Structural Classification Methods Research Articles

Sequence and Structure Properties Uncover the Natural Classification of Protein Complexes Formed by Intrinsically Disordered Proteins via Mutual Synergistic Folding.

Intrinsically disordered proteins mediate crucial biological functions through their interactions with other proteins. Mutual synergistic folding (MSF) occurs when all interacting proteins are disordered, folding into a stable structure in the course of the complex formation. In these cases, the folding and binding processes occur in parallel, lending the resulting structures uniquely heterogeneous features. Currently there are no dedicated classification approaches that take into account the particular biological and biophysical properties of MSF complexes. Here, we present a scalable clustering-based classification scheme, built on redundancy-filtered features that describe the sequence and structure properties of the complexes and the role of the interaction, which is directly responsible for structure formation. Using this approach, we define six major types of MSF complexes, corresponding to biologically meaningful groups. Hence, the presented method also shows that differences in binding strength, subcellular localization, and regulation are encoded in the sequence and structural properties of proteins. While current protein structure classification methods can also handle complex structures, we show that the developed scheme is fundamentally different, and since it takes into account defining features of MSF complexes, it serves as a better representation of structures arising through this specific interaction mode.

T24DISSECTING SUB-PHENOTYPES OF BIPOLAR DISORDER USING MULTIPLE POLYGENIC RISK SCORES

Objects are formed by various structures and such structural information is essential for the identification of objects, especially for street facilities presented by mobile laser scanning (MLS) data with abundant details. However, due to the large volume of data, large variations in point density, noise and complexity of scanned scenes, the achievement of effective decomposition of objects into physical meaningful structures remains a challenge issue. And structural information has been rarely considered to improve the accuracy of distinguishing between objects with global or local similarity, such as traffic signs and traffic lights. Therefore, we propose a structural segmentation and classification method for MLS point clouds that is efficient and robust to variations in point density and complex urban scenes. During the segmentation stage, a novel region growing approach and a multi-size supervoxel segmentation algorithm robust to noise and varying density are combined to extract effective local shape descriptors. Structural components with physically meaningful labels are generated via structural labelling and clustering. During the classification stage, we consider the structural information at various scales and locations and encode it into a conditional random-field model for unary and pairwise inferences. High-order potentials are also introduced into the conditional random field to eliminate regional label noise. These high-order potentials are defined upon regions independent of connection relationships and can therefore take effect on isolated nodes. Experiments with two MLS datasets of typical urban scenes in Paris and Hong Kong were used to evaluate the performance of the proposed method. Nine and eleven different object classes were recognized from these two datasets with overall accuracies of 97.13% and 95.79%, respectively, indicating the effectiveness of the proposed method of interpreting complex urban scenes from point clouds with large variations in point density. Compared with previous studies on the Paris dataset, our method was able to recognize more classes and obtained a mean F1-score of 72.70% of seven common classes, being higher than the best of previous results.

Structural segmentation and classification of mobile laser scanning point clouds with large variations in point density

Objects are formed by various structures and such structural information is essential for the identification of objects, especially for street facilities presented by mobile laser scanning (MLS) data with abundant details. However, due to the large volume of data, large variations in point density, noise and complexity of scanned scenes, the achievement of effective decomposition of objects into physical meaningful structures remains a challenge issue. And structural information has been rarely considered to improve the accuracy of distinguishing between objects with global or local similarity, such as traffic signs and traffic lights. Therefore, we propose a structural segmentation and classification method for MLS point clouds that is efficient and robust to variations in point density and complex urban scenes. During the segmentation stage, a novel region growing approach and a multi-size supervoxel segmentation algorithm robust to noise and varying density are combined to extract effective local shape descriptors. Structural components with physically meaningful labels are generated via structural labelling and clustering. During the classification stage, we consider the structural information at various scales and locations and encode it into a conditional random-field model for unary and pairwise inferences. High-order potentials are also introduced into the conditional random field to eliminate regional label noise. These high-order potentials are defined upon regions independent of connection relationships and can therefore take effect on isolated nodes. Experiments with two MLS datasets of typical urban scenes in Paris and Hong Kong were used to evaluate the performance of the proposed method. Nine and eleven different object classes were recognized from these two datasets with overall accuracies of 97.13% and 95.79%, respectively, indicating the effectiveness of the proposed method of interpreting complex urban scenes from point clouds with large variations in point density. Compared with previous studies on the Paris dataset, our method was able to recognize more classes and obtained a mean F1-score of 72.70% of seven common classes, being higher than the best of previous results.

