SEARCH · PubMed Health

Results for “Clustering Algorithms”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,693 records · Page 94Linked to original sources

PubMed2005

Segmentation of complex cell clusters in microscopic images: application to bone marrow samples.

BACKGROUND: Morphologic examination of bone marrow and peripheral blood samples continues to be the cornerstone in diagnostic hematology. In recent years, interest in automatic leukocyte classification using image analysis has increased rapidly. Such systems collect a series of images in which each cell must be segmented accurately to be classified correctly. Although segmentation algorithms have been developed for sparse cells in peripheral blood, the problem of segmenting the complex cell clusters characterizing bone marrow images is harder and has not been addressed previously. METHODS: We present a novel algorithm for segmenting clusters of any number of densely packed cells. The algorithm first oversegments the image into cell subparts. These parts are then assembled into complete cells by solving a combinatorial optimization problem in an efficient way. RESULTS: Our experimental results show that the algorithm succeeds in correctly segmenting densely clustered leukocytes in bone marrow images. CONCLUSIONS: The presented algorithm enables image analysis-based analysis of bone marrow samples for the first time and may also be adopted for other digital cytometric applications where separation of complex cell clusters is required.

Algorithms↗

PubMed2006

TreeSOM: Cluster analysis in the self-organizing map.

Clustering problems arise in various domains of science and engineering. A large number of methods have been developed to date. The Kohonen self-organizing map (SOM) is a popular tool that maps a high-dimensional space onto a small number of dimensions by placing similar elements close together, forming clusters. Cluster analysis is often left to the user. In this paper we present the method TreeSOM and a set of tools to perform unsupervised SOM cluster analysis, determine cluster confidence and visualize the result as a tree facilitating comparison with existing hierarchical classifiers. We also introduce a distance measure for cluster trees that allows one to select a SOM with the most confident clusters.

Age Factors↗

PubMed1997

Recognition of temporally changing action potentials in multiunit neural recordings.

We present a method to iteratively train an artificial neural network (ANN) or other supervised pattern classifier in order to adaptively recognize and track temporally changing patterns. This method uses recently acquired data and the existing classifier to create new training sets, from which a new classifier is then trained. The procedure is repeated periodically using the most recently trained classifier. This scheme was evaluated by applying it to simulated situations that arise in chronic recordings of multiunit neural activity from peripheral nerves. The method was able to track the changes in these simulated chronic recordings and to provide better unit recognition rates than an unsupervised clustering method suited to this problem.

Action Potentials↗

PubMed2006

Determination of the minimum number of microarray experiments for discovery of gene expression patterns.

BACKGROUND: One type of DNA microarray experiment is discovery of gene expression patterns for a cell line undergoing a biological process over a series of time points. Two important issues with such an experiment are the number of time points, and the interval between them. In the absence of biological knowledge regarding appropriate values, it is natural to question whether the behaviour of progressively generated data may by itself determine a threshold beyond which further microarray experiments do not contribute to pattern discovery. Additionally, such a threshold implies a minimum number of microarray experiments, which is important given the cost of these experiments. RESULTS: We have developed a method for determining the minimum number of microarray experiments (i.e. time points) for temporal gene expression, assuming that the span between time points is given and the hierarchical clustering technique is used for gene expression pattern discovery. The key idea is a similarity measure for two clusterings which is expressed as a function of the data for progressive time points. While the experiments are underway, this function is evaluated. When the function reaches its maximum, it indicates the set of experiments reach a saturated state. Therefore, further experiments do not contribute to the discrimination of patterns. CONCLUSION: The method has been verified with two previously published gene expression datasets. For both experiments, the number of time points determined with our method is less than in the published experiments. It is noted that the overall approach is applicable to other clustering techniques.

Algorithms↗

PubMed2003

Multistage gene expression profiling in a differentially susceptible mouse colon cancer model.

