Support Vector Machine Clustering Research Articles

Using Bioinformatic Approaches to Identify Pathways Targeted by Human Leukemogens

We have applied bioinformatic approaches to identify pathways common to chemical leukemogens and to determine whether leukemogens could be distinguished from non-leukemogenic carcinogens. From all known and probable carcinogens classified by IARC and NTP, we identified 35 carcinogens that were associated with leukemia risk in human studies and 16 non-leukemogenic carcinogens. Using data on gene/protein targets available in the Comparative Toxicogenomics Database (CTD) for 29 of the leukemogens and 11 of the non-leukemogenic carcinogens, we analyzed for enrichment of all 250 human biochemical pathways in the Kyoto Encyclopedia of Genes and Genomes (KEGG) database. The top pathways targeted by the leukemogens included metabolism of xenobiotics by cytochrome P450, glutathione metabolism, neurotrophin signaling pathway, apoptosis, MAPK signaling, Toll-like receptor signaling and various cancer pathways. The 29 leukemogens formed 18 distinct clusters comprising 1 to 3 chemicals that did not correlate with known mechanism of action or with structural similarity as determined by 2D Tanimoto coefficients in the PubChem database. Unsupervised clustering and one-class support vector machines, based on the pathway data, were unable to distinguish the 29 leukemogens from 11 non-leukemogenic known and probable IARC carcinogens. However, using two-class random forests to estimate leukemogen and non-leukemogen patterns, we estimated a 76% chance of distinguishing a random leukemogen/non-leukemogen pair from each other.

Vehicle Classification Method Based on Single-Point Magnetic Sensor

In this paper a novel and scientific vehicle classification method is proposed, which is used on a new single-point magnetic sensor. The original waveform is transformed into numerical format by the data fusion technology for feature extraction. The extracted feature subsets are evaluated by Filter-Filter-Wrapper model, and then the nonredundant feature subset which fully reflects the difference of various vehicle types and is adaptable to the vehicle classifier is determined. On the basis of the optimal feature subset, this paper provides a novel vehicle classification algorithm based on Clustering Support Vector Machines(C-SVM). Particle Swarm Optimization (PSO) is used to search the optimal kernel parameter and slack penalty parameter. The cross-validation result of 460 samples shows that the classification rate of proposed vehicle classification method is better than 99%. It demonstrates that the vehicle classification method would be able to enhance efficiency of data mining, capability of machine learning and accuracy of vehicle classification.

Bayes Clustering and Structural Support Vector Machines for Segmentation of Carotid Artery Plaques in Multicontrast MRI

Accurate segmentation of carotid artery plaque in MR images is not only a key part but also an essential step for in vivo plaque analysis. Due to the indistinct MR images, it is very difficult to implement the automatic segmentation. Two kinds of classification models, that is, Bayes clustering and SSVM, are introduced in this paper to segment the internal lumen wall of carotid artery. The comparative experimental results show the segmentation performance of SSVM is better than Bayes.

Protein Local Structure Prediction through Improved Clustering Support Vector Machines (ICSVM)

Accurate protein secondary structure prediction plays an important role in direct tertiary structure modeling, and can also significantly enhance sequence analysis and sequence-structure threading for structure and function determination. Understanding the sequence-to-structure relationship is a central task in bioinformatics. Adequate knowledge about this can improve the accuracy for protein structure prediction. The conventional algorithm such as clustering and SVM can not reveal the complex nonlinear relationship adequately on a huge amount of data individually. So the model CSVMs (Clustering Support Vector Machines) was designed by merging the concept of both clustering and SVM. It has been seen that the generalization power for CSVMs is strong enough to recognize the complicated pattern of sequence-to-structure relationships. CSVMs can only predict the protein local structure with which it is being trained. But if a new type of protein segment comes then it may happen that the CSVMs will fail. That is, none of the cluster will treat it as a positive sample. So in this paper we introduced another robust method called Improved Support Vector Machines (ICSVM) which can handle the unseen example efficiently. Keywords: Clustering algorithm, SVM, Protein structure prediction, CSVMs, ICSVM.

