Prediction of protein folding class from amino acid composition

An empirical relation between the amino acid composition and three-dimensional folding pattern of several classes of proteins has been determined. Computer simulated neural networks have been used to assign proteins to one of the following classes based on their amino acid composition and size: (1) 4α-helical bundles, (2) parallel (α/β)₈ barrels, (3) nucleotide binding fold, (4) immunoglobulin fold, or (5) none of these. Networks trained on the known crystal structures as well as sequences of closely related proteins are shown to correctly predict folding classes of proteins not represented in the training set with an average accuracy of 87%. Other folding motifs can easily be added to the prediction scheme once larger databases become available. Analysis of the neural network weights reveals that amino acids favoring prediction of a folding class are usually over represented in that class and amino acids with unfavorable weights are underrepresented in composition. The neural networks utilize combinations of these multiple small variations in amino acid composition in order to make a prediction. The favorably weighted amino acids in a given class also form the most intramolecular interactions with other residues in proteins of that class. A detailed examination of the contacts of these amino acids reveals some general patterns that may help stabilize each folding class. © 1993 Wiley-Liss, Inc.     

Machine learning techniques for protein function prediction

Proteins play important roles in living organisms, and their function is directly linked with their structure. Due to the growing gap between the number of proteins being discovered and their functional characterization (in particular as a result of experimental limitations), reliable prediction of protein function through computational means has become crucial. This paper reviews the machine learning techniques used in the literature, following their evolution from simple algorithms such as logistic regression to more advanced methods like support vector machines and modern deep neural networks. Hyperparameter optimization methods adopted to boost prediction performance are presented. In parallel, the metamorphosis in the features used by these algorithms from classical physicochemical properties and amino acid composition, up to text-derived features from biomedical literature and learned feature representations using autoencoders, together with feature selection and dimensionality reduction techniques, are also reviewed. The success stories in the application of these techniques to both general and specific protein function prediction are discussed.     

Topological maps of protein sequences

A new method based on neural networks to cluster proteins into families is described. The network is trained with the Kohonen unsupervised learning algorithm, using matrix pattern representations of the protein sequences as inputs. The components (x, y) of these 20×20 matrix patterns are the normalized frequencies of all pairs xy of amino acids in each sequence. We investigate the influence of different learning parameters in the final topological maps obtained with a learning set of ten proteins belonging to three established families. In all cases, except in those where the synaptic vectors remains nearly unchanged during learning, the ten proteins are correctly classified into the expected families. The classification by the trained network of mutated or incomplete sequences of the learned proteins is also analysed. The neural network gives a correct classification for a sequence mutated in 21.5%±7% of its amino acids and for fragments representing 7.5%±3% of the original sequence. Similar results were obtained with a learning set of 32 proteins belonging to 15 families. These results show that a neural network can be trained following the Kohonen algorithm to obtain topological maps of protein sequences, where related proteins are finally associated to the same winner neuron or to neighboring ones, and that the trained network can be applied to rapidly classify new sequences. This approach opens new possibilities to find rapid and efficient algorithms to organize and search for homologies in the whole protein database.     

Cross-validation of protein structural class prediction using statistical clustering and neural networks.

We present an approach to predicting protein structural class that uses amino acid composition and hydrophobic pattern frequency information as input to two types of neural networks: (1) a three-layer back-propagation network and (2) a learning vector quantization network. The results of these methods are compared to those obtained from a modified Euclidean statistical clustering algorithm. The protein sequence data used to drive these algorithms consist of the normalized frequency of up to 20 amino acid types and six hydrophobic amino acid patterns. From these frequency values the structural class predictions for each protein (all-alpha, all-beta, or alpha-beta classes) are derived. Examples consisting of 64 previously classified proteins were randomly divided into multiple training (56 proteins) and test (8 proteins) sets. The best performing algorithm on the test sets was the learning vector quantization network using 17 inputs, obtaining a prediction accuracy of 80.2%. The Matthews correlation coefficients are statistically significant for all algorithms and all structural classes. The differences between algorithms are in general not statistically significant. These results show that information exists in protein primary sequences that is easily obtainable and useful for the prediction of protein structural class by neural networks as well as by standard statistical clustering algorithms.     