The DNA alkylating agent, azoxymethane (AOM), induces tumor formation in the distal colon of susceptible mice. Differential susceptibility to this colonotropic carcinogen has been well characterized in A/J (sensitive) and AKR/J (resistant) mice. However, the reasons underlying the differential response to AOM and the molecular mechanisms involved in colon tumor progression remain unclear. To address these issues, we used a cDNA microarray approach to determine time-related changes in gene expression patterns in A/J and AKR/J colons following carcinogen treatment. In the present study, mice were injected intraperitoneally with either AOM (10mg/kg body weight once a week for 6 weeks) or 0.9% NaCl solution (vehicle controls). Total RNA was isolated from the distal colons at 1, 4, and 24 weeks post-AOM exposure. RNA was reverse transcribed and cDNA samples labeled with Cy3 and Cy5 were hybridized to a glass chip containing 4608 mouse cDNA duplicate clones. The resulting mRNA expression levels were analyzed using GLEAMS 3.0, a Unix/Linux-based software program. Genes with more than twofold variations in expression levels were considered significant. Further clustering analysis was performed based on gene expression patterns at different time points using a novel adaptive centroid algorithm (ACA). Of the 4608 genes, 118 clustered into 11 significant groups that displayed similar and distinct expression patterns between the strains following carcinogen treatment. Nine clusters were selected for further analysis based on their divergence in response between A/J and AKR/J and their potential role in tumorigenesis. Overall, our data indicate time- and strain-specific genetic alterations during different stages of colon tumorigenesis following AOM treatment.

Adenocarcinoma↗

PubMed2004

Biclustering in gene expression data by tendency.

The advent of DNA microarray technologies has revolutionized the experimental study of gene expression. Clustering is the most popular approach of analyzing gene expression data and has indeed proven to be successful in many applications. Our work focuses on discovering a subset of genes which exhibit similar expression patterns along a subset of conditions in the gene expression matrix. Specifically, we are looking for the Order Preserving clusters (OPCluster), in each of which a subset of genes induce a similar linear ordering along a subset of conditions. The pioneering work of the OPSM model[3], which enforces the strict order shared by the genes in a cluster, is included in our model as a special case. Our model is more robust than OPSM because similarly expressed conditions are allowed to form order equivalent groups and no restriction is placed on the order within a group. Guided by our model, we design and implement a deterministic algorithm, namely OPCTree, to discover OP-Clusters. Experimental study on two real datasets demonstrates the effectiveness of the algorithm in the application of tissue classification and cell cycle identification. In addition, a large percentage of OP-Clusters exhibit significant enrichment of one or more function categories, which implies that OP-Clusters indeed carry significant biological relevance.

Algorithms↗

PubMed2004

Validating the independent components of neuroimaging time series via clustering and visualization.

Recently, independent component analysis (ICA) has been widely used in the analysis of brain imaging data. An important problem with most ICA algorithms is, however, that they are stochastic; that is, their results may be somewhat different in different runs of the algorithm. Thus, the outputs of a single run of an ICA algorithm should be interpreted with some reserve, and further analysis of the algorithmic reliability of the components is needed. Moreover, as with any statistical method, the results are affected by the random sampling of the data, and some analysis of the statistical significance or reliability should be done as well. Here we present a method for assessing both the algorithmic and statistical reliability of estimated independent components. The method is based on running the ICA algorithm many times with slightly different conditions and visualizing the clustering structure of the obtained components in the signal space. In experiments with magnetoencephalographic (MEG) and functional magnetic resonance imaging (fMRI) data, the method was able to show that expected components are reliable; furthermore, it pointed out components whose interpretation was not obvious but whose reliability should incite the experimenter to investigate the underlying technical or physical phenomena. The method is implemented in a software package called Icasso.

Algorithms↗

PubMed2005

Cluster analysis: a useful tool for the analysis of cerebral laser-Doppler scanning data.

Laser-Doppler (LD) fluxmetry (LDF) is a widely used method for the measurement of relative tissue perfusion. Assessing LD-flux at multiple locations using a scanning technique greatly reduces movement artefacts and makes repetitive measurements at the same location possible. However, measurements in brain are often confounded by superficial cortical vessels. Commonly applied strategies to circumvent this problem, such as defining a cut-off point to exclude the high flux data of vessels or calculating the median from multiple locations to estimate regional cerebral blood flow (rCBF) all have specific shortcomings. The aim of this study was to analyse LD-data by mathematically discriminating between parenchymal and vessel data based on the distribution of flux data. Data was obtained by scanning the cortex of 15 male Sprague-Dawley rats using a matrix of 6x10 equidistant (500 microm) points. Standard statistical analysis as well as cluster analysis using the complete linkage algorithm was performed. The LD-data showed a bimodal frequency distribution with low values representing parenchymal and high values representing vessel flux. Parenchyma and vessels were reliably discriminated by cluster analysis. This was shown by mapping the vessel clusters on the scan matrix with the location of the superficial cortical vessels using Chi-square testing (p<0.0001). The parenchymal data followed a Gaussian normal distribution (p<0.851), whereas the vessel data did not (p<0.0001). Thus, cluster analysis is useful to discriminate parenchymal from vessel flux, thereby significantly improving the accuracy of LD-scanning data.

