A new feature encoding scheme for HIV-1 protease cleavage site prediction

HIV-1 protease has been the subject of intense research for deciphering HIV-1 virus replication process for decades. Knowledge of the substrate specificity of HIV-1 protease will enlighten the way of development of HIV-1 protease inhibitors. In the prediction of HIV-1 protease cleavage site techniques, various feature encoding techniques and machine learning algorithms have been used frequently. In this paper, a new feature amino acid encoding scheme is proposed to predict HIV-1 protease cleavage sites. In the proposed method, we combined orthonormal encoding and Taylor’s venn-diagram. We used linear support vector machines as the classifier in the tests. We also analyzed our technique by comparing some feature encoding techniques. The tests are carried out on PR-1625 and PR-3261 datasets. Experimental results show that our amino acid encoding technique leads to better classification performance than other encoding techniques on a standalone classifier.     

Flap opening mechanism of HIV-1 protease

The active site of aspartic proteases, such as HIV-1 protease (PR), is covered by one or more flaps, which restrict access to the active site. For HIV-1 PR, X-ray diffraction studies suggested that in the free enzyme the two flaps are packed onto each other loosely in a semi-open conformation, while molecular dynamics (MD) studies observed that the flaps can also separate into open conformations. In this study, the mechanism of flap opening and the structure and dynamics of HIV-1 PR with semi-open and open flap conformations were investigated using molecular dynamics simulations. The flaps showed complex dynamic behavior as two distinct mechanisms of flap opening and various stable flap conformations (semi-open, open and curled) were observed during the simulations. A network of weakly polar interactions between the flaps were proposed to be responsible for stabilizing the semi-open flap conformation. It is hypothesized that such interactions could be responsible for making flap opening a highly sensitive gating mechanism which control access to the active site.     

最优支持向量机用于HIV-1蛋白酶抑制剂的QSAR建模

为了建立HIV蛋白酶抑制剂QSAR的优良模型,本文采用粒子群优化法搜索支持向量机的多参数复杂模型空间,以此形成最优支持向量机。通过与传统的梯度下降法、网格搜索法等模型选择方法的比较,采用并行计算的基于PSO算法的最优支持向量机法在模型精度及稳定性、搜索效率等方面都有优良的性能,实例测试也表明所建QSAR模型,有良好的泛化能力,所建模型对研究HIV药物有重要促进作用。     

一种可最优化计算特征规模的互信息特征提取

利用矩阵特征向量分解,提出一种可最优化计算特征规模的互信息特征提取方法．首先,论述了高斯分布假设下的该互信息判据的类可分特性,并证明了现有典型算法都是本算法的特例;然后,在给出该互信息判据严格的数学意义基础上,提出了基于矩阵特征向量分解计算最优化特征规模算法;最后,通过实际数据验证了该方法的有效性     

Effect of allosteric molecules on structure and drug affinity of HIV-1 protease by molecular dynamics simulations

Recent experiments show that small molecules can bind onto the allosteric sites of HIV-1 protease (PR), which provides a starting point for developing allosteric inhibitors. However, the knowledge of the effect of such binding on the structural dynamics and binding free energy of the active site inhibitor and PR is still lacking. Here, we report 200 ns long molecular dynamics simulation results to gain insight into the influences of two allosteric molecules (1H-indole-6-carboxylic acid, 1F1 and 2-methylcyclohexano, 4D9). The simulations demonstrate that both allosteric molecules change the PR conformation and stabilize the structures of PR and the inhibitor; the residues of the flaps are sensitive to the allosteric molecules and the flexibility of the residues is pronouncedly suppressed; the additions of the small molecules to the allosteric sites strengthen the binding affinities of 3TL-PR by about 12–15 kal/mol in the binding free energy, which mainly arises from electrostatic term. Interestingly, it is found that the action mechanisms of 1F1 and 4D9 are different, the former behaviors like a doorman that keeps the inhibitor from escape and makes the flaps (door) partially open; the latter is like a wedge that expands the allosteric space and meanwhile closes the flaps. Our data provide a theoretical support for designing the allosteric inhibitor.     