基于 RBF 神经网络的蛋白质二级结构预测

蛋白质二级结构对于研究其功能具有重要作用。采用主成分分析方法对氨基酸的基本物化属性及其二级结构倾向性进行降维降噪处理,使用径向基神经网络对蛋白质二级结构进行预测。主成分分析使得之前 20 ×12 矩阵变为 20 ×4 矩阵,极大地减少了神经网络输入端的维数。在仿真过程中,当窗口大小为 21,扩展函数为 7 时,预测精确度达到了 71. 81%。实验结果表明 RBF 神经网络可以有效的用于蛋白质二级结构的预测。     

Adaptive encoding neural networks for the recognition of human signal peptide cleavage sites

MOTIVATION: Data representation and encoding are essential for classification of protein sequences with artificial neural networks (ANN). Biophysical properties are appropriate for low dimensional encoding of protein sequence data. However, in general there is no a priori knowledge of the relevant properties for extraction of representative features. RESULTS: An adaptive encoding artificial neural network (ACN) for recognition of sequence patterns is described. In this approach parameters for sequence encoding are optimized within the same process as the weight vectors by an evolutionary algorithm. The method is applied to the prediction of signal peptide cleavage sites in human secretory proteins and compared with an established predictor for signal peptides. CONCLUSION: Knowledge of physico-chemical properties is not necessary for training an ACN. The advantage is a low dimensional data representation leading to computational efficiency, easy evaluation of the detected features, and high prediction accuracy. Availability: A cleavage site prediction server is located at the Humboldt University http://itb.biologie.hu-berlin.de/ approximately jo/sig-cleave/ACNpredictor.cgi Contact: jo@itb.hu-berlin.de; berndj@zedat.fu-berlin.de     

Structure optimization of an artificial neural filter detecting membrane-spanning amino acid sequences

An artificial neural network has been developed for the recognition and prediction of transmembrane regions in the amino acid sequences of human integral membrane proteins. It provides an additional prediction method besides the common hydrophobicity analysis by statistical means. Membrane/nonmembrane transition regions are predicted with 92% accuracy in both training and independent test data. The method used for the development of the neural filter is the algorithm of structure evolution. It subjects both the architecture and parameters of the system to a systematical optimization process and carries out local search in the respective structure and parameter spaces. The training technique of incomplete induction as part of the structure evolution provides for a comparatively general solution of the problem that is described by input-output relations only. Seven physicochemical side-chain properties were used to encode the amino acid sequences. It was found that geometric parameters like side-chain volume, bulkiness, or surface area are of minor importance. The properties polarity, refractivity, and hydrophobicity, however, turned out to support feature extraction. It is concluded that membrane transition regions in proteins are encoded in sequences as a characteristic feature based on the respective side-chain properties. The method of structure evolution is described in detail for this particular application and suggestions for further development of amino acid sequence filters are made. © 1996 John Wiley & Sons, Inc.     

QBES: predicting real values of solvent accessibility from sequences by efficient, constrained energy optimization

Solvent accessibility, one of the key properties of amino acid residues in proteins, can be used to assist protein structure prediction. Various approaches such as neural network, support vector machines, probability profiles, information theory, Bayesian theory, logistic function, and multiple linear regression have been developed for solvent accessibility prediction. In this article, a much simpler quadratic programming method based on the buriability parameter set of amino acid residues is developed. The new method, called QBES (Quadratic programming and Buriability Energy function for Solvent accessibility prediction), is reasonably accurate for predicting the real value of solvent accessibility. By using a dataset of 30 proteins to optimize three parameters, the average correlation coefficients between the predicted and actual solvent accessibility are about 0.5 for all four independent test sets ranging from 126 to 513 proteins. The method is efficient. It takes only 20 min for a regular PC to obtain results of 30 proteins with an average length of 263 amino acids. Although the proposed method is less accurate than a few more sophisticated methods based on neural network or support vector machines, this is the first attempt to predict solvent accessibility by energy optimization with constraints. Possible improvements and other applications of the method are discussed.     

Discriminating lysosomal membrane protein types using dynamic neural network

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.     