Algorithms↗

PubMed2006

Rapid tracking of small displacements with ultrasound.

Time-delay estimators, such as normalized cross correlation and phase-shift estimation, form the computational basis for elastography, blood flow measurements, and acoustic radiation force impulse (ARFI) imaging. This paper examines the performance of these algorithms for small displacements (less than half the ultrasound pulse wavelength). The effects of noise, bandwidth, stationary echoes, kernel size, downsampling, interpolation, and quadrature demodulation on the accuracy of the time delay estimates are measured in terms of bias and jitter. Particular attention is given to the accuracy and resolution of the displacement measurements and to the computational efficiency of the algorithms. In most cases, Loupas' two-dimensional (2-D) autocorrelator performs as well as the gold standard, normalized cross correlation. However, Loupas' algorithm's calculation time is significantly faster, and it is particularly suited to operate on the signal data format most commonly used in ultrasound scanners. These results are used to implement a real-time ARFI imaging system using a commercial ultrasound scanner and a computer cluster. Images processed with the algorithms are examined in an ex vivo liver ablation study.

Algorithms↗

PubMed2005

EXPANDER--an integrative program suite for microarray data analysis.

BACKGROUND: Gene expression microarrays are a prominent experimental tool in functional genomics which has opened the opportunity for gaining global, systems-level understanding of transcriptional networks. Experiments that apply this technology typically generate overwhelming volumes of data, unprecedented in biological research. Therefore the task of mining meaningful biological knowledge out of the raw data is a major challenge in bioinformatics. Of special need are integrative packages that provide biologist users with advanced but yet easy to use, set of algorithms, together covering the whole range of steps in microarray data analysis. RESULTS: Here we present the EXPANDER 2.0 (EXPression ANalyzer and DisplayER) software package. EXPANDER 2.0 is an integrative package for the analysis of gene expression data, designed as a 'one-stop shop' tool that implements various data analysis algorithms ranging from the initial steps of normalization and filtering, through clustering and biclustering, to high-level functional enrichment analysis that points to biological processes that are active in the examined conditions, and to promoter cis-regulatory elements analysis that elucidates transcription factors that control the observed transcriptional response. EXPANDER is available with pre-compiled functional Gene Ontology (GO) and promoter sequence-derived data files for yeast, worm, fly, rat, mouse and human, supporting high-level analysis applied to data obtained from these six organisms. CONCLUSION: EXPANDER integrated capabilities and its built-in support of multiple organisms make it a very powerful tool for analysis of microarray data. The package is freely available for academic users at http://www.cs.tau.ac.il/~rshamir/expander.

Algorithms↗

PubMed2005

Identification of non-cross-resistant platinum compounds with novel cytotoxicity profiles using the NCI anticancer drug screen and clustered image map visualizations.

The widespread clinical use of platinum compounds in cancer chemotherapy has prompted a search for new platinum agents. To search for platinum agents with novel profiles of activity, we used clustered image maps, the COMPARE algorithm, and other numerical methods to analyze platinum compounds submitted to the National Cancer Institute's anticancer drug screen and tested against the screen's 60 diverse human cancer cell lines (the NCI-60). A total of 107 platinum compounds for which the data were adequate could be clustered into 12 groups, 11 of which were characterized by distinctive activity profiles against the cell lines. Each group (except the mixed one) was then found to have a characteristic chemical structure as well. Four of the groups were subjected to further analysis. Mean graph representations of the averaged activity profiles of the different groups served to highlight their similarities and differences. To identify compounds that might retain activity in the setting of resistance to clinically used platinum compounds, we determined the activity levels of 38 of the compounds (representative of the different activity-structure groups) against cisplatin and oxaliplatin-resistant ovarian cancer cell lines. Many of the compounds retained activity against the resistant cells, providing evidence that they differ from cisplatin and oxaliplatin, not only in their selective activity against the various NCI-60 cell types, but are also in their susceptibility to mechanisms of resistance. Since platinum compounds have generally been classified as alkylating agents, we also compared their patterns of activity with those of representative alkylating agents, with NCI-60 growth rates, and with the profiles of 1582 molecular markers in the NCI-60 cells. Much more analysis remains to be done, but the absence of any definitive, biologically interpretable molecular predictor of activity is consistent with the idea that platinum compounds have multiple intracellular targets and that cells can have multiple mechanisms of resistance.