An MRF-based kernel method for nonlinear feature extraction

Nonlinear kernel-based feature extraction algorithms have recently been proposed to alleviate the loss of class discrimination after feature extraction. When considering image classification, a kernel function may not be sufficiently effective if it depends only on an information resource from the Euclidean distance in the original feature space. This study presents an extended radial basis kernel function that integrates multiple discriminative information resources, including the Euclidean distance, spatial context, and class membership. The concepts related to Markov random fields (MRFs) are exploited to model the spatial context information existing in the image. Mutual closeness in class membership is defined as a similarity measure with respect to classification. Any dissimilarity from the additional information resources will improve the discrimination between two samples that are only a short Euclidean distance apart in the feature space. The proposed kernel function is used for feature extraction through linear discriminant analysis (LDA) and principal component analysis (PCA). Experiments with synthetic and natural images show the effectiveness of the proposed kernel function with application to image classification.     

Sparse two-dimensional local discriminant projections for feature extraction

Two-dimensional local graph embedding discriminant analysis (2DLGEDA) and two-dimensional discriminant locality preserving projections (2DDLPP) were recently proposed to directly extract features form 2D face matrices to improve the performance of two-dimensional locality preserving projections (2DLPP). But all of them require a high computational cost and the learned transform matrices lack intuitive and semantic interpretations. In this paper, we propose a novel method called sparse two-dimensional locality discriminant projections (S2DLDP), which is a sparse extension of graph-based image feature extraction method. S2DLDP combines the spectral analysis and L₁-norm regression using the Elastic Net to learn the sparse projections. Differing from the existing 2D methods such as 2DLPP, 2DDLP and 2DLGEDA, S2DLDP can learn the sparse 2D face profile subspaces (also called sparsefaces), which give an intuitive, semantic and interpretable feature subspace for face representation. We point out that using S2DLDP for face feature extraction is, in essence, to project the 2D face images on the semantic face profile subspaces, on which face recognition is also performed. Experiments on Yale, ORL and AR face databases show the efficiency and effectiveness of S2DLDP.     

A multi-manifold discriminant analysis method for image feature extraction

In this paper, we propose a Multi-Manifold Discriminant Analysis (MMDA) method for an image feature extraction and pattern recognition based on graph embedded learning and under the Fisher discriminant analysis framework. In an MMDA, the within-class graph and between-class graph are, respectively, designed to characterize the within-class compactness and the between-class separability, seeking for the discriminant matrix to simultaneously maximize the between-class scatter and minimize the within-class scatter. In addition, in an MMDA, the within-class graph can represent the sub-manifold information, while the between-class graph can represent the multi-manifold information. The proposed MMDA is extensively examined by using the FERET, AR and ORL face databases, and the PolyU finger-knuckle-print databases. The experimental results demonstrate that an MMDA is effective in feature extraction, leading to promising image recognition performance.     

Stochastic neighbor projection on manifold for feature extraction

This paper develops a manifold-oriented stochastic neighbor projection (MSNP) technique for feature extraction. MSNP is designed to find a linear projection for the purpose of capturing the underlying pattern structure of observations that actually lie on a nonlinear manifold. In MSNP, the similarity information of observations is encoded with stochastic neighbor distribution based on geodesic distance metric, then the same distribution is required to be hold in feature space. This learning criterion not only empowers MSNP to extract nonlinear feature through a linear projection, but makes MSNP competitive as well by reason that distribution preservation is more workable and flexible than rigid distance preservation. MSNP is evaluated in three applications: data visualization for faces image, face recognition and palmprint recognition. Experimental results on several benchmark databases suggest that the proposed MSNP provides a unsupervised feature extraction approach with powerful pattern revealing capability for complex manifold data.     

Human facial feature extraction for face interpretation and recognition

Facial features' extraction algorithms which can be used for automated visual interpretation and recognition of human faces are presented. Here, we can capture the contours of the eye and mouth by a deformable template model because of their analytically describable shapes. However, the shapes of the eyebrow, nostril and face are difficult to model using a deformable template. We extract them by using an active contour model (snake). In the experiments, 12 models are photographed, and the feature contours are extracted for each portrait.     

