Protein Secondary Structure Prediction with Partially Recurrent Neural Networks

Abstract

Partially recurrent neural networks with different topologies are applied for secondary structure prediction of proteins. The state of some activations in the network is available after a pattern presentation via feedback connections as additional input during the processing of the next pattern in a sequence. A reference data set containing 91 proteins in the training set and 15 non-homologous proteins in the test set is used for training and testing a network with a modified, hierarchical Elman architecture. The network predicts the secondary structures α-helix, β-sheet, and “coil” for each amino acid. The percentage of correctly classified amino acids is 67.83% on the training set and 63.98% on the test set. The best performance of a three-layer feedforward network is 62.7% on the same test set. A cascaded network, where the outputs of the recurrent network are processed by a second net with 13 × 3 inputs, four hidden and three output units has a predictive performance of 64.49%. The best corresponding feedforward net has a performance of 64.3%.     

Ant Colony Algorithm and Optimization of Test Conditions in Analytical Chemistry

The research for the new algorithm is in the forward position and an issue of general interest in chemometrics all along.A novel chemometrics method,Chemical Ant Colony Algorithm,has first been developed.In this paper,the basic principle,theevaluation function,and the parameter choice were discussed.This method has been successfully applied to the fitting of nonlinear multivariate function and the optimization of test conditions in chrome-azure-S-Al spctrophotometric system.The sum of residual square of the results is 0.0009,which has reached a good convergence result.     

基于迭代自组织数据分析算法与蚁群算法建立有机物黏度的QSPR模型

为了构建310个有机物分子结构与其黏度之间的定量结构-性质关系(QSPR)模型,探讨影响有机物液体黏度的结构因素,首先运用迭代自组织数据分析技术(ISODATA)将样本集初步分类,划分为训练集和测试集,进而应用DRAGON2.1软件计算310个有机物分子的分子结构描述符,以蚁群算法(ACO)筛选分子描述符,得到5个参数,随后分别采用多元线性回归法(MLR)和支持向量机法(SVM)建立ACO-MLR模型和ACOSVM模型.结果表明,非线性ACO-SVM模型(相关系数R2train=0.9013,R2test=0.9026)的性能优于线性ACOMLR模型(R2train=0.7680,R2test=0.8725).ACO-MLR模型和ACO-SVM模型对测试集所得预测值与实验值的相关系数分别为0.934和0.950,预测效果令人满意.本文应用Williams图对模型的应用域进行了一定的研究,所建立的模型为工程上提供了一种根据分子结构预测有机物黏度的有效方法.     

A Cooperative Approach for the Extraction of Protein Motifs

Many problems in chemistry depend on the ability to identify the global solution of a function, which can be a minimum or a maximum. Because the number of local optima grows exponentially with the complexity of the problems, finding the global optimum tur…     

Assessment of AI-Based Protein Structure Prediction for the NLRP3 Target

The recent successes of AlphaFold and RoseTTAFold have demonstrated the value of AI methods in highly accurate protein structure prediction. Despite these advances, the role of these methods in the context of small-molecule drug discovery still needs to be thoroughly explored. In this study, we evaluated whether the AI-based models can reliably reproduce the three-dimensional structures of protein–ligand complexes. The structure we chose was NLRP3, a challenging protein target in terms of obtaining a three-dimensional model both experimentally and computationally. The conformation of the binding pockets generated by the AI models was carefully characterized and compared with experimental structures. Further molecular docking results indicated that AI-predicted protein structures combined with molecular dynamics simulations offers a promising approach in small-molecule drug discovery.     

Prediction of RNA Secondary Structure Based on Particle Swarm Optimization

A novel method for the prediction of RNA secondary structure was proposed based on the particle swarm optimization(PSO). PSO is known to be effective in solving many different types of optimization problems and known for being able to approximate the global optimal results in the solution space. We designed an efficient objective function according to the minimum free energy, the number of selected stems and the average length of selected stems. We calculated how many legal stems there were in the sequence,...     

应用连续小波变换预测蛋白质的二级结构

将代码为lgca蛋白质的氨基酸序列映射为疏水值序列，在合适的尺度下，通过 连续小波变换法分别对其α螺旋,α螺旋和β折叠之间的连接多肽(即部分规则和无 规则二级结构)进行预测，准确率分别为76．5％和85．7％．从PDBsum数据库中随 机抽取100个蛋白质作为测试对象，其中全α螺旋、全β折叠、α／β以及α+β蛋 白质各25个．在100个蛋白质中共有1618个连接多肽和747个α螺旋.本法预测到的 连接多肽共有1536个，其中1308个与实际结构一致，平均预测准确率为85.2％；预 测到的α螺旋有770个，其中581个与实际结构一致，平均预测准确率为75．5％． 结果表明：该法可较好地预测蛋白质的α螺旋、连接多肽，具有极大的发展前景．     

