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 613 records · Page 34Linked to original sources

PubMed2001

Locomotion towards a goal alters the synchronous firing of neurons recorded simultaneously in the subiculum and nucleus accumbens of rats.

Rats were implanted with recording electrodes aimed at the subiculum and nucleus accumbens. They were subsequently placed in a cylindrical environment, where they searched for locations where they would receive rewarding medial forebrain bundle stimulation. At times a tone was sounded, indicating that the reward location was in the center of the environment. Animals quickly learned to switch from random running to goal directed locomotion when the tone was on. To quantify the synchronous firing between simultaneously recorded neurons in the subiculum and nucleus accumbens, a gravitational clustering algorithm was employed. Individual neurons were modeled as particles in N dimensional space. Every spike discharge of the neuron augmented the 'gravitational charge' on its model particle. Synchronous firing between two cells caused their corresponding particles to draw together over time, due to the concurrent appearance of gravitational charge. All pair-wise combinations of cells isolated in subiculum and nucleus accumbens were examined using this algorithm. The firing of nine out of 52 subicular-accumbens cell pairings was significantly more synchronous when the tone was on, and the rat was running towards the central goal. This was also seen for 15 out of 22 subicular-subicular cell pairings. Conversely, only two out of 51 accumbens-accumbens pairings displayed significant tone dependent changes in synchronous firing. Thus, synchronous interactions between subiculum and nucleus accumbens occur preferentially when the animal is required to locate a fixed goal in space, i.e., the functional connectivity is altered by the navigational demands of the spatial reward task.

Algorithms↗

PubMed2001

A what-and-where fusion neural network for recognition and tracking of multiple radar emitters.

A neural network recognition and tracking system is proposed for classification of radar pulses in autonomous Electronic Support Measure systems. Radar type information is considered with position-specific information from active emitters in a scene. Type-specific parameters of the input pulse stream are fed to a neural network classifier trained on samples of data collected in the field. Meanwhile, a clustering algorithm is used to separate pulses from different emitters according to position-specific parameters of the input pulse stream. Classifier responses corresponding to different emitters are separated into tracks, or trajectories, one per active emitter, allowing for more accurate identification of radar types based on multiple views of emitter data along each emitter trajectory. Such a What-and-Where fusion strategy is motivated by a similar subdivision of labor in the brain. The fuzzy ARTMAP neural network is used to classify streams of pulses according to radar type using their functional parameters. Simulation results obtained with a radar pulse data set indicate that fuzzy ARTMAP compares favorably to several other approaches when performance is measured in terms of accuracy and computational complexity. Incorporation into fuzzy ARTMAP of negative match tracking (from ARTMAP-IC) facilitated convergence during training with this data set. Other modifications improved classification of data that include missing input pattern components and missing training classes. Fuzzy ARTMAP was combined with a bank of Kalman filters to group pulses transmitted from different emitters based on their position-specific parameters, and with a module to accumulate evidence from fuzzy ARTMAP responses corresponding to the track defined for each emitter. Simulation results demonstrate that the system provides a high level of performance on complex, incomplete and overlapping radar data.

Algorithms↗

PubMed1997

An Incremental Adaptive Network for On-line Supervised Learning and Probability Estimation.

In this paper, a novel hybrid utilization of the Fuzzy ARTMAP (FAM) neural network and the Probabilistic Neural Network (PNN) is proposed for on-line learning and probability estimation tasks. There are two distinct advantages to the hybrid network. First, FAM is used as an underlying clustering algorithm to classify the input patterns into different recognition categories during the learning phase, resulting in a significant reduction in the number of pattern nodes required in the PNN. Second, a non-parametric posterior probability distribution estimation procedure, in accordance with the PNN paradigm (i.e. the Parzen-windows estimator), is employed during the prediction phase, where a probabilistic interpretation corresponding to Bayes decision theory can be provided for the predictions of FAM. In addition, several modifications are proposed to integrate both of the networks effectively into a unified platform for enhancing generalization. This hybrid approach also realizes an incremental learning system in which the necessity to specify a static network configuration a priori is eliminated as the network is able to "grow" to accommodate new input patterns sequentially and can thus operate in non-stationary environments. The performance of the network is evaluated with benchmark classification tasks and the results are compared with other approaches. Simulation results indicate that this hybrid network is capable of achieving a value near to the Bayes optimal classification rate. Copyright 1997 Elsevier Science Ltd.

Journal Article↗

PubMed1997

An Efficient Method to Construct a Radial Basis Function Neural Network Classifier.

