Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Clustering Algorithms”

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.

At least 199 records · Page 11Linked to original sources
PubMed2005

Clustering and re-clustering for pattern discovery in gene expression data.

The combined interpretation of gene expression data and gene sequences is important for the investigation of the intricate relationships of gene expression at the transcription level. The expression data produced by microarray hybridization experiments can lead to the identification of clusters of co-expressed genes that are likely co-regulated by the same regulatory mechanisms. By analyzing the promoter regions of co-expressed genes, the common regulatory patterns characterized by transcription factor binding sites can be revealed. Many clustering algorithms have been used to uncover inherent clusters in gene expression data. In this paper, based on experiments using simulated and real data, we show that the performance of these algorithms could be further improved. For the clustering of expression data typically characterized by a lot of noise, we propose to use a two-phase clustering algorithm consisting of an initial clustering phase and a second re-clustering phase. The proposed algorithm has several desirable features: (i) it utilizes both local and global information by computing both a "local" pairwise distance between two gene expression profiles in Phase 1 and a "global" probabilistic measure of interestingness of cluster patterns in Phase 2, (ii) it distinguishes between relevant and irrelevant expression values when performing re-clustering, and (iii) it makes explicit the patterns discovered in each cluster for possible interpretations. Experimental results show that the proposed algorithm can be an effective algorithm for discovering clusters in the presence of very noisy data. The patterns that are discovered in each cluster are found to be meaningful and statistically significant, and cannot otherwise be easily discovered. Based on these discovered patterns, genes co-expressed under the same experimental conditions and range of expression levels have been identified and evaluated. When identifying regulatory patterns at the promoter regions of the co-expressed genes, we also discovered well-known transcription factor binding sites in them. These binding sites can provide explanations for the co-expressed patterns.

Algorithms↗
PubMed2006

Comparisons of graph-structure clustering methods for gene expression data.

Although many numerical clustering algorithms have been applied to gene expression data analysis, the essential step is still biological interpretation by manual inspection. The correlation between genetic co-regulation and affiliation to a common biological process is what biologists expect. Here, we introduce some clustering algorithms that are based on graph structure constituted by biological knowledge. After applying a widely used dataset, we compared the result clusters of two of these algorithms in terms of the homogeneity of clusters and coherence of annotation and matching ratio. The results show that the clusters of knowledge-guided analysis are the kernel parts of the clusters of Gene Ontology (GO)-Cluster software, which contains the genes that are most expression correlative and most consistent with biological functions. Moreover, knowledge-guided analysis seems much more applicable than GO-Cluster in a larger dataset.

Algorithms↗
PubMed2003

Mining gene expression data using a novel approach based on hidden Markov models.

In this work we have developed a new framework for microarray gene expression data analysis. This framework is based on hidden Markov models. We have benchmarked the performance of this probability model-based clustering algorithm on several gene expression datasets for which external evaluation criteria were available. The results showed that this approach could produce clusters of quality comparable to two prevalent clustering algorithms, but with the major advantage of determining the number of clusters. We have also applied this algorithm to analyze published data of yeast cell cycle gene expression and found it able to successfully dig out biologically meaningful gene groups. In addition, this algorithm can also find correlation between different functional groups and distinguish between function genes and regulation genes, which is helpful to construct a network describing particular biological associations. Currently, this method is limited to time series data. Supplementary materials are available at http://www.bioinfo.tsinghua.edu.cn/~rich/hmmgep_supp/.

Algorithms↗
PubMed2005

goCluster integrates statistical analysis and functional interpretation of microarray expression data.

MOTIVATION: Several tools that facilitate the interpretation of transcriptional profiles using gene annotation data are available but most of them combine a particular statistical analysis strategy with functional information. goCluster extends this concept by providing a modular framework that facilitates integration of statistical and functional microarray data analysis with data interpretation. RESULTS: goCluster enables scientists to employ annotation information, clustering algorithms and visualization tools in their array data analysis and interpretation strategy. The package provides four clustering algorithms and GeneOntology terms as prototype annotation data. The functional analysis is based on the hypergeometric distribution whereby the Bonferroni correction or the false discovery rate can be used to correct for multiple testing. The approach implemented in goCluster was successfully applied to interpret the results of complex mammalian and yeast expression data obtained with high density oligonucleotide microarrays (GeneChips). AVAILABILITY: goCluster is available via the BioConductor portal at www.bioconductor.org. The software package, detailed documentation, user- and developer guides as well as other background information are also accessible via a web portal at http://www.bioz.unibas.ch/gocluster CONTACT: michael.primig@unibas.ch

Algorithms↗
PubMed2004

A hybrid clustering approach to recognition of protein families in 114 microbial genomes.