Acoustic emission for diagnosing cable way steel support towers

The paper reports results of the study on the possibility of using the acoustic emission method in diagnosing fatigue and corrosion damage in steel elements of the cable way support towers. The assessment of the sensitivity of the structure to the recorded destructive processes is based on the structural damage classification method using the patterns created as a result of statistical and mathematical processing of acoustic emission signals through image analysis and grouping methods.

A Two-Fold Structural Classification Method for Determining the Accurate Ensemble of Protein Structures

A Two-Fold Structural Classification Method for Determining the Accurate Ensemble of Protein Structures

A Comparative Atlas-Based Recognition of Mild Cognitive Impairment With Voxel-Based Morphometry.

An accurate and reliable brain partition atlas is vital to quantitatively investigate the structural and functional abnormalities in mild cognitive impairment (MCI), generally considered to be a prodromal phase of Alzheimer’s disease. In this paper, we proposed an automated structural classification method to identify MCI from healthy controls (HC) and investigated whether the classification performance was dependent on the brain parcellation schemes, including Automated Anatomical Labeling (AAL-90) atlas, Brainnetome (BN-246) atlas, and AAL-1024 atlas. In detail, structural magnetic resonance imaging (sMRI) data of 69 MCI patients and 63 HC matched well on gender, age, and education level were collected and analyzed with voxel-based morphometry method first, then the volume features of every region of interest (ROI) belonging to the above-mentioned three atlases were calculated and compared between MCI and HC groups, respectively. At last, the abnormal volume features were selected as the classification features for a proposed support vector machine based identification method. After the leave-one-out cross-validation to estimate the classification performance, our results reported accuracies of 83, 92, and 89% with AAL-90, BN-246, and AAL-1024 atlas, respectively, suggesting that future studies should pay more attention to the selection of brain partition schemes in the atlas-based studies. Furthermore, the consistent atrophic brain regions among three atlases were predominately located at bilateral hippocampus, bilateral parahippocampal, bilateral amygdala, bilateral cingulate gyrus, left angular gyrus, right superior frontal gyrus, right middle frontal gyrus, left inferior frontal gyrus, and left precentral gyrus.

Pore structure classification and logging evaluation method for carbonate reservoirs: A case study from an oilfield in the Middle East

ABSTRACTBased on the data of 121 thin sections, 24 mercury injection and physical properties of the carbonate reservoir in A oilfield of the Middle East, the reservoir in the study area is divided into four pore-throat systems by analyzing the pore-throat volume verses permeability-contribution curve of core mercury injection and corresponding depth NMR logging data. Taking into account the contribution of each pore-throat system to the rock, a new pore structure parameter P based on NMR logging data is proposed. On this basis, the P and flow porosity calculated from NMR logging data are used as variables, and the pore structure of carbonate reservoirs is divided into four types by using the K-means clustering method in combination with the characteristics of capillary pressure curves and thin sections. With the input of NMR logging data and conventional logging data, the classification model of pore structure is established by Rotation Forest algorithm. The accuracy of the classification model based on NMR logging is 98.56%, and the accuracy of the classification model based on conventional logging is 89.9%. Compared with the Random Forest algorithm and the Fisher discriminant method, the Rotation Forest algorithm has high prediction accuracy and strong stability. The research shows that the pore structure classification method proposed in this paper is in good agreement with the interpretation results, which can provide some reference value for finding effective reservoirs in the future.

Evaluation of the pore structure of tight sandstone reservoirs based on multifractal analysis: a case study from the Kepingtage Formation in the Shuntuoguole uplift, Tarim Basin, NW China

Both the microscopic pores and the pore structure of a reservoir affect its properties, including permeability and the distribution of oil and gas. Due to the stronger pore structure heterogeneity in tight sandstone reservoirs, it is difficult to characterize the pore structure of tight sandstone with traditional Euclidean geometry. In this study, based on the comprehensive utilization of reservoir data, such as petrophysical property data, mercury injection capillary pressure data and thin sections images, image processing and multifractal analyses are used to classify and describe the pore structure of tight sandstone in the Kepingtage Formation in the Shuntuoguole low uplift, Tarim Basin. The relationships among pore structure parameters, physical properties, and multifractal feature parameters are discussed in detail. Finally, a pore structure classification method using multifractal parameters based on K-means clustering analysis is proposed and applied to tight sandstone. The results show that the pore structure of the Kepingtage Formation can be divided into four types with distinct multifractal characteristics. The multifractal parameters correlate well with the porosity and permeability. The multifractal parameters αmin, αmax, Dmin, and Dmax are positively correlated with the average pore throat radius (rt) but are negatively correlated with displacement pressure (Pd). The parameters αmin, αmax, Dmin, and Dmax are the most sensitive indicators of pore structure and can serve as good indicators of the pore structure type. This pore structure classification method based on multifractal analysis and K-means clustering can be effectively used to classify the pore structure of tight sandstones. This study provides an effective means of pore structure classification and heterogeneity characterization based on thin sections, which is especially valuable in regions without high-pressure mercury injection data.