杂合型全局优化法优化水分子团簇结构

基于遗传算法、快速模拟退火及共轭梯度方法提出了一种快速的杂合型全局优化方法(fast hybrid global optimization algorithm, FHGOA),并将这一方法应用于TIP3P和TIPS2模型水分子团簇(H2O)n结构的优化.在进行TIP3P模型水分子团簇结构的优化过程中,发现了能量比文献值更低的团簇结构,且执行效率有较大提高.把该方法应用到优化TIPS2模型的水分子团簇,发现最优结构和采用TTM2-F模型优化的水分子团簇结构在n < 17时完全相同,为全表面结构;而在n=17、19、22时为单中心水分子笼状结构;在n=25、27时为双中心水分子笼状结构.说明随着团簇中水分子个数的增加,采用TIPS2和TTM2-F势能函数优化的团簇最优结构有相同的变化趋势.     

SPOT-Fold: Fragment-Free Protein Structure Prediction Guided by Predicted Backbone Structure and Contact Map

Protein structure determination has long been one of the most challenging problems in molecular biology for the past 60 years. Here we present an ab initio protein tertiary-structure prediction method assisted by predicted contact maps from SPOT-Contact and predicted dihedral angles from SPIDER 3. These predicted properties were then fed to the crystallography and NMR system (CNS) for restrained structure modeling. The resulted structures are first evaluated by the potential energy calculated by CNS, followed by dDFIRE energy function for model selections. The method called SPOT-Fold has been tested on 241 CASP targets between 67 and 670 amino acid residues, 60 randomly selected globular proteins under 100 amino acids. The method has a comparable accuracy to other contact-map-based modeling techniques. © 2019 Wiley Periodicals, Inc.     

Prediction of λmax of 1,4-naphthoquinone derivatives using ant colony optimization

Ant colony optimization (ACO) is a meta-heuristic algorithm, which is derived from the observation of real ants. In this paper, ACO algorithm is proposed to feature selection in quantitative structure property relationship (QSPR) modeling and to predict λ_max of 1,4-naphthoquinone derivatives. Feature selection is the most important step in classification and regression systems. The performance of the proposed algorithm (ACO) is compared with that of a stepwise regression, genetic algorithm and simulated annealing methods. The average absolute relative deviation in this QSPR study using ACO, stepwise regression, genetic algorithm and simulated annealing using multiple linear regression method for calibration and prediction sets were 5.0%, 3.4% and 6.8%, 6.1% and 5.1%, 8.6% and 6.0%, 5.7%, respectively. It has been demonstrated that the ACO is a useful tool for feature selection with nice performance.     

新型室温熔盐二(三氟甲基磺酸酰)亚胺锂-乙酰胺体系的谱学研究

从分析二(三氟甲基磺酸酰)亚胺锂(LiTFSI)与乙酰胺形成熔盐的作用机制出发,通过红外和拉曼光谱的谱学分析并应用非局部密度泛函方法进行量化计算来对二者的相互作用进行了讨论.发现乙酰胺通过Li—O键与LiTFSI中Li+配位而破坏了LiTFSI的离子键,形成很大的配位阳离子,且正电荷被屏蔽在乙酰胺分子中;而TFSI-离子中电荷的部分离域导致电荷被终端—CF3基团屏蔽在整个分子中,这样两个大的阴阳离子间的库伦作用很弱;同时Li—O配位也导致乙酰胺分子间的氢键断裂,因而室温下体系以液体状态稳定存在.     

Combining Cryo-EM Density Map and Residue Contact for Protein Secondary Structure Topologies

Although atomic structures have been determined directly from cryo-EM density maps with high resolutions, current structure determination methods for medium resolution (5 to 10 Å) cryo-EM maps are limited by the availability of structure templates. Secondary structure traces are lines detected from a cryo-EM density map for α-helices and β-strands of a protein. A topology of secondary structures defines the mapping between a set of sequence segments and a set of traces of secondary structures in three-dimensional space. In order to enhance accuracy in ranking secondary structure topologies, we explored a method that combines three sources of information: a set of sequence segments in 1D, a set of amino acid contact pairs in 2D, and a set of traces in 3D at the secondary structure level. A test of fourteen cases shows that the accuracy of predicted secondary structures is critical for deriving topologies. The use of significant long-range contact pairs is most effective at enriching the rank of the maximum-match topology for proteins with a large number of secondary structures, if the secondary structure prediction is fairly accurate. It was observed that the enrichment depends on the quality of initial topology candidates in this approach. We provide detailed analysis in various cases to show the potential and challenge when combining three sources of information.     

