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.

At least 487 records · Page 27Linked to original sources
PubMed2004

Machine learning based pattern recognition applied to microarray data.

MOTIVATION: Microarrays have allowed the expression level of thousands of genes or proteins to be measured simultaneously. Data sets generated by these arrays consist of a small number of observations (e.g., 20-100 samples) on a very large number of variables (e.g., 10,000 genes or proteins). The observations in these data sets often have other attributes associated with them such as a class label denoting the pathology of the subject. Finding the genes or proteins that are correlated to these attributes is often a difficult task since most of the variables do not contain information about the pathology and as such can mask the identity of the relevant features. We describe a genetic algorithm (GA) that employs both supervised and unsupervised learning to mine gene expression and proteomic data. The pattern recognition GA selects features that increase clustering, while simultaneously searching for features that optimize the separation of the classes in a plot of the two or three largest principal components of the data. Because the largest principal components capture the bulk of the variance in the data, the features chosen by the GA contain information primarily about differences between classes in the data set. The principal component analysis routine embedded in the fitness function of the GA acts as an information filter, significantly reducing the size of the search space since it restricts the search to feature sets whose principal component plots show clustering on the basis of class. The algorithm integrates aspects of artificial intelligence and evolutionary computations to yield a smart one pass procedure for feature selection, clustering, classification, and prediction.

Algorithms↗
PubMed2025

Integrative multi-omics analysis proposes a metabolic classification of gliomas: distinct metabolic states, immune infiltration, and prognosis.

BACKGROUND: The tumor microenvironment (TME) of glioma harbors diverse cell types; however, cell metabolic heterogeneity remains to be explored. This study aims to characterize the metabolic features of different cell types in the TME by integrating multiple datasets, including genomics, bulk and single-cell transcriptomics, and metabolomics. METHODS: Unsupervised machine learning was used to construct an energy metabolic classifier based on the metabolic pathways identified from bulk RNA-seq of gliomas in the TCGA dataset. The classifier was externally validated using multiple datasets, including genomics, bulk RNA-seq, snRNA-seq, and the metabolomics data. Furthermore, metabolic heterogeneity associated with the classifier was further characterized at single-cell resolution. RESULTS: The energy metabolism-based classifier stratified patients into two prognostic clusters: patients in cluster 1 were characterized by high pathway activity of glycolysis, the pentose phosphate pathway (PPP), and fatty acid oxidation (FAO), whereas patients in cluster 2 exhibited higher activity in glutaminolysis. This metabolic classifier revealed both intratumoral and intertumoral metabolic heterogeneity, and the complexity was further validated by the metabolomics profiling and snRNA-seq data from the CPTAC dataset. Notably, OSMR, highly expressed in cluster 1, showed significant co-expression with key glycolytic enzyme genes. The OSM/OSMR/JAK1/STAT3 axis potently drives malignant progression of glioma cells, specially enhancing their invasive and migratory capabilities. Single-cell resolution analyses demonstrated that tumor metabolic heterogeneity is primarily driven by malignant cells rather than non-malignant components, while tumor microenvironment (TME) factors were also found to modulate malignant cell metabolism. Significantly, glycolytic activity in glioma cells increased during the phenotypic transition from PN (proneural) to MES (mesenchymal), with cluster 1 metabolic phenotypes predominating in the tumor core. Compared to cluster 2, cluster 1 patients exhibited higher mRNA expression of immunosuppressive checkpoint genes, which correlated with pronounced immunosuppression in the TME. Furthermore, various immune cells demonstrated distinct metabolic preferences at single-cell resolution. CONCLUSIONS: This study developed an energy metabolic-based classifier for gliomas with prognostic and therapeutic potential. Metabolic reprogramming was linked with the PN-to-MES transition of glioma cells and immunosuppression in the tumor microenvironment. Multi-omics data, especially snRNA-seq, offered insights into metabolism heterogeneity at single-cell resolution, enabling personalized treatment strategies.

Humans↗
PubMedDate not supplied

Assessing the predictive power of unsupervised visualization techniques to improve the identification of GPCR-focused compound libraries.