Feed-forward neural networks for secondary structure prediction

A feed-forward neural network has been employed for protein secondary structure prediction. Attempts were made to improve on previous prediction accuracies using a hierarchical mixture of experts (HME). In this method input data are clustered and used to train a series of different networks. Application of an HME to the prediction of protein secondary structure is shown to provide no advantages over a single network. We have also tried various new input representations, chosen to incorporate the effect of residues a long distance away in the one-dimensional amino acid chain. Prediction accuracy using these methods is comparable to that achieved by other neural networks.^1–4     

氨基酸邻域对二级结构的影响程度研究

通过研究神经网络权值矩阵的算法,挖掘蛋白质二级结构与氨基酸序列间的内在规律,提高一级序列预测二级结构的准确度。神经网络方法在特征分类方面具有良好表现,经过学习训练后的神经元连接权值矩阵包含样本的内在特征和规律。研究使用神经网络权值矩阵打分预测;采用错位比对方法寻找敏感的氨基酸邻域;分析测试集在不同加窗长度下的共性表现。实验表明,在滑动窗口长度L=7时,预测性能变化显著;邻域位置P=4的氨基酸残基对预测性能有加强作用。该研究方法为基于局部序列特征的蛋白质二级结构预测提供了新的算法设计。     

Characteristic sequential residue environment of amino acids in proteins

The occurrence of all di- and tripeptide segments of proteins was counted in a large data base containing about 119 000 residues. It was found that the abundance of the amino acids does not determine the frequency of the various di- and tripeptide segments. In addition, the frequency of the various tripeptides cannot be predicted from the observed pair-frequency values. The pair-frequency distribution of amino acids is highly asymmetrical, pairs formed from identical residues are generally preferred and amino acids cannot be clustered on the basis of their first neighbour preferences. These data indicate the existence of general short range regularities in the primary structure of proteins. The consequences of these short range regularities were studied by comparing Chou-Fasman parameters with analogous parameters determined from the results of conformational energy calculations of single amino acids. This comparison shows that Chou-Fasman parameters carry significant information about the environment of each amino acid. The success of the Chou-Fasman's prediction and the properties of the pair and triplet distribution of the amino acid residues suggest that every amino acid has a characteristic sequential residue environment in proteins. The observed preferences could be invoked, for example, in protein design or in the study of the evolutionary relationship of proteins.     

Estimation of oxygen mass transfer coefficient in stirred tank reactors using artificial neural networks

The estimation of volumetric mass transfer coefficient, k(L)a, in stirred tank reactors using artificial neural networks has been studied. Several operational conditions (N and V(s)), properties of fluid (μ(a)) and geometrical parameters (D and T) have been taken into account. Learning sets of input-output patterns were obtained by k(L)a experimental data in stirred tank reactors of different volumes. The inclusion of prior knowledge as an approach which improves the neural network prediction has been considered. The hybrid model combining a neural network together with an empirical equation provides a better representation of the estimated parameter values. The outputs predicted by the hybrid neural network are compared with experimental data and some correlations previously proposed in the literature for tanks of different sizes.     

Predicting protein homocysteinylation targets based on dihedral strain energy and pKa of cysteines

A multitude of complex diseases have been linked to elevated homocysteine levels; however, till date there is no plausible explanation for a single amino acid's involvement in so many diseases. Since homocysteine is a reactive thiol amino acid and the majority of plasma homocysteine is protein thiol bound, we hypothesized that homocysteine might bind to accessible cysteine residues in target proteins, thereby modulating its structure or function or both. The parameters that dictate homocysteine-protein interaction are not well understood, and the few known homocysteine binding proteins were identified by a candidate protein approach. In this study, we identified potential homocysteine interacting proteins based on cysteine content, solvent accessibility of cysteine residues, and dihedral strain energies and pKa of these cysteines. Pathway mapping of the cysteine-rich proteins revealed that proteins in the coagulation cascade, notch receptor-mediated signaling, LDL endocytosis, programmed cell death, and extracellular matrix proteins were significantly over-represented with cysteine-rich proteins, and we believe that homocysteine has a high probability to bind to proteins in these pathways. In fact, several clinical studies have implicated high homocysteine levels to be associated with diseases like thrombosis, neural tube defects, and so forth, which result from dysfunction of one or more of the proteins identified in our study. Further, we successfully validated our prediction parameters on the proteins that have already been experimentally shown to bind homocysteine, and our structural analysis argues a plausible explanation for these prior reported protein interactions with homocysteine that could not be previously explained.     