Turbopump Condition Monitoring Using Incremental Clustering and One-class Support Vector Machine

: Turbopump condition monitoring is a significant approach to ensure the safety of liquid rocket engine (LRE). Because of lack of fault samples, a monitoring system cannot be trained on all possible condition patterns. Thus it is important to differentiate abnormal or unknown patterns from normal pattern with novelty detection methods. One-class support vector machine (OCSVM) that has been commonly used for novelty detection cannot deal well with large scale samples. In order to model the normal pattern of the turbopump with OCSVM and so as to monitor the condition of the turbopump, a monitoring method that integrates OCSVM with incremental clustering is presented. In this method, the incremental clustering is used for sample reduction by extracting representative vectors from a large training set. The representative vectors are supposed to distribute uniformly in the object region and fulfill the region. And training OCSVM on these representative vectors yields a novelty detector. By applying this method to the analysis of the turbopump’s historical test data, it shows that the incremental clustering algorithm can extract 91 representative points from more than 36 000 training vectors, and the OCSVM detector trained on these 91 representative points can recognize spikes in vibration signals caused by different abnormal events such as vane shedding, rub-impact and sensor faults. This monitoring method does not need fault samples during training as classical recognition methods. The method resolves the learning problem of large samples and is an alternative method for condition monitoring of the LRE turbopump

Metabolomic analysis of liver and skeletal muscle tissues in C57BL/6J and DBA/2J mice exposed to 2,3,7,8-tetrachlorodibenzo-p-dioxin

2,3,7,8-Tetrachlorodibenzo-p-dioxin (TCDD) has been demonstrated to have the adverse effects on human health. In this study, we applied a metabolomic approach in conjunction with unsupervised and supervised machine learning methods to investigate the toxic effects of TCDD. By using liquid chromatography/quadrupole time-of-flight mass spectrometry, non-targeted metabolomic analysis revealed the metabolic signatures of the toxicity in aryl hydrocarbon receptor (AhR)-high affinity C57BL/6J (C6) mice as well as low affinity strain-DBA/2J (D2) mice. Lysophospholipids and long chain fatty acids were strikingly elevated in the C6 mice exposed to TCDD in both liver and skeletal muscle tissues. Meanwhile, the level of palmitoylcarnitine, which is one of the important indicators in fatty acid β-oxidation, increased significantly. Moreover, several nucleosides and amino acids decreased markedly. On the other hand, much less differentiating metabolites were highlighted in another strain-D2 mouse model. Taking liver and skeletal muscle tissues together, the levels of inosine, valine and glutamine decreased significantly. One lysophospholipid and two fatty acids were found to be enhanced. The principal components analysis and support vector machine clustering results also exhibited discriminations in the liver and skeletal muscle tissues of the mice. The obtained results indicated that TCDD could disrupt several metabolic pathways, including fatty acid biosynthesis and amino acid metabolism in both C6 and D2 mice. The increased rate of fatty acid beta-oxidation, however, was only observed in the liver and skeletal muscle tissues of C6 mice. The perturbation of the tricarboxylic acid (TCA) cycle was testified in two strains but the change was much slighter in D2 mice. It was of particular interest to note that the succinate level was enhanced in the liver tissues of both strains, and particularly, the change was up to 11.49-fold in the liver of C6 mice treated with TCDD. Collectively, the discrimination of D2 mice was not as distinct as that of C6 mice when exposed to the same dosage. Furthermore, D2 was confirmed to be less-sensitive rather than resistant to a high dose of TCDD.

Analytical and Chemometric Evaluation of the Situation of Waterbodies in the Polish Tatra Mountains

AbstractChemometric methods are powerful in finding hidden structures and latent information in environmental and other analytical datasets. This work shows the application of cluster analysis, discriminant analysis, and support vector machines for the evaluation of waterbodies in the Polish Tatra Mountains. After the analysis of in situ parameters and the determination of concentrations of cations and anions, cluster analysis shows that the previous separation into Western Tatras and High Tatras should be reconsidered, as the Bystra stream in the border region might have been incorrectly assigned to the Western Tatras up to now. Discriminant analysis not only confirms the geographical separation of waterbodies, but also the fact that the sampling time is a crucial factor in environmental analysis. Samples taken in different months do not result in a homogenous object of investigation. A uniform date should therefore be chosen so that the results will be comparable. The influence of the sampling month on the classification of samples is also approved by support vector machines.