Principal component analysis and self-organizing maps (SOMs) were compared to cluster and visualize the chemical space of a large and diverse data set. The data set comprised about 3000 G-protein-coupled receptor (GPCR) ligands for about 130 receptors and 3000 non-GPCR ligands from the World Drug Index. The molecules were described with a topological pharmacophore point histogram descriptor and a chemical fingerprint descriptor. To assess the predictive power of the clustering, a leave-multiple-out cross validation with k nearest neighbor classification was performed. The results of the classification tests and the visualization showed a clear superiority of the SOM method. SOM correctly divided the data set into two main clusters, one for the GPCR and the other for the non-GPCR ligands. Our results suggest that a continuous GPCR-ligand space exists.

Drug Design↗
PubMed2004

A general clustering approach with application to the Miyazawa-Jernigan potentials for amino acids.

In this article, we address the problem of classification of amino acids. Starting from the Miyazawa-Jernigan matrix obtained from the relative positions of amino acids in the crystal structure of globular proteins, we develop a fully unsupervised method of classification for the amino acids. The method is based in the subdominant ultrametric associated to the distance induced by the Miyazawa-Jernigan matrix and the maximum likelihood principle to determine the cluster structure. We obtain a classification consistent with the five groups used in the literature, although with some peculiarities. We also show the stability of our results against changes of the method used to classify the amino acids. Proteins 2004.

Algorithms↗
PubMed2002

Segmentation techniques for tissue differentiation in MRI of ophthalmology using fuzzy clustering algorithms.

This paper presents MRI segmentation techniques to differentiate abnormal and normal tissues in Ophthalmology using fuzzy clustering algorithms. Applying the best-known fuzzy c-means (FCM) clustering algorithm, a newly proposed algorithm, called an alternative fuzzy c-mean (AFCM), was used for MRI segmentation in Ophthalmology. These unsupervised segmentation algorithms can help Ophthalmologists to reduce the medical imaging noise effects originating from low resolution sensors and/or the structures that move during the data acquisition. They may be particularly helpful in the clinical oncological field as an aid to the diagnosis of Retinoblastoma, an inborn oncological disease in which symptoms usually show in early childhood. For the purpose of early treatment with radiotherapy and surgery, the newly proposed AFCM is preferred to provide more information for medical images used by Ophthalmologists. Comparisons between FCM and AFCM segmentations are made. Both fuzzy clustering segmentation techniques provide useful information and good results. However, the AFCM method has better detection of abnormal tissues than FCM according to a window selection. Overall, the newly proposed AFCM segmentation technique is recommended in MRI segmentation.

Algorithms↗
PubMed2000

Nonlinear dimensionality reduction by locally linear embedding.

Many areas of science depend on exploratory data analysis and visualization. The need to analyze large amounts of multivariate data raises the fundamental problem of dimensionality reduction: how to discover compact representations of high-dimensional data. Here, we introduce locally linear embedding (LLE), an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs. Unlike clustering methods for local dimensionality reduction, LLE maps its inputs into a single global coordinate system of lower dimensionality, and its optimizations do not involve local minima. By exploiting the local symmetries of linear reconstructions, LLE is able to learn the global structure of nonlinear manifolds, such as those generated by images of faces or documents of text.

Algorithms↗
PubMed2024

Proteomic profiles of peritoneal fluid-derived small extracellular vesicles correlate with patient outcome in ovarian cancer.

Cancer-derived small extracellular vesicles (sEVs) are capable of modifying the tumor microenvironment and promoting tumor progression. Ovarian cancer (OvCa) is a lethal malignancy that preferentially spreads through the abdominal cavity. Thus, the secretion of such vesicles into the peritoneal fluid could be a determinant factor in the dissemination and behavior of this disease. We designed a prospective observational study to assess the impact of peritoneal fluid-derived sEVs (PFD-sEVs) in OvCa clinical outcome. For this purpose, 2 patient cohorts were enrolled: patients with OvCa who underwent a diagnostic or cytoreductive surgery and nononcological patients, who underwent abdominal surgery for benign gynecological conditions and acted as the control group. Systematic extraction of PFD-sEVs from surgical samples enabled us to observe significant quantitative and qualitative differences associated with cancer diagnosis, disease stage, and platinum chemosensitivity. Proteomic profiling of PFD-sEVs led to the identification of molecular pathways and proteins of interest and to the biological validation of S100A4 and STX5. In addition, unsupervised analysis of PFD-sEV proteomic profiles in high-grade serous ovarian carcinomas (HGSOCs) revealed 2 clusters with different outcomes in terms of overall survival. In conclusion, comprehensive characterization of PFD-sEV content provided a prognostic value with potential implications in HGSOC clinical management.