A new Motzkin class for joint RNA secondary structures

In general RNA prediction problem includes genetic mapping, physical mapping and structure prediction. The ultimate goal of structure prediction is to obtain the three dimensional structure of bimolecules through computation. The key concept for solving the above mentioned problem is the appropriate representation of the biological structures. Even though, the problems that concern representations of certain biological structures like secondary structures either are characterized as NP-complete or with high complexity, few approximation algorithms and techniques had been constructed, mainly with polynomial complexity, concerning the prediction of RNA secondary structures. In this paper, a new class of Motzkin paths is introduced, the so-called semi-elevated inverse Motzkin peakless paths for the representation of two interacting RNA molecules. The basic combinatorial interpretations on single RNA secondary structures are extended via these new Motzkin paths on two RNA molecules and can be applied to the prediction methods of joint structures formed by interacting RNAs.     

Enhanced recognition of protein transmembrane domains with prediction-based structural profiles

MOTIVATION: Membrane domain prediction has recently been re-evaluated by several groups, suggesting that the accuracy of existing methods is still rather limited. In this work, we revisit this problem and propose novel methods for prediction of alpha-helical as well as beta-sheet transmembrane (TM) domains. The new approach is based on a compact representation of an amino acid residue and its environment, which consists of predicted solvent accessibility and secondary structure of each amino acid. A recently introduced method for solvent accessibility prediction trained on a set of soluble proteins is used here to indicate segments of residues that are predicted not to be accessible to water and, therefore, may be 'buried' in the membrane. While evolutionary profiles in the form of a multiple alignment are used to derive these simple 'structural profiles', they are not used explicitly for the membrane domain prediction and the overall number of parameters in the model is significantly reduced. This offers the possibility of a more reliable estimation of the free parameters in the model with a limited number of experimentally resolved membrane protein structures. RESULTS: Using cross-validated training on available sets of structurally resolved and non-redundant alpha and beta membrane proteins, we demonstrate that membrane domain prediction methods based on such a compact representation outperform approaches that utilize explicitly evolutionary profiles and multiple alignments. Moreover, using an external evaluation by the TMH Benchmark server we show that our final prediction protocol for the TM helix prediction is competitive with the state-of-the-art methods, achieving per-residue accuracy of approximately 89% and per-segment accuracy of approximately 80% on the set of high resolution structures used by the TMH Benchmark server. At the same time the observed rates of confusion with signal peptides and globular proteins are the lowest among the tested methods. The new method is available online at http://minnou.cchmc.org.     

Basic mechanisms for graded persistent activity: discrete attractors,continuous attractors,and dynamic representations

Persistent neural activity is observed in many systems, and is thought to be a neural substrate for holding memories over time delays of a few seconds. Recent work has addressed two issues. First, how can networks of neurons robustly hold such an active memory? Computer systems obtain significant robustness to noise by approximating analogue quantities with discrete digital representations. In a similar manner, theoretical models of persistent activity in spiking neurons have shown that the most robust and stable way to store the short-term memory of a continuous parameter is to approximate it with a discrete representation. This general idea applies very broadly to mechanisms that range from biochemical networks to single cells and to large circuits of neurons. Second, why is it commonly observed that persistent activity in the cortex can be strongly time-varying? This observation is almost ubiquitous, and therefore must be taken into account in our models and our understanding of how short-term memories are held in the cortex.     

Genetic algorithm-based optimization of hydrophobicity tables

SUMMARY: The genomic abundance and pharmacological importance of membrane proteins have fueled efforts to identify them based solely on sequence information. Previous methods based on the physicochemical principle of a sliding window of hydrophobicity (hydropathy analysis) have been replaced by approaches based on hidden Markov models or neural networks which prevail due to their probabilistic orientation. In the current study, an optimization of the hydrophobicity tables used in hydropathy analysis is performed using a genetic algorithm. As such, the approach can be viewed as a synthesis between the physicochemically and statistically based methods. The resulting hydrophobicity tables lead to significant improvement in the prediction accuracy of hydropathy analysis. Furthermore, since hydropathy analysis is less dependent on the basis set of membrane proteins is used to hone the statistically based methods, as well as being faster, it may be valuable in the analysis of new genomes. Finally, the values obtained for each of the amino acids in the new hydrophobicity tables are discussed.