadrant of the A₂ lattice Voronoi region formed by W and T regions. This paper also presents the implementation of a multistage A₂LVQ (MA₂LVQ) with an architecture built from successive A₂ quantizer blocks. Synthesis results show that the execution time of the low-complexity A₂LVQ reaches up to 35.97 ns. The MA₂LVQ is implemented using both low-complexity A₂LVQ and ordinary A₂ architectures. The system with the former architecture utilizes less logic and register elements by 47%.     

Parallel protein secondary structure prediction schemes using Pthread and OpenMP over hyper-threading technology

Protein secondary structure prediction has a fundamental influence on today’s bioinformatics research. In this work, tertiary classifiers for the protein secondary structure prediction are implemented on Denoeux Belief Neural Network (DBNN) architecture. Hydrophobicity matrix, orthogonal matrix, BLOSUM62 matrix and PSSM matrix are experimented separately as the encoding schemes for DBNN. Hydrophobicity matrix, BLOSUM62 matrix and PSSM matrix are applied to DBNN architecture for the first time. The experimental results contribute to the design of new encoding schemes. Our accuracy of the tertiary classifier with PSSM encoding scheme reaches 72.01%, which is almost 10% better than the previous results obtained in 2003. Due to the time consuming task of training the neural networks, Pthread and OpenMP are employed to parallelize DBNN in the Hyper-Threading enabled Intel architecture. Speedup for 16 Pthreads is 4.9 and speedup for 16 OpenMP threads is 4 in the 4 processors shared memory architecture. Both speedup performance of OpenMP and Pthread is superior to that of other research. With the new parallel training algorithm, thousands of amino acids can be processed in reasonable amount of time. Our research also shows that Hyper-Threading technology for Intel architecture is efficient for parallel biological algorithms.

Constraint-handling through multi-objective optimization: The hydrophobic-polar model for protein structure prediction

In the multi-objective approach to constraint-handling, a constrained problem is transformed into an unconstrained one by defining additional optimization criteria to account for the problem constraints. In this paper, this approach is explored in the context of the hydrophobic-polar model, a simplified yet challenging representation of the protein structure prediction problem. Although focused on such a particular case of study, this research work is intended to contribute to the general understanding of the multi-objective constraint-handling strategy. First, a detailed analysis was conducted to investigate the extent to which this strategy impacts on the characteristics of the fitness landscape. As a result, it was found that an important fraction of the infeasibility translates into neutrality. This neutrality defines potentially shorter paths to move through the landscape, which can also be exploited to escape from local optima. By studying different mechanisms, the second part of this work highlights the relevance of introducing a proper search bias when handling constraints by multi-objective optimization. Finally, the suitability of the multi-objective approach was further evaluated in terms of its ability to effectively guide the search process. This strategy significantly improved the performance of the considered search algorithms when compared with respect to commonly adopted techniques from the literature.     

HEVC帧内预测Planar和DC模式的VLSI架构设计与实现

在研究新一代高性能视频编码标准（HEVC）帧内预测中planar和DC模式预测算法的基础上,分别设计了高效VLSI架构,通过状态机的自适应控制和模块的复用来实现速度的提高和面积的减少。针对planar模式,设计了一种基于状态机自适应控制的寄存器累加架构;针对DC模式,设计了一种基于算法的分割处理架构。实验结果表明,所设计的架构在TSMC180 nm的工艺下最高频率为350 MHz,面积合计为68.1 kgate,能够实现对4∶2∶0格式7 680×4 320@30 f/s视频序列的实时编码,最高工作频率可以达到23.4 MHz。     

应用ANN/HMM混合模型预测蛋白质二级结构

针对3状态隐马尔可夫模型（hidden Markov model,HMM）预测蛋白质二级结构准确率不高的问题,提出15状态HMM,通过改进的算法与BP神经网络相结合进行二级结构预测。研究对象为CB513数据集中筛选出的492条蛋白质序列,将其随机均分7组。应用混合模型进行预测,对准确率进行7交叉验证,Q3准确率达7721%,SOV值为7252%。结果表明,混合模型既能充分考虑相邻氨基酸残基间的相互影响,也能在一定程度上照顾二级结构的远程相关性,因此带来了较好的预测准确率。     