Humans↗
PubMed2006

Binary state pattern clustering: a digital paradigm for class and biomarker discovery in gene microarray studies of cancer.

Class and biomarker discovery continue to be among the preeminent goals in gene microarray studies of cancer. We have developed a new data mining technique, which we call Binary State Pattern Clustering (BSPC) that is specifically adapted for these purposes, with cancer and other categorical datasets. BSPC is capable of uncovering statistically significant sample subclasses and associated marker genes in a completely unsupervised manner. This is accomplished through the application of a digital paradigm, where the expression level of each potential marker gene is treated as being representative of its discrete functional state. Multiple genes that divide samples into states along the same boundaries form a kind of gene-cluster that has an associated sample-cluster. BSPC is an extremely fast deterministic algorithm that scales well to large datasets. Here we describe results of its application to three publicly available oligonucleotide microarray datasets. Using an alpha-level of 0.05, clusters reproducing many of the known sample classifications were identified along with associated biomarkers. In addition, a number of simulations were conducted using shuffled versions of each of the original datasets, noise-added datasets, as well as completely artificial datasets. The robustness of BSPC was compared to that of three other publicly available clustering methods: ISIS, CTWC and SAMBA. The simulations demonstrate BSPC's substantially greater noise tolerance and confirm the accuracy of our calculations of statistical significance.

Algorithms↗
PubMed2006

Spike sorting based upon machine learning algorithms (SOMA).

We have developed a spike sorting method, using a combination of various machine learning algorithms, to analyse electrophysiological data and automatically determine the number of sampled neurons from an individual electrode, and discriminate their activities. We discuss extensions to a standard unsupervised learning algorithm (Kohonen), as using a simple application of this technique would only identify a known number of clusters. Our extra techniques automatically identify the number of clusters within the dataset, and their sizes, thereby reducing the chance of misclassification. We also discuss a new pre-processing technique, which transforms the data into a higher dimensional feature space revealing separable clusters. Using principal component analysis (PCA) alone may not achieve this. Our new approach appends the features acquired using PCA with features describing the geometric shapes that constitute a spike waveform. To validate our new spike sorting approach, we have applied it to multi-electrode array datasets acquired from the rat olfactory bulb, and from the sheep infero-temporal cortex, and using simulated data. The SOMA sofware is available at http://www.sussex.ac.uk/Users/pmh20/spikes.

Action Potentials↗
PubMed2005

Diversity of ganglion cells in the mouse retina: unsupervised morphological classification and its limits.

The dendritic structures of retinal ganglion cells in the mouse retina were visualized by particle-mediated transfer of DiI, microinjection of Lucifer yellow, or visualization of green fluorescent protein expressed in a transgenic strain. The cells were imaged in three dimensions and the morphologies of a series of 219 cells were analyzed quantitatively. A total of 26 parameters were studied and automated cluster analysis was carried out using the k-means methods. An effective clustering, judged by silhouette analysis, was achieved using three parameters: level of stratification, extent of the dendritic field, and density of branching. An 11-cluster solution is illustrated. The cells within each cluster are visibly similar along morphological dimensions other than those used statistically to form the clusters. They could often be matched to ganglion cell types defined by previous studies. For reasons that are discussed, however, this classification must remain provisional. Some steps toward more definitive methods of unsupervised classification are pointed out.

Amino Acids↗
PubMed2004

Schematic influences on category learning and recognition memory.

The results from 3 category learning experiments suggest that items are better remembered when they violate a salient knowledge structure such as a rule. The more salient the knowledge structure, the stronger the memory for deviant items. The effect of learning errors on subsequent recognition appears to be mediated through the imposed knowledge structure. The recognition advantage for deviant items extends to unsupervised learning situations. Exemplar-based and hypothesis-testing models cannot account for these results. The authors propose a clustering account in which deviant items are better remembered because they are differentiated from clusters that capture regularities. The function of clusters is akin to that of schemas. Their results and analyses expose connections among research in category learning, schemas, stereotypes, and analogy.