BACKGROUND: Grouping proteins into sequence-based clusters is a fundamental step in many bioinformatic analyses (e.g., homology-based prediction of structure or function). Standard clustering methods such as single-linkage clustering capture a history of cluster topologies as a function of threshold, but in practice their usefulness is limited because unrelated sequences join clusters before biologically meaningful families are fully constituted, e.g. as the result of matches to so-called promiscuous domains. Use of the Markov Cluster algorithm avoids this non-specificity, but does not preserve topological or threshold information about protein families. RESULTS: We describe a hybrid approach to sequence-based clustering of proteins that combines the advantages of standard and Markov clustering. We have implemented this hybrid approach over a relational database environment, and describe its application to clustering a large subset of PDB, and to 328577 proteins from 114 fully sequenced microbial genomes. To demonstrate utility with difficult problems, we show that hybrid clustering allows us to constitute the paralogous family of ATP synthase F1 rotary motor subunits into a single, biologically interpretable hierarchical grouping that was not accessible using either single-linkage or Markov clustering alone. We describe validation of this method by hybrid clustering of PDB and mapping SCOP families and domains onto the resulting clusters. CONCLUSION: Hybrid (Markov followed by single-linkage) clustering combines the advantages of the Markov Cluster algorithm (avoidance of non-specific clusters resulting from matches to promiscuous domains) and single-linkage clustering (preservation of topological information as a function of threshold). Within the individual Markov clusters, single-linkage clustering is a more-precise instrument, discerning sub-clusters of biological relevance. Our hybrid approach thus provides a computationally efficient approach to the automated recognition of protein families for phylogenomic analysis.

Algorithms↗
PubMed2002

INCLUSive: integrated clustering, upstream sequence retrieval and motif sampling.

INCLUSive allows automatic multistep analysis of microarray data (clustering and motif finding). The clustering algorithm (adaptive quality-based clustering) groups together genes with highly similar expression profiles. The upstream sequences of the genes belonging to a cluster are automatically retrieved from GenBank and can be fed directly into Motif Sampler, a Gibbs sampling algorithm that retrieves statistically over-represented motifs in sets of sequences, in this case upstream regions of co-expressed genes.

Algorithms↗
PubMed2005

A novel approach for clustering proteomics data using Bayesian fast Fourier transform.

MOTIVATION: Bioinformatics clustering tools are useful at all levels of proteomic data analysis. Proteomics studies can provide a wealth of information and rapidly generate large quantities of data from the analysis of biological specimens. The high dimensionality of data generated from these studies requires the development of improved bioinformatics tools for efficient and accurate data analyses. For proteome profiling of a particular system or organism, a number of specialized software tools are needed. Indeed, significant advances in the informatics and software tools necessary to support the analysis and management of these massive amounts of data are needed. Clustering algorithms based on probabilistic and Bayesian models provide an alternative to heuristic algorithms. The number of clusters (diseased and non-diseased groups) is reduced to the choice of the number of components of a mixture of underlying probability. The Bayesian approach is a tool for including information from the data to the analysis. It offers an estimation of the uncertainties of the data and the parameters involved. RESULTS: We present novel algorithms that can organize, cluster and derive meaningful patterns of expression from large-scaled proteomics experiments. We processed raw data using a graphical-based algorithm by transforming it from a real space data-expression to a complex space data-expression using discrete Fourier transformation; then we used a thresholding approach to denoise and reduce the length of each spectrum. Bayesian clustering was applied to the reconstructed data. In comparison with several other algorithms used in this study including K-means, (Kohonen self-organizing map (SOM), and linear discriminant analysis, the Bayesian-Fourier model-based approach displayed superior performances consistently, in selecting the correct model and the number of clusters, thus providing a novel approach for accurate diagnosis of the disease. Using this approach, we were able to successfully denoise proteomic spectra and reach up to a 99% total reduction of the number of peaks compared to the original data. In addition, the Bayesian-based approach generated a better classification rate in comparison with other classification algorithms. This new finding will allow us to apply the Fourier transformation for the selection of the protein profile for each sample, and to develop a novel bioinformatic strategy based on Bayesian clustering for biomarker discovery and optimal diagnosis.

Algorithms↗
PubMed2001

Extracting information from cDNA arrays.

High-density DNA arrays allow measurements of gene expression levels (messenger RNA abundance) for thousands of genes simultaneously. We analyze arrays with spotted cDNA used in monitoring of expression profiles. A dilution series of a mouse liver probe is deployed to quantify the reproducibility of expression measurements. Saturation effects limit the accessible signal range at high intensities. Additive noise and outshining from neighboring spots dominate at low intensities. For repeated measurements on the same filter and filter-to-filter comparisons correlation coefficients of 0.98 are found. Next we consider the clustering of gene expression time series from stimulated human fibroblasts which aims at finding co-regulated genes. We analyze how preprocessing, the distance measure, and the clustering algorithm affect the resulting clusters. Finally we discuss algorithms for the identification of transcription factor binding sites from clusters of co-regulated genes. (c) 2001 American Institute of Physics.