Antineoplastic Agents↗

PubMed2005

Performance evaluation of functional medical imaging compression via optimal sampling schedule designs and cluster analysis.

In previous work we have described a technique for the compression of positron emission tomography (PET) image data in the spatial and temporal domains based on optimal sampling schedule designs (OSS) and cluster analysis. It can potentially achieve a high data compression ratio greater than 80:1. However, the number of distinguishable cluster groups in dynamic PET image data is a critical issue for this algorithm that has not been experimentally analyzed on clinical data. In this paper, the problem of experimentally determining the ideal cluster number for the algorithm for PET brain data is addressed.

Algorithms↗

PubMed2002

Euclidian space and grouping of biological objects.

MOTIVATION: Biological objects tend to cluster into discrete groups. Objects within a group typically possess similar properties. It is important to have fast and efficient tools for grouping objects that result in biologically meaningful clusters. Protein sequences reflect biological diversity and offer an extraordinary variety of objects for polishing clustering strategies. Grouping of sequences should reflect their evolutionary history and their functional properties. Visualization of relationships between sequences is of no less importance. Tree-building methods are typically used for such visualization. An alternative concept to visualization is a multidimensional sequence space. In this space, proteins are defined as points and distances between the points reflect the relationships between the proteins. Such a space can also be a basis for model-based clustering strategies that typically produce results correlating better with biological properties of proteins. RESULTS: We developed an approach to classification of biological objects that combines evolutionary measures of their similarity with a model-based clustering procedure. We apply the methodology to amino acid sequences. On the first step, given a multiple sequence alignment, we estimate evolutionary distances between proteins measured in expected numbers of amino acid substitutions per site. These distances are additive and are suitable for evolutionary tree reconstruction. On the second step, we find the best fit approximation of the evolutionary distances by Euclidian distances and thus represent each protein by a point in a multidimensional space. The Euclidian space may be projected in two or three dimensions and the projections can be used to visualize relationships between proteins. On the third step, we find a non-parametric estimate of the probability density of the points and cluster the points that belong to the same local maximum of this density in a group. The number of groups is controlled by a sigma-parameter that determines the shape of the density estimate and the number of maxima in it. The grouping procedure outperforms commonly used methods such as UPGMA and single linkage clustering.

Algorithms↗

PubMed2005

Parallelisation of the blast algorithm.

Retrieving homologous DNA and protein sequences from existing databases is a fundamental routine in bioinformatics research. Programs of the NCBI BLAST family are widely used for this purpose. We evaluated paraBLAST, a parallelised version of the NCBI BLAST algorithm, using a Message Passing Interface (MPI) on a multi-node compute cluster. Here, we propose static and dynamic database-partitioning schemes based on the availability of the cluster. We evaluated the application of the algorithm in querying nucleotide sequences against a large-scale sequence database with different numbers of database partitions, and hence, different numbers of CPUs. Since the program's tasks are performed independently of each other, each available CPU can run its own copy of BLAST queries, resulting in reduced interference between processes and leading to a highly scalable solution.

Algorithms↗

PubMed1987

Isolation and characterization of a nuclear depressive syndrome.

We investigated the nosology of endogenous depression by numerical taxonomy. Five hundred and sixty-nine patients diagnosed as having unipolar major depressive disorder in the NIMH Clinical Research Branch Program on the Psychobiology of Depression-Clinical were studied. Thirty-six symptoms which might distinguish endogenous from non-endogenous depressions were chosen from the literature. Patients' symptom profiles assessed by structured interview were grouped by two methods: a K-means improvement of Ward's method of cluster analysis, and a latent class algorithm. The methods produced very similar groups and several internal validity criteria suggested that the groups were not spurious. Cluster 1, 'nuclear depression,' included a nucleus of patients common to multiple definitions of endogenous depression. The non-nuclear group scored as less neurotic than the nuclear group on personality tests administered during the index episode. The groups do not differ in frequency, number or severity of reported life events prior to onset of the index episode. The nuclear group shows a poor prognosis on two-year prospective follow-up, greater disturbance on personality inventories, and increased heritability of depression in siblings.