Prediction-based geometric feature extraction for 2D laser scanner

This paper presents a novel algorithm for detecting line and circle features from 2D laser range scans. Unlike the conventional methods that use two stages for separating the features: data segmentation and feature separation in each segment, the proposed algorithm adopts a new structure and thus the computation complexity is much reduced. Moreover, it does not depend on prior knowledge of the environment, and it requires a minimum number of points per segment. We utilize prediction to achieve the above goals, so the algorithm is named prediction-based feature extraction (PFE). The efficiency and accuracy of the method is demonstrated by the experiments results.     

A collaborative representation based projections method for feature extraction

In graph embedding based methods, we usually need to manually choose the nearest neighbors and then compute the edge weights using the nearest neighbors via L2 norm (e.g. LLE). It is difficult and unstable to manually choose the nearest neighbors in high dimensional space. So how to automatically construct a graph is very important. In this paper, first, we give a L2-graph like L1-graph. L2-graph calculates the edge weights using the total samples, avoiding manually choosing the nearest neighbors; second, a L2-graph based feature extraction method is presented, called collaborative representation based projections (CRP). Like SPP, CRP aims to preserve the collaborative representation based reconstruction relationship of data. CRP utilizes a L2 norm graph to characterize the local compactness information. CRP maximizes the ratio between the total separability information and the local compactness information to seek the optimal projection matrix. CRP is much faster than SPP since CRP calculates the objective function with L2 norm while SPP calculate the objective function with L1 norm. Experimental results on FERET, AR, Yale face databases and the PolyU finger-knuckle-print database demonstrate that CRP works well in feature extraction and leads to a good recognition performance.     

A feature extraction algorithm for multi-peak signals in electronic noses

The Lorentzian model is a powerful feature extraction technique for electronic noses. In a previous work, it was applied to single-peak transient signals and was shown to achieve lower classification error rate than other feature extraction techniques. Here, we generalize the Lorentzian model by showing how to apply it to transient signals that are comprised of more than a single peak. The model is based on a fast and robust fitting of the measured signals to a physically meaningful analytic curve. We show that this model fits equally well to sensors of different technologies and embeddings, suggesting its applicability to a diverse repertoire of sensors and analytic devices.     

A new feature extraction approach based on one dimensional gray level co-occurrence matrices for bearing fault classification

ABSTRACT

Recently, precise and deterministic feature extraction is one of the current research topics for bearing fault diagnosis. For this aim, an experimental bearing test setup was created in this study. In this setup, vibration signals were obtained from the bearings on which artificial faults were generated in specific sizes. A new feature extraction method based on co-occurrence matrices for bearing vibration signals was proposed instead of the conventional feature extraction methods, as in the literature. The One (1) Dimensional–Local Binary Patterns (1D-LBP) method was first applied to bearing vibration signals, and a new signal whose values ranged between 0–255 was obtained. Then, co-occurrence matrices were obtained from these signals. The correlation, energy, homogeneity, and contrast features were extracted from these matrices. Different machine learning methods were employed with these features to carry out the classification process. Three different data sets were used to test the proposed approach. As a result of analysing the signals with the proposed model, the success rate is 87.50% for dataset1 (different speed), 96.5% for dataset2 (fault size (mm)) and 99.30% for dataset3 (fault type – inner ring, outer ring, ball) was found, respectively.     

A fast method of feature extraction for kernel MSE

In this paper, a fast method of selecting features for kernel minimum squared error (KMSE) is proposed to mitigate the computational burden in the case where the size of the training patterns is large. Compared with other existent algorithms of selecting features for KMSE, this iterative KMSE, viz. IKMSE, shows better property of enhancing the computational efficiency without sacrificing the generalization performance. Experimental reports on the benchmark data sets, nonlinear autoregressive model and real problem address the efficacy and feasibility of the proposed IKMSE. In addition, IKMSE can be easily extended to classification fields.     