Humans↗
PubMed2005

Combinatorial pattern discovery approach for the folding trajectory analysis of a beta-hairpin.

The study of protein folding mechanisms continues to be one of the most challenging problems in computational biology. Currently, the protein folding mechanism is often characterized by calculating the free energy landscape versus various reaction coordinates, such as the fraction of native contacts, the radius of gyration, RMSD from the native structure, and so on. In this paper, we present a combinatorial pattern discovery approach toward understanding the global state changes during the folding process. This is a first step toward an unsupervised (and perhaps eventually automated) approach toward identification of global states. The approach is based on computing biclusters (or patterned clusters)-each cluster is a combination of various reaction coordinates, and its signature pattern facilitates the computation of the Z-score for the cluster. For this discovery process, we present an algorithm of time complexity c in RO((N + nm) log n), where N is the size of the output patterns and (n x m) is the size of the input with n time frames and m reaction coordinates. To date, this is the best time complexity for this problem. We next apply this to a beta-hairpin folding trajectory and demonstrate that this approach extracts crucial information about protein folding intermediate states and mechanism. We make three observations about the approach: (1) The method recovers states previously obtained by visually analyzing free energy surfaces. (2) It also succeeds in extracting meaningful patterns and structures that had been overlooked in previous works, which provides a better understanding of the folding mechanism of the beta-hairpin. These new patterns also interconnect various states in existing free energy surfaces versus different reaction coordinates. (3) The approach does not require calculating the free energy values, yet it offers an analysis comparable to, and sometimes better than, the methods that use free energy landscapes, thus validating the choice of reaction coordinates. (An abstract version of this work was presented at the 2005 Asia Pacific Bioinformatics Conference [1].).

Journal Article↗
PubMed2026

A Practical Workflow for Spatial Transcriptomics Data Analysis: From Data Acquisition to Advanced Analyses.

Spatial transcriptomics (ST) profiles genome-wide gene expression while preserving the two-dimensional spatial context of mRNA molecules within tissue sections, enabling studies of tissue architecture and microenvironment-associated biology. However, ST analysis remains challenging because data import, quality control, integration, deconvolution, spatial statistics, and visualization often require multiple software environments and reproducible parameter choices. This protocol presents a practical computational workflow for public ST datasets in R, beginning with data acquisition and software setup and proceeding through Seurat-based data loading, quality control, normalization, multi-sample integration, clustering, and spatially variable gene analysis. The workflow then applies complementary deconvolution strategies, including reference-guided SPOTlight analysis and unsupervised STdeconvolve topic modeling, followed by Giotto-based spatial cell-cell communication analysis and interactive region-of-interest (ROI) selection using a custom Python Dash application. By emphasizing script-based execution, explicit parameter rationales, expected outputs, and troubleshooting checkpoints, the protocol provides an adaptable framework for standard array-based ST datasets and related platforms after dataset- and platform-specific parameter evaluation.

Spatial Transcriptomics↗
PubMed2003

Informatics for unveiling hidden genome signatures.

With the increasing amount of available genome sequences, novel tools are needed for comprehensive analysis of species-specific sequence characteristics for a wide variety of genomes. We used an unsupervised neural network algorithm, a self-organizing map (SOM), to analyze di-, tri-, and tetranucleotide frequencies in a wide variety of prokaryotic and eukaryotic genomes. The SOM, which can cluster complex data efficiently, was shown to be an excellent tool for analyzing global characteristics of genome sequences and for revealing key combinations of oligonucleotides representing individual genomes. From analysis of 1- and 10-kb genomic sequences derived from 65 bacteria (a total of 170 Mb) and from 6 eukaryotes (460 Mb), clear species-specific separations of major portions of the sequences were obtained with the di-, tri-, and tetranucleotide SOMs. The unsupervised algorithm could recognize, in most 10-kb sequences, the species-specific characteristics (key combinations of oligonucleotide frequencies) that are signature features of each genome. We were able to classify DNA sequences within one and between many species into subgroups that corresponded generally to biological categories. Because the classification power is very high, the SOM is an efficient and fundamental bioinformatic strategy for extracting a wide range of genomic information from a vast amount of sequences.