Adult↗

PubMed2005

A grid layout algorithm for automatic drawing of biochemical networks.

MOTIVATION: Visualization is indispensable in the research of complex biochemical networks. Available graph layout algorithms are not adequate for satisfactorily drawing such networks. New methods are required to visualize automatically the topological architectures and facilitate the understanding of the functions of the networks. RESULTS: We propose a novel layout algorithm to draw complex biochemical networks. A network is modeled as a system of interacting nodes on squared grids. A discrete cost function between each node pair is designed based on the topological relation and the geometric positions of the two nodes. The layouts are produced by minimizing the total cost. We design a fast algorithm to minimize the discrete cost function, by which candidate layouts can be produced efficiently. A simulated annealing procedure is used to choose better candidates. Our algorithm demonstrates its ability to exhibit cluster structures clearly in relatively compact layout areas without any prior knowledge. We developed Windows software to implement the algorithm for CADLIVE. AVAILABILITY: All materials can be freely downloaded from http://kurata21.bio.kyutech.ac.jp/grid/grid_layout.htm; http://www.cadlive.jp/ SUPPLEMENTARY INFORMATION: http://kurata21.bio.kyutech.ac.jp/grid/grid_layout.htm; http://www.cadlive.jp/

Algorithms↗

PubMed2002

Development and production of an oligonucleotide MuscleChip: use for validation of ambiguous ESTs.

BACKGROUND: We describe the development, validation, and use of a highly redundant 120,000 oligonucleotide microarray (MuscleChip) containing 4,601 probe sets representing 1,150 known genes expressed in muscle and 2,075 EST clusters from a non-normalized subtracted muscle EST sequencing project (28,074 EST sequences). This set included 369 novel EST clusters showing no match to previously characterized proteins in any database. Each probe set was designed to contain 20-32 25 mer oligonucleotides (10-16 paired perfect match and mismatch probe pairs per gene), with each probe evaluated for hybridization kinetics (Tm) and similarity to other sequences. The 120,000 oligonucleotides were synthesized by photolithography and light-activated chemistry on each microarray. RESULTS: Hybridization of human muscle cRNAs to this MuscleChip (33 samples) showed a correlation of 0.6 between the number of ESTs sequenced in each cluster and hybridization intensity. Out of 369 novel EST clusters not showing any similarity to previously characterized proteins, we focused on 250 EST clusters that were represented by robust probe sets on the MuscleChip fulfilling all stringent rules. 102 (41%) were found to be consistently "present" by analysis of hybridization to human muscle RNA, of which 40 ESTs (39%) could be genome anchored to potential transcription units in the human genome sequence. 19 ESTs of the 40 ESTs were furthermore computer-predicted as exons by one or more than three gene identification algorithms. CONCLUSION: Our analysis found 40 transcriptionally validated, genome-anchored novel EST clusters to be expressed in human muscle. As most of these ESTs were low copy clusters (duplex and triplex) in the original 28,000 EST project, the identification of these as significantly expressed is a robust validation of the transcript units that permits subsequent focus on the novel proteins encoded by these genes.

Algorithms↗

PubMed2005

TAMO: a flexible, object-oriented framework for analyzing transcriptional regulation using DNA-sequence motifs.

SUMMARY: TAMO (Tools for Analysis of MOtifs) is an object-oriented computational framework for interpreting transcriptional regulation using DNA-sequence motifs. To simplify the application of multiple motif discovery programs to genome-wide data, TAMO provides a sophisticated motif object with interfaces to several popular programs. In addition, TAMO provides modules for integrating motif analysis with diverse data sources including genomic sequences, microarrays and various databases. Finally, TAMO includes tools for sequence analysis, algorithms for scoring, comparing and clustering motifs, and several useful statistical tests. Recently, we have applied these tools to analyze tens of thousands of motifs derived from hundreds of microarray experiments.

Algorithms↗