Journal Article↗
PubMed2001

A Bayesian approach to the identification of panmictic populations and the assignment of individuals.

We present likelihood-based methods for assigning the individuals in a sample to source populations, on the basis of their genotypes at co-dominant marker loci. The source populations are assumed to be at Hardy-Weinberg and linkage equilibrium, but the allelic composition of these source populations and even the number of source populations represented in the sample are treated as uncertain. The parameter of interest is the partition of the set of sampled individuals, induced by the assignment of individuals to source populations. We present a maximum likelihood method, and then a more powerful Bayesian approach for estimating this sample partition. In general, it will not be feasible to evaluate the evidence supporting each possible partition of the sample. Furthermore, when the number of individuals in the sample is large, it may not even be feasible to evaluate the evidence supporting, individually, each of the most plausible partitions because there may be many individuals which are difficult to assign. To overcome these problems, we use low-dimensional marginals (the 'co-assignment probabilities') of the posterior distribution of the sample partition as measures of 'similarity', and then apply a hierarchical clustering algorithm to identify clusters of individuals whose assignment together is well supported by the posterior distribution. A binary tree provides a visual representation of how well the posterior distribution supports each cluster in the hierarchy. These methods are applicable to other problems where the parameter of interest is a partition of a set. Because the co-assignment probabilities are independent of the arbitrary labelling of source populations, we avoid the label-switching problem of previous Bayesian methods.

Algorithms↗
PubMed2004

Stability-based validation of clustering solutions.

Data clustering describes a set of frequently employed techniques in exploratory data analysis to extract "natural" group structure in data. Such groupings need to be validated to separate the signal in the data from spurious structure. In this context, finding an appropriate number of clusters is a particularly important model selection question. We introduce a measure of cluster stability to assess the validity of a cluster model. This stability measure quantifies the reproducibility of clustering solutions on a second sample, and it can be interpreted as a classification risk with regard to class labels produced by a clustering algorithm. The preferred number of clusters is determined by minimizing this classification risk as a function of the number of clusters. Convincing results are achieved on simulated as well as gene expression data sets. Comparisons to other methods demonstrate the competitive performance of our method and its suitability as a general validation tool for clustering solutions in real-world problems.

Algorithms↗
PubMed1999

DNA profiling of Mycobacterium tuberculosis from the Eastern Cape Province of South Africa and the detection of a high level of genetic diversity.

The genetic diversity in 502 isolates of Mycobacterium tuberculosis from the Eastern Cape Province of South Africa was DNA-profiled using random amplified polymorphic DNA sequences generated by four primers, and analyzed using the Dice similarity coefficient and the Ward cluster algorithm. Three major cluster groups and ten clusters were detected and shown to be significant at the five percent level using analysis of molecular variance (AMOVA). It is proposed that the three major cluster groups may represent three different entries of M. tuberculosis into South Africa during colonial times. No significant genetic differences could be detected between the urban and rural populations, suggesting that migration may play an important role in the wide transmission of all strains of the organism found in this province. However, a genetic distinction (p = 0.10) could be detected between rural individuals from the southern, more prosperous, region and the northern, less prosperous, regions of the province, which may represent either a limited migration between distant rural communities or a difference in health treatment historically in the two areas. AMOVA indicates the existence of a higher degree of population structure between drug sensitive and drug-resistant individuals than between urban and rural individuals (p = 0.05). Two clusters, C1 and C3, contained a large proportion of the isolates resistant to between one and three first-line drugs. Isolates resistant to more than three antibiotics were genetically diverse, suggesting that they are as yet not being transmitted at a high rate between individuals.

Antitubercular Agents↗
PubMed1997

Social stress and trauma: synthesis and spatial analysis.

In the last decade violence has emerged as a public health issue, with concomitant interest in surveillance and prevention. This paper is an extension of earlier work seeking to expand the ecological analysis of violence across jurisdictional boundaries, sharpen the level of resolution of such analysis, and ultimately inform small area policy applications in terms of public health initiatives for violence reduction. The underlying model is drawn from stress theory and rests on a set of social indicators representing stress in the Baltimore area. In the earlier work, a set of 24 variables describing violence and socioeconomic conditions across some 1358 areas was factor analyzed and the resulting scores were mapped and interpreted. The present paper takes the analysis a step further in an attempt to identify groups of observations with common traits in order to assist public health professionals and other relevant decision-makers in the process of trauma surveillance, response, and prevention. Cluster analysis was used to combine most similar observations in terms of the three orthogonal factors, and the resulting cluster affiliations were mapped in geographic space. Although no spatial contiguity constraint was put on the clustering algorithm, many statistical clusters were also found to constitute geographic clusters. This implies that the process identified neighborhoods or parts of neighborhoods with shared traits in terms of the underlying set of stressors. Analysis of this type could be used by policy-makers to classify neighborhoods in terms of their needs for various services in addition to public health interventions, including policing, fire protection, building inspection, social work, and education.