Radial basis function neural network (RBFN) has the power of the universal function approximation. But how to construct an RBFN to solve a given problem is usually not straightforward. This paper describes a method to construct an RBFN classifier efficiently and effectively. The method determines the middle layer neurons by a fast clustering algorithm and computes the optimal weights between the middle and the output layers statistically. We applied the proposed method to construct an RBFN classifier for an unconstrained handwritten digit recognition. The experiment showed that the method could construct an RBFN classifier quickly and the performance of the classifier was better than the best result previously reported.

Journal Article↗

PubMedDate not supplied

Computer-aided diagnosis for pulmonary nodules based on helical CT images.

In this paper, we present a computer-assisted automatic diagnostic system for lung cancer that detects nodule candidates at an early stage from helical CT images of the thorax. Our diagnostic system consists of analytical and diagnostic procedures. In the analytical procedure, first we extract the lung and the pulmonary blood vessel regions using the fuzzy clustering algorithm, then we analyze the features of these regions using image-processing techniques. In the diagnostic procedure, we define diagnostic rules utilizing the extracted features which support the determination of the candidate nodule locations. We show the effectiveness of our system by giving the results from its application to image data for mass screening of 450 patients.

Algorithms↗

PubMed2003

Cluster analysis of human autoantibody reactivities in health and in type 1 diabetes mellitus: a bio-informatic approach to immune complexity.

Informatic methodologies are being applied successfully to analyze the complexity of the genome. But beyond the genome, the immune system reflects the state of the body in health and disease. Traditionally, immunologists have reduced the immune system, where possible, to one-to-one relationships between particular antigens and particular antibodies or T-cell clones. Autoimmune diseases, caused by an immune attack against a body component, are usually investigated by following the response to single self-antigens. In this study, we apply informatics to analyze patterns of autoantibodies rather than single species of autoantibodies. This study was designed not to replace traditional approaches to immune diagnosis, but to test whether meaningful patterns of autoantibodies might exist. Using an unbiased solid-phase ELISA antibody test, we detected serum IgG and IgM antibodies in the sera of 20 healthy persons and 20 persons with type 1 diabetes mellitus binding to an array of 87 different antigens, mostly self-antigens. The healthy subjects manifested autoantibodies to a variety of self-antigens, many known to be associated with autoimmune diseases. We investigated the patterns of these autoantibodies using a coupled two-way clustering algorithm developed for analyzing data from gene arrays. We now report that the reactivity patterns of autoantibodies to particular subsets of self-antigens exhibited non-trivial structure, which significantly discriminated between healthy persons and persons with type 1 diabetes. The results show that despite the wide prevalence of autoantibodies, the patterns of reactivity to defined subsets of self-antigens can provide information about the state of the body.

Autoantibodies↗

PubMedDate not supplied

Automatic segmentation of non-enhancing brain tumors in magnetic resonance images.

Tumor segmentation from magnetic resonance (MR) images may aid in tumor treatment by tracking the progress of tumor growth and/or shrinkage. In this paper we present the first automatic segmentation method which separates non-enhancing brain tumors from healthy tissues in MR images to aid in the task of tracking tumor size over time. The MR feature images used for the segmentation consist of three weighted images (T1, T2 and proton density (PD)) for each axial slice through the head. An initial segmentation is computed using an unsupervised fuzzy clustering algorithm. Then, integrated domain knowledge and image processing techniques contribute to the final tumor segmentation. They are applied under the control of a knowledge-based system. The system knowledge was acquired by training on two patient volumes (14 images). Testing has shown successful tumor segmentations on four patient volumes (31 images). Our results show that we detected all six non-enhancing brain tumors, located tumor tissue in 35 of the 36 ground truth (radiologist labeled) slices containing tumor and successfully separated tumor regions from physically connected CSF regions in all the nine slices. Quantitative measurements are promising as correspondence ratios between ground truth and segmented tumor regions ranged between 0.368 and 0.871 per volume, with percent match ranging between 0.530 and 0.909 per volume.

Astrocytoma↗

PubMed2002

Use of CpG island microarrays to identify colorectal tumors with a high degree of concurrent methylation.

We provide a comprehensive description of our microarray-based technique for the simultaneous detection of multiple CpG islands in cancer. Amplicons from tumor and control samples were pools of differentially methylated CpG island fragments hybridized to a panel of approximately 8000 CpG island tags. Data analysis identified 694 CpG island loci hypermethylated in a group of 14 colorectal tumors. The Stanford hierarchical cluster algorithm segregated the tumors into two subgroups, one of which exhibited a high level of concurrent hypermethylation while the other had little or no methylation. This is in agreement with previous observations of a CpG island methylation phenotype present in colorectal tumors. The present study demonstrates that this microarray-based technique is useful in classifying tumors according to their methylation profiles.

Algorithms↗

PubMed2003

Automatic segmentation of thalamic nuclei from diffusion tensor magnetic resonance imaging.