Reservoir Pore Structure Classification Technology of Carbonate Rock Based on NMR T 2 Spectrum Decomposition

The carbonate reservoir has a number of properties such as multi-type pore space, strong heterogeneity, and complex pore structure, which make the classification of reservoir pore structure extremely difficult. According to nuclear magnetic resonance (NMR) T2 spectrum characteristics of carbonate rock, an automatic pore structure classification and discrimination method based on the T2 spectrum decomposition is proposed. The objective function is constructed based on the multi-variate Gaussian distribution properties of the NMR T2 spectrum. The particle swarm optimization algorithm was used to solve the objective function and get the initial values and then the generalized reduced gradient algorithm was proposed for solving the objective function, which ensured the stability and convergence of the solution. Based on the featured parameters of the Gaussian function such as normalized weights, spectrum peaks and standard deviations, the combinatory spectrum parameters (by multiplying peak value and normalized weight for every peak) are constructed. According to the principle of fuzzy clustering, the carbonate rock pore structure is classified automatically and the discrimination function of each pore structure type is obtained using Fisher discrimination analysis. The classification results were analyzed with the corresponding casting thin section and scanning electron microscopy. The study shows that the type of the pore structure based on the NMR T2 spectrum decomposition is strongly consistent with other methods, which provides a good basis for the quantitative characterization of the carbonate rock reservoir pore space and lays a foundation of the carbonate rock reservoir classification based on NMR logging.

A Novel Decision-Tree Method for Structured Continuous-Label Classification

Structured continuous-label classification is a variety of classification in which the label is continuous in the data, but the goal is to classify data into classes that are a set of predefined ranges and can be organized in a hierarchy. In the hierarchy, the ranges at the lower levels are more specific and inherently more difficult to predict, whereas the ranges at the upper levels are less specific and inherently easier to predict. Therefore, both prediction specificity and prediction accuracy must be considered when building a decision tree (DT) from this kind of data. This paper proposes a novel classification algorithm for learning DT classifiers from data with structured continuous labels. This approach considers the distribution of labels throughout the hierarchical structure during the construction of trees without requiring discretization in the preprocessing stage. We compared the results of the proposed method with those of the C4.5 algorithm using eight real data sets. The empirical results indicate that the proposed method outperforms the C4.5 algorithm with regard to prediction accuracy, prediction specificity, and computational complexity.

Coalbody structure classification method based on dual-lateral and RXO crossplot analysis

According to the positive correlation of coal ash content and natural gamma, using a new coal core reposition method, which is ordered by global and local extreme, coal samples from medium-thickness seam are reasonably located. Integrated the data of coal macrostructure characteristics, coal petrography analysis and coal gas production test, it studies the relationship between coalbody structure and amplitude variation of different well logging data, and the tectonic coal recognition method with well logging data in fresh-water mud invasion. The results show that: the anomalous response of natural gamma ray, neutron, density and apparent resistivity does not reflect the coalbody structure type. In fresh-water drilling mud invasion, using the crossplot technique of dual-lateral, RXO resistivity response and the coalbody structure can classify granulated coal accurately; the proposed method is of good practicability and high reliability.

Urban structure classification using the 3D normal distribution transform for practical robot applications

Previous urban structure classification methods are intractable for practical robots in two viewpoints: storing point clouds and complex computation for using conditional random fields. This paper presents a classification method based on normal distribution transform (NDT) grids for practical robots. NDT grids store point clouds in the form of the mean and covariance, instead of directly dealing with huge point clouds. By taking the advantage of NDT grids, we design geometric-featured voxel (GFV) based on NDT grids to represent urban structures as a voxel model. The proposed method consists of three steps: GFV generation, segmentation, and classification. In the segmentation, GFVs are clustered according to units of urban structures by spectral clustering. For the classification, the clustered GFVs are classified as one kind of urban structures by supervised learning. Geometric characteristics of urban structures are expressed by a histogram of geometric words. Experimental results prove that the proposed method based on NDT grids is suitable for practical robots in terms of memory requirement, computation time, and even classification accuracy.

