Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “unsupervised clustering”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

622 records · Page 35Linked to original sources
PubMedDate not supplied

Refining competition in the self-organising tree map for unsupervised biofilm image segmentation.

The Self Organising Tree Map (SOTM) neural network is investigated as a means of segmenting micro-organisms from confocal microscope image data. Features describing pixel and regional intensities, phase congruency and spatial proximity are explored in terms of their impact on the segmentation of bacteria and other micro-organisms. The significance of individual features is investigated, and it is proposed that, within the context of micro-biological image segmentation, better object delineation can be achieved if certain features are more dominant in the initial stages of learning. In this way, other features are allowed to become more/less significant as learning progresses: as more knowledge is acquired about the data being segmented. We argue that the efficiency and flexibility of the SOTM in adapting to, and preserving the topology of input space, makes it an appropriate candidate for implementing this idea. We propose a refinement to the competitive search strategy that allows for a more appropriate fusion of signal and proximal features, thereby promoting a segmentation that is more sensitive to the regional associations of different microbial matter. A refined stop criterion is also suggested such that the dynamically generated number of classes becomes more data dependant. Preliminary experiments are presented and it is found that favouring intensity characteristics in the early phases of learning, whilst relaxing proximity constraints in later phases of learning, offers a general mechanism through which we can improve the segmentation of microbial constituents.

Algorithms↗
PubMed2000

Unsupervised segmentation of multiparameter MRI in experimental cerebral ischemia with comparison to T2, diffusion, and ADC MRI parameters and histopathological validation.

This study presents histological validation of an objective (unsupervised) computer segmentation algorithm, the iterative self-organizing data analysis technique (ISODATA), for analysis of multiparameter magnetic resonance imaging (MRI) data in experimental focal cerebral ischemia. T2-, T1-, and diffusion (DWI) weighted coronal images were acquired from 4 to 168 hours after stroke on separate groups of animals. Animals were killed immediately after MRI for histological analysis. MR images were coregistered/warped to histology. MRI lesion areas were defined using DWI, apparent diffusion coefficient (ADC) maps, T2-weighted images, and ISODATA. The last techniques clearly discriminated between ischemia-altered and morphologically intact tissue. ISODATA areas were congruent and significantly correlated (r = 0.99, P < 0.05) with histologically defined lesions. In contrast, DWI, ADC, and T2 lesion areas showed no significant correlation with histologically evaluated lesions until subacute time points. These data indicate that multiparameter ISODATA methodology can accurately detect and identify ischemic cell damage early and late after ischemia, with ISODATA outperforming ADC, DWI, and T2-weighted images in identification of ischemic lesions from 4 to 168 hours after stroke.

Algorithms↗
PubMed2005

Targeted disruption of glycerol kinase gene in mice: expression analysis in liver shows alterations in network partners related to glycerol kinase activity.

Glycerol kinase deficiency (GKD) is an X-linked inborn error of metabolism with metabolic and neurological crises. Liver shows the highest level of glycerol kinase (GK) activity in humans and mice. Absence of genotype-phenotype correlations in patients with GKD indicates the involvement of modifier genes, including other network partners. To understand the molecular pathogenesis of GKD, we performed microarray analysis on liver mRNA from neonatal glycerol kinase (Gyk) knockout (KO) and wild-type (WT) mice. Unsupervised learning revealed that the overall gene expression profile of the KO mice was different from that of WT. Real-time PCR confirmed the differences for selected genes. Functional gene enrichment analysis was used to find 56 increased and 37 decreased gene functional categories. PathwayAssist analysis identified changes in gene expression levels of genes involved in organic acid metabolism indicating that GK was part of the same metabolic network which correlates well with the patients with GKD having metabolic acidemia during their episodic crises. Network component analysis (NCA) showed that transcription factors sterol regulatory element-binding protein (SREBP)-1c, carbohydrate response element-binding protein (ChREBP), hepatocyte nuclear factor-4 alpha (HNF-4alpha) and peroxisome proliferative-activated receptor-alpha (PPARalpha) had increased activity in the Gyk KO mice compared with WT mice, whereas SREBP-2 was less active in the Gyk KO mice. These studies show that Gyk deletion causes alterations in expression of genes in several regulatory networks and is the first time NCA has been used to expand on microarray data from a mouse KO model of a human disease.