Generalized mean for feature extraction in one-class classification problems

Biased discriminant analysis (BDA), which extracts discriminative features for one-class classification problems, is sensitive to outliers in negative samples. This study focuses on the drawback of BDA attributed to the objective function based on the arithmetic mean in one-class classification problems, and proposes an objective function based on a generalized mean. A novel method is also presented to effectively maximize the objective function. The experimental results show that the proposed method provides better discriminative features than the BDA and its variants.     

Kernel nonnegative matrix factorization for spectral EEG feature extraction

Nonnegative matrix factorization (NMF) seeks a decomposition of a nonnegative matrix X0 into a product of two nonnegative factor matrices U0 and V0, such that a discrepancy between X and UV is minimized. Assuming U=XW in the decomposition (for W0), kernel NMF (KNMF) is easily derived in the framework of least squares optimization. In this paper we make use of KNMF to extract discriminative spectral features from the time–frequency representation of electroencephalogram (EEG) data, which is an important task in EEG classification. Especially when KNMF with linear kernel is used, spectral features are easily computed by a matrix multiplication, while in the standard NMF multiplicative update should be performed repeatedly with the other factor matrix fixed, or the pseudo-inverse of a matrix is required. Moreover in KNMF with linear kernel, one can easily perform feature selection or data selection, because of its sparsity nature. Experiments on two EEG datasets in brain computer interface (BCI) competition indicate the useful behavior of our proposed methods.     

Performance comparison of feature extraction algorithms for target detection and classification

This paper addresses the problem of target detection and classification, where the performance is often limited due to high rates of false alarm and classification error, possibly because of inadequacies in the underlying algorithms of feature extraction from sensory data and subsequent pattern classification. In this paper, a recently reported feature extraction algorithm, symbolic dynamic filtering (SDF), is investigated for target detection and classification by using unmanned ground sensors (UGS). In SDF, sensor time series data are first symbolized to construct probabilistic finite state automata (PFSA) that, in turn, generate low-dimensional feature vectors. In this paper, the performance of SDF is compared with that of two commonly used feature extractors, namely Cepstrum and principal component analysis (PCA), for target detection and classification. Three different pattern classifiers have been employed to compare the performance of the three feature extractors for target detection and human/animal classification by UGS systems based on two sets of field data that consist of passive infrared (PIR) and seismic sensors. The results show consistently superior performance of SDF-based feature extraction over Cepstrum-based and PCA-based feature extraction in terms of successful detection, false alarm, and misclassification rates.     

A feature extraction method for use with bimodal biometrics

Bimodal biometrics has been found to outperform single biometrics and are usually implemented using the matching score level or decision level fusion, though this fusion will enable less information of bimodal biometric traits to be exploited for personal authentication than fusion at the feature level. This paper proposes matrix-based complex PCA (MCPCA), a feature level fusion method for bimodal biometrics that uses a complex matrix to denote two biometric traits from one subject. The method respectively takes the two images from two biometric traits of a subject as the real part and imaginary part of a complex matrix. MCPCA applies a novel and mathematically tractable algorithm for extracting features directly from complex matrices. We also show that MCPCA has a sound theoretical foundation and the previous matrix-based PCA technique, two-dimensional PCA (2DPCA), is only one special form of the proposed method. On the other hand, the features extracted by the developed method may have a large number of data items (each real number in the obtained features is called one data item). In order to obtain features with a small number of data items, we have devised a two-step feature extraction scheme. Our experiments show that the proposed two-step feature extraction scheme can achieve a higher classification accuracy than the 2DPCA and PCA techniques.     

Complete discriminant evaluation and feature extraction in kernel space for face recognition

This work proposes a method to decompose the kernel within-class eigenspace into two subspaces: a reliable subspace spanned mainly by the facial variation and an unreliable subspace due to limited number of training samples. A weighting function is proposed to circumvent undue scaling of eigenvectors corresponding to the unreliable small and zero eigenvalues. Eigenfeatures are then extracted by the discriminant evaluation in the whole kernel space. These efforts facilitate a discriminative and stable low-dimensional feature representation of the face image. Experimental results on FERET, ORL and GT databases show that our approach consistently outperforms other kernel based face recognition methods.