Survey of Decision-Tree Method for Structured Continuous-Label Classification

Structured continuous-label classification is a variety of classification in which the label is continuous in the data, but the goal is to classify data into classes that are a set of predefined ranges and can be organised in a hierarchy. In traditional decision (classification) tree algorithms, categorical (class) variable as the label is assumed. When the label is a continuous variable in the data, two achievable approaches based on existing DT algorithms can be used to handle the situations. For the first approach uses a data discretisation method in the preprocessing stage to convert the continuous label into a class label defined by a finite set of non-overlapping intervals and then applies a DT algorithm. In the second approach using the continuous label directly, simply applies a regression tree algorithm. These approaches have their own drawbacks. In the hierarchy, the ranges at the lower levels are more specific and inherently more difficult to predict, whereas the ranges at the upper levels are less specific and inherently easier to predict. Therefore, both prediction specificity and prediction accuracy must be considered when building a DT from this kind of data. In this survey paper, we survey the classification techniques related to the continuous label. More classification approaches are there in the literature. The main goal of the survey is present an overview of previous classification techniques. Various methods that are written by the different authors are presented in this survey.

Structural Classification Methods Based on Weighted Finite-State Transducers for Automatic Speech Recognition

The potential of structural classification methods for automatic speech recognition (ASR) has been attracting the speech community since they can realize the unified modeling of acoustic and linguistic aspects of recognizers. However, the structural classification approaches involve well-known tradeoffs between the richness of features and the computational efficiency of decoders. If we are to employ, for example, a frame-synchronous one-pass decoding technique, features considered to calculate the likelihood of each hypothesis must be restricted to the same form as the conventional acoustic and language models. This paper tackles this limitation directly by exploiting the structure of the weighted finite-state transducers (WFSTs) used for decoding. Although WFST arcs provide rich contextual information, close integration with a computationally efficient decoding technique is still possible since most decoding techniques only require that their likelihood functions are factorizable for each decoder arc and time frame. In this paper, we compare two methods for structural classification with the WFST-based features; the structured perceptron and conditional random field (CRF) techniques. To analyze the advantages of these two classifiers, we present experimental results for the TIMIT continuous phoneme recognition task, the WSJ transcription task, and the MIT lecture transcription task. We confirmed that the proposed approach improved the ASR performance without sacrificing the computational efficiency of the decoders, even though the baseline systems are already trained with discriminative training techniques (e.g., MPE).

Cutoff Scanning Matrix (CSM): structural classification and function prediction by protein inter-residue distance patterns

BackgroundThe unforgiving pace of growth of available biological data has increased the demand for efficient and scalable paradigms, models and methodologies for automatic annotation. In this paper, we present a novel structure-based protein function prediction and structural classification method: Cutoff Scanning Matrix (CSM). CSM generates feature vectors that represent distance patterns between protein residues. These feature vectors are then used as evidence for classification. Singular value decomposition is used as a preprocessing step to reduce dimensionality and noise. The aspect of protein function considered in the present work is enzyme activity. A series of experiments was performed on datasets based on Enzyme Commission (EC) numbers and mechanistically different enzyme superfamilies as well as other datasets derived from SCOP release 1.75.ResultsCSM was able to achieve a precision of up to 99% after SVD preprocessing for a database derived from manually curated protein superfamilies and up to 95% for a dataset of the 950 most-populated EC numbers. Moreover, we conducted experiments to verify our ability to assign SCOP class, superfamily, family and fold to protein domains. An experiment using the whole set of domains found in last SCOP version yielded high levels of precision and recall (up to 95%). Finally, we compared our structural classification results with those in the literature to place this work into context. Our method was capable of significantly improving the recall of a previous study while preserving a compatible precision level.ConclusionsWe showed that the patterns derived from CSMs could effectively be used to predict protein function and thus help with automatic function annotation. We also demonstrated that our method is effective in structural classification tasks. These facts reinforce the idea that the pattern of inter-residue distances is an important component of family structural signatures. Furthermore, singular value decomposition provided a consistent increase in precision and recall, which makes it an important preprocessing step when dealing with noisy data.

Identification and classification of uncertainties in the application of environmental models

In the support of environmental management, models are frequently used. The outcomes of these models however, rarely show a perfect resemblance to the real-world system behavior. This is due to uncertainties, introduced during the process of abstracting information about the system to include it in the model. To provide decision makers with realistic information about these model outcomes, uncertainty analysis is indispensable. Because of the multiplicity of frameworks available for uncertainty analysis, the outcomes of such analyses are rarely comparable. In this paper a method for structured identification and classification of uncertainties in the application of environmental models is presented. We adapted an existing uncertainty framework to enhance the objectivity in the uncertainty identification process. Two case studies demonstrate how it can help to obtain an overview of unique uncertainties encountered in a model. The presented method improves the comparability of uncertainty analyses in different model studies and leads to a coherent overview of uncertainties affecting model outcomes.