Animals↗
PubMed1993

Self-organizing neural networks as a means of cluster analysis in clinical chemistry.

Connectionist systems (often termed "neural networks") are an alternative way to solve data processing tasks. They differ radically from conventional "von-Neumann" computing devices. Recent work on neural networks in clinical chemistry was done using supervised learning schemes, resulting in models which resemble classical discriminant analysis. The aim of the present study is to make clinical chemists familiar with basic concepts of self-organizing neural networks employing unsupervised learning schemes. Using a benchmark data set on the composition of milk from 22 different mammals, it is demonstrated that self-organizing neural networks are capable of performing tasks similar to classical cluster analysis and principal component analysis. Self-organizing neural networks could be envisaged to provide an alternative way for reducing the dimensionality of complex multivariate data sets, thus producing easily comprehensible low-dimensional "maps" of essential features.

Animals↗
PubMed2006

Understanding and reducing variability of SOM neighbourhood structure.

The self-organizing map (SOM) is a nonlinear unsupervised method for vector quantization. In the context of classification and data analysis, the SOM technique highlights the neighbourhood structure between clusters. The correspondence between this clustering and the input proximity is called the topology preservation. We present here a stochastic method based on bootstrapping in order to increase the reliability of the induced neighbourhood structure. Considering the property of topology preservation, a local approach of variability (at an individual level) is preferred to a global one. The resulting (robust) map, called R-map, is more stable relatively to the choice of the sampling method and to the learning options of the SOM algorithm (initialization and order of data presentation). The method consists of selecting one map from a group of several solutions resulting from the same self-organizing map algorithm, but obtained with various inputs. The R-map can be thought of as the map, among the group of solutions, corresponding to the most common interpretation of the data set structure. The R-map is then the representative of a given SOM network, and the R-map ability to adjust the data structure indicates the relevance of the chosen network.

Algorithms↗
PubMed2001

Database mining applied to central nervous system (CNS) activity.

A data set of 389 compounds, active in the central nervous system (CNS) and divided into eight classes according to the receptor type, was extracted from the RBI database and analyzed by Self-Organizing Maps (SOM), also known as Kohonen Artificial Neural Networks. This method gives a 2D representation of the distribution of the compounds in the hyperspace derived from their molecular descriptors. As SOM belongs to the category of unsupervised techniques, it has to be combined with another method in order to generate classification models with predictive ability. The fuzzy clustering (FC) approach seems to be particularly suitable to delineate clusters in a rational way from SOM and to get an automatic objective map interpretation. Maps derived by SOM showed specific regions associated with a unique receptor type and zones in which two or more activity classes are nested. Then, the modeling ability of the proposed SOM/FC Hybrid System tools applied simultaneously to eight activity classes was validated after dividing the 389 compounds into a training set and a test set, including 259 and 130 molecules, respectively. The proper experimental activity class, among the eight possible ones, was predicted simultaneously and correctly for 81% of the test set compounds.

Central Nervous System↗
PubMed2001

Volume learning algorithm artificial neural networks for 3D QSAR studies.

The current study introduces a new method, the volume learning algorithm (VLA), for the investigation of three-dimensional quantitative structure-activity relationships (QSAR) of chemical compounds. This method incorporates the advantages of comparative molecular field analysis (CoMFA) and artificial neural network approaches. VLA is a combination of supervised and unsupervised neural networks applied to solve the same problem. The supervised algorithm is a feed-forward neural network trained with a back-propagation algorithm while the unsupervised network is a self-organizing map of Kohonen. The use of both of these algorithms makes it possible to cluster the input CoMFA field variables and to use only a small number of the most relevant parameters to correlate spatial properties of the molecules with their activity. The statistical coefficients calculated by the proposed algorithm for cannabimimetic aminoalkyl indoles were comparable to, or improved, in comparison to the original study using the partial least squares algorithm. The results of the algorithm can be visualized and easily interpreted. Thus, VLA is a new convenient tool for three-dimensional QSAR studies.

Algorithms↗