Multi-class cluster support vector machines

Based on the idea of nonparallel hyperplanes,a novel multi-class cluster support vector machine method was proposed to settle the multi-class classification problem of support vector machines.For a k-class classification problem,it trained k-hyperplanes respectively,and each one lay as close as possible to self-class while being apart from the rest classes as far as possible.Then,labels of new samples were determined by the class of their nearest hyperplane,thus the inherent limitations of One-Against-One(OAO) and One-Against-All(OAA) methods can be avoided,such as "decision blind-area" and "unbalanced classes".Finally,experiments on UCI and HCL2000 datasets show that the proposed method significantly outperforms traditional OAO and OAA in terms of recognition accuracy.

Fault diagnosis for ship sewage treatment equipment based on clustering support vector machine

To solve the problems of condition monitoring and fault diagnosis for ship sewage treatment equipment, a fault diagnosis model based on clustering Support Vector Machines (SVM) was proposed. In the model, the neural network clustering algorithm was used to realize clustering analysis and to obtain the normal subspaces and the abnormal subspaces in the condition monitoring sample space. Then, to the abnormal subspaces, the multi-classification SVM based on binary tree architecture was designed to carry out the fault diagnosis and recognition. Compared with the traditional SVM learning algorithms, the proposed algorithm avoided the blind classification and improved the classification performance in some extent. The model was applied to a ship sewage treatment equipment to train and exam the measured samples. Experiment results show this method has good generalization and expendibility.

The Sleipnir library for computational functional genomics

Motivation: Biological data generation has accelerated to the point where hundreds or thousands of whole-genome datasets of various types are available for many model organisms. This wealth of data can lead to valuable biological insights when analyzed in an integrated manner, but the computational challenge of managing such large data collections is substantial. In order to mine these data efficiently, it is necessary to develop methods that use storage, memory and processing resources carefully.Results: The Sleipnir C++ library implements a variety of machine learning and data manipulation algorithms with a focus on heterogeneous data integration and efficiency for very large biological data collections. Sleipnir allows microarray processing, functional ontology mining, clustering, Bayesian learning and inference and support vector machine tasks to be performed for heterogeneous data on scales not previously practical. In addition to the library, which can easily be integrated into new computational systems, prebuilt tools are provided to perform a variety of common tasks. Many tools are multithreaded for parallelization in desktop or high-throughput computing environments, and most tasks can be performed in minutes for hundreds of datasets using a standard personal computer.Availability: Source code (C++) and documentation are available at http://function.princeton.edu/sleipnir and compiled binaries are available from the authors on request.Contact: ogt@princeton.edu

Comparative Proteomic Analysis of Non-small-cell Lung Cancer and Normal Controls Using Serum Label-Free Quantitative Shotgun Technology

The aim of this study was to distinguish non-small-cell lung cancer from normal controls and explore the new potential biomarkers of lung cancer by serum proteomics technology. Label-free quantitative liquid chromatography tandem mass spectrometry (1D-LC/MS/MS) analysis was performed on eight non-small-cell lung cancer (NSCLC) serum samples and eight normal controls. The proteomic data we obtained was analyzed by normalized, randomly paired t test and integrated bioinformatic methods, including hierarchical clustering analysis, principal-component analysis, and support vector machine. We obtained 931 proteins with at least two peptides identified from the 16 serum samples, and 62 proteins were differentially expressed between non-small-cell lung cancer patients and normal controls. There were 16 proteins expressed much higher in the lung cancer group than in the controls. Two hundred eight proteins were shared in all 16 serum samples. Through hierarchical clustering analysis and principal-component analysis based on the 62 differentially expressed proteins, we could distinguish non-small-cell lung cancer from the normal controls. The prediction accuracy of non-small-cell lung cancer analyzed by the support vector machine algorithm based on 208 proteins which were shared in all serum samples is 93.75%. Protein expression patterns have changed in the serum of non-small-cell lung cancer patients. Label-free quantitative LC/MS/MS may be a good method to improve the diagnostic accuracy for lung cancer and it can help in discovering the new biomarkers.