Cluster Analysis↗
PubMed2004

Tracking evolving communities in large linked networks.

We are interested in tracking changes in large-scale data by periodically creating an agglomerative clustering and examining the evolution of clusters (communities) over time. We examine a large real-world data set: the NEC CiteSeer database, a linked network of >250,000 papers. Tracking changes over time requires a clustering algorithm that produces clusters stable under small perturbations of the input data. However, small perturbations of the CiteSeer data lead to significant changes to most of the clusters. One reason for this is that the order in which papers within communities are combined is somewhat arbitrary. However, certain subsets of papers, called natural communities, correspond to real structure in the CiteSeer database and thus appear in any clustering. By identifying the subset of clusters that remain stable under multiple clustering runs, we get the set of natural communities that we can track over time. We demonstrate that such natural communities allow us to identify emerging communities and track temporal changes in the underlying structure of our network data.

Cluster Analysis↗
PubMed2002

Methods for assessing reproducibility of clustering patterns observed in analyses of microarray data.

MOTIVATION: Recent technological advances such as cDNA microarray technology have made it possible to simultaneously interrogate thousands of genes in a biological specimen. A cDNA microarray experiment produces a gene expression 'profile'. Often interest lies in discovering novel subgroupings, or 'clusters', of specimens based on their profiles, for example identification of new tumor taxonomies. Cluster analysis techniques such as hierarchical clustering and self-organizing maps have frequently been used for investigating structure in microarray data. However, clustering algorithms always detect clusters, even on random data, and it is easy to misinterpret the results without some objective measure of the reproducibility of the clusters. RESULTS: We present statistical methods for testing for overall clustering of gene expression profiles, and we define easily interpretable measures of cluster-specific reproducibility that facilitate understanding of the clustering structure. We apply these methods to elucidate structure in cDNA microarray gene expression profiles obtained on melanoma tumors and on prostate specimens.

Cluster Analysis↗
PubMed2006

Identification of functional modules in a PPI network by clique percolation clustering.

Large-scale experiments and data integration have provided the opportunity to systematically analyze and comprehensively understand the topology of biological networks and biochemical processes in cells. Modular architecture which encompasses groups of genes/proteins involved in elementary biological functional units is a basic form of the organization of interacting proteins. Here we apply a graph clustering algorithm based on clique percolation clustering to detect overlapping network modules of a protein-protein interaction (PPI) network. Our analysis of the yeast Sacchromyces cerevisiae suggests that most of the detected modules correspond to one or more experimentally functional modules and half of these annotated modules match well with experimentally determined protein complexes. Our method of analysis can of course be applied to protein-protein interaction data for any species and even other biological networks.

Algorithms↗
PubMed2005

A multi-clustering fusion scheme for data partitioning.

A multi-clustering fusion method is presented based on combining several runs of a clustering algorithm resulting in a common partition. More specifically, the results of several independent runs of the same clustering algorithm are appropriately combined to obtain a distinct partition of the data which is not affected by initialization and overcomes the instabilities of clustering methods. Subsequently, a fusion procedure is applied to the clusters generated during the previous phase to determine the optimal number of clusters in the data set according to some predefined criteria.

Algorithms↗
PubMed2000

Fuzzy clustering analysis of the first 10 MEIC chemicals.

In this paper, we discuss the classification results of the toxicological responses of 32 in vivo and in vitro test systems to the first 10 MEIC chemicals. In this order we have used different fuzzy clustering algorithms, namely hierarchical fuzzy clustering, hierarchical and horizontal fuzzy characteristics clustering and a new clustering technique, namely fuzzy hierarchical cross-classification. The characteristics clustering technique produces fuzzy partitions of the characteristics (chemicals) involved and thus it is a useful tool for studying the (dis)similarities between different chemicals and for essential chemicals selection. The cross-classification algorithm produces not only a fuzzy partition of the test systems analyzed, but also a fuzzy partition of the considered 10 MEIC (multicentre evaluation of in vitro cytotoxicity) chemicals. In this way it is possible to identify which chemicals are responsible for the similarities or differences observed between different groups of test systems. In another way, there is a specific sensitivity of a chemical for one or more toxicological tests.

Algorithms↗