The nuclei of the thalamus have traditionally been delineated by their distinct cyto/myeloarchitectural appearance on histology. Here, we show that diffusion tensor magnetic resonance imaging (DTI) can noninvasively resolve the major thalamic nuclei based on the characteristic fiber orientation of the corticothalamic/thalamocortical striations within each nucleus. Using an automatic clustering algorithm, we extracted the Talairach coordinates for the individual thalamic nuclei. The center-of-mass coordinates for the segmented nuclei were found to agree strongly with those obtained from a histological atlas. The ability to resolve thalamic nuclei with DTI will allow for morphometric analysis of specific nuclei and improved anatomical localization of functional activation in the thalamus.

Algorithms↗

PubMed2005

Molecular classification of renal tumors by gene expression profiling.

Renal tumor classification is important because histopathological subtypes are associated with distinct clinical behavior. However, diagnosis is difficult because tumor subtypes have overlapping microscopic characteristics. Therefore, ancillary methods are needed to optimize classification. We used oligonucleotide microarrays to analyze 31 adult renal tumors, including clear cell renal cell carcinoma (RCC), papillary RCC, chromophobe RCC, oncocytoma, and angiomyolipoma. Expression profiles correlated with histopathology; unsupervised algorithms clustered 30 of 31 tumors according to appropriate diagnostic subtypes while supervised analyses identified significant, subtype-specific expression markers. Clear cell RCC overexpressed proximal nephron, angiogenic, and immune response genes, chromophobe RCC oncocytoma overexpressed distal nephron and oxidative phosphorylation genes, papillary RCC overexpressed serine protease inhibitors, and extracellular matrix products, and angiomyolipoma overexpressed muscle developmental, lipid biosynthetic, melanocytic, and distinct angiogenic factors. Quantitative reverse transcriptase-polymerase chain reaction and immunohistochemistry of formalin-fixed renal tumors confirmed overexpression of proximal nephron markers (megalin/low-density lipoprotein-related protein 2, alpha-methylacyl CoA racemase) in clear cell and papillary RCC and distal nephron markers (beta-defensin 1, claudin 7) in chromophobe RCC/oncocytoma. In summary, renal tumor subtypes were classified by distinct gene expression profiles, illustrating tumor pathobiology and translating into novel molecular bioassays using fixed tissue.

Gene Expression Profiling↗

PubMed1989

Clustering a large number of compounds. 1. Establishing the method on an initial sample.

The National Cancer Institute Division of Cancer Treatment has revised its drug-screening program. About 230,000 compounds in our repository are available for screening under the new protocol. This paper is the first on an attempt to extract a representative sample of these compounds by clustering. It reviews the establishment of the clustering method on a 4980-compound initial sample. The clustering algorithm is fairly simple. However, the molecular fragments employed to match the compounds are somewhat complex to distinguish a large number of compounds.

Algorithms↗

PubMedDate not supplied

METAPRINT: a metabolic fingerprint. Application to cassette design for high-throughput ADME screening.

METAPRINT, a metabolic fingerprint, has been developed by predicting metabolic pathways and corresponding potential metabolites. Calculated drug-likeness parameters (log P and MW) have been incorporated into METAPRINT to allow the encoding of metabolic diversity within a chemical library. The application of METAPRINT in the design of cassette dosing experiments is demonstrated using a library of alpha-1a antagonists synthesized at Glaxo Wellcome. Results obtained by Ward's clustering algorithm suggest that METAPRINTs are able to discriminate between low- and high-clearance compounds. Cassette design was performed by maximizing the intracassette Euclidean distances between compounds in METAPRINT space, using simulated annealing. Calculated distances in METAPRINT space were in accordance with experimental data.

Computational Biology↗

PubMed2002

Identification of ligand binding sites on proteins using a multi-scale approach.

Identification of a ligand binding site on a protein is pivotal to drug discovery. To date, no reliable and computationally feasible general approach to this problem has been published. Here we present an automated efficient method for determining binding sites on proteins for potential ligands without any a priori knowledge. Our method is based upon the multiscale concept where we deal with a hierarchy of models generated using a k-means clustering algorithm for the potential ligand. This is done in a simple approach whereby a potential ligand is represented by a growing number of feature points. At each increasing level of detail, a pruning of potential binding site is performed. A nonbonding energy function is used to score the interactions between molecules at each step. The technique was successfully employed to seven protein-ligand complexes. In the current paper we show that the algorithm considerably reduces the computational effort required to solve this problem. This approach offers real opportunities for exploiting the large number of structures that will evolve from structural genomics.

Algorithms↗

PubMed2004

Existence of specific "folds" in polyproline II ensembles of an "unfolded"alanine peptide detected by molecular dynamics.