Systematic comparison of SCOP and CATH: a new gold standard for protein structure analysis

BackgroundSCOP and CATH are widely used as gold standards to benchmark novel protein structure comparison methods as well as to train machine learning approaches for protein structure classification and prediction. The two hierarchies result from different protocols which may result in differing classifications of the same protein. Ignoring such differences leads to problems when being used to train or benchmark automatic structure classification methods. Here, we propose a method to compare SCOP and CATH in detail and discuss possible applications of this analysis.ResultsWe create a new mapping between SCOP and CATH and define a consistent benchmark set which is shown to largely reduce errors made by structure comparison methods such as TM-Align and has useful further applications, e.g. for machine learning methods being trained for protein structure classification. Additionally, we extract additional connections in the topology of the protein fold space from the orthogonal features contained in SCOP and CATH.ConclusionVia an all-to-all comparison, we find that there are large and unexpected differences between SCOP and CATH w.r.t. their domain definitions as well as their hierarchic partitioning of the fold space on every level of the two classifications. A consistent mapping of SCOP and CATH can be exploited for automated structure comparison and classification.AvailabilityBenchmark sets and an interactive SCOP-CATH browser are available at .

Automatic detection of preclinical neurodegeneration

Treatment of neurodegenerative diseases is likely to be most beneficial in the very early, possibly preclinical stages of degeneration. We explored the usefulness of fully automatic structural MRI classification methods for detecting subtle degenerative change. The availability of a definitive genetic test for Huntington disease (HD) provides an excellent metric for judging the performance of such methods in gene mutation carriers who are free of symptoms. Using the gray matter segment of MRI scans, this study explored the usefulness of a multivariate support vector machine to automatically identify presymptomatic HD gene mutation carriers (PSCs) in the absence of any a priori information. A multicenter data set of 96 PSCs and 95 age- and sex-matched controls was studied. The PSC group was subclassified into three groups based on time from predicted clinical onset, an estimate that is a function of DNA mutation size and age. Subjects with at least a 33% chance of developing unequivocal signs of HD in 5 years were correctly assigned to the PSC group 69% of the time. Accuracy improved to 83% when regions affected by the disease were selected a priori for analysis. Performance was at chance when the probability of developing symptoms in 5 years was less than 10%. Presymptomatic Huntington disease gene mutation carriers close to estimated diagnostic onset were successfully separated from controls on the basis of single anatomic scans, without additional a priori information. Prior information is required to allow separation when degenerative changes are either subtle or variable.

Structural image analysis methods to classify dendritic structures

There are many possible approaches for direct image classification of dendritic crystals. Dendritic crystallization can be observed by iron in special conditions; common examples are fern leafs or dendritic crystallized snowflakes. This contribution is especially focused on the new structural classification methods we used (Hough transform, fractal dimension estimation, and fuzzy assisted filtering and classification) and relates to our previous contribution. It contains the discriminatory analysis results of all methods we have used so far as well.

Protein structure alignment considering phenotypic plasticity

Protein structure comparison exhibits differences and similarities of proteins and protein families and may help to elucidate protein sequence and structure evolution. Despite many methods to score protein structure similarity with and without flexibility and to align proteins accurately based on their structures, a meaningful evolutionary distance measure and alignment method which models the cost of mutations, insertions and deletions occurring in protein sequences on the structure level is still missing. Here, we introduce a new measure for protein structure similarity and propose a novel method called phenotypic plasticity method (PPM) which explicitly tries to model the evolutionary distance of two proteins on the structure level by measuring the cost of 'morphing' one structure into the other one. PPM aligns protein structures taking variations naturally observed in groups of structures ('phenotypic plasticity') into account while preserving the overall topological arrangement of the structures. The performance of PPM in detecting similarities between protein structures is evaluated against well-known structure classification methods on two benchmark sets. The larger set consists of more than 3.6 million structure pairs from the SCOP database which are also consistently classified in CATH. In the current parameterization, PPM already performs comparable or better than other methods such as TM-Align and Vorolign on those two sets according to various evaluation criteria showing that the method is able to reliably classify known protein structures, to detect their similarities and to compute accurate alignments despite phenotypic plasticity. Executables are available upon request. Datasets and supplementary data (datasets and superpositions) can be accessed on http://www.bio. ifi.lmu.de/PPM.