Animals↗
PubMed2005

Unsupervised learning and mapping of active brain functional MRI signals based on hidden semi-Markov event sequence models.

In this paper, a novel functional magnetic resonance imaging (fMRI) brain mapping method is presented within the statistical modeling framework of hidden semi-Markov event sequence models (HSMESMs). Neural activation detection is formulated at the voxel level in terms of time coupling between the sequence of hemodynamic response onsets (HROs) observed in the fMRI signal, and an HSMESM of the hidden sequence of task-induced neural activations. The sequence of HRO events is derived from a continuous wavelet transform (CWT) of the fMRI signal. The brain activation HSMESM is built from the timing information of the input stimulation protocol. The rich mathematical framework of HSMESMs makes these models an effective and versatile approach for fMRI data analysis. Solving for the HSMESM Evaluation and Learning problems enables the model to automatically detect neural activation embedded in a given set of fMRI signals, without requiring any template basis function or prior shape assumption for the fMRI response. Solving for the HSMESM Decoding problem allows to enrich brain mapping with activation lag mapping, activation mode visualizing, and hemodynamic response function analysis. Activation detection results obtained on synthetic and real epoch-related fMRI data demonstrate the superiority of the HSMESM mapping method with respect to a real application case of the statistical parametric mapping (SPM) approach. In addition, the HSMESM mapping method appears clearly insensitive to timing variations of the hemodynamic response, and exhibits low sensitivity to fluctuations of its shape.

Algorithms↗
PubMed2005

Molecular signatures in childhood acute leukemia and their correlations to expression patterns in normal hematopoietic subpopulations.

Global expression profiles of a consecutive series of 121 childhood acute leukemias (87 B lineage acute lymphoblastic leukemias, 11 T cell acute lymphoblastic leukemias, and 23 acute myeloid leukemias), six normal bone marrows, and 10 normal hematopoietic subpopulations of different lineages and maturations were ascertained by using 27K cDNA microarrays. Unsupervised analyses revealed segregation according to lineages and primary genetic changes, i.e., TCF3(E2A)/PBX1, IGH@/MYC, ETV6(TEL)/RUNX1(AML1), 11q23/MLL, and hyperdiploidy (>50 chromosomes). Supervised discriminatory analyses were used to identify differentially expressed genes correlating with lineage and primary genetic change. The gene-expression profiles of normal hematopoietic cells were also studied. By using principal component analyses (PCA), a differentiation axis was exposed, reflecting lineages and maturation stages of normal hematopoietic cells. By applying the three principal components obtained from PCA of the normal cells on the leukemic samples, similarities between malignant and normal cell lineages and maturations were investigated. Apart from showing that leukemias segregate according to lineage and genetic subtype, we provide an extensive study of the genes correlating with primary genetic changes. We also investigated the expression pattern of these genes in normal hematopoietic cells of different lineages and maturations, identifying genes preferentially expressed by the leukemic cells, suggesting an ectopic activation of a large number of genes, likely to reflect regulatory networks of pathogenetic importance that also may provide attractive targets for future directed therapies.

Bone Marrow↗
PubMed2005

Evolutionary optimization of a hierarchical object recognition model.