Equilibrium ensembles of octaalanine (Ac-Ala8-NHMe) in water, prepared with MD, are analyzed for contributing microstates with an RMSD-based conformational clustering algorithm. The extracted ensemble-averaged properties are in excellent agreement with numerous spectroscopic measurements reported with small alanine model peptides in water. However, the dominantly polyproline II-like ensemble of the peptide is found to be populated with a handful of highly position-specific "folds", including beta-turns, beta-hairpins, and helix nuclei, which could be the "seeds" that initiate proteins along their folding pathways.

Dipeptides↗

PubMed2005

Phenotypic anchoring of global gene expression profiles induced by N-hydroxy-4-acetylaminobiphenyl and benzo[a]pyrene diol epoxide reveals correlations between expression profiles and mechanism of toxicity.

The goal of this study was to compare changes in gene expression induced by exposure to different carcinogens and to anchor these changes to the induced levels of toxicity and mutagenesis. The human TK6 lymphoblastoid cell line was used as an in vitro model system, and reactive metabolites of two human carcinogens, benzo[a]pyrene and 4-aminobiphenyl, were used as model compounds. We first determined the toxicity of the model compounds N-hydroxy-4-acetylaminobiphenyl (N-OH-AABP) and benzo[a]pyrene diol epoxide (BPDE) in TK6 cells. BPDE was about 1000-fold more toxic and mutagenic than N-OH-AABP in TK6 cells on a molar basis. We next treated cells with three doses of each compound that resulted in low, medium, and high toxicities (5, 15, and 40%) and harvested cells at different times after exposure. Using comparable levels of toxicity as the phenotypic anchor, we compared the patterns of gene expression induced by each reactive metabolite using printed cDNA microarrays comprising approximately 18,000 human gene/EST sequences. The microarray data from the N-OH-AABP and BPDE treatment groups were compared using self-organizing map clustering algorithms, as well as a statistical regression modeling approach. While subsets of genes indicative of a generalized stress response [Hsp 40 homologue (DNAJ), Hsp70, Hsp105, and Hsp 125] were detected after exposure to both compounds at all concentrations, there were also many differentially regulated genes, including phase I xenobiotic metabolism [e.g., glutathione transferase omega (GSTTLp28) and antioxidant enzymes (Apxl)]. Other differentially regulated genes included those encoding proteins involved in all major DNA repair pathways, including excision repair (e.g., ERCC5), mismatch repair (e.g., MLH3), damage specific DNA binding protein (e.g., DDB2), and cisplatin resistance-associated overexpressed protein (LUC7A, CRA). Differences in the transcriptional response of TK6 cells to N-OH-AABP or BPDE exposure may explain the dramatic differences in the toxicity and mutagenicity of these human carcinogens.

7,8-Dihydro-7,8-dihydroxybenzo(a)pyrene 9,10-oxide↗

PubMed1997

Automated detection of the left ventricular region in magnetic resonance images by Fuzzy c-Means model.

A new method for automated detection of the Left Ventricular (LV) region in Magnetic Resonance Imaging is presented. This method is based on the Fuzzy c-Means (FCM) clustering algorithm. The FCM is applied to each static frame of the cardiac cycle to detect the LV region. Delineation of this region is essential in the quantitative analysis of the cardiac function. The effectiveness of the method is demonstrated by application to sequences of cardiac images.

Algorithms↗

PubMed2004

Patterns of microsatellite variability in the Drosophila melanogaster complex.

Forty-seven microsatellite loci were amplified in Drosophila melanogaster, Drosophila simulans, Drosophila mauritiana and Drosophila sechellia. The two cosmopolitan species D. melanogaster and D. simulans were found to be the most variable ones, followed by D. mauritiana and D. sechellia. A model based clustering algorithm was applied to the population samples of D. melanogaster, D. simulans and D. sechellia. No evidence for population substructure was detected within species--most likely due to insufficient power. A Markov chain Monte Carlo method developed for demographic inference based on microsatellites provided unambiguous evidence for population contraction in D. melanogaster, D. simulans and D. sechellia, despite that the D. melanogaster and D. simulans population samples were of non-African origin and represented recently expanded populations.

Africa↗

PubMed2000

Molecular profiling of human cancer.

Traditionally, tumours have been categorized on the basis of histology. However, the staining pattern of cancer cells viewed under the microscope is insufficient to reflect the complicated underlying molecular events that drive the neoplastic process. By surveying thousands of genes at once, using DNA arrays, it is now possible to read the molecular signature of an individual patient's tumour. When the signature is analysed with clustering algorithms, new classes of cancer emerge that transcend distinctions based on histological appearance alone. Using DNA arrays, protein arrays and appropriate experimental models, the ultimate goal is to move beyond correlation and classification to achieve new insights into disease mechanisms and treatment targets.

Gene Expression Profiling↗