一种基于子序列分布的蛋白质结构类预测方法

蛋白质结构类预测方法的预测能力主要取决于两个方面：一方面，方法采用的序列描述中包含多少有效的蛋白质结构类信息；另一方面，方法采用的判别函数对序列描述中包含的有效信息的利用程度。子序列分布是蛋白质结构类预测中的一种新的序列描述，广义平方距离是组分耦联方法中的判别函数，它包含序列描述中不同组分之间的耦合效应。本文改进了组分耦联方法中的判别函数，解决了当协方差矩阵不可逆时组分耦联方法不能解决的问题，从而把子序列分布与包含耦合效应的判别函数结合起来，对Chou等选取的含有359个蛋白质(结构域)的训练集做了预测，自检测和jackknife检测结果分别为100％和96．7％，这一结果比组分耦联方法提高了5．6和12．6个百分点，比基于自相关函数方法提高了3．3和6．2个百分点。     

A compact hybrid feature vector for an accurate secondary structure prediction

Amino acid propensity score is one of the earliest successful methods used in protein secondary structure prediction. However, the score performs poorly on small-sized datasets and low-identity protein sequences. Based on current in silico method, secondary structure can be predicted from local folds or local protein structure. In biology, the evolution of secondary structure produces local protein structure with different lengths. To precisely predict secondary structures, we propose a derivative feature vector, DPS that utilizes the optimal length of the local protein structure. DPS is the unification of amino acid propensity score and dihedral angle score. This new feature vector is further normalized to level the edges. Prediction is performed by support vector machines (SVM) over the DPS feature vectors with class labels generated by secondary structure assignment method (SSAM) and secondary structure prediction method (SSPM). All experiments are carried out on RS126 sequences. The results from this proposed method also highlight the overall accuracy of our method compared to other state-of-the-art methods. The performance of our method was acceptable specifically in dealing with low number and low identity sequences.     

RealNet: a neural network architecture for real-time systems scheduling

Real-time embedded systems are spreading to more and more new fields and their scope and complexity have grown dramatically in the last few years. Nowadays, real-time embedded computers or controllers can be found everywhere, both in very simple devices used in everyday life and in professional environments. Real-time embedded systems have to take into account robustness, safety and timeliness. The most-used schedulability analysis is the worst-case response time proposed by Joseph and Pandya (Comput J 29:390–395,1986). This test provides a bivaluated response (yes/no) indicating whether the processes will meet their corresponding deadlines or not. Nevertheless, sometimes the real-time designer might want to know, more exactly, the probability of the processes meeting their deadlines, in order to assess the risk of a failed scheduling depending on critical requirements of the processes. This paper presents RealNet, a neural network architecture that will generate schedules from timing requirements of a real-time system. The RealNet simulator will provide the designer, after iterating and averaging over some trials, an estimation of the probability that the system will not meet the deadlines. Moreover, the knowledge of the critical processes in these schedules will allow the designer to decide whether changes in the implementation are required.This revised version was published online in November 2004 with a correction to the accepted date.     

基于GEP-BP网络集成的蛋白质二级结构预测方法研究*

为提高蛋白质二级结构预测的精度,提出了一种基于GEP-BP网络集成的两层结构预测模型。首先利用基因表达式编程（GEP）的全局搜索能力同时进化设计BP网络的结构和连接权,并将进化最后一代的个体用BP算法进一步训练学习,然后采用组合方法将部分个体集成构成模型的第一层;根据神经网络输出之间具有相关性,用第二层网络对第一层的预测结果进行精炼。用PDBSelect25中的36条蛋白质共6 122个残基进行测试,结果表明提出的模型能有效预测蛋白质二级结构,将预测精度提高到73.02%。     

改进型动态隧道神经网络在蛋白质预测的应用

神经网络具有容易陷入局部极小的缺点,动态隧道神经网络通过“钻隧道”方式,让目标函数跳出局部最小,找到更小的可行域,从而避免神经网络陷入局部极小。传统的动态隧道技术隧道方向单一并且随意,因此具有不稳定性。为了有效提高动态隧道的搜索效率,提出了一种改进型动态隧道神经网络算法。该算法增加搜索的隧道数,引入夹角弹性系数控制隧道方向,考察隧道之间的相互影响。在对alpha、beta和coil型蛋白质的二级结构预测的实验中,改进型动态隧道神经网络算法预测的效果优于神经网络算法和传统的动态隧道神经网络算法。     

预测蛋白质结构拟物算法的研究与改进

研究了具有两种氨基酸（疏水氨基酸和亲水氨基酸）的三维非格点的蛋白质模型。给出了该模型蛋白质结构预测问题改进的拟物算法。氨基酸链的初始设置由完全随机改为随机线形结构,并找到了更优的计算参数。结果对于三个氨基酸链都找到了更好的最低势能值。