A major problem in designing artificial neural networks is the proper choice of the network architecture. Especially for vision networks classifying three-dimensional (3-D) objects this problem is very challenging, as these networks are necessarily large and therefore the search space for defining the needed networks is of a very high dimensionality. This strongly increases the chances of obtaining only suboptimal structures from standard optimization algorithms. We tackle this problem in two ways. First, we use biologically inspired hierarchical vision models to narrow the space of possible architectures and to reduce the dimensionality of the search space. Second, we employ evolutionary optimization techniques to determine optimal features and nonlinearities of the visual hierarchy. Here, we especially focus on higher order complex features in higher hierarchical stages. We compare two different approaches to perform an evolutionary optimization of these features. In the first setting, we directly code the features into the genome. In the second setting, in analogy to an ontogenetical development process, we suggest the new method of an indirect coding of the features via an unsupervised learning process, which is embedded into the evolutionary optimization. In both cases the processing nonlinearities are encoded directly into the genome and are thus subject to optimization. The fitness of the individuals for the evolutionary selection process is computed by measuring the network classification performance on a benchmark image database. Here, we use a nearest-neighbor classification approach, based on the hierarchical feature output. We compare the found solutions with respect to their ability to generalize. We differentiate between a first- and a second-order generalization. The first-order generalization denotes how well the vision system, after evolutionary optimization of the features and nonlinearities using a database A, can classify previously unseen test views of objects from this database A. As second-order generalization, we denote the ability of the vision system to perform classification on a database B using the features and nonlinearities optimized on database A. We show that the direct feature coding approach leads to networks with a better first-order generalization, whereas the second-order generalization is on an equally high level for both direct and indirect coding. We also compare the second-order generalization results with other state-of-the-art recognition systems and show that both approaches lead to optimized recognition systems, which are highly competitive with recent recognition algorithms.

Algorithms↗
PubMed2005

Sorting points into neighborhoods (SPIN): data analysis and visualization by ordering distance matrices.

SUMMARY: We introduce a novel unsupervised approach for the organization and visualization of multidimensional data. At the heart of the method is a presentation of the full pairwise distance matrix of the data points, viewed in pseudocolor. The ordering of points is iteratively permuted in search of a linear ordering, which can be used to study embedded shapes. Several examples indicate how the shapes of certain structures in the data (elongated, circular and compact) manifest themselves visually in our permuted distance matrix. It is important to identify the elongated objects since they are often associated with a set of hidden variables, underlying continuous variation in the data. The problem of determining an optimal linear ordering is shown to be NP-Complete, and therefore an iterative search algorithm with O(n3) step-complexity is suggested. By using sorting points into neighborhoods, i.e. SPIN to analyze colon cancer expression data we were able to address the serious problem of sample heterogeneity, which hinders identification of metastasis related genes in our data. Our methodology brings to light the continuous variation of heterogeneity--starting with homogeneous tumor samples and gradually increasing the amount of another tissue. Ordering the samples according to their degree of contamination by unrelated tissue allows the separation of genes associated with irrelevant contamination from those related to cancer progression. AVAILABILITY: Software package will be available for academic users upon request.

Algorithms↗
PubMed2004

Gene expression profiling of leiomyoma and myometrial smooth muscle cells in response to transforming growth factor-beta.

Altered expression of the TGF-beta system is recognized to play a central role in various fibrotic disorders, including leiomyoma. In this study we performed microarray analysis to characterize the gene expression profile of leiomyoma and matched myometrial smooth muscle cells (LSMC and MSMC, respectively) in response to the time-dependent action of TGF-beta and, after pretreatment with TGF-beta type II receptor (TGF-beta RII) antisense oligomer-blocking/reducing TGF-beta autocrine/paracrine actions. Unsupervised and supervised assessments of the gene expression values with a false discovery rate selected at P < or = 0.001 identified 310 genes as differentially expressed and regulated in LSMC and MSMC in a cell- and time-dependent manner by TGF-beta. Pretreatment with TGF-beta RII antisense resulted in changes in the expression of many of the 310 genes regulated by TGF-beta, with 54 genes displaying a response to TGF-beta treatment. Comparative analysis of the gene expression profile in TGF-beta RII antisense- and GnRH analog-treated cells indicated that these treatments target the expression of 222 genes in a cell-specific manner. Gene ontology assigned these genes functions as cell cycle regulators, transcription factors, signal transducers, tissue turnover, and apoptosis. We validated the expression and TGF-beta time-dependent regulation of IL-11, TGF-beta-induced factor, TGF-beta-inducible early gene response, early growth response 3, CITED2 (cAMP response element binding protein-binding protein/p300-interacting transactivator with ED-rich tail), Nur77, Runx1, Runx2, p27, p57, growth arrest-specific 1, and G protein-coupled receptor kinase 5 in LSMC and MSMC using real-time PCR. Together, the results provide the first comprehensive assessment of the LSMC and MSMC molecular environment targeted by autocrine/paracrine action of TGF-beta, highlighting potential involvement of specific genes whose products may influence the outcome of leiomyoma growth and fibrotic characteristics by regulating inflammatory response, cell growth, apoptosis, and tissue remodeling.