Non-linear system modelling via online clustering and fuzzy support vector machines

This paper describes a novel non-linear modelling approach by online clustering, fuzzy rules and support vector machine. Structure identification is realised by an online clustering method and fuzzy support vector machines, and the fuzzy rules are generated automatically. Time-varying learning rates are applied for updating the membership functions of the fuzzy rules. Finally, the upper bounds of the modelling errors are proven.

Support Vector Machine Implementations for Classification & Clustering

BackgroundWe describe Support Vector Machine (SVM) applications to classification and clustering of channel current data. SVMs are variational-calculus based methods that are constrained to have structural risk minimization (SRM), i.e., they provide noise tolerant solutions for pattern recognition. The SVM approach encapsulates a significant amount of model-fitting information in the choice of its kernel. In work thus far, novel, information-theoretic, kernels have been successfully employed for notably better performance over standard kernels. Currently there are two approaches for implementing multiclass SVMs. One is called external multi-class that arranges several binary classifiers as a decision tree such that they perform a single-class decision making function, with each leaf corresponding to a unique class. The second approach, namely internal-multiclass, involves solving a single optimization problem corresponding to the entire data set (with multiple hyperplanes).ResultsEach SVM approach encapsulates a significant amount of model-fitting information in its choice of kernel. In work thus far, novel, information-theoretic, kernels were successfully employed for notably better performance over standard kernels. Two SVM approaches to multiclass discrimination are described: (1) internal multiclass (with a single optimization), and (2) external multiclass (using an optimized decision tree). We describe benefits of the internal-SVM approach, along with further refinements to the internal-multiclass SVM algorithms that offer significant improvement in training time without sacrificing accuracy. In situations where the data isn't clearly separable, making for poor discrimination, signal clustering is used to provide robust and useful information – to this end, novel, SVM-based clustering methods are also described. As with the classification, there are Internal and External SVM Clustering algorithms, both of which are briefly described.

Clustering support vector machines for protein local structure prediction

Abstract Understanding the sequence-to-structure relationship is a central task in bioinformatics research. Adequate knowledge about this relationship can potentially improve accuracy for local protein structure prediction. One of approaches for protein local structure prediction uses the conventional clustering algorithms to capture the sequence-to-structure relationship. The cluster membership function defined by conventional clustering algorithms may not reveal the complex nonlinear relationship adequately. Compared with the conventional clustering algorithms, Support Vector Machine (SVM) can capture the nonlinear sequence-to-structure relationship by mapping the input space into another higher dimensional feature space. However, SVM is not favorable for huge datasets including millions of samples. Therefore, we propose a novel computational model called Clustering Support Vector Machines (CSVMs). Taking advantage of both theory of granular computing and advanced statistical learning methodology, CSVMs are built specifically for each information granule partitioned intelligently by the clustering algorithm. This feature makes learning tasks for each CSVM more specific and simpler. CSVMs modeled for each granule can be easily parallelized so that CSVMs can be used to handle complex classification problems for huge datasets. Average accuracy for CSVMs is over 80%, which indicates that the generalization power for CSVMs is strong enough to recognize the complicated pattern of sequence-to-structure relationships. Compared with the conventional clustering algorithm, our experimental results show that accuracy for local structure prediction has been improved noticeably when CSVMs are applied.

Extracting predicates from mining models for efficient query evaluation

Modern relational database systems are beginning to support ad hoc queries on mining models. In this article, we explore novel techniques for optimizing queries that contain predicates on the results of application of mining models to relational data. For such queries, we use the internal structure of the mining model to automatically derive traditional database predicates. We present algorithms for deriving such predicates for a large class of popular discrete mining models: decision trees, naive Bayes, clustering and linear support vector machines. Our experiments on Microsoft SQL Server demonstrate that these derived predicates can significantly reduce the cost of evaluating such queries.