A Novel Approach to the Prediction of Transmembrane Proteins

A novel method based on continuous, wavelet transform (CWT) for predicting the number and location of helices in membrane proteins is presented. The PDB code of lyst is chosen as an example to describe the prediction of transmembrane helices (HTM) by using CWT. The results indicate that CWT is a promising approach for the prediction of HTM.     

Geometry Optimization of Ba2+(H2O)n Clusters Using a Fast Hybrid Global Optimization Algorithm

A global optimization called fast hybrid global optimization algorithm was proposed based on genetic algorithm, fast simulated algorithm and conjugated gradient algorithm. We employ it to search the global minimum energy structures of Ba²⁺(H₂O)_n clusters for n = 1–30 within the TIP4P model. The results show that Ba²⁺(H₂O)_n clusters have the n+0 structure while n = 1–8. When n is in the range 9 ≤ n ≤ 18, the number of water molecules in the first shell around the barium ion is 8 and the other water molecules arrange in the outer shell. In the global minimum structure of Ba²⁺(H₂O)₁₉, the number of the first shell water molecules adds up to 9, and the value is kept until n = 30. According to the computational results, a conclusion that hydration numbers for Ba²⁺ is 9 can be drawn, which is in agreement with the result by a Monte Carlo simulation.     

A New Hybrid Model of Amino Acid Substitution for Protein Functional Classification

In recent years, methods of protein sequences analysis have been gradually evolved into two directions: One is based on the models of probability and statistics1-4; the other is based on the digital signal processing technologies 5-8. The latter mainly converts the protein character sequences into digital signals and uses some signal processing methods to analyze them, i.e., fast Fourier transform (FFT). However, it is still unsolved how to characterize the protein sequences accurately with …     

Haruspex: A Neural Network for the Automatic Identification of Oligonucleotides and Protein Secondary Structure in Cryo-Electron Microscopy Maps

In recent years, three-dimensional density maps reconstructed from single particle images obtained by electron cryo-microscopy (cryo-EM) have reached unprecedented resolution. However, map interpretation can be challenging, in particular if the constituting structures require de-novo model building or are very mobile. Herein, we demonstrate the potential of convolutional neural networks for the annotation of cryo-EM maps: our network Haruspex has been trained on a carefully curated set of 293 experimentally derived reconstruction maps to automatically annotate RNA/DNA as well as protein secondary structure elements. It can be straightforwardly applied to newly reconstructed maps in order to support domain placement or as a starting point for main-chain placement. Due to its high recall and precision rates of 95.1 % and 80.3 %, respectively, on an independent test set of 122 maps, it can also be used for validation during model building. The trained network will be available as part of the CCP-EM suite.     

Optimization Based on Retention Prediction and Information Theory for Liquid-Chromatographic Analysis of Alkylbenzenes

Abstract

The mobile phase composition and column length are optimized for analyses of six alkylbenzenes in reversed-phase liquid chromatography with the aid of retention prediction and information theory. Optimal conditions selected according to the resolution Rs and information theory are evaluated from the viewpoint of the precision and analytical efficiency (rapidity) of chromatography. The combination of the information-theoretical optimization with the retention prediction will accelerate the development in the automation of liquid-chromatographic analysis.     

Ab initio prediction of helical segments in polypeptides

An ab initio method has been developed to predict helix formation for polypeptides. The approach relies on the systematic analysis of overlapping oligopeptides to determine the helical propensity for individual residues. Detailed atomistic level modeling, including entropic contributions, and solvation/ionization energies calculated through the solution of the Poisson-Boltzmann equation, is utilized. The calculation of probabilities for helix formation is based on the generation of ensembles of low energy conformers. The approach, which is easily amenable to parallelization, is shown to perform very well for several benchmark polypeptide systems, including the bovine pancreatic trypsin inhibitor, the immunoglobulin binding domain of protein G, the chymotrypsin inhibitor 2, the R69 N-terminal domain of phage 434 repressor, and the wheat germ agglutinin.     

Structure Analysis of Streptococcal Protein G Fc Binding Domain

The gene fragment (191 bp) encoding protein G IgG Fc binding domain was isolated by PCR from group G streptococcus (CMCC32138), and a clone containing this gene fragment was found to give fine reactivity to human IgG when expressed in Escherichia coli. The complete nucleotide sequence of the gene fragment was determined. One base pair differs from previously reported protein Gnucleotide sequences, and resultsin an amino acid change (Ala-Thr), but this variation makes no difference in binding to the IgG Fc part by ELISA.The secondary structure of the protein G IgG Fc binding domain has been estimated by circular dichroism and assigned by computer algorithm.It shows a typical α-helix region in this domain.By breaking this α-helix region with recombinant DNA techniques, a 44 peptide, which contained the N-terminal 27 amino acid residues of this domain, was expressed in E. coli and showed no reactivity to IgG.The hydropathicity of this domain was also analyzed and compared with that of protein A relevant