Apoptosis↗
PubMed2004

Leiomyoma and myometrial gene expression profiles and their responses to gonadotropin-releasing hormone analog therapy.

Gene microarray was used to characterize the molecular environment of leiomyoma and matched myometrium during growth and in response to GnRH analog (GnRHa) therapy as well as GnRHa direct action on primary cultures of leiomyoma and myometrial smooth muscle cells (LSMC and MSMC). Unsupervised and supervised analysis of gene expression values and statistical analysis in R programming with a false discovery rate of P < or = 0.02 resulted in identification of 153 and 122 differentially expressed genes in leiomyoma and myometrium in untreated and GnRHa-treated cohorts, respectively. The expression of 170 and 164 genes was affected by GnRHa therapy in these tissues compared with their respective untreated group. GnRHa (0.1 microm), in a time-dependent manner (2, 6, and 12 h), targeted the expression of 281 genes (P < or = 0.005) in LSMC and MSMC, 48 of which genes were found in common with GnRHa-treated tissues. Functional annotations assigned these genes as key regulators of processes involving transcription, translational, signal transduction, structural activities, and apoptosis. We validated the expression of IL-11, early growth response 3, TGF-beta-induced factor, TGF-beta-inducible early gene response, CITED2 (cAMP response element binding protein-binding protein/p300-interacting transactivator with ED-rich tail), Nur77, growth arrest-specific 1, p27, p57, and G protein-coupled receptor kinase 5, representing cytokine, common transcription factors, cell cycle regulators, and signal transduction, at tissue levels and in LSMC and MSMC in response to GnRHa time-dependent action using real-time PCR, Western blotting, and immunohistochemistry. In conclusion, using different, complementary approaches, we characterized leiomyoma and myometrium molecular fingerprints and identified several previously unrecognized genes as targets of GnRHa action, implying that local expression and activation of these genes may represent features differentiating leiomyoma and myometrial environments during growth and GnRHa-induced regression.

Active Transport, Cell Nucleus↗
PubMed2006

Spectral embedding finds meaningful (relevant) structure in image and microarray data.

BACKGROUND: Accurate methods for extraction of meaningful patterns in high dimensional data have become increasingly important with the recent generation of data types containing measurements across thousands of variables. Principal components analysis (PCA) is a linear dimensionality reduction (DR) method that is unsupervised in that it relies only on the data; projections are calculated in Euclidean or a similar linear space and do not use tuning parameters for optimizing the fit to the data. However, relationships within sets of nonlinear data types, such as biological networks or images, are frequently mis-rendered into a low dimensional space by linear methods. Nonlinear methods, in contrast, attempt to model important aspects of the underlying data structure, often requiring parameter(s) fitting to the data type of interest. In many cases, the optimal parameter values vary when different classification algorithms are applied on the same rendered subspace, making the results of such methods highly dependent upon the type of classifier implemented. RESULTS: We present the results of applying the spectral method of Lafon, a nonlinear DR method based on the weighted graph Laplacian, that minimizes the requirements for such parameter optimization for two biological data types. We demonstrate that it is successful in determining implicit ordering of brain slice image data and in classifying separate species in microarray data, as compared to two conventional linear methods and three nonlinear methods (one of which is an alternative spectral method). This spectral implementation is shown to provide more meaningful information, by preserving important relationships, than the methods of DR presented for comparison. Tuning parameter fitting is simple and is a general, rather than data type or experiment specific approach, for the two datasets analyzed here. Tuning parameter optimization is minimized in the DR step to each subsequent classification method, enabling the possibility of valid cross-experiment comparisons. CONCLUSION: Results from the spectral method presented here exhibit the desirable properties of preserving meaningful nonlinear relationships in lower dimensional space and requiring minimal parameter fitting, providing a useful algorithm for purposes of visualization and classification across diverse datasets, a common challenge in systems biology.

Algorithms↗